Forthcoming and Online First Articles

International Journal of Advanced Intelligence Paradigms

International Journal of Advanced Intelligence Paradigms (IJAIP)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Advanced Intelligence Paradigms (106 papers in press)

Regular Issues

  • Enhanced Differential Evolution with Information Preserving Selection Strategy   Order a copy of this article
    by Pravesh Kumar 
    Abstract: In the present paper, two modifications for Differential Evolution (DE) algorithm are proposed. The first modification is the proposal of a new selection technique called Information Preserving Strategy (IPS), tries to preserve and utilize the important information about the search domain. The corresponding DE variant is called IpDE. The second modification is a new mutation strategy and called Enhance DE algorithm (EDE). Furthermore a new variant named IpEDE by combining EDE and IpEDE is also proposed. The performance of the proposed variants IpDE, EDE and IpEDE are validated on a set of test problems including standard test problems and the selected test problems of CEC-2008. The algorithms are compared with some of the prominent DE variants and it is observed that the proposed modifications help in improving the performance of DE in terms of convergence rate and solution quality.
    Keywords: Differential evolution; Information preserving selection; Mutation; Global Optimization.

  • Optimal Path Planning with Hybrid Firefly Algorithm and Cuckoo Search Optimization   Order a copy of this article
    by Monica Sood, Vinod Kumar Panchal 
    Abstract: Background/Objective: Path planning is one of the core and extensively studied problems in robotics. The scope of path planning is not only limited to robotics, it has gained its pertinence in many of the application areas including simulations and gaming, computer graphics, very large scale integration (VLSI) and many more. This paper aims to propose an optimization algorithm to identify the optimum path from defined source to destination without any obstacle collision. Method: A hybrid algorithm is proposed by combining the properties of two swarm intelligence techniques: Cuckoo search and Firefly algorithm. The multi agent firefly algorithm makes use of the levy flight property for the random movement of fireflies and put forth the best path from defined source to destination without colliding with any of the obstacle. The property of clever cuckoos brood parasitic behaviour of imitating the pattern of hosts egg is used by fireflies to handle the present obstacles in the path. Result/Conclusion: The experimental results obtained work in an adequately acceptable agreement with the proposed hybrid algorithm. Three experiments are performed considering the red band satellite image of the urban and vegetation area of Alwar region in Rajasthan, India. The experimental results calculated indicate the efficiency of proposed hybrid algorithm as compared to individual cuckoo search and firefly algorithm. The proposed hybrid algorithm detected the optimum path at iteration number 27 with a path length of 246 pixels and with a simulation time of minimum 112 seconds and maximum 167 seconds. Whereas, cuckoo search achieved the optimum path at iteration 49 with a simulation time of minimum 179 seconds and maximum 230 seconds. In the similar manner, firefly algorithm achieved optimum path length at 56 iterations with a simulation time of minimum 151 seconds and maximum 195 seconds respectively.
    Keywords: Optimal Path Planning; Cuckoo Search; Firefly Algorithm; Nature Inspired Computing; Computational Intelligence; Machine Learning.

  • Diminishing the selfish nodes by reputation and pricing system through SRA scenario   Order a copy of this article
    by John Paul Antony T, Victor S P 
    Abstract: In MANET, every hub relies upon different hubs to forward the information to its expected goal. But those as it may, couple of hubs are not prepared to share the assets because of its narrow minded conduct. The reputation and Pricing system gives a solution to the existing problem. We propose a scenario of Price and Reputation system (P&RS) that helps to diminish the selfish nodes in a successful manner. Additionally by productively join the procedure of both Notoriety and Value Framework and by building the Stratified Territory cognizant Spread record Table (DAT) to internationally gather the notoriety data. The Stratified Report Assisted (SRA) frameworks overcome the deficiencies of these current frameworks by effectively consolidate the procedure of both Reputation and Price system.
    Keywords: Selfish node; Disseminated table; watches dog; Reputation.

  • Supervised Microarray Gene Retrieval System Based on KLFDA and ELM   Order a copy of this article
    by Thomas Scaria, T. Christopher 
    Abstract: Microarray gene data processing has gained considerable research interest these days. However, processing microarray gene data is highly challenging due to its volume. Taking this challenge into account, this work proposes a supervised microarray gene retrieval system which relies on two phases namely, feature dimensionality minimization and classification. The objective of feature dimensionality minimization is to make the classification process easier by weeding out the unwanted data. The feature dimensionality of the datasets is minimized by KLFDA and the processed dataset is passed to the classification phase, which is achieved by ELM. The proposed approach is evaluated upon three different benchmark datasets such as colon tumour, central nervous system and ALL-AML. From the experimental results, it is proven that the proposed combination of KLFDA and ELM works better for all the three datasets in terms of accuracy, sensitivity and specificity rates.
    Keywords: microarray gene retrieval; classification; feature dimensionality minimization.

  • OPTIMISED RETINA VERIFICATION SYSTEM FOR PATHOLOGICAL RETINA   Order a copy of this article
    by Rani Bms 
    Abstract: In retinal biometrics acknowledgment rate is influenced by the vasculature unpredictability of retinal pictures.Vascular example turns out to be extremely unpredictable in effected retinal images because of pathological signs. In this paper retina verification which includes an AWN classifier to detect blood vessel structure from pathological retina. Distinct retinal feature which remains constant under pathological changes is bifurcation angle. This paper demonstrates a method for extraction of bifurcation angle. The particular bifurcation focuses had been created and positions are ascertained of a similar bifurcation indication. Sparse matrix representation used for retina template storing for optimization of memory and the template is compared .
    Keywords: Retinal biometrics;vascular;AWN classifier;bifurcation angle;retina template;sparse matrix.

  • On Interval Covering Salesman Problem   Order a copy of this article
    by Siba Prasada Tripathy, Amit Tulshyan, Samarjit Kar, Tandra Pal 
    Abstract: After a disaster, during humanitarian relief transportation or mass fatality management, cost of journey between two places may be uncertain due to the variation of degree of devastation in the affected area. In such scenarios, a viable model is essential to handle the situation in cost-effective and reliable manner, which is able to handle this uncertainty. In this paper, we introduce Interval Covering Salesman Problem (ICSP), where cost of an edge is represented by interval number. ICSP is a variant of Covering Salesman Problem (CSP) which is helpful for many real world problems in uncertain environment. Here, we formulate a mathematical model for ICSP with uncertain cost associated with the cost of travel between two nodes/places. Here, we have proposed a Metameric Genetic Algorithm (MGA) for ICSP and presented its simulation results. For implementation, we have used some benchmark TSP instances by changing the costs to interval numbers.
    Keywords: Traveling Salesman problem; Covering Salesman Problem; Uncertainty; Interval Constraint; Metameric Genetic Algorithm; Global parent.

  • OABC Scheduler: A Multi-Objective Load Balancing Based Task Scheduling in a Cloud Environment   Order a copy of this article
    by Shameer A.P, A.C. Subhajini 
    Abstract: The primary goal of scheduling is to allocate each task to the corresponding virtual machine on the cloud. Load balancing of virtual machines (VMs) is an imperative part of task scheduling in clouds. At whatever point, certain VMs are over-loaded and remaining VMs are under loaded with tasks for scheduling, the load must be adjusted to accomplish ideal machine use. This paper proposes a multi-objective task scheduling algorithm utilizing oppositional artificial bee colony algorithm (OABC), which expects to accomplish well-balanced load across virtual machines for minimizing the execution cost and completion time. The generated solution is competent to the quality of service (QoS) and enhances IaaS suppliers' believability and financial advantage. The OABC algorithm is planned based on oppositional strategy, employee bee, onlooker bee, scout bee and suitable fitness function for the corresponding task. The experimental results demonstrate that a proposed approach accomplishes better task scheduling result (minimum cost, time and energy) compare to other approaches.
    Keywords: Cloud computing; Virtual machine; Load balancing; oppositional artificial bee colony; Time; Cost; Task scheduling.

  • An inventive and innovative approach to monitor warehouse with Drone and IoT   Order a copy of this article
    by Aswath G.I., Shriram Vasudevan, Sundaram RMD, Giri Dhararajan, Sowmiya Nagarajan 
    Abstract: In the recent years, the technology growth in the sector of USVs / UAVs has been enormous. When it comes to UAVs, Quad copters play a major role and the platforms / hardware-software availability has become abundant which offer more choices and enhanced performance. One must be aware of the usage of the UAVs towards delivery of goods, pizzas etc. Taking the growth and available facilities, we have attempted to use the Quad copters towards enhancing/increasing the efficiency in monitoring the warehouse through a frugal and cost effective approach. We have proposed to use the drones inside a warehouse for inventory monitoring. Through the literature survey, we un-derstood that there is a lot of loss because of inefficient monitoring techniques, which mostly involve human efforts. While manual verification is both time consuming and error prone, we have used Drones, Data Analytics, Android and IoT as the backbone to simplify the process. This approach is found to be affordable, accurate and viable. Our drone will fly inside the warehouse, track the goods and components rack wise, and give an alert/update to the store manager through both web interface and android application that we have developed. This way, we can track every individual box in the warehouse, while eliminating the chance for it to be lost/untracked.
    Keywords: Drones; Warehouse Inventory control; IOT controlled drone; RFID; NFC; Raspberry Pi; Android; and Intelligent Warehouse Monitoring.

  • Attribute Weight Gain Ratio (AWGR): New Distance Measure to select optimal features from multivalued attributes   Order a copy of this article
    by L.N.C. Prakash K., Kodali Anuradha 
    Abstract: Identifying the appropriate features or attributes remains the most prominent stage of any information retrieval and knowledge discovery. The process involves selecting specific features and their subsets holding the vital portion of the data. However, despite the prominence of this stage, most feature selection techniques opt for choosing mono-valued features. Accordingly, these techniques cannot be extended to use in multivalued attributes which require capturing different features from the dataset in parallel. To enable optimal feature selection for multivalued attributes, this manuscript proposes a novel technique aiming at calculating the optimal combination of multivalued attribute entries regarding clusters in unsupervised learning, and classes in supervised learning. The proposal is a distance metric that motivated from the traditional relevance assessing metrics information gain and gains ratio. To analyze the performance of the proposed technique, the classification approach SVM trained on optimal multivalued attribute features selected using proposed distance measuring metric, which is further used to perform classification process. Also, to evince the significance of the proposed distance measuring metric regarding clustering process, k-means clustering method with Attribute Weight Gain Ratio is executed on benchmark datasets. Simulation results depict superior performance of the model for feature selection for multivalued attributes.
    Keywords: Multiclass attributes; optimal feature; k-means clustering; transaction weight; mining techniques.
    DOI: 10.1504/IJAIP.2020.10021278
     
  • Collaborative Computing Methods With Enhanced Trust and Security Mechanisms   Order a copy of this article
    by Dileep Kumar Gopaluni, R. Praveen Sam 
    Abstract: Security and protection issues have been researched with regards to a solitary association practicing control over its clients' entrance to resources. In such a registering domain, security arrangements are characterized and overseen statically inside the limit of an association and are regularly halfway controlled. Be that as it may, growing huge scale Internet-based application frameworks exhibits new difficulties. There is a requirement for a model, and a system for demonstrating, indicating, and upholding the understanding set up by teaming up associations regarding trust and security issues. This trust understanding is expected to build up between authoritative security approaches that oversee the communication, coordination, cooperation, and resource sharing of the collective group of networks. In this paper application-level, trust-based security innovations to help Internet-based shared frameworks are introduced. In this paper a efficient collaborative method is proposed which performs network creation and authorization of nodes in network and then maintain security and trust levels on the network so as to provide secure path for data transmission among trusted nodes of a network. In the proposed work Enhanced Key Management Scheme (EKMS) is introduced for enhancing security in the network and several constraints are proposed for identifying trusted nodes in network. The manuscript also concentrates on Intrusion Detection system(IDS) for identifying any faults in the established network for smooth and efficient collaborative computing networking. The proposed method uses NS2 simulator for network creation and MATLAB environment for analyzing the performance of the collaborative network.
    Keywords: security; trust; collaborative computing; certificate authority; network authentication; intrusion detection system.
    DOI: 10.1504/IJAIP.2021.10029394
     
  • Development of Deep Intelligent System in Complex Domain for Human Recognition   Order a copy of this article
    by Swati Srivastava, Bipin K. Tripathi 
    Abstract: This paper aims to develop a deep intelligent system that can perform human recognition through proficient and compressed deep learning. The proposed Complex Deep Intelligent System(CDIS) incorporates multiple segments that includes image representation in lower dimensional feature space, Fused Fuzzy Distribution(FFD) and Complex Hybrid Neural Classifier(CHNC). One of the advantages of our CHNC is reduction in computational complexity because very few novel complex higher order neurons are sufficient to recognize a human identity. Further, the proposed intelligent system uses the advantages of both supervised and unsupervised learning to enhance the recognition rates. CDIS outperforms the best results accounted in the literature on three benchmark biometric datasets-CASIA iris, Yale face and Indian face datasets with 99.8%, 100% and 98.0% recognition accuracies respectively.
    Keywords: Fused fuzzy distribution (FFD); complex hybrid neural classifier (CHNC); biometric; deep architecture.
    DOI: 10.1504/IJAIP.2018.10047356
     
  • Big data secure storing in cloud and privacy preserving mechanism for outsourced cloud data   Order a copy of this article
    by Dr B. Renuka 
    Abstract: Big data is a buzz word in this decade it gets tremendous concentration in these days by the researchers because of the characteristics and features. And also big data gives lot of challenges to the world that is storage, processing and security. In any technology security is the prime concern in this manuscript, we map to misuse new complications of enormous information regarding security, further more, confer our thought toward viable and insurance protecting enlisting in the immense data time. Specifically, we at first formalize the general building of gigantic data examination, recognize the relating security necessities, and present a capable and assurance sparing outline for immense data which is secured in cloud.
    Keywords: Privacy Preserving; Security; Big data; Cloud Computing; outsourced data.

  • A Novel Approach for increased transaction security with Biometrics and One Time Password A complete implementation.   Order a copy of this article
    by Deveshwar H, Gowtham V, K.V. Shriram 
    Abstract: The advent of distributed and ubiquitous computing systems have resulted in the increase of digital financial transactions, consequentially making security a primary concern. Here we address the problem by proposing the usage of biometric sensors embedded in mobile systems to authenticate and generate a One Time Pin (OTP), as opposed to the existing systems that incorporate static and constant pins. This reduces the risk of spoofing and will make the user impervious to attacks on the Automatic Teller Machine (ATM) centers. We have proposed the usage of a central server that keeps track of requests and processes for the same. This ensures a wider scope for randomization of the pins, hence reducing predictability to almost zero.
    Keywords: Biometrics; Fingerprint; One Time Pin (OTP); Mobile devices; Transactions; Debit/Credit cards.

