International Journal of Intelligent Enterprise (70 papers in press)
Solving Quadratic Assignment Problem by Symbiotic Organisms Search Algorithm
by Heba Rashad, Abdel Nasser H. Zaied, Yongquan Zhou
Abstract: Symbiotic Organisms Search algorithm (SOS) is a new meta-heuristic algorithm based on the symbiotic relationship between the biological, which was proposed in recent years. In this paper, we propose new robust and powerful metaheuristic algorithm called an improved version of symbiotic organisms search algorithm integrated with construction algorithm and mutation operators (ISOS) to solve quadratic assignment problems. The Quadratic Assignment Problem (QAP) considers NP-hard combinatorial optimization problem and has various practical applications. A set of benchmarks from QAPLIB Library are employed to evaluate the performance of proposed algorithm. ISOS is compared to several algorithms in the literature. The comparisons show that the proposed algorithm shows reliable, efficient and promising results.
Keywords: Symbiotic organisms search algorithm; Optimization; Quadratic assignment problem; Combinatorial Optimization.
Gandhian management perspective for enhancing productivity and innovation in Public Sector Organization.
by Shashi Kant, Pramod Chandra, Vinay Sharma, Rajat Agrawal
Abstract: This paper underpins the importance of establishing Public Sector Undertakings (PSU) in India with special reference to one of the key industrial organizations, Bharat Heavy Electricals Ltd (BHEL), which focuses on elements of innovation that drives productivity inculcating the Gandhian management perspective. In the present competitive world, BHEL and other industrial PSUs are passing through a transitional phase of enhancing their productive competitiveness through both process and product innovation for sustainable growth. This requires introduction and adaption of non-conventional or modern modes of management based on the principles of Mahatma Gandhi. The need, importance and implication of Gandhian perspective in industrial organization got reemphasize. Mahatma Gandhis fundamental philosophical approach might not be radically different from that of others but it exists in the form of an approach that structurally recommends a pathway of wealth generation, productivity, wealth distribution, and economic prosperity for all. The paper intends to find traces of Gandhian management perspective in Indian PSUs and also tries to elicit relevant Gandhian elements of industrial organization management.
Keywords: Public sector undertaking; ethical management; sustainable leadership; Gandhian management perspective; Gandhian innovation.
A Study on the Barriers to Lean Manufacturing Implementation for Small-Scale Industries in Himachal Region (India)
by Anbesh Jamwal, Ankur Aggarwal, Sumit Gupta, Parul Sharma
Abstract: In todays competitive market, lean philosophy has a vital role to play which is mainly governed by a reduction in cost, ameliorated quality, and higher expectations of customers as well as superior productivity. It has been globally witnessed that the companies which implement lean manufacturing in their system result into improved productivity and better customer satisfaction, along with the cost reduction. Lean manufacturing is the most important productivity improvement tool. The aim of this research is to identification and confirmation of the barriers to lean implementation in small-scale industries in the Himachal Region (India) and to build up a relationship between the barriers. A Total Interpretive Structural Modeling approach is applied to identify the relationship of various barriers. It is evident from the research that the cost of facilities is a major barrier to implementing lean in the small-scale industries. However, the government gives the financial support for the small-scale industries in Himachal Pradesh.
Keywords: Lean Manufacturing (LM); Barriers; Total Interpretive Structural Modeling (TISM); Inter-relationship.
Incorporating carbon emissions in queuing models to determine lot sizes and inventory buffers in a supply chain
by Petrus Setya Murdapa, Nyoman Pujawan, Putu Dana Karningsih, Arman Hakim Nasution
Abstract: In this paper, we present a supply chain model that considers both inventory-related costs and emissions. We used the queueing-based performance model wherein emissions in three stages of supply chain activities are captured. The model was solved by the decomposition approach. For model validation, we have used a discrete event simulation. The computation results show that the two results, i.e., the decomposition approach and the simulation, are very close, indicating the accuracy the approach that we used. Experiments were conducted to test the applicability of the model. The numerical examples show that the change in parameter values is not always responded the same way by the total inventory-related costs and the emission costs, indicating the importance of including these two response variables in the model.
Keywords: Carbon emission; inventory buffering; lot sizing; performance model; supply chain.
Economic, Political and Institutional Determinants of Foreign Direct Investment Inflow in Emerging and Developing Asia
by Anil Kumar Goyal
Abstract: This study investigates the role of Economic, Political and Institutional factors in attracting foreign direct investment (FDI) inflow in top 5 host economies of Emerging and Developing Asia consisting of China, Hong Kong, Singapore, India, and Viet Nam for a period of eleven years for the period 2006-2016. The study is based on determinants, identified from literature review on the basis of their relevance and significance, of FDI inflow in top 5 host economies of Developing Asia. Annual data of dependent and independent variables for the period ranging from 2006-2016 has been collected from World Development Indicators, World Governance Indicators, World Bank. In the present study independent variables are categorized as Economic, Political and Institutional factors on the basis of their nature, effect and significance. The study uses Fixed Effects Panel Regression in order to measures the significance of determinants of FDI inflows in top 5 host economies of Developing Asia. Findings of Panel Regression Model reveal that most of the Economic Variables seem to be statistically significant and determinants FDI inflow as compared to Institutional and Political variables of FDI. After imputing variables into Economic, Political and Institutional, multiple regression estimates indicate that the coefficients of Economic and Institutional factors are significant as determinants of FDI inflow in Developing Asia.
Keywords: Determinants of FDI inflow; Economic; Political and Institutional factors; top 5 host economies of Emerging and Developing Asia consisting of China; Hong Kong; Singapore; India; and Viet Nam; Panel Data; Fixed Effect; Multiple Regression.
Entrepreneurial passion facing its ecosystems obstacles: The case of Tunisia
by SAMIRA BOUSSEMA
Abstract: Entrepreneurship is one of the most appropriate remedies to the various economic crises. It is presented as a complex process that faces several barriers, thereby inhibiting a projects implementation phase. In fact, after a careful review of the literature, we noticed that empirical research on reasons behind unimplemented entrepreneurial projects are very rare, suggesting a failure in modeling the process in general and the pre-start phase in particular. In this paper, we try then to identify the main constraints to entrepreneurial passion in Tunisia by studying a representative sample of project promoters who have been unable to carry out their business projects. Using structural equation methods, we found that these promoters face barriers like a lack in entrepreneurial training and services provided by supporting organizations.
Keywords: Entrepreneurial passion; unimplementation of projects; Structural modeling.
Implementing just-in-time (JIT) based supply chain for the bulk items in an integrated steel plant
by Ram Naresh Roy
Abstract: Due to increasing global competition, organizations are continuously improving their operational practices and cost efficiency to get a competitive edge. This paper involves a case study in ABC Steel plant (anonymised) dealing with a huge amount of bulk-materials handling and transportation, and proposes a JIT-based model of handling and transporting which may lead to potential cost savings. The paper discusses the important requirements of JIT procurement and transportation through a literature review. The existing system of ABC Steel plant has been studied and modelled as a pull-system, and an MRP model has been used to calculate the amount of various raw materials needed for making the hot-iron or steel. The total costs of transporting bulk materials from various sources for steelmaking in the existing system (model-1) and the proposed JIT system (model-2) have been calculated. The differences between the two indicated the potential savings for different levels of safety-stock and different levels of JIT implementation.
Keywords: JIT supply chain; logistics; bulk materials; integrated steel plant; MRP model; cost-savings and productivity; lean procurement.
Framework to Identify a Set of Univariate Time Series Forecasting Techniques to aid in Business Decision Making
by IRAM NAIM, Tripti Mahara
Abstract: Forecasting is generally involved in business activities to anticipate or predict the future. With availability of numerous techniques and models, forecasters regularly face a genuine issue to select the most appropriate technique for different time series available in an organization. Most of the time, it is not possible to find one technique that can be used for all-time series as the selection is dependent upon the characteristics of a time series. Hence, the research proposes a selection tree to aid in decision making based upon availability of type of dataset and time series characteristics. The framework is validated using four real case studies. This study also presents advancement to existing forecasting method selection tree by exploring a new dimension of complex seasonal pattern for long time series.
Keywords: Univariate Time Series; Time series Pattern; model selection; trend analysis; seasonal data; complex seasonality; long time series.
Special Issue on: Smart City Applications
Performance study of Routing Protocols based on node mobility in MANETs
by Younes BEN CHIGRA, Abderahim GHADI, Mohamed BOUHORMA
Abstract: Mobile Ad Hoc network (MANET) is established by a set of smart mobile nodes without any central intelligence. Hence, nodes auto-discover their surrounding and establish needed links between source and destination node. Moreover, mobile nodes change arbitrary their position, which lead to frequent link failure. Therefore, the dynamic behaviour of nodes has a drastic impact on networks performances such as end-to-end delay, packet loss ratio and traffic control that is generated during route update process. Consequently, the main issue in MANETs operations is the design of an efficient routing protocol able to deliver required quality of service in case of nodes mobility and manage the intrinsic limitation of wireless networks, like scares bandwidth, limited energy and processing capabilities. The purpose of this paper is to study the impact of nodes mobility on routing performances and look forward an appropriate optimisation that might enhance efficiency of routing protocol in high dynamic environment.
Keywords: Routing protocols; Network performances; Mobile Ad Hoc Network (MANETs); Mobility; Traffic overhead; Routing metrics.
A memetic algorithm for fleet size and mix vehicle routing problems with electric modular vehicles
by Dhekra Rezgui, Jouhaina Chaouachi Siala, Wassila Aggoune-Mtalaa, Hend Bouziri
Abstract: This work deals with an extension of the well-known Vehicle RoutingrnProblem with Time Windows (VRPTW), where the fleet consists of electric modular vehicles (EMVs). The main drawback of managing electric vehicles isrnthat they have a limited range. Here the vehicles are modular which means that payload modules are carried by a cabin module and can be detached at certain customer locations allowing the rest of the vehicle to continue the tour. This can also permit to recharge the battery of some modules to further capitalize on the gained energy. To tackle the resulting research problem, a comprehensive mathematical formulation is proposed to take into account the multiple constraints linked with the modularity, the electric charging, time windows to serve the customers and capacity issues. Due to the NP-hardness of the problem, a memetic algorithm is implemented and tested for designing good quality solutions in reasonable computational times. Extensive computational experiments carried out on some benchmark instances show the effectiveness of both the problem formulation and the memetic algorithm.
Keywords: Urban logistics; Vehicle Routing Problem; Metaheuristics; Electric Modular Vehicles.
Micro Navigation System for Smart Parking Area
by Hicham LAHDILI, Zine El Abidine Alaoui Ismaili
Abstract: Despite its limited accuracy, Navigation systems depending on GPS are currently attracting considerable interest due to their increasing convenience in the field of transportation area. So far, most outdoor navigation applications are using GPS and the absence of a low-cost alternative with acceptable accuracy satisfying the indoor applications requirements has become one of the motivational topics to follow up. Therefore, different studies have been recently conducted in order to develop an accurate indoor localization system. In this paper, we will propose a micro-navigation system for parking area with a visual positioning system (VPS) based on the surveillance camera network adaptation and the image processing theory. From the data provided by the VPS, a navigation tool will be presented besides. The proposed system has achieved an accuracy error of 0.08M, and proved a remarkable improvement in terms of finding parking places time-consuming. We believe that we have designed an innovative solution responding to traffic jams and pollution issues as well as stress and finding parking places time-consuming.
Keywords: smart parking; indoor navigation application; vehicle positioning system; real time; image processing.
Smart Cities Reconsidered: the Entrepreneurial Challenge
by Domingos Santos
Abstract: The concept of the smart city acquired increasing expression and has become a strongly discussed field in the recent past among, either the research community, either the political stakeholders. Studying and intervening on the urban dynamics requires a shift from focusing on forms of knowledge and innovation outputs towards focusing on learning and innovation dynamics, exploring the diverse dimensions of knowledge building and promoting social capital. This paper aims, first, to contribute to clarify the meaning of the word smart in the context of urban development through an approach based on an in-depth literature review of pertinent studies and then, to establish the links with the dimensions of entrepreneurship that can help guide more effective urban development and planning policies, illustrating with the Smart Coimbra initiative. Besides the paper aims to inform and improve policy-making on the subject of promoting entrepreneurial mindsets and contexts, speculating on some principles and guidelines that may help fertilize urban dynamics and build smarter and more entrepreneurial cities.
Keywords: Smart city; urban development; entrepreneurship; entrepreneurship policy; innovation policy.
Architecture of a Decision Support System Based on Big Data for Monitoring Type 2 Diabetics
by Boudhir Anouar Abdelhakim, Ben Ahmed Mohammed, Fellaji Soumaya
Abstract: Type 2 diabetes is one of chronic diseases that require continuous and real-time monitoring to prevent the occurrence of complications. On the one hand, the doctor must have information about the patient's daily life (vital signs, stress, sedentary lifestyle, physical activities, nutrition, etc.). On the other hand, the prescribed treatment must be evaluated each time to test the validity of the diagnosis. To achieve this goal, a decision support system based on the Big Data Mining technology must be designed in order to have a centralized knowledge of diabetics. This system will improve the quality of monitoring and treatment from the different data collected. Thus, this paper presents an architecture of a decision support system allowing doctors to monitor the health status of their patients, based on data collected from different resources, in order to enrich the knowledge database and prescribe new treatments based on similar cases and experiences of doctors and patients belonging to this system.
Keywords: Big data; Analytics; Hadoop;Lambda Architecture; Healthcare.
MultiPrime Cloud-RSA: A Fast Homomorphic Encryption Scheme for Data Confidentiality Protection in Clouds
by Khalid EL MAKKAOUI, Abderrahim Beni-Hssane, Abdellah Ezzati
Abstract: Concerns over data confidentiality are amongst the main barriersrnlimiting the widespread adoption of cloud solutions. Indeed, scientists haverninvented a new promising form of encryption, homomorphic encryption (HE),rnwhich can be considered as a powerful tool to get over these concerns. Sincerncloud environments are more vulnerable to attacks and since cloud consumersrnfrequently access to cloud computing services using light-weight devices, the HE schemes must be promoted, in terms of security level and running time, to operate efficiently. In El Makkaoui et al. (2017), we boosted the normal RSA cryptosystem at security level, Cloud-RSA. In this paper, we suggest a new fast variant of the Cloud-RSA scheme, MultiPime Cloud-RSA, to accelerate its decryption process. The variant uses a modulus of the form n = p1p2...pk for k>= 2 and employs the Chinese remaindering to decrypt. Theoretical and simulation results show that the new variant offers a large decryption speed-up over the Cloud-RSA scheme whilst maintaining a recommended security level.
Keywords: Cloud-RSA Scheme; Cloud Computing; Confidentiality; Multiplicative Homomorphism; Chinese Remainder Theorem (CRT); Fast Decryption.
Training and Evaluation of TreeTagger on Amazigh Corpus
by Amri Samir, Zenkouar Lahbib
Abstract: Part of Speech (POS) tagging has high importance in the domain of Natural Language Processing (NLP). POS tagging determines grammatical category to any token, such as noun, verb, adjective, person, gender, etc. Some of the words are ambiguous in their categories and what tagging does is to clear of ambiguous word according to their context. Many taggers are designed with different approaches to reach high accuracy. In this paper we present a Machine Learning algorithm, which combines decision trees model and HMM model to tag Amazigh unknown words.
In case of statistical methods such as TreeTagger, this will have added practical advantages also. This paper presents creation of a POS tagged corpus and evaluation of TreeTagger on Amazigh text. The results of experiments on Amazigh text show that TreeTagger provides overall tagging accuracy of 93.19%, specifically, 94.10% on known words and 70.29% on unknown words.
Keywords: Amazigh; Corpus; Machine Learning; POS tagging; TreeTagger.
Game Theory based Analysis of Inter-cluster Communication in a DRHT Network
by El Arbi Abdellaoui Alaoui, Mustapha El Moudden, Khalid Nassiri, Said Agoujil
Abstract: The system performance of the delay tolerant networks (DTN) can be significantly improved by using the DTN routing hierarchical topology (DRHT) which incorporates three fundamental concepts: ferries messages, ferries routes and clusters. The intra-cluster routing is managed by the cluster head, while the inter-cluster routing is managed by the ferries messages. In this paper, we analyse the behavior of data dissemination problem of ferries in the DRHT. More specifically, in order to analyse the inter-cluster communication in the DRHT, we formulate non-cooperative game and game stochastic which model the behavior of the ferries.
Keywords: Delay Tolerant Networks (DTN); DRHT; Game theory; Nash equilibrium; Game stochastic.
Towards a ubiquitous students response system for monitoring learning performances
by Aimad Karkouch, Hajar MOUSANNIF, Hassan Al MOATASSIME
Abstract: Receiving feedbacks from students about their learning experience is a key part of any pedagogical approach. Students feedbacks could be retrieved in a variety of ways using various Students Response Systems (SRS), however, existing SRS suffer from lack of seamless integration into learning environments, becoming a potential source of distraction for the learning process. We propose a Ubiquitous Students Response System (U-SRS) that is capable of continuously and seamlessly monitoring various students learning performances features, making sense of them and providing insights for teachers, enabling them to adapt their pedagogical approach according to their students immediate needs. The proposed U-SRS takes advantages of machine learning and the Internet of Things paradigm to enable its services in connected classrooms. We present our solutions design, its architecture and features used to build learning performance predictive models along with implementation and various prototypes. Finally, we highlight the advantages of U-SRS over existing solutions.
Keywords: Students Response System; Students feedback; Internet of Things; Machine learning.
A Smart Architecture Design for Health Remote monitoring Systems and Heterogeneous Wireless Sensor Network technologies: A Machine learning breathlessness prediction prototype
by Mohamed EDDEBBAH, Mohamed Moussaoui, LAAZIZ Yassin
Abstract: In this paper, we propose a remote patient monitoring architecture based on WBAN Wireless Body Sensor Network for breathlessness prediction using machine learning mechanism, we develop a new gateway architecture able to interconnect heterogeneous sensor networks not equipped with the HTTP / TCP / UDP stack. to ensure interoperability and facilitate seamless access to data from different types of body sensors that communicate via multiple technologies. We have designed an application-layer approach for a Web Service Gateway to interact with heterogeneous WSN. The gateway manages the service consumption and communicates with the server via the SOAP protocol. The proposed platform targeted to monitor and process patient health data. An improved Machine Learning algorithm is used for patient health status prediction to perform patient self-training models based on k-means algorithm. For our platform evaluation we study the gateway power consumption then we investigate the communication delay between the gateway and the server over three communication scenarios (3G, ADSL, LOCAL).
Keywords: IoT; WSN; Machine learning; K-means; Self-training; Remote patient monitoring.