  • Performance Measures of Diseases Affected Iris Images using Sigmoidal Multilayer Feed Forward Neural Network   Order a copy of this article
    by S.G. Gino Sophia, V. Ceronmani Sharmila 
    Abstract: Iris is a scarce natural password used for human identification with reliability and security. The iris is affected by the number of diseases, so it leads to affects the iris recognition process. So study and analyze the types of diseases affecting the eye images. The localization of an iris is to perform using edge detection with the parameters of neighbors of a pixel and the structuring element of the morphological technique. The iris images are trained by the neural networks and analyzing the regression and performance graphs. Compare the various diseases affected iris and normal images using the periodogram power spectral density of matlab.
    Keywords: Enhancement; Histogram; Localization; Neighbors of a pixel; Neural Networks; Regression; Normalization.
    DOI: 10.1504/IJAIP.2021.10023728
     
  • EARLY DETECTION OF CHRONICAL KIDNEY DISEASE USING DATA MINING METHODS   Order a copy of this article
    by Suresh Cse, M. Nirupama Bhat 
    Abstract: Early examination and acknowledgment of kidney disease is a fundamental issue to help stop the development to kidney failure. Data mining and examination strategies can be used for anticipating Chronic Kidney Disease (CKD) by utilizing obvious patient's data and assurance records. In this examination, careful examination techniques, for instance, Decision Trees, Logistic Regression, Naive Bayes, and Artificial Neural Networks are used for predicting CKD. Pre-treatment of the data is performed to trait any missing data and perceive the components that should be considered in the identification models. The different careful examination models are assessed and contemplated in perspective of exactness of estimations. The examination gives a decision help contraption that can help in the identification of CKD. With the certifications of careful examination in tremendous data, and the usage of machine learning figurings, anticipating future isn't any more a troublesome task, especially to wellbeing division, that has seen a great headway following the change of new PC developments that delivered diverse fields of research. Various undertakings are done to adjust to remedial data impact on one hand, and to get important gaining from it, predict diseases and suspect the cure of course. This incited experts to apply all the particular progressions like huge data examination, farsighted examination, machine learning and learning computations with a particular true objective to remove profitable data and help in choosing. In this paper, we will present a examination on the headway of colossal data in human administrations structure.
    Keywords: keen examination; machine adjustment; huge data examination; Kidney failure problems; learning estimations; diagnostics;data examination; data mining; sensible examination.

  • A BRIEF STUDY ABOUT NATURE INSPIRED OPTIMIZATION ALGORITHMS   Order a copy of this article
    by S.Thanga Revathi, N.Rama Raj 
    Abstract: Nature inspires Human beings to a greater extent as the Mother Nature has guided us to solve many complex problems around us. Algorithms are developed by analysing the behaviour of the nature and from the working of groups of social agents like ants, bees, and insects. An algorithm developed based on this is called Nature Inspired Algorithms. These nature-inspired algorithms can be based on swarm intelligence, biological systems, physical and chemical systems. A few algorithms are effective, and have proved to be very efficient and thus have become popular tools for solving real-world problems. Swarm intelligence is one of the most important algorithms developed from the inspiration of group of habitats. The purpose of this paper is to present a list of comprehensive collective algorithms that invoke the research scope in that area.
    Keywords: Optimization algorithms; Nature Inspired algorithms; Genetic algorithms.

  • Automatic Detection of Brain Cancer Using Cluster Evaluation and Image Processing Techniques   Order a copy of this article
    by Bobbillapati Suneetha, A. Jhansi Rani 
    Abstract: The Brain Cancer is perceived through radiologist utilizing MRI, which takes fundamentally a most outrageous time. Most of the brain tumor acknowledgment procedures give compound information about the brain tumor and they require in giving a correct result on nearness of tumor. Consequently, a formal guidance with a radiologist is necessary, which transforms into a surplus utilization if there ought to be an event of a non-tumor understanding. The objective of this work is to develop a supporting system that would assist the radiologist with having beforehand said result which reduces the time taken as a primary concern tumor revelation. The proposed procedure includes following stages. At first, the MRI (Magnetic Resonance Imaging) Brain Image is acquired from Brain MRI Image instructive gathering. In second stage the picked up MRI Image is given to the Pre-Processing stage, where the film craftsmanship marks are removed. In third stage, the high repeat parts are removed from MRI Image using distinctive filtering techniques. Finally, the proposed method investigates the best upgrade methodology, known as Ant Colony Optimization (ACO) is considered in this proposed work. The proposed techniques diminish the time unconventionality for brain tumor area which in like manner consolidates more exactness. In this work the MRI brain images are considered as info. The end clients themselves look at the MRI report by typical vitalization without counseling radiologist.
    Keywords: image processing; improvement; Median and Adaptive filter; automatic detection ,filtering; brain cancer; cluster evaluation.
    DOI: 10.1504/IJAIP.2018.10018471
     
  • A Frugal and Innovative, Intelligent Messaging Assistant A Futuristic approach   Order a copy of this article
    by Shriram Vasudevan, Rahul Ignatius, Himanshu Batra, Aswin Tekur 
    Abstract: : For systems receiving large amount of information and requiring prompt decision making, it is the need of the hour to facilitate quick sifting of the data (regardless of scale) and follow a specified course of action at the least possible response time, to provide real time decision making capability. Our system allows users to handle large amount of data streaming in and adopt an appropriate course of action with a trained data model approach. Our system will assess incoming text (or audio which can be converted to text by a Speech to Text conversion system) and decide the criticality (i.e. urgency) of the message based on datasets pre-marked and certain configurations preset by the user. Our system will evaluate the received request and generate a score based on multiple parameters (such as geo, user history, time). A larger score implies that the message is of high importance and a low score implies a message is trivial and may be discarded or placed in a spam folder, based on users specified preferences. The provision of a real time decision system will be very useful for use cases where large amount of information is received and course of action is to be decided instantly. Scalability of conventional systems is an issue as deployment of more personnel to facilitate decision-making may not be feasible. We elaborate three use cases for our system, enterprise scenario, a first responders scenario and a personal use case scenario (as a personal message/call assistant).
    Keywords: Message filtering; real-time decision system; scalable message ranking system; scalable text classification system.

  • Brain Tumour Segmentation using Weighted K-Means based on Particle Swarm Optimization   Order a copy of this article
    by Naresh Pal 
    Abstract: In medical science, Image Segmentation (IS) is a challenging task, it subdivides the image into mutually exclusive regions. An IS is the most fundamental and essential process of classification, description and visualization of the region of interest in several medical images. In the medical field, diagnosis of brain and other medical images are using Magnetic Resonance Imaging (MRI), which is a very helpful diagnostic tool. The traditional technique using MRI Brain Tumour Segmentation (BTS) is extremely time consuming task. This research paper concentrates on the improved medical IS method based on hybrid clustering methods. This hybrid technique is a combination of Weighted K-Means and Fuzzy C-Means (WKFCM), K-means and Particle Swarm Optimization (KPSO). The proposed techniques, identify the brain tumour accurately with less execution time. An experimental result demonstrated that proposed hybrid clustering technique performance is better than the earlier methods like FCM, KM, Mean Shift (MS), expectation maximization, and PSO in three different benchmark brain databases.
    Keywords: Weighted K-means; Fuzzy C-means; image segmentation;.

  • An Embedded System and IoT based approach to determine milk quality at milk collection center - pertaining to Indian conditions.   Order a copy of this article
    by Juluru Anudeep, Kowshik G, Shriram KV 
    Abstract: Milk is considered to be the ideal food because of its abundant nutrients required by both infants and adults. It is one of the best sources of protein, fat, carbohydrate, vitamins and minerals. Possible reasons behind adulteration of milk may include demand and supply gap, perishable nature of milk, low purchasing capability of customer and lack of suitable detection tests. India is one of the largest consumer and producer of milk in the world. A recent study by Indias food safety regulator (FSSAI) found that 68.4% of milk samples examined didnt meet its standards [1]. In 2008, 6 teenagers died of food poisoning in the eastern state of Jharkhand after drinking sour milk at their boarding school [2]. In Spite of implementing various precautionary methods, government and private stakeholders are still struggling to uproot adulteration from the food supply chain. Our innovation is focused on early detection of milk adulterants and ensures the quality of milk for the consumers. We have come up with an IoT solution that will consistently track sensitive and crucial parameters of milk and uploads the parameters into the website by performing data analytics so that user can have a track of their consuming milk.
    Keywords: IoT; sensors; data analytics; webpage; pH; temperature monitoring; milk colour detection; Lactometer.

  • A method for Solving Cold start problem Using Market Basket Analysis.   Order a copy of this article
    by Nitin Mishra 
    Abstract: Recommendation System is the base of E-commerce business across the world. After the advent of 4G technology in developed and developing countries rn, people are using internet more than ever. Lot of options are available for almost everything on Internet. People are confused with all the options. Now a days screens have become smaller and data has become many times. It has been observed that sometimes people leave the portal although information is there. Due to this, web application is unable to present users for their need. Recommendation system makes this easier by giving users options on the basis of history of the user in the system. Now, you can get choices on the basis of your likes and dislikes. But, this recommendation system fails when we have no information about the user and item. In simple words, we did not have user history and we cannot use recommendation algorithm. In this paper, we are suggesting a market basket Analysis (MBA) technique to help us solving this problem to some level. Using data available by Movielense,we develop our model and test on movie domain. We have used movielens dataset as a dataset to prove our method. Market Basket Analysis technique have been used to determine popularity sequence of the movies.rnWe have tested our method on the movielense dataset and be found that a consistent performance between 30 to 60 percent can be obtained.
    Keywords: Recommender systems,Cold-start Problem,Market Basket Analysis,Associative Rule Mining.

  • On Roman Domination of Circular-arc Graphs   Order a copy of this article
    by Akul Rana, Angshu Kumar Sinha, Anita Pal 
    Abstract: Let G = (V;E) be a graph with vertex set V and edge set E. A Roman dominating function is a mapping f : V → {0; 1; 2} such that every vertex u for which f(u) = 0 is adjacent to at least one vertex v with f(v) = 2. The weight of a Roman dominating function is the value $f(V)=sumlimits_{vin V}f(v)$. The minimum weight of a Roman dominating function on a graph G is called the Roman domination number $gamma_R(G)$. The Roman domination problem on a graph G is to fi nd $gamma_R(G)$. This problem is NP-complete for general graphs. In this paper, the same problem restricted to a class of graphs called circular-arc graphs are considered. In particular, an O(n^2) time algorithm is designed using a dynamic programming approach to compute the Roman domination number of circular arc graphs, one of the non-tree type graph classes. Also, we have obtained the bounds of $gamma_R(G)$ for circular-arc graphs.
    Keywords: Design of algorithms; Circular-arc graph; Domination; Roman domination.
    DOI: 10.1504/IJAIP.2018.10020075
     
  • SEA2: Semantic Extractor, Aligner and Annotator - A Framework for Automatic Deep Web Data Extraction, Alignment and Annotation based on Semantics   Order a copy of this article
    by UMAMAGESWARI BASKARAN, Kalpana Ramanujam 
    Abstract: Nowadays huge number of web databases is accessible through front-end search query forms. The data records returned are embedded within HTML templates and returned to the end-user in the form of web pages. These web pages are dynamically generated and are not indexed to search engines. Therefore, they are referred as Deep web pages. They are intended for human understanding whereas they make automated processing difficult. In order to enable machine processing, as needed by many data analytics applications such as business intelligence, product intelligence etc., the data records embedded in those deep web pages has to be extracted and annotated. This paper proposes an automated solution based on inferred semantic rules to perform extraction and annotation of structured data records from Deep web pages. Experimental result shows that the use of domain knowledge in the form of inferred semantic rules improves the accuracy of deep web data extraction process.
    Keywords: deep web; web database; HTML templates; web data extraction; annotation; server-side templates; DOM tree; semantic labeling; hidden web; surface web.

  • An improved algorithm for detecting overlapping communities in social network   Order a copy of this article
    by Mehjabin Kkatoon, W. Aisha Banu 
    Abstract: Social networks or complex networks, contains hidden communities- which used to have some structure and the effort to discover those structures of the communities is a significant step in analyzing the large-scale structure of complex networks. Till now many algorithms have been developed for the detection of those hidden communities inside the complex networks. Community detection algorithms results in either detecting the partitions of the network i.e. non-overlapping communities or detecting the covers of the node i.e. overlapping communities. In this paper an algorithm for detecting the overlapping communities has been proposed. The proposed algorithm has been compared with other community detection algorithms based on various functional metrics like modularity, conductance, assortativity and centrality values of the formed overlapped communities has been compared with the whole network . The data sets have been collected from one of the most social network i.e. from Facebook of different areas, i.e. from politics, from shopping sites i.e. of Amazon and Flipkart.. The proposed algorithm is semi-supervised algorithm and it can be applied to networks of huge number of nodes i.e. of around 1000 nodes. The proposed approach can detect the individuals in the social network who sometimes belongs to more than one community.
    Keywords: centrality; modularity; overlapping community; social network; community detection.
    DOI: 10.1504/IJAIP.2021.10044781
     
  • Openflow Groups Based Fast Failover Mechanism for Software Defined Networks (SDN)   Order a copy of this article
    by Harish Sekar, Shriram K Vasudevan 
    Abstract: Software-defined networking (SDN contains several sorts of network technology which is used to design, build and manage networks. The abstraction of lower-level functionality in SDN enables network administrators to handle the network services. We have dealt with the link fault tolerance issue using SDN. Link fault tolerance has been handled so far either by using the protection or the restoration scheme. We have proposed a hybrid scheme of both the techniques and per-link Bidirectional forwarding detection sessions are applied for each links and handled the problem accordingly. Our method also ensures that the transfer of control to the controller from the switch does not take place unnecessarily. This has been done with a target of reducing the overall response time for link resiliency. Therefore these techniques make sure that the link failure is handled with Software Defined Network (SDN). Our methods have been compared with the traditional scheduling and link fast failover methods to prove by results, that it can handle scheduling and recovery with a better response time
    Keywords: OpenFlow; SDN; Managing Networks; Scheduling; Link Failure; Recovery.

  • Human Action Recognition Using Spatio-Temporal Skeletal Data   Order a copy of this article
    by Awadhesh Kumar Srivastava, K.K. Biswas 
    Abstract: Human action recognition from video is an important task with multiple challenges like cluttered background, luminance, occlusions etc. Availability of depth sensor like Kinect makes the action recognition task a bit easy but it brings new challenges in terms of computation cost and noise. We present a novel, computationally economical but effective method for human activity recognition using skeleton data. We consider the relative changes in body parts positions to recognize the activity in the video and propose sum of temporal differences of Joint-Pair-distances (STD) as feature descriptors. Further, we show that using random forest as a classifier with these features, can produce better accuracies compared to various recent state of the art methods. We establish this by experimenting with publicly available MSR-action 3D dataset and MSR-Daily Activity datasets. The results show that proposed method archives accuracies of 93.9% in former dataset while 87% in latter dataset.
    Keywords: surveillance; tracking; RGB video; human gesture; activity recognition; depth data; skeleton data; MS-kinect;.
    DOI: 10.1504/IJAIP.2018.10023078
     
  • Efficient Wastewater Discharge Location Speculation System based on Ensemble Classification   Order a copy of this article
    by Brintha Malar C., S. Akilandeswari 
    Abstract: Water pollution is one of the serious threats to the society, as water is the primary need of every organism thriving on earth. It is necessary to control and detect water pollution by assessing the quality of water. However, the production of wastewater is always there and is inevitable. Hence, it is equally important to treat the wastewater in a better way, such that the environment is not affected. The pollution control board has formulated certain standards, which provides the range of values for each pollutant and the feasible discharge locations. Taking these standards as the input for training the system, this work extracts basic statistical features such as mean, standard deviation, entropy and variance for training the classification system. The ensemble classification is incorporated, which includes k-Nearest Neighbour (k-NN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM). The performance of the proposed approach is evaluated in terms of accuracy, sensitivity and specificity. The results of the proposed approach are found to be satisfactory.
    Keywords: water pollution; ensemble classification; wastewater discharge.