Improving smart learning experience quality through the use of extracted data from social networks
by Kenza Sakout Andaloussi, Laurence Capus, Ismail Berrada, Karim Boubouh
Abstract: With the development of smart cities applications, the need for smart learning is increasing. Although current systems are supposed supporting smart learning, they do not really meet the expectations. In fact, for learner models, data are still mostly gathered through questionnaires and are not predicted, then standards are not satisfied. Regarding the domain model, it appears that collaborative learning is not considered. Finally, for the adaptation process, it depends on two main criteria namely the learning style and the knowledge level, in addition, it concerns only one or two of these aspects: content, navigation or presentation. This paper explores the feasibility of learner modelling based on data extracted and inferred from social networks, according to the IMS-LIP specification. An adaptive learning system has been developed on the basis of this innovative approach. The first results confirm that this new way can improve the smart learning experience.
Keywords: Smart learning; educational hypermedia system; adaptation; learner model; Felder & Silverman learning style; Big five personality traits; social networks.
Detection of drivers alertness level based on the Viola & Jones method and logistic regression analysis
by Samir ALLACH
Abstract: The analysis of the face elements state is a crucial step for the drivers alertness level detection. In this article, we propose a drivers assistant system that activates alarms to alert the drowsy and/or tired driver.
Our proposed system contains the following steps: firstly, the recognition of the facial elements (eyes, mouth). Secondly, the system determines the states of the mouth and eyes. Finally, it triggers the alarm in the case of the danger. For the extraction and recognition of the face and its elements (eyes, mouth), we use the Viola & Jones method and we also use Logistic Regression analysis that takes the supplied vector image to determine if the driver is in drowsiness and / or fatigue.
The tests performed on the real video sequences, using an Embedded System, provide good results and may function in real time
Keywords: Smart Mobility; ITS; Drowsiness and fatigue detection; Yawning Frequency; Embedded system.
French Medical Named Entity Recognition: A Hybrid Approach
by Imane Allaouzi
Abstract: With the availability of a huge amount of medical textual document in digital form, the automatic extraction of relevant information from these documents is becoming a very challenging task because of the volume and the heterogeneous structure of medical text, which contains complex vocabulary. Therefore, there is an urgent need for medical information extraction techniques. One of the most important of these techniques is Named Entity Recognition (NER). In this paper, we propose a system of French Medical NER using a hybrid approach. And since the medical domain contains various types of information, we have taken into account both clinical and biomedical data to generalize the performance of our proposed system.
Keywords: Information Extraction; Medical Named Entity Recognition; Multi-class Classification; Machine Learning; Knowledge-based approach; UMLS; NLP; Text Mining.
AWS and IoT for Real-time Remote Medical Monitoring
by Abdelilah Bouslama, Yassin Laaziz, Abdelhak Tali, Mohamed Eddabbah
Abstract: Remote medical care services based on IT are becoming increasingly present in health systems and will play a fundamental role in the future to address the lack of human and material resources, and to cope with the significant increase in demand for healthcare, especially from the elderly. In this paper we present the architecture of a remote and real-time medical monitoring system, based on Cloud computing and IoT. We show through a benchmarking study covering the aspects of performance, functionality and cost, that Cloud Computing Services from Amazon (AWS) are the most appropriate for this application amount other considered Cloud providers. All items necessary for the implementation of the solution have been designated and their role in the system has been well explained
Keywords: Real-time; Monitoring; AWS; IoT; Cloud Computing; Cloud providers.
Use of Cloud Computing and GIS on Vehicle Traffic Management
by Ahmed Ziani, Zouhair Abdelghani Sadouq, Adellatif Medouri
Abstract: It is challenge of traffic congestion has become recurrent problems in urban cities. Vehicular traffic becomes an important research area due to its features and applications as road safety and efficient traffic management. Vehicles are expected to carry relatively more communication systems. Hence, several technologies have been deployed to promote Vehicular traffic management. Geographic Information Systems (GIS) plays an essential role in wide range of areas and is extensively adopted nowadays. GIS is a collection of tools that captures, stores, analyses, manages, and presents data that are linked to geographical locations. Cloud computing is a construct that allows to access applications that actually reside at a location other than a computer or other internet connected devices. The combination of cloud computing and GIS provide new prospects for the development of information storage and of GIS applications. In this paper, architecture for GIS Cloud System for Vehicular traffic management is proposed.
Keywords: Geographical Information Systems; cloud GIS; Cloud Computing; Vehicular traffic; Microsoft's Windows Azure; Traccar Web UI.
IT GOVERNANCE IN COLLABORATION MODE: BUILDING IT COLLABORATION NETWORK USING A SOCIO TECHNICAL APPROACH BASED ON ACTOR NETWORK THEORY
by MOHAMMED SALIM BENQATLA, BOUCHAIB BOUNABAT
Abstract: Abstract: IT Governance of projects needs collaboration among several organisms. Collaboration is ensured by building network of collaboration between the collaborating entities; IT Collaboration between organizations can play an important role to achieve business objectives. In order to build such networks of collaboration at a real scale need modeling social interactions between different actors in order to share, analyze, and suggest improvements for a collaborative perspective. This paper describes a new tool for collaboratively modeling based on Actor Network Theory. *CollabANT system is based on Actor Network Theory and Game Theory algorithm that efficiently provides abstract models of collaboration between different actors aiming at uncovering cost allocations concerns. We demonstrate the effectiveness of our approach with a real case study. The analyze of *interessement phase reveals that we are able to increase the cost saving objectives within a collaborative mode. We also present a what-if simulation feature to assess the impact of scenarios related to future collaboration evolution. Furthermore, we provide a live deployment of the *CollabANT system that allows users to explore the dynamics of collaboration networks in place as well as their involvement over time.
Keywords: Actor Network Theory; IT governance; Cost-Sharing; Cooperative game theory; Shapley value; Collaboration Network; socio-technique.
Special Issue on: Digital Innovation and Intelligence Analysis of E-Business Collaborations and Societal Challenges
Clustering of Text Documents with Keyword weighting function
by CHRISTY A, MeeraGandhi.G G, Vaithyasubramanian S
Abstract: In this digital world, Data is available in abundance everywhere and it is growing at a phenomenal rate. Making data available readily for decision making is an important task of data analyst. In this article, we propose an unsupervised learning algorithm for text document clustering by adopting keyword weighting function. Documents are pre-processed and relevant keywords based on their weights are grouped together. Clustered Keyword Weighting (CKW) takes each class in the training collection as a known cluster, and searches for feature weights iteratively to optimize the clustering objective function, in order to retrieve the best clustering result. Performance of CKW is validated by clustering BBC news collection text collections. Experiments were conducted with simple K-Means, Hierarchical clustering algorithms and our keyword weighting and clustering approach has shown improved cluster quality compared to the other methods.rn
Keywords: Documents; Cluster; Unsupervised; Feature; K-Means; Normalized; etc. rn.
Fuzzy Association Rule Mining for Economic Development Indicators
by Deepesh Kumar Srivastava, Basav Roychoudhury, Harsh Vardhan Samalia
Abstract: This paper is focused on fuzzy mining approach to extract fuzzy association rules among the economic development indicators that are Net official development assistance received (ODA), foreign direct investment (FDI) and gross domestic product (GDP) for developing country India.This study is an attempt to explore the use of fuzzy association rule mining on time series data and to extract interesting association rules therefrom. The extracted rules exhibit the relative volatile nature of these three development indicators. A fuzzy membership function is used to transform the quantitative values of percentage change of each successive year datum into fuzzy sets in linguistic terms. The scalar cardinality of each linguistic term is calculated on the yearly data. Only those fuzzy association rules that qualified the criteria of minimum support and minimum confidence value were taken into consideration. The rules thus mined out exhibit quantitative regularities and can be used for the better suggestion to appropriate policy makers.
Keywords: Development indicators; Association rules; Fuzzy sets; Membership function.
Integrating the Power of Social Media Dataset Impact in Medical Diagnosis
by Suresh A, A. Jayanthiladevi
Abstract: Technology gives consumer the power to investigate products to label them and criticize them in equal measure, and more. The emergence of Internet-based social media has made it possible for one person to communicate with hundreds or even thousands of other people about products and the companies that provide them. Due the impact of consumer-to-consumer communications is a most impressiveness in the marketplace. Therefore many companies today have pages on social networks to complement the information held about products, the feedback of consumers about products and tend to relate more to a company after reading various reviews. This paper is discusses about the dataset used in this work for medical diagnosis, experimental scenario and also about obtained result and discussion of the proposed system and reason for achievements on decision making process. We have collected 10000 records from weblog dataset for experiments in this work for behavioural analysis. Initially, feature selection by using knowledge base and send it for classification using WEKA tool and JAVA. WEKA is a collection of machine learning algorithms for data mining tasks. The proposed algorithms applied to the dataset from Java code and it contains tools for data analysis and predictive modeling. The input dataset of the WEKA are used in the form of CSV file. The various results obtained by the proposed model and other models and classifiers. Performance of the proposed hybrid behaviour analysis model which is the combination of SMO classifier and Rule based Classification algorithm. The performance comparative analysis between the proposed rules based classifier, C4.5 and SMO. The performance of the proposed hybrid behaviour analysis model provides better performance than individual performance of other classifiers.
Keywords: social network; online buying; consumer behavior; and Rule based classifier: C4.5 and SMO and Hybrid model.
DESIGN OF INTERLEAVED FLYBACK CONVERTER
by Ramya Devasahayam
Abstract: This project proposes a transformer design to achieve soft switching low power fly back converter.This proposed paper is having the soft switching which reduces the power loss in main switch while improving the over all EMI in the converter.rnThis paper proposes the design methodology for the transformer in a fly back converter which automatically accomplishes the complete soft switching of the main switch rn
Keywords: transformer design,soft switching.