  • Optimal Allocation of Multiple FACTS Devices Considering Power Generation Pricing for Optimal Reactive Power Dispatch Using Kinetic Gas Molecule Optimization   Order a copy of this article
    by Pradeep Panthagani, R. Srinivasa Rao 
    Abstract: Optimal Reactive power dispatch (OPRD) is a very immense issue in a power system, which is a complicated non-linear optimization issues with a combination of discrete and continuous control variables. Optimization techniques are playing a major role in providing more effective result for such complications. An efficient optimization technique called Kinetic Gas Molecule Optimization (KGMO) is proposed for solving multi-Objective OPRD (MOPRD) problem in this work. Regarding this three major FACTS (Flexible AC Transmission System) devices such as devices like Static Var Compensator (SVC), Thyristor controlled Series Compensator (TCSC) and Unified Power Flow Controller (UPFC) are optimally allocated in the test system. Since the cost of system increases considerably with these devices, a novel approach of considering Power Generation Pricing in MOPRD is done in this work. For this purpose, KGMO is applied along with Pareto optimality (PO) concept, which gave considerably superior results compared to conventional results. This is implemented and tested in IEEE 30 bus system considering multiple objectives.
    Keywords: FACTS (Flexible AC Transmission System); KGMO (Kinetic Gas Molecule Optimization); ORPD (Optimal Reactive Power Dispatch); Multi-objective ORPD (MORPD); Static Var Compensator (SVC); Thyristor controlled Series Compensator (TCSC); UPFC (Unified Power Flow Controller);.
    DOI: 10.1504/IJAIP.2018.10024248
     
  • Effective Statistical Texture Features for Segmenting Mammogram Images Based on M-ARKFCM with Multi-ROI Segmentation Method   Order a copy of this article
    by Ramayanam Suresh, A. Nagaraja Rao, B. Eswara Reddy 
    Abstract: Mammogram segmentation using multi-region of interest is one of the most emerging research areas in the field of medical image analysis. The steps involved in the research are classified into two types: 1) segmentation of mammogram images 2) extraction of texture features from mammogram images. In recent years, the mammogram segmentation systems become welldeveloped, but still Feature Extraction (FE) algorithms are facing problems like poor outcome in severe lighting variations, illuminance, etc. In order to overcome these difficulties, an effective methodology is proposed in this paper, which consists of three stages. In the first stage, mammogram images from the Mammographic Image Analysis Society (MIAS) dataset is enhanced using Laplacian filtering. Then, the preprocessed mammogram images are used for segmentation using Modified Adaptively Regularized Kernel based Fuzzy C Means (MARKFCM). After segmentation, Statistical texture FE is applied for distinguishing the patterns of cancer and non-cancer regions in mammogram images. Finally, the experimental outcome shows that the proposed approach improves the segmentation efficiency by means of statistical parameters compared to the existing methodologies.
    Keywords: Image segmentation; mammographic image analysis society; modifiedadaptively regularized kernel-based fuzzy c means; texture features;.
    DOI: 10.1504/IJAIP.2018.10021290
     
  • A Review of Different Techniques Used for Routing in wireless Sensor Networks   Order a copy of this article
    by Tanaji Dhaigude, Latha Parthiban 
    Abstract: The aim of this paper is to summarize all information related to routing in wireless sensor networks (WSNs). The available routing techniques are divided in 3 ways: hierarchical, flat and location based routing. WSNs are made of small nodes, wireless communication capabilities and computation. Various researchers are working on the technique which can be a combination of effective routing and optimized energy consumption. From last two decades this has been issue to improve the power usage of the router used in WSNs. The energy issue can be addressed by using different protocols in WSNs router. Currently available protocols are: query based, multipath, QoS based, Negotiation based and coherent based. In this paper each routing technique is discussed in great detail with their advantages and disadvantages. Authors also have highlighted the future area of research.
    Keywords: wireless sensor networks; Fault Tolerance; Scalability; Energy consumption.

  • Content Based Fabric Image Retrieval System by Exploiting Dictionary Learning Approach   Order a copy of this article
    by Jasperline Thangaraj, Gnanadurai D 
    Abstract: Owing to the skyrocketing growth of the image utilization, it is necessary to organize the images by some means. CBIR is the system that matches the query image with the image database and fetches the relevant images with respect to the query image. This makes the image search process easier and it has found many applications in almost all domains. The main issues of a CBIR system are the accuracy and time consumption. This work presents a Content Based Fabric Image Retrieval System (CBFIR) which relies on the extraction of colour and texture features. The initial clusters are built by the Fuzzy C Means (FCM) algorithm and the dictionaries are constructed for every cluster. The clusters of each dictionary are updated by Simultaneous Orthogonal Matching Pursuit (SOMP) algorithm. The proposed approach compares the test image with the constructed dictionaries, so as to detect the dictionary with sparsest representation. The performance of the proposed approach is observed to be satisfactory in terms of accuracy, precision and recall rates.
    Keywords: Fabric image retrieval; image clustering; feature extraction; dictionary learning.

  • An Energy-Efficient Ensemble Clustering Based on Multiple Disjoint and Non Linear Structures for Wireless Sensor Network   Order a copy of this article
    by Sheeja Rani, Siva Sankar 
    Abstract: The evolution of small-scale, cost effective and intelligent sensors with effective communication capabilities between users has instigated the emergence of wireless sensor networks (WSNs). As the energy of each sensor node in WSN is generally restricted, efficient use of energy is considered to be the foremost problem to be addressed. Besides, with larger sensor nodes in WSN, load balancing is regarded as the second issue to be addressed. Different clustering algorithms produce different partitions because it imposes different structure on the data. Hence, the performance of single clustering algorithm is not sufficient. For these cases, ensemble clustering through non-linearity becomes an interesting alternative. Here, an ensemble of Normalized Spectral Cluster and Separation K Means clustering algorithm is employed. The new framework called Normalized Spectral Cluster and Separation K Means (NSC-SKM). NSC-SKM determines optimal clusters in a network. In fact, the framework uses the eigenvector corresponding to the subsequent infinitesimal eigenvalue of the Laplacian, therefore achieving balance between sensor nodes in the cluster. As a result, multiple disjointed issues is said to be addressed, ensuring load balancing. Then an enhancement approach is investigated to minimize the energy consumption and improves the network lifetime, through non-linear structures. It has been achieved by mapping the sensor nodes non-linearly into a higher-dimensional feature space via a separation function. The energy and load performance of NSC-SKM framework is studied through an extensive simulation experiments which demonstrate the appeal of the proposed framework through significant performance gains compared to baseline solutions.
    Keywords: Wireless Sensor Networks; Load Balancing; Normalized Spectral Cluster; Separation K Means; Graph Theory; Similarity Matrix; Eigen value; Laplacian.

  • Asymmetric Enciphering of Images using Affine Transform and Fractional Fourier Transform   Order a copy of this article
    by Savita Anjana, Indu Saini, Phool Singh, Anil Kumar Yadav 
    Abstract: This paper presents an asymmetric enciphering technique for binaryrnand grayscale images that uses affine transform with amplitude and phaserntruncation operation in fractional Fourier domain. Affine transform is used tornintroduce randomness for additional security, and to resist specific attackrnrecently mounted on asymmetric schemes. The scheme is validated for binaryrnand grayscale images in MATLAB. The affine transform parameter and thernorders of fractional Fourier transform serve as encryption keys in addition torntwo private keys of asymmetric cryptosystem. The scheme has been tested forrnits sensitivity to these parameters. The scheme is also evaluated for itsrnrobustness against the occlusion and noise attacks. Other usual attacks and the specific attack on the scheme are also discussed
    Keywords: Asymmetric cryptosystem; affine transform; fractional Fourierrntransform; binary and grayscale images.
    DOI: 10.1504/IJAIP.2021.10026407
     
  • Fuzzy-based efficient task scheduling scheme on heterogeneous multicore processor   Order a copy of this article
    by K. Indragandhi, P.K. Jawahar 
    Abstract: A scheduler plays a major role in scheduling a task in multicore processor which will improve the performance by efficiently utilising the resources of each core. A heterogeneous multicore processor contains cores with different capabilities. The main objective of this work is to implement fuzzy logic-based efficient task scheduling scheme for the non-periodic tasks on soft real time heterogeneous multicore processor. Two fuzzy logic-based scheduling schemes namely dynamic priority generator (DPG) and efficient task scheduling scheme (ETSS) is proposed. Simulink model was designed for different test cases to measure the performance of the proposed system. Results shows that CPU utilisation of core 2 is 56.7% for the first set of membership function and core 3 is 49.4% for the second set of membership function among the heterogeneous quad core.
    Keywords: heterogeneous; multicore processor; fuzzy inference system; task scheduling; membership function.
    DOI: 10.1504/IJAIP.2018.10025677
     
  • Certain properties of interval-valued intuitionistic fuzzy graph   Order a copy of this article
    by Hossein Rashmanlou, Ali Asghar Talebi, Seyed Hossein Sadati 
    Abstract: The basis of the concept of interval valued intuitionistic fuzzy sets was introduced byrnK. Atanassov. Interval valued intuitionistic models provide more precision, rnexibility, andrncompatibility to a system than do classic fuzzy mode. In this paper, we have introducedrncertain concepts of covering, matching and paired domination using strong arcs or e ectivernedge in IVIFGs with suitable examples. We investigated some properties of them. Also,rnwe have calculated strong node covering number, strong independent number and otherrnparameters of complete and complete bipartite IVIFGs.
    Keywords: Interval-valued intuitionistic fuzzy gragh; strong arcs (e ective edge); covering,rnmatching; paired domination.
    DOI: 10.1504/IJAIP.2024.10061856
     
  • Estimating the Perspicacious features of ECG Recording Based on Template Classification for detecting Atrial Fibrillation   Order a copy of this article
    by V.R. Vimal, P. Anandan, V. Induja 
    Abstract: Atrial Fibrillation (AF) is the most extreme basic managed cardiovascular arrhythmia, happening in 1-2% of the overall public and is related with generous demise. It is likewise in charge of 15% to 20% of all strokes. The avaliable AF distinguishing techniques are here and there unfit to segregate AF from some different arrhythmias and may misclassify other unpredictable rhythms or uproarious ECGs as AF, bringing about false cautions. The focal point of our exploration work is to build up a calculation to recognize AF with high precision, vigor to commotion, and low false caution rate. Since AF influences both the heart rate inconstancy and ECG morphology, the proposed strategy joins characterization in view of heart rate fluctuation highlights and layouts of the ECG waveforms. The idea of Compressive Sensing essentially called CS that has starting late been associated as a low multifaceted nature weight structure for whole deal seeing of electrocardiogram signals using Wireless Body Sensor Networks. This strategy keeps an eye on the issue of estimating heartbeat rate in compressive recognizing electrocardiogram (ECG) accounts, keeping up a vital separation from the redoing with whole signal. Methodologies considered a structure in which ECG signals are addressed under the kind of CS straight estimations. Then QRS territories are evaluated from compacted space by handling the relationship with pressed ECG ,based on QRS design.rnrn
    Keywords: Wireless body sensor networks; Atrial fibrillation; Compressive Sensing.
    DOI: 10.1504/IJAIP.2018.10025790
     
  • Classification and Comparison of IP Traceback Techniques for DoS/DDoS/DRDoS Defense   Order a copy of this article
    by Marjan Kuchaki Rafsanjani, Hashem Bagheri Nezhad 
    Abstract: The invention of the Internet environment has increased the speed of data transmission, however, the attacks in this environment are growing exponentially. Furthermore, identifying the source of the attacks is very difficult due to the vibrant and anonymous nature of the Internet. Denial-of-Service (DoS) attacks are one type of the attacks in this environment that can be done in many forms. Denial-of-Service (DoS) or Distributed-Denial-of-Service (DDoS) or Distributed-Reflector-Denial-of-Service (DRDoS) attacks try to saturate the victim network servers (with external requests) and also they try to disable its resource for its lawful users. IP tracback is the ability to identify the source of this type of attacks. Thus, IP traceback is an important step to defense against these types of the attacks. Many IP traceback schemes have been presented till now. In this article, we review several presented schemes in the recent decade and we compare these methods against the predefined metrics that help the researchers to discover the gaps to perform the further research in this area.
    Keywords: IP traceback; Traceback schemes; Packet marking; Packet logging; DoS/DDoS/DRDoS defense;.

  • Abnormality Identification of Breast Mammogram Image Segmentation with Iterative Restricted Mode Algorithm   Order a copy of this article
    by Nagiii Reddyyy 
    Abstract: The breast Image division is a regular issue in medicinal picture preparing. For the scientist to remove the data with great determination without loss of points of interest. In this paper, we propose a division strategy by utilizing the iterative restricted mode (IRM) calculation and Markov Random field (MRF) model to recognize the variation from the norm in mammogram pictures. For all cycles the most reduced vitality name making is permitted by IRM. This strategy takes after the high compacted connection between limit name MRFs. In this model is tried with 5 pictures and assessment is done utilizing target assessment criteria, namely the Jaccard coefficient (JC) and Volumetric Similarity (VS) and Variation Of Information (VOI). Global Consistency Error (GCE) and Probability Rand Index (PRI). By utilizing Image quality measurements the execution assessment of divided pictures likewise assessed. The reproduced comes about proposed by utilizing T1 weighted pictures are contrasted and the current model.
    Keywords: MRI method; repetitive mode; Markov Random field; segmentation of Images; Kernel; Quality metrics.

  • LSTM based Statistical framework for human activity recognition using mobile sensor data   Order a copy of this article
    by Krishna Kishore 
    Abstract: Fall detection plays an essential part in the healthcare monitoring system and also helps the elderly and disabled people. Advances in supporting technologies have pushed researchers to focus on activity recognition to improve the quality of needy people in their emergency. In this paper, authors have proposed a methodology for an efficient detection of automatic fall, which can perceive every possible fall event by using Human Activity Recognition (HAR). Eigen features and some other time related features are computed to the data, collected from the sensors associated with Android based mobile devices. These features will be analyzed to classify physical activities such as fall, walking, sitting, upstairs, downstairs, jogging, etc. In this work, Long Short Term Memory (LSTM) Neural Network is used to classify human activities. Based on this, alerts will be generated in case of fall detection, otherwise data will be archived for the future references. Performance of the proposed framework is evaluated on two benchmark datasets (WISDOM and UCI) and one real time tracked dataset. The accuracy of the proposed framework on tracked dataset is 91.48% and outperforms other classifiers
    Keywords: Fall detection; Smartphone Sensors; Activities of Daily Living (ADL); Human Activity Recognition; Long Short-Term Memory Classification; etc.