Heterogeneous Network Security Management
by Narmadha Ramakrishnan
Abstract: The main objective of this paper is to develop authentication delay model for inter domain or intra-domain authentications. Authentication is a security mechanism used to identify mobile nodes(MN) and prevent unauthorized usage when inter-domain or intra domain handoff happens. The latency due to authentication procedure is known as authentication delay. The authentication delay depends on Message propagation time, Message transmission time, Message encryption/decryption time, Authentication request service and waiting time at the Access Point, Authentication request service and waiting time at the server, Key encryption & decryption time, Key generation time and the registration request service and waiting time, etc., In existing systems, Authentication Delay modelling of homogeneous network domain has been carried out and actual values are not applied for modelling the authentication delay. In the proposed system Authentication Delay modelling of heterogeneous network domain will be carried out and actual values will be applied for modelling the authentication delay.rnrn
Keywords: Security; Interworking networks; Authentication; Key Management.
Special Issue on: ICACB'18 Advanced Intelligent and Communication Systems
An Incremental Approach for Hierarchical Community Mining in Evolving Social Graphs
by Keshab Nath
Abstract: Community members which are highly connected with each other
inside a community tends to create sub-communities, commonly termed as
intrinsic or hierarchical communities. Finding intrinsic communities help us to
reach out specific user needs, understanding the network dynamics and unveiling
the functional and hidden aspects in the network, which is difficult without
unveiling intra and inter community all kinds of relationship.With the passage of
time, members of a community may acquire different interests, leads to movement
of members within different communities. Frequent changes in the relationship
of members towards a community make the task of community detection even
In this work, we propose a new community detection method, ECEnet,
(Embedded Communities from Evolving Networks), for handling intrinsic
communities in evolving networks.We adopt a density variation concept to detect
the hidden communities in growing networks.We use a newmembership function
to measure the contiguity of a member towards a community. We use both
synthetic and real-world social networks for our experimentation. Experimental
results reveal that ECEnet is successful in detecting hidden communities in
Keywords: Hidden Communities; Evolving Networks; Dynamic Communities;rnIncremental Clustering; Embedded Cluster; Density Variation.
OBJECT CATEGORIZATION AND FLAME APPREHENSION
by Santhosh Kumar B, Velliangiri S, Ajayan J
Abstract: Object categorization is a customary errand of PC observation which includes deciding if a picture contains some particular class of question. The thought is firmly related with acknowledgment, arrangement, and misgiving. There are numerous techniques to speak to a division of articles, from shape investigation, or neighbourhood inscriptions, for example, SIFT, and so forth. The possible point is to extricate semantics from video to be utilized as a part of larger amount action examination undertakings. Arranging the kind of an uncovered video question is a significant advance in accomplishing this objective. Nonetheless, late research has demonstrated that question groups and their areas in pictures can be found in a freely way too. Our contemporary question arrangement calculation influences utilization of the closer view pixel to delineate to every individual associated area to make a blueprint for the protest. Customarily fire sensors which sense the nearness of specific particles created by smoke and fire by photometry were utilized to recognize fire. Normal sensors mean to detect particles, accordingly, an essential shortcoming of point locators is that they are separate limited and decay in open spaces. In this paper we depict the computational models utilized in our way to deal with achieve the objectives indicated previously
Keywords: Fire identification; FlameColor; Contour Pattern; Object categorization.
Efficient Wideband Filter Using Closed Loop Resonator with coupling lines
by Oudaya Coumar, S. Tamilselvan
Abstract: This paper is about a wideband filter using closed loop resonator with inter-digital coupling lines. The square resonator is used as closed loop structure integrated with inter-digital coupling on both sides which plays a major key role in this filter design. The proposed wideband filter can be employed in UWB receivers since the operating band of UWB is matching with operating bandwidth of this filter. Design and EM Simulation of the UWB filters characteristics are discussed in this work. The proposed UWB filter produces tremendous bandwidth ranges from 2.3 GHz to 8 GHz. The filter evaluation parameters like return loss, insertion loss, phase and group delay are obtained and their responses are analysed. The complete size measurement of the filter is achieved to be 39mm
Keywords: Insertion Loss (IL); Return Loss (RL); square resonator; and ultra-wideband filter (UWB).
AN ANALYSIS OF COMMITMENT AMONG COLLEGE TEACHERS
by Lovelin Auguskani P, Sreedevi V, Jerlin Priya
Abstract: The study An Analysis of Commitment among College Teachers. was carried out Nagercoil at Kanyakumari District. The study helps to understand the commitment level of college teachers. The study was conducted with a sample size of 158 teaching staff, data has been collected through questionnaire. This research paper is through analyzed with primary data which was collected conveyance sampling techniques.This study investigated the commitment among college teachers. The findings from the analysis indicated that the level of organizational commitment is high among the college teachers in Nagercoil at Kanyakumari District. One Way analysis is used to find Variance between the category of appointment and the three commitments level (affective, continuance, and normative) and find variance between the designation and commitment. Majority of government aided respondents are having high level of affective, and normative commitment and self finance respondents having high level of continuance commitment. Assistant professors are having high level of affective, and continuance commitments, Associate Professors are having high level of normative commitment. In order to maintain this level the management should take various initiatives which will motivate the faculty to remain committed towards their job and responsibilities.
Keywords: Affective; Continuance; Normative; Education; Teachers.
LIFI Based Smart Systems for Industrial Monitoring
by Prabakaran N., Naresh K., Kannadasan Rajendran
Abstract: Light Fidelity (Li-Fi) is an unfolding technology which can be used to transfer data through light. It is a complete transformation to the world of wireless data transfer. Harald Haas from the University of Edinburgh, United Kingdom termed and introduced Light Fidelity to world through the global talk show in which he demonstrated of a Li-Fi prototype at the TED Global conference in Edinburgh on 12th July 2011. Challenging the pre-existing data transfer model namely the Wireless Fidelity (Wi-Fi) on various parameters such as speed, safety, reliability eco-friendliness and efficiency. The light emitting diode in a Li-Fi system is the source of data transfer utilizing visible light as medium of communication. This can provide greater download capacity in comparison to the existing wired or wireless networks due to higher bandwidth of light. With such high potential every electronic day to day use commodity that has role of light over it can be thought of to be used as an internet accesses point. Since it can't penetrate through walls they have short range but are highly secure in the confinement of the surrounding in comparison to Wi-Fi and overcome the radio frequency bandwidth availability issues in the near future.
Keywords: Bandwidth Light emitting diode:rn Light Fidelity; Visible light Communication; Wireless Fidelity;.
Product recommendation system using Optimal Switching Hybrid Algorithm
by Bhuvaneshwari Petchimuthu
Abstract: With the advent e-commerce in the internet era, helps people to do online shopping by just clicking the corresponding website. e-commerce website holds millions of products with a lot of information about it. As it holds the different variety of products in the same category, the customer feels difficult in choosing the product they exposed to. To overcome this product overload issue and to attract the customers, the retailers introduced "Recommender System". The Recommender system works as a heart in the business strategy of e-commerce companies like Amazon, Flip-Kart, E-bay, etc. The Collaborative Filtering technique is a popular and widely used recommendation algorithm in e-commerce application for reaching out to the customers by providing the right product and the services at the right time. Even though it is highly valuable, it faces the challenge of recommending the products for the new user. In case of facing this existing cold start problem, we propose an Optimal Switching Hybrid Approach (OSHA) where demographic filtering technique is used to find the similarity of users and the combination of CF prediction mechanism provide the basis for processing the recommendations. The OSHA is the combination of Collaborative Filtering and Demographic Filtering techniques where it switches between the context depending on the scenario. Similarity prediction measure and K nearest neighbor algorithm are used to predict the similar kind of users with size K. The experimental results show that the proposed algorithm performs better and improves the performance of the recommender system.
Keywords: E-commerce; Collaborative Filtering Technique; Cold Start Problem; Optimal Switching Hybrid Approach; Demographic Filtering technique; K Nearest Neighbor algorithm.
Comparison of Automated Leaf Recognition Techniques
by Mahmudul Hassan, Arnab Kumar Maji
Abstract: Plant plays an important role in different ways in human life and atmosphere. There are large numbers of plant species in the world. Plant species plays a vital role in many domains such as preventing some the diseases, farming, environment, discovery of new drug and other related areas. Recognition of plant species without expert understanding is a huge task. There has been great demand for applying automatic computer vision technologies to increase botanical knowledge. Using leaf features and traits, the classification and identification of plant is carried out. Leaf features like shape, texture and venation are the features most frequently used to differentiate the plant species. Different methodologies are there to extract the feature and to classify the leaf images using classifier. In this paper we are going to discuss on different leaf recognition approaches along with feature extraction methods and their performances.
Keywords: ANN(Articial Neural Network); CNN(Convolution Neural Network); Deep learning; PNN(Probabilistic Neural Network); SVM(Support Vector Machine).
A Detail Study on Context-Aware Architectures in Internet of Things
by Deeba Kanmani, Saravanaguru RA.K
Abstract: Internet of things is used to get the data around the world at your fingertip. As we move towards IoT the role of sensors has become vital. These sensors generate a vast amount of data. Sensors are used to sense and collects parallel information from the given set. We propose Context-aware for an Internet of things architectures which computerize the task. In this paper, we will discuss about the architecture of context-aware, IoT and context-aware reasoning. The principle objective of this paper is to audit existing architecture identified with context-aware and IoT and to make the comparative analysis table. The principle point is to enable the clients to present the issues and our proposed design enhances and delivers important information.