  • A Survey on Wireless Networks to Balancing the Load in Wireless Mesh   Order a copy of this article
    by Subba Rao 
    Abstract: Now a days wireless technology occupy the very prominent role in all the sectors and WMNs have play the prominent role in coming generations because it has many benefits over other wireless networks. However, still there are many technical issues are there which are going to discussed in WMN. The major problem of WMNs is sustained the balancing. In WMNs, comparison between the incoming data traffic to a node is greater than the outgoing data traffic, then congestion is high in this network. Various authors have proposed to reduce the congestion and for improving the network throughput. This paper discussed about analysis of various load balancing techniques to facilitate the researchers as well as practitioners in choosing a proper load balancing technique for improving the network performance.
    Keywords: Wireless mesh network;Gateway;Load balance;Path;Router;NS2; etc.

  • Prediction and Detection of Kidney Diseases using Ensemble Classification   Order a copy of this article
    by Suresh Babu 
    Abstract: Chronic Kidney Disease (CKD) is the most dangerous disease occurred in many of the persons now days. As the research is going on there is exact reason for damaging of kidneys. Some research says that this may be due to the lack of drinking water and high blood pressure and Diabetes and some of the diseases such as severe dehydration, kidney trauma. After all the research done, in this paper, the new prediction and detection of chronic kidney disease using ensemble data mining classification is described for the better results.
    Keywords: CKD; Diabetes; Diabetes.

  • Towards Smart Healthcare System in Airlines with IoT and Cloud Computing   Order a copy of this article
    by Veeraa Anjaneyuluu 
    Abstract: The world is becoming smart with the advances brought in the new technologies. In the recent past, Internet of Things(IoT) is playing major role in all the fields of the world. Smart health care application are developing with many accepts and Cloud Computing also effective part for data communication around the world. Detection and controlling of contagious diseases is also a major issue, when people travel all over the world in airways. In this paper we propose architecture to smart identification of the person/s with diseases while travelling in airlines. Adoption of this architecture able to control and stop the pervasive healthcare. An effective ways are discussed and to determine the percentage of infection of particular disease using probability tables. Based on our concept and results we are also given directions to development of tools and applications.
    Keywords: Internet of Things; Cloud Computing; Contagious Diseases; Airlines System.

  • MULTI-MODAL FEATURE FUSION AND ITS APPLICATION TO BRAIN TUMOR CLASSIFICATION   Order a copy of this article
    by Jyothsna Devi 
    Abstract: Tumor is a mass of abnormal cells. The tumor that grows inside human skull is termed as brain tumor. Human brain is enclosed by the skull. Tumor that grows in such restricted space can cause problems. Tumors that grow in the brain are categorized as cancerous or noncancerous. If these types of tumors cannot be detected at their early stages may lead to brain damage, and it can be life-threatening. In this work we have used SVM to detect whether the given MRI image of a brain tumor is malignant or benign. Recent literature shows that Support Vector Machines (SVM) is a supervised classification technique that has increased popularity as they exhibit high generalization ability even trained with small set of training data. SVM has good generalization ability to solve many real-time problems. In this work we have used SVM based classifier to identify whether the tumor is malignant or benign. Initially hand crafted features like Discrete Wavelet Transform (DWT) or gist features are extracted from the given MR images, then follows preprocessing and segmentation tasks followed by SVM based classification. Each of these representations have their own advantages of representing images. If we consider any single representation then we are ignoring the advantages of using the other representation. Our proposed method tried to exploit the benefit from different representations of the images. Motivated from the fusion based classification models, in this work we have extracted different representations from the given MR images and fused them to represent the image as a single feature vector. We have applied different fusion techniques to improve the performance of the SVM based tumor classification. Our experimental studies on bench mark datasets show that fusion techniques can enhance the accuracy of SVM classification for brain tumor classification. Along with fusion we have also tried to examine the efficiency of various kernels on the classifiers performance.
    Keywords: Support Vector Machine; Otsu Segmentation; Discrete Wavelet Transform; Non local mean filter; fusion.

  • CUSTOMER REVIEW SUMMARIZATION BASED ON GENERIC WRAPPER AND OPINION MINING   Order a copy of this article
    by K. Priya, K. Dinakaran 
    Abstract: Now-a-days onine shopping by customers is getting increased day by day. Customers are having awareness in the case of buying products based on the features of the products. The features of the product may be model, colour, size, Durability or price.The customer reviews or feedbacks based on the price of the products are collected from three different shopping websites and then consolidated and also ranked under separate website.The customer will be buying the product based on lowest price ,which online shopping website is holding.Through this work customer can avoid confusion while shopping for products.Generic wrapper and VIPS techniques are used.These details can also be posted or shared in social networks webpages for customers convenience.Then the customers can maintain budjet and preventing them from taking wrong decision during online shopping.Searching Time for product information under each website can be reduced for the customers.
    Keywords: Generic wrapper; Wrapper Generation; product review; social network; Review Summarization; E-Commerce.
    DOI: 10.1504/IJAIP.2021.10030025
     
  • Combination of Machine Learning methods to Solve Cold start problem in Recommender system   Order a copy of this article
    by Nitin Mishra, Vimal Mishra 
    Abstract: Recommender systems are special type of intelligent systems which exploits historical of user rating on items to make recommendation of items for those users. They are used in wide range of applications like online shopping, E-Commerce services social networking applications and many more. These are also used in banks and other services. They can also be used in fault finding in critical systems. In our paper we are discussing a problem known as cold start problem where you new user has a problem as he has missing history. We have used clustering approach to cluster users and then using these cluster labels for supervised machine learning to solve the cold start problem of new users. We have validated our solution on movielens dataset and found it to be solving cold start problem in a magical way. so we are claiming our approach to be a novel approach for solving cold start problem using combination of several methods some of which belong to collaborative filtering domain and others belong to content based domain. We have done exhaustive check so that it could be our fault free solution. As our method predict certain items so the results are accurate to our domain and can vary with small amount in similar domains. But theoretically, our Method can be used for solving cold start problem in general in any domain.We also claim that our method performance becomes better with increasing value of N of TopN Recommendation.
    Keywords: Cold start problem;Recommender systems; Machine learning;classification;clustering;k-modes clustering.

  • DEVELOPMENT OF ELECTRONIC PEST CONTROL IN PADDY FIELDS   Order a copy of this article
    by Ram Chandran.M, Vishnu Priya.R. 
    Abstract: Worldwide, agriculture is considered as the backbone of a countrys economy. The contribution of agriculture to Indias economy is steadily declining with Indias economic growth. Still, agriculture plays a significant role in the broadest economic sector. The major objective of the present work is to repel the pests that affect the agricultural fields especially paddy field. The pests that mainly affect the paddy fields are small insects, grasshoppers, and moths. Initially, we capture the images of the field and process these images using MATLAB software where we developed codes that find out whether the small insects are high or low. If the insects are high, then an appropriate pesticide is sprinkled over the field which is controlled by a PIC16F877A microcontroller. Further, we collected the frequency sensitivities of grasshoppers and moths to repel them. The time period of the day at which the grasshoppers and moths are maximum is obtained from previously published paper. Using this information we generate these frequencies at appropriate timings. As a result, the paddy field is free from grasshoppers and moths.
    Keywords: Frequency bandwidth; grasshoppers; image processing; moths; and pest control.

  • Machine Learning Approach to Predict Purchase Decision of Bank Products and Services   Order a copy of this article
    by Saumya Chaturvedi, Vimal Mishra 
    Abstract: We propose a machine learning approach to predict purchase decision of bank products and services. The data were collected from May 2008 to May 2014 of a Portuguese bank. This investigation will help to predict the business of the bank and financial inflation and recent trends in bank product and services. The investigation is focused on the classification and prediction of bank telemarketing calls for term deposit product. We have analyzed a large data set of 41188 observations related with bank client, product, services and socioeconomic attributes. Initially, the dataset was having 150 features and we have selected 21 most relevant features using standard adaptive forward selection and intelligence quotient. We have also compared four machine learning approaches Conditional Inference trees(Ctree), recursive partitioning (Rpart), Support Vector Machines(SVM) and RandomForest. The paper contains an impact analysis of changing training data set and training time of a model. Observatory study shows the integration of both parameters: accuracy and model learning time to form a generalized and optimized solution for predicting bank business.
    Keywords: Machine Learning;Business Intelligence;Data Mining;Decision support systems.

  • Optimized Feature Selection and Categorization of Medical Records with Multi Kernel Boosted Support Vector Machine   Order a copy of this article
    by Lakshmii Prasannaa 
    Abstract: With the fast growth of Internet and mobile usage, huge volumes of medical documents, which contain information of patients, diagnostic, past disease history and medication, are being generated electronically. In the field of text mining, document categorization has become one of the emerging techniques due to large volume of documents in the form of digital data. The main objective of the proposed work is to identify disease treatment relationships and predict the diseases among medical articles. In this paper, highly relevant and more correlated features have been extracted using Probabilistic Latent Dirichlet Allocation (P-LDA) and randomized iterative feature selection approach. These features were classified with Multi Kernel Boosted Support Vector Machine (MKB-SVM), and then their performance was evaluated on both PubMed and MEDLINE databases. Performance evaluation of the proposed approach on DB-1 and DB-2 was 98.7% and 92%, respectively. The evaluation illustrated that the proposed approach outperformed the existing state-of-the-art classification methods.
    Keywords: Allocation of Latent Dirichlet ; Classification of Medical Text; SVM classification; Ada-Boost.Multi-kernel.

  • Optimization of Sparse Linear Array Using State Transition Algorithm   Order a copy of this article
    by Pratistha Brahma, Banani Basu 
    Abstract: State Transition Algorithm (STA) has been used for sparse antenna array designing. A sparse linear array consisting of different core elements has been optimized using STA. The optimal solution is searched by changing the number of sparse elements and current excitation values of the core elements under a set of practical constraints. Number and position of sparse elements are optimized in order to achieve minimum Side Lobe Level (SLL) for a given Half Power Beam Width (HPBW) using various design examples. The paper has been studied the tradeoff between SLL and Directivity of the array for different numbers and positions of the sparse elements. Results obtained using STA has been statistically compared with that of the Particle Swarm Optimization (PSO) algorithm and Artificial Bee Colony (ABC) algorithm and ensures improved performances.
    Keywords: Sparse Antenna Array; STA; PSO; ABC; SLL; Directivity.

  • VLSI Realization of an Efficient Image Scalar Using Vedic Mathematics   Order a copy of this article
    by V. Ramadevi, K. Manjunatha Chari 
    Abstract: A low-complexity algorithm using Vedic Mathematics is intended for VLSI realization of an efficient image scalar. The proposed scalar comprises of a modified area pixel interpolator, edge detector and Vedic Multiplier. To decrease the obscuring and aliasing effects created by the area-pixel model and to conserve the image edge features productively an edge catching method is embraced. Moreover, a Vedic division unit is utilized for enhancing execution of the scaling processor without any rounding error correction techniques. It additionally accomplishes advancement at all levels of digital systems reducing power consumption. The proposed architecture is capable to achieve 5.28-K gates count using 200 MHZ, and computation time is 14.37 ns synthesized by 0.13-μm CMOS technology. Through comparison with previous techniques, this work can reduce gate counts by 18% and want only a one-line-buffer memory.
    Keywords: Image scalar; line buffer; sharpening filter; Vedic mathematics; VLSI;.

  • AN INNOVATIVE and SAFE TECHNOLOGY BASED ALTERNATIVE FOR LEGACY LOCKER SYSTEMS   Order a copy of this article
    by Anudeep J, Kowshik G, Giridhararajan R, Shriram KV 
    Abstract: These days, storing money, gold and other valuables in the bank lockers has become a worrying aspect to the citizens all around the world. According to the statistics on the bank robberies and loots, India almost lost $27.9 million(180 crore rupees) only on loots and burglaries in past 3 years .And there are cases being noticed where the burglars attempted to loot the bank with a disguised costume of a nun on them so as to make the bank managers believe that they are the original owners of the locker. Apart from the incidents happened all around the world, improvisations done to do the lockers safeties every year was mostly found are of only in the mechanical way i.e., lockers were given strength by manipulating the materials used. But, unlike to all those works, we come up with a system that could effectively face these kinds of problems and could even log the data like time of access to locker, changes occurred in the weight of the locker etc., and increase the security of the bank lockers making the individuals feel much safer on their property.As there is no intervention of men it will be a more accurate and safer method.The proposed system works with two levels of security, one of them is face recognition of the owner with the priorly given photo of owner during his registration in the bank.They should pass the face recognition test after which they will enter the second level of authentication where the user has to set the handles to a unique angle key(which is similar that of an ATM Pin) which is provided to them. Our system recognizes the face of the person who visits the bank for access to the locker, by using haar classifier, edge, and line detections features and the faces available in the database and activates the access to the only respective locker. One can noticeably understand that when it is said the person is given access to the locker that means all the other lockers stay deactivated for the access and any trail to open them, triggers the alarm. When the person reaches locker there is a second stage of security, where the person has to open the locker by rotating the handles to a certain angle.This action needs care and can be done perfectly by the owner alone. So, this system could effectively enhance the security of the lockers
    Keywords: Material strength; Haar cascade features,edge and linerndetections,rotating handle locker.

  • Simulation and Practical Implementation under Different Scenarios of Indirect Incremental Conductance Algorithm for MPPT of PV System.   Order a copy of this article
    by Noureddine Bouarroudj, Amor Fezzani, Boualam Benlahbib, Bachir Batoun, Said Drid, Djamel Boukhetala 
    Abstract: Simplicity and good tracking performance have made the incremental conductance (INC) algorithm for maximum power point tracking (MPPT) of photovoltaic (PV) systems the most widely used algorithm. This paper treats of simulation and practical implementation of the indirect INC algorithm with a conventional proportional integral (PI) controller under different scenarios. Firstly, a comparison between indirect INC algorithm and the direct one is carried out, and in which the indirect INC algorithm is shown to be superior. Secondly, a simulation using Matlab/Similink program is conducted under standard climatic conditions, immediate change of irradiance and under immediate change of resistive load value. Finally, the validated indirect INC algorithm is implemented using a real prototype under the same scenarios as in the simulation.
    Keywords: PV-module; Boost converter; Direct INC algorithm; Indirect INC algorithm.
    DOI: 10.1504/IJAIP.2019.10021027
     
  • Signless Laplacian Energy of Bipolar Fuzzy Graphs with Application   Order a copy of this article
    by Hossein Rashmanlou, Muhammad Akram, Danish Saleema 
    Abstract: This paper presents certain notions, including Laplacian energy of bipolar fuzzy graphs(BFGs,rnfor short), signless Laplacian energy of BFGs, Laplacian energy of bipolar fuzzy digraphs(BFDGsrnfor short) and signless Laplacian energy of (BFDGs). Further, it describes useful propertiesrnand bounds of Laplacian energy of BFGs and signless Laplacian energy of BFGs. Moreover,rnthis article discusses an application of proposed concepts in decision-making.
    Keywords: Laplacian energy of bipolar fuzzy graphs; signless Laplacian energy; decisionmaking.