Keywords: Context aware; Internet of Things; Middleware; Context Reasoning; Nature Inspired Algorithm; Middleware architecture.
ENHANCING SECURITY BY TWO WAY DECRYPTION OF MESSAGE PASSING OF EMR IN PUBLIC CLOUD
by PRATHAP R, MOHANASUNDARAM R
Abstract: Encryption is one of the most critical and mandatory technique to provide security in outsourced data. Message passing is the most unsecure place of transfer of dangerous information's, and this message passing is made the end to end encryption to avoid a centralized security agent to access the data. Existing methods of encryption only provide end to end encryption which is not feasible for certain situations like implementing authentication. When the end to end encryption is made, the messages are always not known to the central authentication agent like CBI, in this paper, we provide a two side decryption algorithm that can be decrypted by two entities (one receiver and the other is the central authentication agent). Thus improving the message passing security by allowing the centralized authentication agent to read the transferring words. We implemented this two-way decryption in trip database dataset, and the experiment results prove that our proposed algorithm improves the security of message passing of Electronic Medical Records in public cloud while comparing with existing encryption algorithms.
Keywords: Cloud; EMR; Encryption; Decryption; Authentication; Authorization.
Changed Detection of Landsat 8 Imagery using Object Based Image Analysis with Particle Swarm Optimization
by Amitabha Nath, Amos Bortiew, Gautam Saha
Abstract: This paper addresses the problem of classification of hyperspectral remote sensing image and detection of any changes in the land use pattern using it. Traditional pixel based classification approaches often fails to achieve acceptable accuracy in classifying Landsat images because of its complexity. Therefore, present work aims to apply Object Based Image Analysis (OBIA), which is a concept that combines segmentation and classification together into one unit. We propose a hybrid OBIA architecture, augmented with Particle Swarm Optimization (PSO) technique to fine tune different hyperparameters involved with it. We present its success on a classification problem where two sets of landsat-8 images captured in the year 2016 and 2017 are considered as input and OBIA is applied for classifying the images into four major land use classes and detect any changes in these classes over the period of time. The results are then compared with best pixel based classification approach known as Random Forest (RF) classifier to determine its effectiveness in classification of hyperspectral images. Statistical measures like precision, overall accuracy and kappa coefficient are used as a parameter for comparison.
Keywords: Landsat 8 Image; RF; OBIA; Particle Swarm Optimization; changed detection; accuracy assessment.
Special Issue on: Computational Intelligence in Sustainable Informatics Systems
High Performance Inventive System for Gait Automation and Detection of Physically Disabled Persons
by Vinothkanna Rajendran, Vijayakumar Thangavel, Prabakaran Narayanasamy
Abstract: Physically challenged persons may face many difficulties in the present modern environment as most of the commercial facilities and utilities for a day to day life is designed for normal people to lead a sophisticated life. Particularly people physically disabled face struggles in escalators in malls and public transportation places. It is very difficult for the disabled individual to be identified as one among in a large crowd and they normally feel unconformable to step inside in a running escalator. This research work proposes a novel method to identify the physically challenged persons from a large crowd by their nature of legs, walking pattern and hand sticks and provide necessary preference for them to get inside the escalators. Gait automation and detection mechanism is used for person identification for all gait events and deep learning based neural network (DLNN) is used for learning the patterns and making the system to automatically identify the physically challenged. Experimental results shows that the proposed system automatically measures all the angle of gait events with an accuracy level of 95.4% and thus offers a cost effective solution for gait kinematic analysis for disabled peoples.
Keywords: Physically disabled; Gait; Deep learning neural network (DLNN),.
Optimizing QoS with Load Balancing in Cloud Computing applying Dual Fuzzy Technique
by Chintureena Thingom, Ganesh Kumar R
Abstract: Objective: Cloud computing has become a necessity when the internet usage has increased drastically. This research paper objective is to optimize Quality of Service in Cloud Computing using Dual Fuzzy Technique.
Method: With the competition to provide the best quality service at Cloud data center has increased multiple fold, we are analyzing the parameters of average response time, average completion time, average CPU utilization and Job success. Cloud-Sim Simulator has been used to predict and extensively bring out the best technique. The mathematical model is also used to provide reliable and valid result.
Findings: To achieve the best result, the load in datacenter needs to be efficiently distributed, so that it is managed to process maximum service requests with the best service response time and very few failures. In this paper, we applied Dual Fuzzy Technique for the load balancing in the cloud data center in such way that the response time and execution time is optimized compared to the available systems. The findings were extensive and unique where the existing systems were not very reliable and valid. The graphical representation have pointed out the difference. The parameters used have pointed that Dual Fuzzy Technique can provide the best optimized Quality of Service.
Applications/Improvement: With this technique, cloud computing service provider can provide better quality service. More research work in the future can look up for any other better load balancing algorithm.
Keywords: Cloud Computing; Dual Fuzzy; Quality of Service; Cloud-Sim; Load Balancing.
Design of Master Controller Test Kit for the Railway Diesel Locomotives
by KISHORE KUMAR KAMARAJUGADDA, Movva Pavani
Abstract: In the present paper, a master controller test kit for the diesel locomotives is designed, developed and the prototype is tested. Master controller test kit is used by the locomotive driver to drive the engine which is a human-machine interface. Master controller primarily performs three essential functions such as controlling the regression, progression, and locomotive braking. Stick type master controller is a modular based compact design which is a crew friendly for smooth operation and comfort. In the proposed model, the operation of solenoids is indicated by LEDs, and dynamic braking is shown by providing a Digital Voltmeter for measuring the drop across Braking Control Pot (BKCP) coil. LEDs also indicate reverse and forward directions of the locomotive. With this, all functions of Master Controller, internal wiring, switches, coupler pins, and complete healthiness is ensured at test bench itself. Testing of a master controller by loading on locomotive requires workforce and loco downtime. By using this test stand a layman can also check the master controller in the section itself which saves staff-hours and most significant loco downtime. Designed master controller is able to interface with both microprocessor and non-microprocessor type locomotives. The tested prototype is economical, and its performance is comparable with the existing microcontroller based master controllers.
Keywords: Diesel Locomotive; Throttle Handle; Reverser Handle; Master Controller Testing Kit; Directional Handle; Dynamic Brake Handle.
Study paper on Internet of Things and its utilized protocols with application
by Roopa Jayasingh, Remus Dominic D’mello, Abhishek Soren, Ankit Alex Hansdak, Bidyut Mondal
Abstract: The people of the 21st century have now entered a new era of computing technology which is known by a very common name: the Internet of Things (IOT). Although it is also known by certain other names like machine to machine, Internet of Everything and many more, one thing common in this technology is that it is happening in real and has got quite a potential to shape the future of computer technology in the coming days.IoT is basically a paradigm which generally consists of interactive smart machines which communicate with other smart machines, resulting into generation of informative data which are used to produce necessary actions that controls and command things hence making our day-to-day life a lot simpler. The following thesis is an extensive reference to the utilities, applications and possibilities of the internet of Things.
Keywords: Internet of Things; Message Queuing Telemetry Transport; Constrained Application Protocol; XMPP; Asynchronous messaging; Open System Intercommunication;.
Special Issue on: Big Intelligent Enterprise For Sustainable Computing
Comparative Study on IDS using Machine learning approaches for Software Defined Networks
by Muthamil Sudar K, Deepalakshmi P
Abstract: Software Define Networking (SDN) is an emerging network approach that separates the data plane from control plane and enables programmable features to efficiently handle the network configuration in order to improve network performance and monitoring. Since SDN contains the logically centralized controller which controls the entire network, the attacker mainly focuses on causing vulnerability towards the controller. Hence there is a need of powerful tool called Intrusion Detection System (IDS) to detect and prevent the network from various intrusions. Therefore, incorporation of IDS into SDN architecture is essential one. Now a day, Machine Learning (ML) approaches can provide promising solution for the prediction of attacks with more accuracy and with low error rate. In this paper, we surveyed about some machine learning techniques such as Naive Bayes, Decision tree, Random forest, Multilayer Perceptron algorithms for IDS and compare their performance in terms of attack prediction accuracy and error rate. Additionally, we also discussed about the background of SDN, security issues in SDN, overview of IDS types and various machine learning approaches with the knowledge of datasets.
Keywords: IDS; Machine learning (ML); Software defined networking (SDN); Naïve Bayes; Decision Trees; Random forest; Multilayer perceptron; Datasets.
FINANCIAL ACCESS INDICATORS OF FINANCIAL INCLUSION: A COMPARATIVE ANALYSIS OF SAARC COUNTRIES
by Ravikumar Thangaraj
Abstract: Financial inclusion provides access to formal financial services at reasonable cost to the financially excluded people. Financial inclusion has been one of the most sought after topics in recent times for policy makers, researchers and academicians. Definition of financial inclusion varies from region to region. Financial inclusion is measured using different indicator. The important indicators of financial inclusion measurement include access indicators, usage indicators, quality indicators and financial education indicators. Most of the researchers use access indicators and usage indicators to measure financial inclusion. Access indicators comprise of demographic and geographic branch penetration, demographic and geographic ATM penetration and population per branch. This study focuses on comparative analysis of access indicators of financial inclusion in SAARC countries. The study is based on secondary data available in the Central Banks of SAARC nations, International Monetary Fund, World Bank and Asian Development Bank. The study has found and analyzed about the countries which has performed well in each indicator of financial access.
Keywords: Financial access; financial inclusion; Indicators; SAARC.