  • A Low Quality Medical Imaging Registration Technique for Indian Telemedicine Environment   Order a copy of this article
    by Syed Thouheed Ahmed, Sandhya.M Sandhya.M, Sharmila Sankar 
    Abstract: Telemedicine is growing in India and Indian environment needs to be improved for acquiring and transmitting datasets for consultation and diagnosis. These attributes are correlated with internal image quality enhancement. In this paper, a medical imaging registration and re-verification technique is proposed for low quality datasets transmitted in under-rated transmission channel. The registration approach is integrated with multiple samples of acquired datasets, sequentially processed. Thus improving the mapping, transformation time and peak signal to noise ratio. The re-verification process assures double authentication for registered image on comparison with referenced sample. The approach is tested on open medical data samples of UCL repository transmitted under low line bandwidth of Indian transmission channel and Internet standards. The proposed approach serves as a better means for diagnosis and feature extraction for tele-diagnosis and consultation in Indian rural telemedicine environment.
    Keywords: Image registration; India Telemedicine; Medical Image Processing.

  • An inventive and Innovative Integrated home network media system A novel approach   Order a copy of this article
    by Aswin Tekur, K.V. Shriram 
    Abstract: A common problem in TV viewing is watching programs on a single TV set because only one program can be watched at a time. Streaming is continuous and real-time, causing interruptions and clash among viewers (who wish to view different channels at the same time) and ultimately ruin the viewing experience. Our objective is to present a hardware unit (that is compatible with a smart TV set) to accommodate a range of features, such as: allowing simultaneous transmission of video from multiple channels (to network connected devices over a Limited Area Network), with pause/ play options, recording for certain time duration (made possible using memory buffers). These above functionalities require modification in the TV architecture of currently available systems, to support these functionalities. One component of our system (the transmission unit) can either be an additional hardware component in the TV set, or in the design of a portable flash drive (functioning similar to that of a dongle), for purposes of convenience and portability. The proposed system is aimed at making huge strides in the field of Television viewership and offers meaningful convenience features to enrich viewers experience, with minimal modification to presently used Television systems and make more utilization of network connected devices (such as laptops, tablets, smartphones). By eliminating need for multiple TV connections and using our system instead, one can save money, time and obtain many new features that are not offered by currently available Television sets.
    Keywords: Simultaneous video transmission; Advanced TV system; TV system over Limited Area Network; Home environment Television system; Multi viewer multi program TV system;.

  • Domination and Product Domination in Intuitionistic Fuzzy Soft Graphs   Order a copy of this article
    by R. Jahir Hussain, S. Satham Hussain, Sankar Sahoo, Madhumangal Pal, Anita Pal 
    Abstract: This manuscript deals with the domination and product domination of intuitionistic fuzzy soft graphs. By using the concept of strength of a path, strength of connectedness and strong arc, the domination set is established. The necessary and suficient condition for the minimum domination set of intuitionistic fuzzy soft graph is investigated. Further some properties of domination number of product intuitionistic fuzzy soft graphs are also obtained and the proposed concepts are described with suitable examples. The weight for a domination of intuitionistic fuzzy soft graph is also established.
    Keywords: Intuitionistic fuzzy graphs; Fuzzy soft graphs; Product domination; Strength of connectedness.
    DOI: 10.1504/IJAIP.2019.10022975
     
  • Novel Deep Learning Model with Fusion of Multiple Pipelines for Stock Market Prediction   Order a copy of this article
    by Abhishek Verma 
    Abstract: Deep learning has become a powerful tool in modeling complex relationships in data. Convolutional neural networks constitute the backbone of modern machine intelligence applications, while long short-term memory layers (LSTM) have been widely applied towards problems involving sequential data, such as text classification and temporal data. By combining the power of multiple pipelines of CNN in extracting features from data and LSTM in analyzing sequential data, we have produced a novel model with improved performance in stock market prediction by 20% upon single pipeline model and by five times upon support vector regressor model.rnWe also present multiple variations of our model to show how we have increased accuracy while minimizing the effects of overfitting. Specifically, we show how changes in the parameters of our model affect its scores for training and testing, and compare the performance of a multiple pipelines model using three different kernel sizes versus a single pipeline model.rn
    Keywords: Stock prediction; S&P500; CNN; LSTM; Deep learning.

  • A Key Pre-distribution Protocol for Node to Node and Group Communication in Wireless Sensor Networks using Key Pool Matrix   Order a copy of this article
    by PREMAMAYUDU BPM 
    Abstract: Sensor networks have huge demand in various fields like military, environment monitoring, hospitals and many hostile environments. Further, they are also used in application of internet of things where many number of sensors is connected through internet. These applications demand security issues like confidentiality, authentication, integrity, because of their deployment areas and sensitivity of the data. By considering these issues, the key management plays an important role in many information security solutions which are used information protection. The proposed work exploits the various vulnerabilities in the sensor network and addresses various kinds of solutions for vulnerabilities through proposed key distribution scheme. The key generation and distribution implemented using key pool matrix. The comparison and analytical analysis are shown that the proposed work requires less communication and storage space at each sensor. Further, the prosed work can also increase resilience, reduce key compromise and number of revocation operations compared with other schemes.
    Keywords: Key pre-distribution in wireless sensor networks; Attacks; Node capture.

  • New Features for Language Recognition From Speech Signal   Order a copy of this article
    by M. Sadanandam, V. Kamaskhiprasad 
    Abstract: In this paper, we derive new feature vectors for identifying the language from short utterance of speech of an unknown person. By applying window technique on speech signal , Mel cepstral coefficients (MFCC) and formants of speech are extracted. With these two kinds of features, we derive a new feature set using cluster based computation. Later a classifier is designed one for each language using the new features vectors and applied on recognition output with a specific apriori knowledge. We use OGI database to perform the experiments and achieved good recognition performance.
    Keywords: Format frequencies; Language Identification; MFCC; LID; Minimum phase group delay; LID using new feature set.
    DOI: 10.1504/IJAIP.2019.10023086
     
  • Knowledge Mining from Project Retrospect for Organizational Learning in the Responsive Software Engineering Areas   Order a copy of this article
    by Manikanta Reddy 
    Abstract: The space of Knowledge Administration(KA) offers broadened set of practices that recognizes, gather, store and offer the bits of knowledge and encounters people and associations at work. Contemporary situations show that elegant philosophies are sent broadly by result driven associations to convey working programming at a speedier rate. Obviously the continual detachment of human capital has incited these associations to convey more proactive instruments for information catching, lessons learnt and best practices acquired amid past procedures. On the off chance that appropriately put away, these flexible reviews gives a rich wellspring of learning for overseeing repeating and routine issues on one hand and managing existing programming improvement process on the other. The proposed work plans to portray a system for catching implied information created through the procedure of programming improvement in different structures like lessons learnt, specialists knowledge and gatherings. A lexical asset ASEWordNet specific for nimble programming building area has been produced. This paper considers applying supposition mining and data recovery systems with SENTIWORDNET and ASEWordNet vocabulary for testing the informational collections to order the viewpoints of the caught lessons containing such assessments and verbatim in it.
    Keywords: Knowledge Management; Responsive programming enhancement; Opinion mining; Retrospectives.

  • A novel approach for assessing the damaged region in MRI through improvised GA and SGO   Order a copy of this article
    by PARVATHANENI NAGA SRINIVASU 
    Abstract: A plethora of Magnetic Resonance (MR) image segmentation methods exist in the published literature but most of them fail at recognizing small regions in MR images accurately due to inefficient segmentation techniques. Through this article, we propose a novel and efficient MRI image segmentation technique which employs an improvised Genetic Algorithm (GA) based on twin point cross over mutation for automated segmentation. The resultant image from GA is used as an input for Social Group Optimization technique (SGO), and a lightweight computationally efficient algorithm for refining the segmented image. We have carried out an experiment on benchmark and real time images to compare the proposed technique with the existing segmentation methods which use Teacher Learner based optimization (TLBO). We have observed that proposed approach exhibits better performance over its counterpart.
    Keywords: Harmonic Mean; Genetic algorithm; Social Group Optimization; Laplacian; Magnetic Resonance Imaging.

  • Prediction of Airfoil Self-Noise using Polynomial Regression, Multivariate Adaptive Regression Splines, Gradient Boosting Technique and Deep Learning Technique   Order a copy of this article
    by Sanjiban Sekhar Roy, Paridhi Singh, Gobind Manuja, Raghav Sikaria, Maharishi Parekh 
    Abstract: In the 21st century, human life is advancing at an immeasurable pace and has become incoherent with the pace with which our mother Earth could adjust itself. This has drastically resulted in depletion of resources and wastage of energy. For saving resources, we are trying to find a perpetual resource and for saving energy, we are trying to build more efficient systems and machines. Hence, researchers are trying to reduce wastage of energy wherever possible. One such cause of wastage of energy is the generation of airfoil acoustic noise and attempts by scientists and researchers to minimise this noise dates back to as early as 1989. Noise plays a significant role in the design of automobiles, aircraft, turbines, etc. There have been various studies recently, regarding airfoil self-noise, its generation, its prediction and how to curb the noise and the various ill-effects of it. Estimation of noise needs to be accurate so that the further studies to reduce noise from the airfoil models can be performed efficiently. Thus, the development of a coherent noise prediction tool is vital. Hence, through this paper, we try to estimate the best of such noise prediction tools by discussing and comparing certain regression models. We have divided our dataset into training and testing components and the results have been illustrated using tables and graphs. It is observed that Multivariate Adaptive Regression Splines and Polynomial (MARS) regression models have shown reasonable output whereas outstanding results have been obtained by applying Deep Neural Networks and Ensemble learning method, called Gradient Boosting Method, for the airfoil self-noise prediction problem.
    Keywords: Airfoil acoustic noise; Prediction; Multivariate Adaptive Regression Splines; Deep Neural Network; Polynomial Regression; Gradient Boosting.

  • Technical review on ontology merging   Order a copy of this article
    by Kaladevi Ramar 
    Abstract: Emergence of semantic web made available and accessible of many ontologies through web. It automatically increases the usage and application of ontologies. A single domain ontology is not sufficient to support the requirements anticipated by a distributed scenarios. More ontologies need to be utilized from other applications. These requirements motivate the integration of similar ontologies. However, the main issue is that there is no unique optimum solution for a merging methods and that merging can be achieved asymmetrically or symmetrically. In this paper, various merging techniques are analyzed with its pros and cons. From that, the issues in the existing methodsare listed and the possible research directions for future enhancement are discussed. Hope this can open a way to improve merging solutions as per the application requirements.
    Keywords: ontologies; merging; sematic web; heteogeneity.

  • A Fast R-CNN based novel and improved object recognition technique.   Order a copy of this article
    by Shriram K Vasudevan, Aswath GI, Sargunan Ramaswamy, Vimal Kumar K 
    Abstract: Humans have the natural power to identify objects easily on their own, but a machine cannot. An algorithmic description of recognition task has to be implemented on machines to identify an object in an image. A very challenging and a tough task in the computer vision is to detect objects and to estimate the pose. Object recognition remains to be one such key feature in computer vision technology and it is used for identifying a specific object in a digital image or video. The importance of Object recognition algorithm is very high in real-world applications. Object detection is much more complex and challenging compared to image classification. Some of the applications include Biometric recognition, industrial inspection, Robotics, Intelligent Vehicle System, Human-computer interaction, etc. In a retail business, identifying the products of a single manufacturer is difficult. This research uses, Fast R-CNN Algorithm to detect the products of a particular manufacturer - [Procter & Gamble].
    Keywords: Object Recognition; Deep Learning; Machine Learning; CNN; R-CNN; Fast R-CNN;.

  • L(2,1) and Surjective L(2,1) Labeling of Cartesian Product Between Two Complete Bipartite Graphs   Order a copy of this article
    by Sumonta Ghosh, Anita Pal 
    Abstract: As we expect effective and efficient communication over a complex network, we consider the graph G=K_{m,n} X K_{p,q} to label with L(2,1) labeling and investigate the bound lambda_{2,1}(G) in terms of m,n. We also raise few demerits of L(2,1) labeling and introduced surjective L(2,1) labeling as remedy. Surjective L(2,1) labeling follow the restriction of L(2,1) labeling where all the labels are unique and belongs to cardinality of the vertices in the graph. We also apply surjective L(2,1) labeling on the graph G=K_{m,n} X K_{p,q}. In this paper we designed three different algorithms to incorporate above labeling and also analyzed time complexity of the algorithms.
    Keywords: Cartesian product; L(2,1) labeling; surjective L(2,1) labeling; complete bipartite graph.

  • Median relative intersection of confidence intervals for bandwidth estimation in mean shift clustering technique   Order a copy of this article
    by Prasad Kaviti, Valli Kumari Valli Kumari 
    Abstract: Mean shift algorithm is a non-parametric iterative algorithm widely used in segmentation, clustering, object tracking, etc. However, tuning the bandwidth parameter and selection of kernel with its convergence is required. This paper proposes a modified mean shift in terms of bandwidth selection and its adequate kernel selection. Mean shift equipped with median relative intersection of confidence intervals (MRICI) for multispectral image clustering is proposed. Initially different kinds of bandwidth estimators like static, Silverman, Scott, ICI and MRICI are evaluated and are considered four classes of kernels Gaussian, Epaenchnikov, flat, biweight with general convergence. Later different combinations of the four classes of kernels and different bandwidth estimators of mean shift are evaluated. Results show an improvement in intracluster similarity based on silhouette measure for MRICI bandwidth estimation using the Gaussian kernel of mean shift when compared to other combinations of mean shifts.
    Keywords: mean shift clustering; kernels; bandwidth; confidence intervals; multispectral images.

  • ENHANCED GRADIENT BOOSTING (EGB) - A NOVEL METHOD TO IMPROVE PERFORMANCE OF XGB TECHNIQUE   Order a copy of this article
    by Venkata Nagendra 
    Abstract: Gradient boosting algorithm [1] was produced for high prescient capacity. Its selection was restricted to minimize errors for the previous trees; only one decision tree was created. To build small size models it takes large amount of time. To overcome these drawbacks eXtreme Gradient Boosting (XGBoost) [2] was developed. It decreases the model building time as well as increases the performance. The experimental results demonstrate that EGB (Enhanced Gradient Boosting) algorithm perform better than the remaining algorithms like XGB, Gradient Boosting (GB) etc in the context of class imbalanced dataset. The EGB algorithm works as same as XGB and also works on Balanced data with high accuracy. EGB works well on both Balanced and Imbalanced data. The results obtained show that the Area under Curve obtained through EGB is higher than the Area Under curve obtained through XGB.
    Keywords: Machine Learning; Boosting; Gradient Boosting; Enhanced Gradient Boosting; eXtreme Gradient Boosting (XGBoost); Multithreading.