A Novel Method for Predicting Kidney Diseases Using Optimal Artificial Neural Network in Ultrasound Images
by Balamurugan S.P., G. Arumugam
Abstract: The main aim of this research is to design and develop an efficient approach for predicting ultrasound kidney diseases using multiple stages. Nowadays, kidney disease prediction is one of the crucial procedures in surgical and treatment planning for ultrasound images. Therefore, in this paper, we propose a novel ultrasound kidney diseases prediction using the artificial neural network (ANN). To achieve the concept, we comprise the proposed system into four modules such as preprocessing, feature extraction, feature selection using OGOA and disease prediction using ANN. Initially, we eliminate the noise present in the input image using the optimal wavelet and bilateral filter. Then, a set of GLCM features are extracted from each input image and then we select the important features using oppositional grasshopper optimization algorithm (OGOA). To classify the image as normal or abnormal, the proposed method utilize an artificial neural network (ANN). The performance of the proposed method is evaluated using accuracy, sensitivity, and specificity. The experimentation results show that the proposed system attains the maximum accuracy of 95.83% which is high compared to existing methods.
Keywords: Ultrasound image; neural network; multi-kernel k-means clustering; GLCM features; segmentation; classification; bilateral filter; OGOA.
Recurrent Neural Network based Speech Recognition using MATLAB
by Praveen James, Mun Hou Kit, Chockalingam Aravind Vaithilingam, Alan Tan Wee Chiat
Abstract: The purpose of this paper is to design an efficient Recurrent Neural Network (RNN) based speech recognition system using software with Long Short-Term Memory (LSTM). The design process involves the implementation of speech acquisition, pre-processing, feature extraction, training and pattern recognition tasks for a small vocabulary sentence recognition system using RNN. A vocabulary of 80 words which constitute 20 sentences is used to train and test a vanilla LSTM network. The depth of the layer is chosen as 20, 42 and 60 and the accuracy of each system is determined. The results reveal that the maximum accuracy of 89% is achieved when the depth of the hidden layer is 42. Design complexity and processing time are considered when the signal acquisition, pre-processing, feature extraction, and training algorithm are implemented. In this paper, there are 5 layers namely, the input layer, the fully connected layer, the SoftMax layer, the output layer and one hidden LSTM layer that can be increased for more complex design requirements. The LSTM network stores previous values and is the core component of the speech recognition system. Since the depth of the hidden layer is fixed for a task, increased performance can be achieved by increasing the number of hidden layers. However, the processing time increases as the number of layers increase which necessitates a dedicated hardware device.
Keywords: Speech Recognition; Feature extraction; Pre-processing; RNN; hidden layer; MATLAB.
Real Time Noisy Dataset Implementation of Optical Character Identification Using CNN
by Anand R
Abstract: Optical Character Recognition (OCR) is one of the major research problem in real time applications and its used to recognize all the characters in an image. As English is a universal language, character recognition in English is a challenging task. Deep learning approach is one of the solution for the recognition of optical characters. Aim of this research work is to perform character recognition using Convolutional Neural Network with LeNET Architecture. Dataset used in this work is scanned passport dataset for generating all the characters and digits using tesseract. The Dataset has training set of 60795 and testing set of 7767. Total samples used are 68562 which is separated by 62 labels. Till now there is no research on predicting all 52 characters and 10 digits. The algorithm used in this work is based on deep learning with appropriate some layer which shows significant improvement in accuracy and reduced the error rate. The developed model was experimented with test dataset for prediction and can produce 93.4% accuracy on training, and 86.5% accuracy on the test dataset.
Keywords: Convolutional Neural Networks; Scanned Passport; Deep Learning; Classification; Optical Character Recognition; Discrete Wavelet Transform.
S-Transform Based Efficient Copy Move Forgery Detection Technique in Digital Images
by Rajeev Rajkumar, Sudipta Roy, Manglem Singh
Abstract: Copy-move Forgery (CMF), which copies a part of a picture and pastes it into another location, is one of the common strategies for digital image tampering. Due to the arrival of high-performance hardware and the compact use of image processing software, empowers creating image forgeries easy that are undetectable by the naked eye. For CMF detection, we suggest an efficient and vigorous method that could take care of numerous geometric ameliorations including rotation, scaling, and blurring. In the projected CMF detection system, we use Stock Well Transform (S-Transform) which hybrids the advantages of both Scale Invariant Feature Transform (SIFT) and Wavelet Transform (WT) to extract the key points and their descriptors from the overlapped image blocks. Furthermore, Euclidean distance (ED) between the overlapped blocks are measured to detect the similarities and to identify the tampered or forged region in the image. Besides, a novel Fuzzy min max Neural Network based Decision Tree (FMMNN-DT) classifier is used to recognize the duplicated regions in the forgery image. The proposed system is tested and validated using MICC-F220 dataset and we present comparison among the proposed outcomes with some existing ones which ensure the significance of the proposed.
Keywords: CMF; S-Transform; Feature Extraction; Fuzzy min-max classifier; Decision Tree Classifier.
A Computational Perception of Locating Multiple Longest Common Subsequence in DNA Sequences
by TAMILPAVAI GURUSAMY, SRIPATHY PADHMA R, VISHNUPPRIYA C
Abstract: Bioinformatics is an active research area which combines biological matter as well as computer science research. The longest common subsequence (LCS) is one of the indispensable issue to be unraveled viably in computational science. Discovering LCS is fundamental undertaking in Deoxyribonucleic Acid (DNA) arrangement investigation and other molecular biology. In this paper, new calculation for discovering LCS of two DNA successions and its area is proposed. The objective of this created framework is to discover the area and length of all subsequences which introduces in the two arrangements. To achieve this, DNA sequences are stored in an array and the comparison of DNA sequences are performed using matching algorithm. At the end of matching process, group of subsequence are obtained. Then the length and location of the matched subsequence are computed. After completing the matching process, longest common subsequence(s) is located. In this proposed work, maximally obtained length of LCS is 8. Finally, the computation time is calculated for locating LCS in DNA sequences. In addition to this, computation time is analyzed by gradually increasing the length (in characters count) of DNA sequences from 100, 200, 300, 400 and 500. It concludes that computation time for locating LCS in various lengths of DNA sequences took few seconds difference only.
Keywords: Computational biology; DNA; longest common subsequence; matching algorithm.
Analysis of Double chambered - Single and cascaded Microbial Fuel Cell: Characterization study based on the enrichment of fuel
by G. Thenmozhi, J. Sreelatha, S. Gobinaath
Abstract: Need for green energy, depletion of fossil fuels becomes the immediate requirement for building a clean and sustainable society. Among the various methods of sustainable energy sources, Microbial Fuel cell is an emerging field with vast history as it converts the naturally available materials or bio-products into electricity with the help of microbes. Hence microbial fuel cell is an energy transducer. The experimental set-up is a double chambered microbial fuel cell with four single units among which two are separate and other two single units are cascaded into one. Cow dung and sheep worm kept in the anodic chamber are used both individually and also in combination. vermicompost, curd etc are added to promote the growth of bacteria into it. With this setup, the variation of voltage in the microbial fuel cell with respect to time is observed. Also the performance of microbial fuel cell with fuel enrichment is analyzed. rn
Keywords: Microbial Fuel Cell; energy transducer; cascaded MFC; double chambered microbial fuel cell; cow dung; sheep worm; vermicompost; fuel enrichment; clean energy; Characterization study.
Enhanced Media Independent Handover for vertical handover decision in MANET
by Jagan Nath, Rajesh Kumar Aggarwal, Yudhvir Singh
Abstract: In heterogeneous Mobile Ad Hoc Network (MANET), seamless connectivity of a mobile node is the important challenge. Due to the mobility of the node, it may loss seamless connection. So, vertical handover techniques were presented to solve this issue. However, communication might get cancelled when handover takes place. This results in call drop and some other issues. So as to overcome these issues, an Enhanced Media Independent Handover/IEEE802.21 (EMIH) for vertical handover decision is presented in this paper. In this standard, Adaptive Neuro-Fuzzy Inference System (ANFIS) is included to select optimal network for vertical handover. Simulation results show that performance of the proposed approach outperforms that of the existing approach in terms of handover probability, drop, etc.
Keywords: Mobile Ad hoc Network; vertical handover; optimal network; Adaptive Neuro-Fuzzy Inference System (ANFIS); Received Signal Strength (RSS); Average Bit Rate (ABR); handover probability.
The effect of Lean on job satisfaction
by VARADARAJ ARAVAMUDHAN, ANANTH SENGODAN
Abstract: Lean principles and Lean management are increasingly implemented in various sectors of organizations. Lean has shown visible effects in enhancing productivity, reducing wastage of time and materials while still maintaining customer satisfaction as well as employee satisfaction. Lean philosophy is about people understanding their motives and aspirations. Most of the literature works on Lean say that the key driver for Lean implementation is employee involvement and satisfaction with the process. Hence Lean always focuses on employee motivation and their work performance. This thesis is proposed to study on the impact of Lean on job satisfaction in organizations. The research data will be collected using the survey tool by distributing questionnaires to organizations that implement Lean principles. The respondents who belong to the group that handles everyday work process and services will be selected to participate in the survey. The research survey data will be analysed using Microsoft Excel along with statistical tools like Correlation in order to have an in depth understanding on the findings of the research proposed through several hypothesis.
Keywords: enhancing productivity; reducing wastage of time and materials; employee motivation.