  • Handwritten North Indian Script Recognition Using Machine Learning: A Survey   Order a copy of this article
    by Reya Sharma, BAIJ NATH KAUSHIK, Naveen Gondhi 
    Abstract: The handwritten script recognition is an interesting and significant area of research due to the existence of wide variety of challenges in handwritten Indian scripts. Intensive research work is available on the recognition of scripts like Chinese, Roman, Arabic and Japanese. But the research work done on Indian scripts is still at its infancy, therefore in this paper a review has been presented on the recognition of various handwritten North Indian scripts. Variety of techniques associated with feature extraction and classification of handwritten North Indian scripts are precisely discussed in this work. An attempt has been made with this survey to address and highlight significant results obtained so far in this field and these results are represented in tabular form so as to provide a clear idea by looking the data at once. This survey also provides beneficial future directions for research in handwritten North Indian scripts by analysing the existing difficulties and steps needed for the development of North Indian scripts OCR.
    Keywords: Handwritten Character Recognition; OCR; Devanagari; Gurmukhi.

  • Adaptive Hybrid Transmit Power Control (AHTPC) Algorithm for Wireless Body Area (WBAN) Networks   Order a copy of this article
    by Rajkumar Rajkumar, Samundiswary Samundiswary 
    Abstract: Energy-efficient transmission is considered as a key solution for WBAN which can facilitate long-term and low-power operations. There are several Transmit Power Control (TPC) techniques available in literature, related to WBANs. A TPC technique can be proactive or reactive depending on the channel conditions. While reactive approaches involve control packet overhead and additional delay, the proactive approaches are prone to prediction errors and involve prediction delay. Hence, a hybrid technique is needed which combines the advantages of both proactive and reactive techniques for all type of channel conditions. In this paper, an Adaptive Hybrid TPC (AHTPC) algorithm for WBAN has been developed. In AHTPC, the base station (BS) measures the Received Signal Strength Indicator (RSSI) and Packet Delivery Ratio (PDR) values within an adaptive timer period and stores them in a channel sample matrix. If the values of RSSI and PDR fall outside the range of some lower and upper bounds, the Reactive Transmission Power Control algorithm (RTPC) is executed. If the difference of consecutive RSSI samples becomes larger and the channel condition is considered as fluctuating one, then the Proactive Transmission Power Control algorithm (PTPC) is executed. From the simulation results, it is shown that AHTPC algorithm has reduced energy consumption, less delay, less control packet overhead and increased delivery ratio, when compared to proactive and reactive techniques.
    Keywords: Wireless Body Area Networks (WBAN); Power Control; Adaptive; Hybrid; Channel condition.

  • An Empirical analysis of software maintainability metrics: Object-Oriented Approach versus Traditional   Order a copy of this article
    by Yenduri Gokul 
    Abstract: Software is a great blend of creativity and engineering, which plays a major role in different fields. Software is pre dominantly developed using Object-Oriented approach .Software quality is foremost of all because it has a vast influence on software development life cycle (SDLC). There are many factors influencing quality where maintenance is most important of them. Maintainability of software can be measured using different metrics .In recent times Object-Oriented (OO) approach has become salient in building scientific and business applications but structural approach has its intensification in embedded applications .It is significant to find impact of metrics on each other when different programming languages are considered because they play an significant responsibility in predicting software maintainability. This research empirically analyzed the dependency of various metrics values obtained from software which are similar in both structured (C) and Object Oriented programming (Java) using CCCC and HM tool. Further, the relationships between structured and Object Oriented programming is found out by comparing the different techniques such as data visualization, correlation in terms of maintainability.
    Keywords: Software Quality; Metrics; SDLC; Maintainability.

  • ENHANCED FUZZY LOGIC BASED MPPT FOR STANDALONE PHOTOVOLTAIC SYSTEM   Order a copy of this article
    by Kishore Kumar Kumar, Sivachandran P, Suganyadevi MV 
    Abstract: Solar energy is one of the best growing renewable energy sources across the world. Solar energy offers various advantages such as pollution free, quite in operation, long life, nil input energy cost and less maintenance. The individuality of solar cell is dependent on the environmental parameter mainly with sun irradiance and temperature. In order to minimize the system cost and to maximize the array efficiency the new fuzzy logic control methodology is implemented in DC-DC Boost Converter for extracting maximum power point under various environmental conditions. The new improved fuzzy logic based MPPT is created and compared with conventional incremental conductance (INC) method with various temperature and irradiance condition. The circuit simulations are checked out in MATLAB/SIMULINK Software
    Keywords: Fuzzy Logic; MPPT; DC-DC Boost Converter.

  • A complete analysis of Integrated Vehicle Health Management for Aircraft With Pros, Cons, Suggestions for improvement and Future Prospects.   Order a copy of this article
    by Vimalkumar K, K.V. Shriram 
    Abstract: Integrated vehicle health management is a concept which comprises the integration of sensors, communication technologies, artificial intelligence, data analytics and software health management to facilitate vehicle-wide abilities for diagnosing problems and recommending solution. The IVHM uses sensors to monitor the condition/health of the vehicle by analyzing the data readings from the installed sensors in the vehicle. The Aircraft is such a vehicle which needs to be monitored continuously for the flawless and continuous functioning. The data collected from the sensors installed in the aircraft helps to analyze the present and predict the future performance of the aircraft. Also, the data can also be used to make operational decisions, which are very critical for real-time performance. This paper provides the state-of-the-art report of the IVHM concept with an organized review of the previous research works. The articles are collected from different sources and are analyzed, and the summary of the major works are reported. The paper gives the underlying concept of IVHM and its roadmap, use of IVHM in aircraft, existing approaches and barriers in adopting it for the aircraft, available techniques and future research directions. Overall, this paper shall present the reader with what IVHM is, state of the art and future prospects.
    Keywords: Integrated Vehicle Health Management; IVHM for Aircraft; Prognostics; Prediction; Aircraft safety; Aircraft health monitoring;.

  • SVM-based Multiple Instance Learning Approach to Select the Best Answer in CQA Sites   Order a copy of this article
    by Tirath Prasad Sahu, Naresh Nagwani, Shrish Verma 
    Abstract: A community question answering (CQA) site is an online platform where a user posts a query and receive the best answer among multiple answers posted by others. In most of the CQA site, the best answer is selected manually among multiple answers for a particular question. In the manual process, answers are voted against a question and an answer with highest votes is generally selected as the best answer. Since CQA sites are engaged in receiving the questions frequently, it becomes tedious for the asker or community to select the best answer for every posted question. This paper proposes a support vector machine (SVM)-based multiple-instance learning (MIL) technique for the selection of the best answer among all answers posted for of a particular question in a CQA site. The MIL aims to learn answers (multiple-instance) of a question (a bag) using SVM. The prediction of best answer for the question is derived from the maximum instance margin problem of MIL in supervised classification. It is shown that performance parameters ROC-AUC, PRC-AUC, and G-mean for the proposed model are significantly better than the existing traditional model in prediction of the best answers.
    Keywords: Support vector machine; Community question answering; multiple instance learning; classification; topic modelling; activeness; expertise.

  • Who Will be My Dearest One? An Expert Decision   Order a copy of this article
    by ARUP ROY, SOUMYA BANERJEE 
    Abstract: Recommendation systems assist in finding the right things to the right users. The counterpart matchmaking recommendation system connects on users, enhances the social relationship, saves time, minimizes the risks involved in offline suggestions, and encourages collaboration. Matching implies the ability to recommend potential partners for target users. It matches the profiles based on the preferences provided by the users. In the present era, people are highly involved with their busy schedule. Thus smart recommendation system will be highly demanding service for natives in smart cities. Smart cities, a fully planned and digitized city where people like to adopt online services. Demographic Filtering is the widely used technique for matchmaking recommendation systems. In this research, a novel demographic filtering-based matchmaking framework that precisely identifies the users profiles to provide the top-n recommendations is proposed. The matchmaking is accomplished using the K-means and Ant colony hybrid. Support vector regression is also employed to enhance the performance and make the decision more precise and realistic.
    Keywords: Ant Colony Optimization; Demographic Filtering; K-Means Clustering; Recommendation Systems; Support Vector Regression.

  • A Hybrid DNA Cryptography Based Encryption Algorithm Using the Fusion of Symmetric Key Techniques   Order a copy of this article
    by Animesh Hazra, Soumya Ghosh, Sampad Jash 
    Abstract: The twenty first century, which is the era of e-commerce and e-business where information security plays very vital role. The higher rate of data breaching has raised a query to the safety of digitalization scheme. The security approaches which are made for every industry or organization however big or small should be flexible with the ever changing and challenging data breaching environment. Therefore, the need of encryption and user access controls to safeguard the data has been introduced. This has given birth to various hybrid cryptographic methods, one of them is the DNA cryptography. In this study a brief sketch of DNA cryptology coupled with an innovative algorithm which is founded on the amalgamation of DNA nucleotides, XOR operation and symmetric key concept is presented. The algorithm presented here is truly efficient and one of the salient feature of this technique is the concern of safety that can be customized according to the necessity of sender.
    Keywords: Complement Operation; Data Security; Decryption; Digital Coding; DNA Cryptography; Encryption; Fusion; Substitution; Symmetric; XOR operation.

  • Implementation and comparison of the Image Edge Detection Techniques with complete analysis and suggestions for improvement   Order a copy of this article
    by Parvin N, Kavitha P 
    Abstract: Nowadays, Image processing is one of the most popular technologies. It remains the core area of research in engineering, especially in computer science discipline. Image processing is done either as analog method or digital form. Analog image processing is widely used in the places where we want to use physical form of data, like printouts or photographs. Digital image processing, on the other hand helps in manipulating the digital images, with the help of algorithms and processes. Digital images undergo different stages, namely pre-processing, enhancement and information extraction. Edge detection is a technique generally used in image processing for identifying boundary of objects within an image. It can be a great pre-processing step for image segmentation. There are several types of algorithm to detect the edges. In this paper, analysis is done on three edge detection techniques namely, Prewitt, Roberts and Sobel. It is experimentally observed that Sobel is giving the best result than the other two. This work is implemented on MATLAB R2016a.
    Keywords: digital image processing; image segmentation; Edge detection; Prewitt; Sobel; Roberts;.

  • Template Based Approach for Question Systematization   Order a copy of this article
    by Urmila Shrawankar, Komal Pawar 
    Abstract: Main reason behind questioning is to gather information needed or seek explanation about certain topic. But correct information can be gathered only with a specific error free question. Various applications pursuit for error free standard question. The issue of Statement construction is more concentrated than Question construction. This project work particularly concentrates on error free Question construction using text systematization. Template based approach is used for carrying out this process. Question Template is the basic idea behind Template based approach. Templates are manually designed through coding. This is accompanied by Dictionary approach and powerful Natural Language Processing technique like POS Tagging. This technique follows Maximum Entropy based algorithm. Different error parameters are considered for the correction. This work focuses domain specific WH-type questions of English along with imperative questions. This work has different applications namely, to set exam question papers, to help English learners to study interrogative constructs properly, to produce intermediate output for complex systems like question-answering system.
    Keywords: POS tagger; question templates; systematization; template based approach; WH-questions.
    DOI: 10.1504/IJAIP.2019.10027084
     
  • Energy Efficient Scheduling of Scientific Workflows in Cloud with improved Makespan using Hybrid of Genetic and Max-Min Algorithms   Order a copy of this article
    by S. Balamurugan , S. Saraswathi  
    Abstract: Recently, there is an increased usage of cloud and its resources to deploy and run complex scientific applications. The scientific applications involve large number of dependent tasks and huge data, and only cloud environment can provide a stable platform with its resource provisioning mechanism and scalability. Scheduling a scientific workflow in a cloud environment today faces many issues like high energy consumption, increased makespan due to inefficient scheduling during the execution. In this paper, we propose anenergy efficient based scheduling algorithm to reduce the total energy consumption of cloud virtual machines and also improve the makespan of a scientific workflow. The results proved that the new algorithm reduces the total energy consumption and also reduces the makespan.
    Keywords: Scientific Workflow; Workflow Scheduling; Virtual Machines; Energy Efficiency; Power Utilization; Task assignment; Task migration; makespan; Genetic Algorithm; Max-min Algorithm.

  • Self Organized Map and trust-aware-based quality of service prediction for reliable services selection in distributed computing environment.   Order a copy of this article
    by Youcef Ould-Yahia, Meziane Yacoub, Samia Bouzefrane, Hanifa Boucheneb 
    Abstract: The distributed computing environment allows to provide the outsourced computing services in addition to web-services for IoT and mobile technologies. An emerging research topic is the QoS and security indicator prediction to achieve a reliable service selection that meets user requirements. Collaborative filtering technique is one of the most widely used model in service selection. It is based on similarity computation between users or services. But the main drawback of this method is the lack of data to compute an effective similarity value. Furthermore, malicious users give false feedback which influences the accuracy of prediction. In this work, we propose a novel similarity evaluation model based on Self Organisation Map to address the problem of data lack and a robust index computation to detect the untrustworthy users. The proposed approach uses a K-means based average evaluation to determine the tenderness of the data and an off-line build-up model to increase computational efficiency.
    Keywords: Distributed computing; Web-services; QoS prediction; Trust-aware; Internet of Things; Mobile-edge computing; Self-organizing map.
    DOI: 10.1504/IJAIP.2019.10047456
     
  • Some Properties of Bipolar Complex Neutrosophic Graph   Order a copy of this article
    by Hossein Rashmanlou, Muhammad Shoaib, M.A. Malik, Yahya Talebi, Ali Asghar Talebi 
    Abstract: A neutrosophic graph has many uses in different areas of bio and physics which gives a direction about uncertainty information. The complex neutrosophic graph is the extension of the complex fuzzy graph. In these years, a mathematical approach is a generalized approach of blending different aspects. According to the above mathematical approach, we introduce a strong technique which isrnbipolar complex neutrosophic fuzzy sets and graph theory and introduce the notion of bipolar complex neutrosophic graphs. We will prove that a bipolar complex neutrosophic graph is a generalizationrnof the complex neutrosophic graph. A bipolar complex neutrosophic graph has more exibility andrncompatibility compare to the complex neutrosophic graph. In this paper, our important aim of thernstudy is to apply a few properties namely cartesian products, composition, strong product, semi-strong product and direct product of bipolar complex neutrosophic graph (BCn 􀀀graph in shortly) which have been deeply discussion with different examples and their proofs.
    Keywords: Properties cartesion products; composition; strong product and semi strong product andrndirect product of bipolar complex neutrosophic graph.