Reinforcement based Heterogeneous Ensemble for Anomaly Detection in Streaming Environment
by Sanjith S L, E. George Dharma Prakash Raj
Abstract: Intrusion detection in networks is a challenging process, mainly due to huge amount of data and the imbalanced nature of the data. Further, the ever-changing transmission patterns introduces concept drift, which also exhibits a huge challenge. This work presents a heteroge-neous ensemble based prediction model to detect anomalies in the network environment. The major goal of the proposed model is to pro-vide faster, more efficient real-time predictions and to enhance the re-liability of the model by providing an iterative mechanism to handle concept drifts. The ensemble is created using three varied base learn-ers and the results are aggregated using a voting combiner to provide results. Decision Tree, Random Forest, and Gradient Boosting Trees are used as the base learners. the varied nature of the learners ena-bles effective performances in models. Further, a reinforcement and an iterative training component is introduced into the model to handle concept drift. Experiments were performed on benchmark intrusion detection data and the results indicate the high performing nature of the model. Comparisons were performed with recent state-of-the-art models in literature and they indicate improved performances of the proposed model, indicating the high performing nature of the pro-posed ensemble model.
Keywords: Ensemble Model; Decision Tree; Random Forest; Gradient Boosting Trees; Vot-ing; Anomaly Detection.
Using Technological Modality to Learn Incidental and Intentional Vocabulary for Effective Communication
by Aravind B R
Abstract: Vocabulary is the flesh of a language, which is an indispensable constituent for a language. This research highlight the role of language learners acquisition in incidental and intentional vocabulary by using technological modality. Effective usage of vocabulary in communication and comprehension is crucial and demanding as well. English being the diplomatic language, and which is witnessed as a parameter for graduates, particularly in job acquisition. There are numerous teaching methods were followed for effective learning. In order to benefit, English as a Second Language (ESL) learners and English as a Foreign Language (EFL) learners, Task-based learning (TBL) approach is observed to be an effective learning method. This paper devices to use TED (Technology, Entertainment, and Design) talk video with subtitles in the syllabus of TBL learning for effective learning of incidental and intentional vocabulary in language and succeeded by analyzing the response from the students. The study reveals the significant development and interest in learning a new word by using the authentic instructional TED talk videos for vocabulary learning and vocabulary acquisition.
Keywords: English as a Second Language; English as a Foreign Language; Task-Based Learning; Vocabulary; English and Communication.
CALL DETAIL RECORD BASED TRAFFIC DENSITY ANALYSIS USING GLOBAL k-MEANS CLUSTERING
by Suja C. Nair, Sudheep Elayidom, Sasi Gopalan
Abstract: With the expanding number of vehicles on the road is creating substantial traffic that is hard to control and maintain safety, particularly in extensive urban areas. To estimate the traffic density several works were carried out in the past. However, they are inappropriate and expensive due to the dynamics of traffic flow. Here we intend to use CDR to distinguish the traffic density location and to track the location of the mobile user. In our proposed method to discover the density scope of the traffic, we are using two algorithms called k-means clustering and the k nearest neighbor classification algorithms. The proposed technique will be tested among five different locations during the weekdays and the weekends, which show the noteworthiness of the proposed algorithm and show that our technique has high accuracy.
Keywords: Traffic density; call detail records; data pre-processing; global K-means clustering algorithm; K-nearest neighbor classification.
Regulations on sustainability reporting as a global force in shaping business enterprises: Evidence from India
by Mathivanan Periasamy, Kasilingam Ramaiah
Abstract: McKinsey in 2010 identified the larger role of the state as a business regulator as one of the five global forces that shape business enterprises. In the recent past, this was very evident in India when both the government and the stock market regulator introduced changes in business responsibility reporting of Indian enterprises. Intelligent enterprises adapt swiftly to changing regulatory mechanisms be it voluntary or mandatory. In this paper, we discuss how Indian enterprises respond to sustainability reporting requirements both in the voluntary and mandatory regimes. Among the variables identified for our study companys age, industry type, market capitalization and listing status of the company including index type influences global sustainability reporting practices in India.
Keywords: GRI; Sustainability reporting in India; Mandatory BRR; Sustainability index; Sustainable companies; SRTs.
Indexing Documents With Reliable Indexing Techniques Using Apache Lucene In Hadoop
by E.Laxmi Lydia
Abstract: Mostly 85% of the data is presented in the form of text, which is the human-readable format. Present educational, business, medical organizations, etc. making use of big data Analytics for storage of data and processing that stored data by using information retrieval. Often time\'s text documents have been transferred from one system to another system without any restrictions like, structured, unstructured and semi-structured data. Systems are well performed with high speed and less complexity only when it has all the data arranged in an orderly way. This paper describes how documents of text data are being Indexed using Apache Lucene with approaches in Hadoop. Most of the applications that deal with huge data over the internet are completely lacking. Use of effective analysis and techniques allow users in resulting high-performance and a challenging option in leading Big Data Analytics.\r\n
Keywords: Apache Lucene; Indexing; Big Data; Indexing techniques.\r\n.
Design of cost effective transistor by software simulation for profitable production
by Debasis Mukherjee
Abstract: Reduction of process cost is the key factor for profitability in any industry. Semiconductor industry is also not an exception of this rule. In this paper, a novel transistor structure has been proposed with reduced process cost and almost same functionality compared to conventional MOSFET transistor. Details fabrication steps of the novel transistor have been proposed. Working of the proposed structure resembles conventional MOSFET, but structure wise there are many differences. Necessity of source extension and drain extension has been uninvolved, resulting less fabrication cost and higher concentration of transistors in same chip area. Another improvement is removal of gate spacer, resulting cutting down of process cost. Both the conventional MOSFET and the proposed one have been simulated by Sentaurus TCAD toolkit for 7 nm technology generation. The performance of the proposed transistor has been found satisfactory compared to the conventional MOSFET as per the guidance given in International Technology Roadmap for Semiconductors or ITRS 2013 version.
Keywords: 7 nm; cost; CMOS; device level; fabrication; ITRS; MOSFET; process cost; production; profitability; TCAD; VLSI.
A Supervised Multimodal Search Re ranking Technique using Visual Semantics
by Nikhila T Bhuvan, M. Sudheep Elayidom
Abstract: The multimedia content in a webpage is usually given least importance in webpage ranking. A better user satisfaction could be achieved if the web pages are ranked based on multiple modalities rather than just depending on the textual content. A better ranking of the web pages is proposed using natural language descriptions of images along with the textual content in a webpage is being proposed. The inter-modal correspondences between text and visual data is learned using the Convolutional Neural Network assisted by the datasets of images and their sentence descriptors. The model is based on Convolutional Neural Networks over images to generate the image descriptor and Dandelion API for their similarity measure with the Query. The image description is algorithmically generated rather depending on the image annotations present. Finally, it has been proven that the re-ranked web pages using the generated descriptions significantly outperform the state of art retrieval models.
Keywords: Automatic image annotation; Convolutional Neural Networks; image descriptor; multimodality search; search re ranking; semantic similarity.
Intelligent Systems for Volumetric Feature Recognition from CAD Mesh Models
by Vaibhav Hase, Yogesh Bhalerao, Saurabh Verma, G. Vikhe Patil
Abstract: This paper presents an intelligent technique to recognize the volumetric features from CAD mesh models based on hybrid mesh segmentation. The hybrid approach is an intelligent blending of facet based, vertex based, rule-based, and artificial neural network (ANN) based techniques. Comparing with existing state-of-the-art approaches, the proposed approach does not depend on attributes like curvature, minimum feature dimension, number of clusters, number of cutting planes, the orientation of model and thickness of the slice to extract volumetric features. ANN based intelligent threshold prediction makes hybrid mesh segmentation automatic. The proposed technique automatically extracts volumetric features like blends and intersecting holes along with their geometric parameters. The proposed approach has been extensively tested on various benchmark test cases. The proposed approach outperforms the existing techniques favorably and found to be robust and consistent with coverage of more than 95% in addressing volumetric features.
Keywords: CAD mesh model; hybrid mesh segmentation; volumetric feature recognition.
Advanced Graphical based Security Approach to Handle Hard AI Problems based on Visual Security
by VENKATA SATYA VIVEK TAMMINEEDI, RAJAVARMAN V.N
Abstract: Security is the main aspect to explore human data from different web oriented applications present in Artificial Intelligence (AI). It is very difficult to use different web applications without security to access data in various places. So that various types of security related approaches were introduced to use services in securely in outside environment, but they have some limitations to protect data from outside attackers (Hackers). So that in this paper, we propose and introduce a Novel and Advanced Security Model to provide security from outside attackers in AI related web oriented applications. In this approach, we follow the basic features related to Captcha as a Graphical password to enable security services in our proposed approach. Using Captcha graphical passwords in our approach, we describe pushing attacks, pass-on attacks and guessing attacks in web applications with random selection of Captcha passwords to use web services. Our experimental results show efficient security relations when compare to existing security approaches in terms of Captcha generation, time and other parameters present in web security applications.
Keywords: Captcha as a graphical password; Directory based push attacks; Security attacks; Visual cryptography and Captcha based dictionary attacks.
Influence of Human Resource Management (HRM) Practices on the Organizational Commitment with Specific Reference to Selected Hotels in Chennai
by Dheera V.R, Jayasree Krishnan
Abstract: This study investigates the influence of Human Resource Management (HRM) practices on the Organizational Commitment in Hospitality Industry. The study hypothesizes that HRM practices (Employee Motivation, Rewards and Awards, Grievance Handling, Employee Engagement, Performance Appraisal and Training and Development) will be positively related to commitment to organization and career. The study was conducted with randomly selected employees (300 numbers) of leading hotels in Chennai, Tamilnadu. The statistical results of the data collected from the employees of hotels reveal that majority of the six HRM practices have direct positive and significant relationships with commitment to organization and career. The employees of the hotels felt that Grievance Handling function of HRM practices has to be given more importance and Performance Appraisal System has to be more effective in a manner to motivate employees to perform better.