  • A Novel Variant of Bat Algorithm Inspired from CATD-Pursuit Strategy & Its Performance Evaluations   Order a copy of this article
    by Shabnam Sharma, Sahil Verma, Kiran Jyoti 
    Abstract: This paper presents a novel nature inspired optimization technique, which is a variant of Standard Bat Algorithm. This optimization technique is inspired from the pursuit strategy of microchiroptera bats and their efficient way of adaptation according to dynamic environment. Here dynamic environment describes different movement strategies adopted by prey (target), during their pursuit. Accordingly, bats have to adopt different pursuit strategies to capture the prey (target). In this research work, a variant of Bat Algorithm is proposed considering the pursuit strategy Constant Absolute Target Detection (CATD), adopted by bats, while targeting preys moving erratically. The proposed algorithm is implemented in Matlab. Results obtained are validated in comparison to Standard Bat Algorithm on the basis of best, mean, median, worst and standard deviation. The results demonstrate that the proposed algorithm provides better exploration and avoid trapping in local optimal solution.
    Keywords: Bat Algorithm; Constant Absolute Target Detection (CATD); Computational Intelligence; Echolocation; Meta-heuristic; Nature-Inspired Intelligence; Optimization; Pursuit Strategy; Swarm Intelligence.
    DOI: 10.1504/IJAIP.2021.10030248
     
  • Wireless Smart Automation Using IOT Based Raspberry Pi   Order a copy of this article
    by Vasu Goel, Akash Deep, Madireddy Vivek Reddy, Yedukondala Rao Veeranki 
    Abstract: In this paper we propose a smart door lock system and lighting system for home automation. This door lock system and lighting system is controlled by Radio Frequency Identification (RFID) reader which is programmed by Raspberry Pi to detect the input swipe through our university combo card or a RFID tag and wirelessly sends the signal to the Espruino (ESP) Wi-Fi module and Node Microcontroller Unit (MCU) which in turn activates the lighting system and door lock system. The mainstream application of the system will be in hostel rooms or in our homes wherever door locks are there so that doors can be opened anytime we want without disrupting our work or getting up from our places in case of any injury with a swipe of card
    Keywords: Internet-Of-Things; Raspberry pi; Radio-Frequency Identification; Home automation; MQTT.
    DOI: 10.1504/IJAIP.2019.10026853
     
  • VLSI Implementation of ECG Feature Extraction: A Literature Review   Order a copy of this article
    by Surendhar S, Thirumurugan P, Ezhilmathi N, Sathesh Raaj R 
    Abstract: In this paper, we examine the comparative learning on VLSI Implementation of Electrocardiogram (ECG) feature extraction method to diagnose the different cardiac arrhythmia. ECG features extraction plays an important significant role in diagnosing most of the cardiac diseases to avoid mortality. In ECG, P-QRS-T wave generated using some novel method to find the peak amplitude and time periods. Recently different methods have been implemented in VLSI for analyzing the ECG signal by multiple researchers. Several techniques and algorithms comprise their own merits and demerits. In this paper, the various methods and techniques are discussed in literature review for cardiac analysis.
    Keywords: Area; Detection Error Rate; Delay; ECG signal; Feature Extraction; Power and Support Vector Machines.

  • Comparative Study of Kernel Algorithms On SIMD Vector Processor for 5G Massive MIMO   Order a copy of this article
    by Ravi Sekhar Yarrabothu, Pitchaiah Telagathoti 
    Abstract: Currently world is moving towards achieving Gigabit data rates via 5G mobile revolution. Massive Multi-In-Multi-Out (MIMO) is one of the key enabler and recently lot of interest is evinced in this area. The efficiency of the algorithms to estimate and detect the channel plays a very crucial role for the success of Massive MIMO. The existing algorithms of LTE-A for this purpose are not efficient in terms of power consumption and lower latency, which is one of the foremost necessity of 5G communications. The biggest hurdle to achieve the ultra-low latency in 5G massive MIMO is - a very huge number of computations required for the matrix inversion while performing channel estimation and detection. In this paper, a comparative study has been done for two parallel processing schemes: Gauss-Jordan elimination and LU decomposition kernel algorithms on a single instruction multiple data (SIMD) stream vector processor for the realization of matrix inversion with optimum latency, which is the pre-requisite for the 5G channel estimation and detection. In this paper both matrix inversion algorithms Gauss Jordan and LU decomposition are analyzed and LU decomposition provides the required level of reduction of computational operations, which translates low latency and less battery power consumption.
    Keywords: Massive MIMO; SIMD; 5G ; DMRS; SRS; LTE - A.

  • Data Mining Techniques and Fuzzy Logic to Build a Risk Prediction System for Stroke   Order a copy of this article
    by Farzana Islam, M. Rashedur Rahman 
    Abstract: Nowadays, by using different computational system medical sector predict diseases. These systems not only aid medical experts but also normal people. In recent years stroke becomes life threatening deadly cause and it increased at global alarming state. Early detection of stroke disease can be helpful to make decision and to change the lifestyle of people who are at high risk. There is a high demand to use computational expertise for prognosis stroke. Research has been attempted to make early prediction of stroke by using data mining techniques. This paper proposes rule based classifier along with other techniques. The dataset is collected from Dhaka medical college, situated in Dhaka, Bangladesh To build a more accurate and acceptable model the system uses different classification methods likely- Decision tree, Support vector machine, Artificial neural network and fuzzy model. K-means, EM and fuzzy C-means clustering algorithm are used to label the dataset more accurately. Fuzzy inference system is also built to generate rules. ANFIS provides the most accurate model.
    Keywords: stroke; decision tree; SVM; MLP; artificial neural network; support vector machine; fuzzy model; FIS; ANFIS; data-mining; fcm; clustering; EM clustering; k-means; Bangladeshi dataset; fuzzy rule.
    DOI: 10.1504/IJAIP.2021.10054275
     
  • Clustering Related Behavior of Users by the use of Partitioning And Parallel Transaction Reduction Algorithm   Order a copy of this article
    by Thava Mani C, Rengarajan A 
    Abstract: High-speed development of information in associations in the present universe of business exchanges, broad information preparing is a main issue of Information Technology. Generally, an Apriori calculation is broadly used to discover the incessant thing sets from database. Later downside of the Apriori calculation is overwhelmed by numerous calculations yet those are likewise wasteful to discover visit thing sets from expansive database with less time and with awesome productivity. Henceforth another design is proposed which comprises of coordinated conveyed and parallel processing idea. The experiments are conducted to find out frequent item sets on proposed and existing algorithms by applying different minimum support on different size of database. With increased data set, Apriori gives poor performance as compared to proposed Partitioning and Parallel Transaction Reduction Algorithm (PPTRA). The implemented algorithm shows the better result in terms of time complexity and also handle large database with more efficiency.
    Keywords: Pre-processing; Mining of Association rules; frequent item sets; parallel; Apriori; matrix; minimum support; Partitioning.

  • An optimized fuzzy edge detector for image processing and their use in modular neural networks for pattern recognition   Order a copy of this article
    by Isidra Espinosa-Velazquez, Patricia Melin, Claudia Gonzalez, Frumen Olivas 
    Abstract: In this paper, the development of a fuzzy edge detector optimized with the metaheuristics: Genetic Algorithms and Particle Swarm Optimization is presented, based on the sum of differences method, using as inputs the absolute values of the difference from the pixels in the image. The Pratts figure of merit metric was used to know the performance of the proposed fuzzy edge detector. A modular neural network was designed for the recognition of faces in benchmark images and comparisons were made with different works carried out with other fuzzy edge detection systems. The main contribution of this research work is the development of a new fuzzy edge detector method optimized.
    Keywords: fuzzy logic; fuzzy edge detector; optimization; GA; genetic algorithm; PSO; Particle swarm Optimization; Neural networks.

  • A Study of Feature Reduction Techniques and Classification for Network Intrusion Detection   Order a copy of this article
    by Meenal Jain, Gagandeep Kaur 
    Abstract: The size of network data increasing tremendously, as the web technologies are emerging day by day. This huge amount of data contains large number of attributes which need to be analyzed for particular application. To analyze the significance of such attributes, different feature reduction techniques can be used. In this paper, three feature reduction techniques such as, Principal Component Analysis (PCA), Artificial Neural Network (ANN), and Nonlinear Principal Component Analysis (NLPCA) have been used to analyze the significance of such attributes. Three newly reduced datasets from the original benchmark dataset Coburg Intrusion Detection Data Set (CIDDS-2017), have been created after applying the above techniques. Four supervised learning based classifiers, namely, Decision Tree (DT), K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Na
    Keywords: Principal Component Analysis; Artificial Neural Network; Nonlinear Principal Component Analysis; Decision Tree; K Nearest Neighbor; Support Vector Machine; Naive Bayes; Sensitivity_Mismatch_Measure; Specificity_Mismatch_Measure; Information_ gain.

  • Adapted Rank Order Clustering-based Test Case Prioritization for Software Product Line Testing   Order a copy of this article
    by Satendra Kumar, Raj Kumar, Ashish Saini, Monika Rani 
    Abstract: Software Product Line Testing (SPLT) is a strenuous task due to the explosion of derivable products. It is infeasible to test all the products of a Software Product Line (SPL) so, several contributions have been presented to overcome this issue by reducing the number of products. However, not much consideration has been given to the test order of the products. Test Case Prioritization (TCP) technique arranges the test cases in a sequence to meet a specific performance goal. TCP is required to increase the effectiveness and efficiency of fault detection. In SPL, TCP technique arranges the configurations of products in order to be tested. Adapted Rank Order Clustering (AROC)-based TCP approach is proposed for SPLT. Our AROC method utilizes Binary Weight and Decimal Weight to arrange the products of an SPL. The results of the rigorous experimentation using AROC-based TCP approach are better than the random order and similarity-based order in terms of fault detection rate.
    Keywords: Software Product Line Testing (SPLT); Test Case Prioritization (TCP); Rank Order Clustering; Feature Model.

  • EDC-LISP: An Efficient Divide-and-Conquer Solution to The Longest Increasing Subsequence Problem   Order a copy of this article
    by Seema Rani, Dharmveer Singh Rajpoot 
    Abstract: The Longest Increasing Subsequence problem was initially viewed as an example of a dynamic approach and its major applications include the process of aligning whole genome sequences. We are presenting an optimal solution for the LIS problem using a modified divide-and-conquer approach with o(n log n) time complexity. The proposed method is more efficient and simpler than the earlier LIS solutions using D&C approach. Our approach does not require sorted data and it is more efficient and better than a sequential approach as we can solve the problem by dividing it into smaller subproblems. During the division phase, we do not need any prior knowledge about the length of the LIS the division process is simple and is independent of the type and range of the input sequence and the 'LIS'. We have implemented the proposed approach in C language using input sequences of different lengths ranging from 10 to 100000 elements.
    Keywords: Longest Increasing Subsequence (LIS); Modified Divide-and-Conquer (MD&C); First Row of Young Tableaux (FRYT); First Subproblem (FSP1); Second Sub-problem (SSP2).
    DOI: 10.1504/IJAIP.2021.10048282
     
  • PEBD: Performance Energy Balanced Duplication Algorithm for Cloud Computing   Order a copy of this article
    by Sharon Priya Surendran, Aisha Banu W 
    Abstract: With the increasing demand of cloud data, efficient task scheduling algorithms are required with minimal power consumption. In this paper, the Performance-Energy Balanced Duplication (PEBD) scheduling approach is proposed for energy conservation at the point of task duplication. Initially, the resources are preprocessed with the Manhattan distance based Fuzzy Clustering (MFC).Then resources are scheduled using a Novel duplication aware fault tolerant based League-BAT algorithm and faults expected during job executions can be handled proactively. The fault adaptive firefly optimization is used for minimizing faults and it keeps information about resource failure. Consequently, the optimization ensures that performance is improved with the help of task duplication with low energy consumption. The duplications are restricted and they are strictly forbidden if they provide significant enhancement of energy consumption. Finally, enhanced compress & Join algorithm is used for efficient compression processing. It considers both schedule lengths and energy savings to enhance the scheduling performance with less power consumption. The performance of energy consumption and makespan for the proposed approach is increased with 6% and 0.5 % respectively
    Keywords: Manhattan distance; Fuzzy clustering; Resource scheduling; Duplication; fault tolerance; energy conservation.

  • Friend discovery based on user's interest   Order a copy of this article
    by Kapil Sharma, Sachin Papneja, Nitesh Khilwani 
    Abstract: With the dawn of Web2.0 and Ontological semantic networks, Social Networking Platform popularity and usage has increased dramatically and has been a new area of research for both researchers and academician. Friend Recommendation, which is the one of the indispensable feature of Social media, has taken it to new height. Facebook, Twitter, LinkedIn, MySpace have captivated millions of users now a days. But the antecedent research work on Friend Recommendation cynosure on user current relation in Social Networking. Facebook, one of the most prominent social networking platforms provides the personalized friend recommendation based on FOAF (Friend of a Friend) ontology. MySpace is based on PYMK (People You May Know) friend recommendation. Basic perception behind it is that probability of a person knowing a friend of friend is more than unknown person. This Paper proffers a unique approach of friend recommendation based on the users interest and based on user current location. The main challenge with friend recommendation based on user interest is that user interest keeps on changing. To overcome this challenge, we have proposed recommendation System using Ontology and Spreading Activation. User interest is being captured using the Spreading Activation. Spreading Activation has been used to overcome variation in user interest. Our experimental results have shown the benefits of considering Spreading activation and ontology in friend recommendation in as social networking.
    Keywords: Ontology; Spreading Activation; Social Networking; Friend Recommendation.
    DOI: 10.1504/IJAIP.2022.10035628
     
  • L(2,2,1)-labelling problems on square of path   Order a copy of this article
    by S.K. Amanathulla, Madhumangal Pal 
    Abstract: $L(p,q)$-labeling problem is a well studied problem in the last three decades for its wide application, specially in frequency assignment in (mobile) communication system, $X$-ray crystallography, coding theory, radar, astronomy, circuit design etc. $L(2,2,1)$-labeling is an extension of $L(p,q)$-labeling is now becomes a well studied problem due to its application. Motivated from this point of view, we consider $L(2,2,1)$-labeling problem for squares of paths.rnrnLet $G=(V, E)$ be a graph. The $L(2,2,1)$-labeling of the graph $G$ is a mapping $eta:Vrightarrow {0,1,2,ldots}$ so thatrn$'eta(x)-eta(y)'geq 2$ if $d(x, y)=1$ or $2$, $'eta(x)-eta(y)'geq 1 $ if $d(x, y)=3$, where $V$ is the vertex set and $d(x, y)$ is the distance (i.e. minimum number of edges in the shortest path between $x$ and $y$) between the vertices $x$ and $y$. $lambda_{2,2,1}(G)$ is the $L(2,2,1)$-labeling number of $G$, which is the the largest non-negative integer which is used to label the graph $G$. In labeling problems of graph the main target is to find the exact value of $lambda_{2,2,1}(G)$ or to minimize it.rnrn In this paper we have studied $L(2,2,1)$-labeling of squares of paths and obtain a good result for it. rn Also a labeling procedure is presented to label a square of paths. The result of this paper is exact and also it is unique. This is the first result about $L(2,2,1)$-labeling of squares of paths.
    Keywords: Frequency assignment; L(2; 2; 1)-labeling; squares of paths.
    DOI: 10.1504/IJAIP.2022.10034134
     
  • Improving Mobile Phone Payment Apps Security with QR Code Security   Order a copy of this article
    by Rijwan Khan, Shadab Ansari 
    Abstract: Nowadays, use of smartphones is increasing at a very fast rate. These phones have the capabilities of a small computers with the ease of doing almost all the tasks with a touch. In this way people will not be depend on the cash flow of money. Simple digital transactions will be there in place of cash flow. One of the major recent development in mobile phones is development of mobile banking systems, wallet systems and third-party payment applications. As the digital currency is now being widely used in market, there are a lot of mobile based application developed for digital payments. Almost all the banks are launching their apps with online payment options along with other facilities for their customers. In addition, there are some other players in market who are launching their mobile application based on wallets for such payments. In developing countries like India, digital payment plays a very important role in boosting the economy. Digital payments has shown a remarkable increase from year 2015 onward in India. In this paper, the authors have proposed a method for security testing of these applications. If an app is more secure, it gives a confidence to the users and will result in more users using this app. The QR code contains the details about the payer or payee and is extensively used by the current payment or wallet systems. Authors have proposed a method for securing the QR code security in mobile payment applications.
    Keywords: Mobile Security (MS); Visual Cryptography (VC); Mobile Payment (MP); Cyber Security (CS); Asymmetric Encryption (AE).

  • Energy-Aware Multi-Objective Job Scheduling in Cloud Computing Environment with Water Wave Optimization   Order a copy of this article
    by Hima Bindu G B, T. Sunil Kumar Reddy 
    Abstract: Job scheduling is the process of assigning the jobs to the virtual machine based on their operations is sequential manner. Each operation is composed of set of instructions and has variable completion time. Virtual machines can execute single job at a time and the preemption is not possible at the time of job execution. Therefore, scheduling the job to the appropriate resource is a crucial task in cloud computing. Hence this paper intends to develop an advanced JSP in cloud environment using an enhanced water wave optimization (WWO) algorithm known as Control adaptive based WWO (CAP - WWO). Moreover the proposed scheme is compared with conventional algorithms and the results proved the efficiency of the proposed algorithm.
    Keywords: Job - shop scheduling; WWO; Execution time; Utilization rate; Throughput; Makespan.

  • ANALYSIS OF TURBOSHAFT ENGINE-LOW POWER MARGIN   Order a copy of this article
    by Sasindra Reddy Dappili, Pavan Kumar Kosaraju, Mani Kanta Yetukuri, Prasanna Sai Bodduluri, E.T. Chullai 
    Abstract: Lower power margin is the most commonly occurred problem in turbo shaft engines which are used in helicopters. It is caused due to heavy taintings in air path which leads to fouling. This also leads to reduced air flow of compressor which results in lower power; few more reasons for lower power is damage of hot core components like power turbine blades and impeller. Low power margin is defined as reduction of output shaft power below the minimum required power to lift the helicopter. The engine encountered with low power is confirmed by pilot by measuring the torque with corresponding to altitude and ambient temperature. If the result is not coordinating with the requirements then engine is sent to test bed to find out the problem. The low power snag is confirmed by testing the engine in test bed, if power loss is within the acceptable limit then compressor wash is carried out through which 25% to 35% power is regained. After compressor wash if power is not regained then the engine is sent to Repair and Overhaul division where snag is rectified and sent back to test bed for final analysis. If engine regains the power, then the engine will be dispatched. The engine performance is analyzed through graphs mainly Power vs RPM. During testing, the parameters like power, mass flow rate, delta pressure, GG rpm, PT rpm, ambient temperature etc. are calibrated in test bed using FADEC system. In this paper we compare the power losses due to power turbine blade life cycle completion, impeller damage and chipping of blades found on axial compressors, rectification of snags, procedure followed to rectify the snags, final engine performance comparison and to confirm which snag because more power loss.
    Keywords: Turboshaft ,Compression Fouling; Corrosion ; Engine Testing.

  • Advanced Redistribution Meta Storage Algorithm for Securing Big Data in Cloud computing   Order a copy of this article
    by Akkipogu Vineela, N. Kasiviswanath, Shoba Bindu C. 
    Abstract: In the recent years, Big Data is one of the emerging fields to process the huge volumes of data. However, it faces lot of challenges in terms of security and storage. Implementing cloud computing with big data enriches the security and storage. A secure architecture is required to manage the big data in cloud. This paper proposed architecture for securing the big data using Advanced RedistributiOn MetA storage (AROMA) algorithm. The importance of the proposed approach is to provide Security-as-a-Service for big data storage. The major issue solved by the proposed approach is restricting the cloud service providers from directly accessing the users data. The experimental setup is conducted in the Amazon EC2 environment. The results proved the efficiency of the proposed method.
    Keywords: Big Data; Cloud; Security; Encryption; Storage.

  • Load-balanced Multilayered Clustering Protocol to Maximize the Lifetime of Wireless Sensor Networks   Order a copy of this article
    by Rohan Gupta, Arnab Nandi 
    Abstract: This article introduces an innovative clustering protocol for load balancing in Wireless Sensor Networks (WSNs). In the proposed protocol, square shape clusters of equal area are arranged in a multilayer fashion, and the base station is at the center of the network. The equal area of square clusters offers a nearly equal number of member nodes in each cluster which leads to comparable energy consumption at cluster heads for transmitting and receiving data from member nodes. This article also introduces a new routing approach in which hop selection is based on the difference of angle between the source and destination cluster heads with respect to a particular point. The efficiency of the proposed protocol concerning network lifetime and energy consumption is evaluated and compared with Low-Energy Adaptive Clustering Hierarchy (LEACH), Enhanced-Modified LEACH (E-MODLEACH) and Least Distance clustering (LDC). The efficiency of the proposed protocol is also evaluated for different optimization algorithms like GWO, PSO, and GSA. The proposed protocol is implemented with these algorithms during the cluster formation stage.
    Keywords: WSN; Clustering Protocol; Load Balancing; Network Lifetime; GWO; PSO; GSA; LEACH; E-MODLEACH; LDC.

  • A Real-Time Novel Road Safety System Pertaining to Indian Road Conditions An innovative attempt.   Order a copy of this article
    by Sri Datta Budaraju, K.V. Shriram, Sucharitha V 
    Abstract: The report Road Accidents in India 2016 [10] published by the Ministry of Road Transport and Highways, Government of India, says that about 16000 accidents were caused by bad roads. During the rainy seasons, the visibility of the roads is hindered by the waterlogging. Thus, having an insight into the road conditions before taking a route becomes a necessity. Our work aims at providing the real-time road condition data and notifies the rider about any hazards on his route. The crowdsourcing model involves the drivers to gather the road condition data that is acquired analyzing the live IMU sensor data of their smartphones while driving. The road anomaly information is updated in the common cloud database and made is available for every other rider using the system. Using this information from the crowdsourced cloud database, our navigation system helps safely navigate the riders. The road hazard information can be then sent to concerned government authorities helping them to maintain the roads much more effectively. The accident information which is also acquired using the IMU sensors can be used to indicate the accident-prone zones and the accident intensities. This is a simple, efficient and low-cost solution in terms of development and deployment.\r\n\r\n
    Keywords: Android;Accelerometer;Cloud;Crash;IMU Sensors;Navigation;Potholes;Z-Thresh.

  • Case-Based Reasoning Methodology for eLearning Recommendation System   Order a copy of this article
    by Swati Shekapure, Dipti D. Patil 
    Abstract: Increasingly, eLearning has become a leading development trend in the industry. As far as the learning methodology is concerned, it has been observed that traditional learning methods such as teacher and student, chalk and duster have turned to modern & innovative learning. Due to a revolution in technology, everyone started learning by using the internet. They have been using devices like smartphones, laptops, e-books, I-pod and so on for gaining instructions. So, while they procure the learning they admit certain records, which are not significant to answer all their exploratory questions. Ultimately, there was a huge delay while scrutinizing the essential material on the internet, so there was an extremity to customize the search by acquiring certain information of a user to improve the search quality and save time. The recommended eLearning system is a case based system using a case-based reasoning approach and a distinct classification algorithmic rule to categorize the students learning interest. This system assembles student's learning preferences from a distinct discussion and systematically categorizes that characteristic into a learning standard.
    Keywords: Case-Based Reasoning; K Nearest Neighbor; Learning Style; Recommendation system.
    DOI: 10.1504/IJAIP.2022.10035296
     
  • An Efficient Implicit Lagrangian Twin Bounded Support Vector Machine   Order a copy of this article
    by Umesh Gupta, Deepak Gupta 
    Abstract: In this paper, an enhanced and improved version of Lagrangian twin bounded support vector machine (LTBSVM) is proposed termed as efficient implicit Lagrangian twin bounded support vector machine based on fuzzy membership with the dual formulation in order to reduce the sensitivity of different noise and outliers if present in the datasets. Here, the fuzzy membership values are determined according to the distribution of the samples. In this paper, we adopt the quadric and centroid fuzzy based approach for LTBSVM and propose Quadric based Fuzzy membership approach for LTBSVM (FQLTBSVM) and Centroid based Fuzzy membership approach for LTBSVM (FCLTBSVM). The problems make strongly convex by using L2- norm of the vector of slack variable unlike L1- norm of vector slack variable. Further, the solution of the problem is obtained through simple linear convergent iterative approach instead of solving a quadratic programming problem (QPP). Further, comparative performance analysis of proposed FQLTBSVM, FCLTBSVM with twin support vector machine (TSVM), twin bounded support vector machine (TBSVM) and LTBSVM has been done on different standard real-world datasets as well as artificial datasets using linear and Gaussian kernel. This analysis gives a prominent decision which announces that proposed approaches are more effective and applicable in terms of generalization performance and computational speed to other approaches. Our proposed approaches statistically validate and verify based on various parameters such as accuracy, sensitivity, recall, precision, F1-score and G-mean.
    Keywords: twin support vector machine; twin bounded support vector machine; Lagrangian function; iterative approaches.

  • An efficient memory based differential evolution for constrained optimization   Order a copy of this article
    by Raghav Prasad Parouha 
    Abstract: In optimization, the performance of differential evolution and their hybrid versions exist in literature is highly affected by the inappropriate choice of its operators like mutation and crossover. In general practice, during simulation DE does not employ any strategy of memorizing the so-far-best results obtained in the initial part of the previous generation. In this paper, a new Memory based DE (MBDE) presented where two swarm operators have been introduced. These operators based on the p^best and g^best mechanism of particle swarm optimization. The proposed MBDE is employed to solve CEC2006 and CEC2010 constrained benchmark functions. The results of MBDE are compared with state-of-the-art algorithms. Numerical, statistical and graphical analysis reveals the competency of the proposed algorithm.
    Keywords: Differential Evolution; Particle Swarm Optimization; Mutation; Crossover; Elitism; Constrained optimization; Elitism.

  • Aspect-based Opinion Mining of Customer Reviews for Product Usability Evaluation using Natural Language Processing   Order a copy of this article
    by Ajay Kumar, Pradip Swarnakar, Saurabh Maurya 
    Abstract: With the commencement of Web 2.0, more appraise started to be given to the active engagement of users and communities on the web, primarily through the knowledge contribution of each member to supplement global information. Opinion Mining (OM), also known as sentiment analysis (SA), is a field of Web Content Mining that targets to find out valuable information from users' opinions. More often, potential buyers always look for feedback from other users based on their judgment and experiences about the product. This helps them in making an informed decision. But the task of analyzing the significant number of reviews present on the Internet may be tiresome and time consuming for a person. So, this study proposes a model by which the products will be analyzed, and ratings will be given to the individual feature of the product based on the reviews. Thus the comparison among various products from both subjective and objective perceptions on the feature level is performed. A user looking for a specific set of features in a product can quickly analyze the products and compare this product to others based on the required features. The system will also recommend products to the user based on his requirements. This study uses the Natural Language Processing toolkit provided by Stanford to mine the opinion words and corresponding feature terms using dependency grammar and feature list. The results of the proposed model are presented to the user in a relaxed and understandable manner.
    Keywords: Sentiment Analysis; Web Mining; User Perception; Natural Language Processing; Opinion Score.

  • A Community Based Trusted Collaborative Filtering Recommender Systems Using Pareto Dominance Approach   Order a copy of this article
    by Anupama Angadi, Satya Keerthi Gorripati 
    Abstract: Recommender System algorithms provided clarification to information overload problem suffered by netizens. The Collaborative Recommender Filtering approach takes the user-item rating matrix as an input and recommends items based on the perceptions of similar neighbours. However, sparsity issue in the rating matrix leads to untrustworthy predictions. However, the conventional Collaborative Recommender Filtering method chooses ineffective descriptive users as neighbours for each target user. This hints that the recommendations made by the system remain inaccurate. The proposed approach addresses this issue by applying a pre-filtering process and integrates community detection with Pareto dominance, which considers trusted neighbours from the community into which the active user pertains and eliminates dominant users from the neighbourhood. The results on the proposed framework showed a noteworthy improvement in all the accuracy measures when related to the traditional approaches.
    Keywords: Community Detection; Recommender Systems; Sparsity; Pareto dominance; Cold Start; Trust propagation;.

  • DOCUMENT SUMMARIZATION USING RECURRENT NEURAL NETWORK   Order a copy of this article
    by Vijayakumar K, Dafni Rose J 
    Abstract: Document Summarization is the process which condenses the given document to generate a summary which captures the main essence of the entire document. In recent years, there has been increased interest in automatic summarization. Automatic summarization refers to summarizing a document using software and it helps to reduce large text documents to a short set of words or a paragraph that delivers the main meaning of the full text. The extracted features from the documents are used for the automatic summarization process and remain a successfully proven approach but it leads to drawbacks with respect to structure, redundancy, coherence. Existing methods for single document summarization usually make use of only the first sentence or fixed number of words from the beginning contained in the specified document. This paper proposes a technique that uses contents of the entire document to provide more knowledge to help single document summarization. The proposed system mainly aims at generating a summary of at least a minimum length unlike the existing system that generates empty summary if it couldnt find the keyword present in the input document which meets the attention weight beyond a threshold. Also, the proposed system is focused in maintaining the structure of the summaries generated for the given document.
    Keywords: text; summarize; document; recurrent.

  • Web Server Workload Prediction using Time Series Model   Order a copy of this article
    by Mahendra Pratap Yadav, Akanksha Kunwar, Ram Chandra Bhushan, Dharmendra Kumar Yadav 
    Abstract: In distributed systems, multi-tier storage systems and cloud data-centers are used for resource sharing among several clients. To fulfill the clients request, the cloud providers share it's resources and manage the workload, which introduces many performance challenges and issues. One of the main challenges is resource provisioning in virtual machine (VMs or Container) since VMs are subjected to meet the demand of users with different profiles and Quality of Service (QoS). This proactive resource management approach requires an appropriate workload prediction strategy for real-time series data. The time series model exhibits prominent periodic patterns for the workload that evolves from one point of time to another with some short of time in random fluctuation. In this paper, a solution for the prediction of web server load problem has been proposed, which is based on seasonal ARIMA (Autoregressive Integrated Moving Average Model) model. ARIMA is a forecasting technique which predicts the future value based on its inertia. In seasonal ARIMA, seasonal AR and MA are used to predict the value xt (CPU workload time series) with the help of data values and errors at time lags that are multiple to the span of seasonality. We have evaluated our proposed method using real-world web workload data.
    Keywords: Cloud Computing; Elasticity; Auto-scaling; Time Series; Machine Learning.
    DOI: 10.1504/IJAIP.2022.10034175