Keywords: HRM Practices; Motivation; Rewards and Awards; Grievance Handling; Employee Engagement; Performance Appraisal; Training and Development; Commitment to Organization and Career; Hotel Industry.
Rendezvous Agents-based Routing Protocol (RARP) for delay sensitive data transmission over wireless sensor networks with mobile sink
by V.T. VENKATESWARLU, P.V. NAGANJANEYULU, D.N. RAO
Abstract: The data collected by the sensor nodes will be transferred to sink in traditional wireless sensor networks. The data transmission routes either direct or through the route established using intermediate nodes in between source sensor and sink. Due to the constrained energy reserves of the sensors, a transmission route should operate with minimal energy that tends to longevities the survival of the network. The other critical requirement of these sensor networks is the transmitting delay sensitive data with the ability of fault tolerance and ordering the data to be transmitted that is done by the factors involved to define the priority of that data. The numerous contributions observed in contemporary literature are dealing with the objectives stated. However, these objectives are still grabbing the attention of the present research domain, which is due to the phenomenal changes in network topologies, and the dense span of the network regions. This manuscript endeavored to portray a novel routing strategy to transmit delay-sensitive data from sensors to sink that aimed to achieve fault tolerance, priority-based transmission and longevities the network lifespan. The network context of the proposal is a sensor network with the mobile sink. A novel routing is portrayed that partitions the network area into regions and establishes rendezvous agents for the mobile sink at all of these regions and defines a method to order the areas which is followed by the mobile sink to visit the regions. The process of ordering the regions is furbished under many quality of service objectives portrayed in this manuscript. The performance of the proposed model assessed through simulation study and the same is compared with other contemporary model having similar objectives. The energy consumption efficiency under optimal packet delivery with minimal latency is the objective considered for the performance analysis.
Keywords: LEACH protocol; PASCCC; line-based data dissemination; rendezvous points; smoke/CO system.
Rapid Retrieval of Secured Data from the Sensor Cloud using a Relative Record Index and Energy Management of Sensors
by Geetha S, Deepalakshmi P
Abstract: A massive amount of data is produced by sensors. The data eventually finds a place in the cloud through a base station. Occasionally, the data collection process is disrupted as a result of the energy level of the sensor network. The energy of sensor batteries can be drained by voids. Void sensors do not propagate messages intended for the destination. We have addressed the issue of voids in sensors with the Dynamic Void Removal Algorithm. Data stored in the cloud is being used and retrieved by multiple customers through specifying the relative record index of the sensor data collected. A security mechanism is built with the help of the relative record index associated with sensor data collection. Authenticated customers are given a secret key to rapidly retrieve data from the cloud. Meanwhile sensor networks require a secure mutual authentication scheme in an anxious network environment; we use the Relative Record Index method to design a new user authentication procedure. Our etiquette can handle all problems thrown up by the former schemes. Furthermore, it enhances Wireless Sensor Network authentication with a higher degree of security than other protocols. Therefore, our protocol is more suited to an open and higher-security Sensor Network environment despite greater computation cost and energy.
Keywords: Wireless Sensor Network (WSN); Sensor Cloud (SC); Void Sensors (VS); Dynamic Void Removal Algorithm (DVRA); Relative Record Index (RRI).
SMSS : Does Social,Mobile,Spatial and Sensor data have high impact on big data analytics
by CHEMMALAR SELVI, LAKSHMI PRIYA
Abstract: Big Data refers to the huge torrent of large-scale datasets that are being generated at an exponential growth. Since we live in this digital world, the era of big data as emerged in part and parcel of our lives. The emergence of big data has reached in almost several domains like healthcare industry, telecom industry, molecular biology, biochemistry, physics, astronomy, computer science, business and others. In this paper, we have termed the types of big data by the form SMSS data which is simply meaning Spatial Mobile Social Sensor data. This paper aims to provide the importance of big data analytics brought over the different types of data extracted from different data sources. To achieve this objective, we have made an intensive study of several literatures and considered a variety of big data applications which are being discussed to showcase its value. Also, a generic framework is proposed that can be applicable to any kind of big data types extracted from such a diverse heterogeneous data sources. Finally, a few open source tools that can be used for processing the big data is presented.
Keywords: Big data types; social data; spatial data; sensor data; mobile data.
OFFLINE STUDY FOR IMPLEMENTING HUMAN COMPUTER INTERFACE FOR ELDERLY PARALYZED PATIENTS USING ELECTROOCULOGRAPHY AND NEURAL NETWORKS
by S. Ramkumar, K.Sathesh Kumar, K. Maheswari, P.Packia Amutha Priya, G. Emayavaramban, J.Macklin Abraham Navamani
Abstract: Earlier days people with disability face lot of difficulty in communication due to neuromuscular attack. They are unable to share ideas and thoughts with others so they need some assist to overcome this condition. To overcome the condition in this paper we discussed the capabilities of designing Electrooculogram (EOG) based Human Computer Interface (HCI) by ten subjects using power spectral density techniques and Neural Network. In this study we compare the right hander performance with left hander performance. Outcomes of the study concluded that lefthander performance was marginally appreciated compared to right hander performance in terms of classification accuracy with an average accuracy of 93.38% for all left hand subjects and 91.38 % for all the right subjects using Probabilistic Neural Network (PNN) and also we analyzed that during the training left handers were interestingly participated and also they can able to perform the following eleven tasks easily compared with right handers. Offline analysis was conducted individually to identify the performance of left and right handers using Bit Transfer Rate. From this study we concluded that potentiality of creating HCI was possible by means of left handers and also study proves that right hander need some more training to achieve this. Finally the experiment outperforms our previous study in terms of performance by changing the subjects from right hander to left handers.
Keywords: Electrooculography; Periodogram; Human Computer Interface,Probabilistic Neural Network.
Studies on European Call Option of Binomial Option Pricing Model Using Taguchis L27 Orthogonal Array
by Amir Ahmad Dar, N. Anuradha
Abstract: There are several parameters affecting the European call option value such as strike price K, the price of an underlying asset S_0 , volatility σ, and time period t interest rate r. In this paper, the Binomial option pricing model is utilized to assess the estimations of European call option value. To explore the effects of input factors, Taguchi method of orthogonal L27 design experiment is carried out using an orthogonal array, Analysis of Variance (ANOVA), and Analysis of Mean (ANOM) were used. The purpose of this paper to find the best optimal combination by varying the parameters at constant interest rate r and the effects of parameters are discussed. The ANOM distinguishes which parameter influences higher on European call option value and furthermore, it demonstrates the best combination where the European call option will get the greatest value. The ANOVA estimates the percentage contribution of every parameter on European call option and the analysis is carried out using MINITAB software.
Keywords: Binomial model; Taguchi’s method; ANOM; ANOVA; call Option.
Special Issue on: Innovative Business and Organisational Transformation Practices
Price Discovery and Volatility Transmission in the Spot and Futures Market of Pepper: An Empirical Analysis
by Asha Nadig, Viswanathan T
Abstract: Pepper, the king of spices, is one of the oldest and widely traded spices across the world over many centuries. As a commodity traded in the spot, futures and export market, global demand and supply play a crucial role in shaping pepper price and volatility. As price risks are integral to farmers and traders, forecasting successive prices will be of great help to them. The price risk can be minimised through effective hedging. The futures market provides a platform for both hedging and speculation. Hence understanding the relationship between spot and future market is essential for the traders of commodities. Understanding the relationship between the two markets include price forecasting, price discovery and volatility spill over between the spot and futures market.
This paper examines the price discovery mechanism and volatility transmission between the spot and futures prices of pepper. Applying the statistical, seasonal variation and econometric models for forecasting, forecasting accuracy is tested. By applying the simple linear regression model, the study concluded that the subsequent price of pepper in the spot market cannot be predicted appropriately. The Holt Winters model gives biased estimate of future prices. The goodness of fit analysed through the Akaike information criterion (AIC) gives better values of forecasting. The ARIMA model is the appropriate model to forecast the price of pepper.
Keywords: Forecasting; Price discovery; Cointegration; Volatility spill over.
Analyzing the Entrepreneurial Intentions through Intellectual Capital: Evidences from India
by Ahmed Musa Khan, Mohd Yasir Arafat, Mohd Anas Raushan
Abstract: Intellectual capital is defined as the knowledge that can be converted into value. Intellectual capital has received a considerable attention from in the field of innovation performance. Still, there is a paucity of research which identifies the role of intellectual capital in creating ventures. This research is an attempt to examine the influence of intellectual capital on start-ups. A large data set of responses from 3360 respondents from India has been provided by the largest entrepreneurship research project Global Entrepreneurship Monitor has been used. A logistic regression technique is employed to measure the influence of intellectual capital on entrepreneurial intentions. The results show that all the components of intellectual capital, human capital, structural capital and relational capital have a positive and significant impact on entrepreneurial intentions. The study suggests that policies should be proposed to develop human capital, structural capital and facilitate interaction between existing and potential entrepreneurs so that new venture creation can be fostered. This research falls among the initial studies investigating the relationship between intellectual capital and entrepreneurial intentions. The review of literature reveals that very few studies based on large data set are conducted in developing countries like India.
Keywords: Intellectual Capital; Entrepreneurial Intentions; Human Capital; Structural Capital; Relational Capital.