Template-Type: ReDIF-Article 1.0 Author-Name: Krishna Kumar Mohbey Author-X-Name-First: Krishna Kumar Author-X-Name-Last: Mohbey Author-Name: G.S. Thakur Author-X-Name-First: G.S. Author-X-Name-Last: Thakur Title: Framework for finding maximal association rules in mobile web service environment using soft set Abstract: Electronic commerce is very popular nowadays. It is a fast and convenient way to transfer information and communicate with people. E-commerce uses various web services to perform a specific task. When a particular user accessed web services, they are sequentially stored into a database that is called web service sequences. Association rules are used to correlate different web services for knowledge prediction. In this paper, we design a framework for generating maximal association rules of accessed web service sequences using soft set. Soft set uses binary values for their standard representation. This framework converts web service sequences into Boolean-valued information system using the concept of coexistence attributes in a sequence. We define the concept of maximal association rules between attribute sets. Here, maximal support and confidence are also defined using soft set. Experimental results show that the proposed soft-set-based framework provides identical rules when compared with other maximal association rules and rough-set-based rules. Journal: Int. J. of Data Science Pages: 86-105 Issue: 1 Volume: 3 Year: 2018 Keywords: web services sequence; maximal association rule; soft set; coexist services; Boolean value system. File-URL: http://www.inderscience.com/link.php?id=90623 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:86-105 Template-Type: ReDIF-Article 1.0 Author-Name: Imad Rahal Author-X-Name-First: Imad Author-X-Name-Last: Rahal Author-Name: Jonathon Walz Author-X-Name-First: Jonathon Author-X-Name-Last: Walz Title: Secondary protein structure prediction combining protein structural class, relative surface accessibility, and contact number Abstract: With huge amounts of molecular data produced from ever-increasing numbers of genomic and proteomic studies, predicting the secondary structure of proteins from amino acid sequences has become a common expectation among scientists. Several studies in the literature have demonstrated that the accuracy of such predictions can be drastically improved by incorporating additional types of protein data into the prediction process; however, no work has studied the effect of incorporating multiple types of protein data simultaneously. In this work, we report our findings from an extensive experimental study that uses neural networks designed to study the effect of using different combinations of protein data on the accuracy of predicting secondary protein structures. Overall, our experimental results indicate that accuracy improves the most when incorporating contact number, relative surface accessibility or any combination that includes at least one of the two into the prediction process. Journal: Int. J. of Data Science Pages: 68-85 Issue: 1 Volume: 3 Year: 2018 Keywords: protein structure prediction; neural networks; machine learning; scientific data mining; data science; bioinformatics; protein structural class; relative surface accessibility; protein contact number. File-URL: http://www.inderscience.com/link.php?id=90624 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:68-85 Template-Type: ReDIF-Article 1.0 Author-Name: João Nunes De Mendonça Neto Author-X-Name-First: João Nunes De Mendonça Author-X-Name-Last: Neto Author-Name: Luiz Paulo Lopes Fávero Author-X-Name-First: Luiz Paulo Lopes Author-X-Name-Last: Fávero Author-Name: Renata Turola Takamatsu Author-X-Name-First: Renata Turola Author-X-Name-Last: Takamatsu Title: Hurst exponent, fractals and neural networks for forecasting financial asset returns in Brazil Abstract: Our scope is to verify the existence of a relationship between long-term memory in fractal time series and the prediction error of financial asset returns obtained by artificial neural networks (ANNs). We expect that the fractal time series with larger memory can achieve predictions with lower error, since the correlation between elements of the series favours the quality of ANN prediction. As a long-term memory measure, the Hurst exponent of each time series was calculated, and the root mean square error (RMSE) produced by ANN in each time series was used to measure the prediction error. Hurst exponent computation was conducted through the rescaled range analysis (R/S) algorithm. The ANN's architecture used time-lagged feedforward neural networks (TLFN), with backpropagation supervised learning process and gradient descent for error minimisation. Brazilian financial assets traded at BM%FBovespa, specifically public companies shares and real estate investment funds were considered. Journal: Int. J. of Data Science Pages: 29-49 Issue: 1 Volume: 3 Year: 2018 Keywords: Hurst exponent; fractals; ANNs; artificial neural networks; time series forecasting; financial assets. File-URL: http://www.inderscience.com/link.php?id=90625 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:29-49 Template-Type: ReDIF-Article 1.0 Author-Name: Geetika Munjal Author-X-Name-First: Geetika Author-X-Name-Last: Munjal Author-Name: Pooja Sharma Author-X-Name-First: Pooja Author-X-Name-Last: Sharma Author-Name: Deepti Gaur Author-X-Name-First: Deepti Author-X-Name-Last: Gaur Title: Sequence similarity using composition method Abstract: Deoxyribo nucleic acid (DNA) has enormous capacity to carry very important information in the form of character strings. Sequence analysis is the process of applying a wide range of methods to DNA sequences for understanding the structure, feature or evolution of these nucleotides strings. The analysis uses mathematical methods to convert these character strings to numerical values, and these numerical values are used to find similarity between the sequences. DNA sequences only contain four nucleotides: A, C, G and T, but in order to find information from these sequences, sequence comparison becomes essential. In this paper, various methods to analyse DNA sequences including usage of entropy, divergence, LZ complexity and the role of hybridisation are explored. A hybrid model based on the composition vector and distance methods is proposed to find dissimilarity between sequences and this hybrid model is tested on sequences of species downloaded from National Center for Biotechnology Information (NCBI). Journal: Int. J. of Data Science Pages: 19-28 Issue: 1 Volume: 3 Year: 2018 Keywords: nucleotides; entropy; frequency vector. File-URL: http://www.inderscience.com/link.php?id=90626 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:19-28 Template-Type: ReDIF-Article 1.0 Author-Name: Antoine Bossard Author-X-Name-First: Antoine Author-X-Name-Last: Bossard Title: On the Poisson distribution applicability to the Japanese seismic activity Abstract: The Japanese isles are located on the Pacific ring of fire, thus facing intense seismic activity. Earthquakes are recorded on a daily basis, and it is easy to understand that (strong) earthquake forecasting is critical and an actively researched topic. In this study, we are investigating the applicability of the Poisson distribution for earthquake forecasting specifically on the Japanese territory. We shall thus analyse recent seismic data aiming at identifying parameters for the Poisson distribution that induce best forecasting, and also at deducing patterns and relations between, for instance, seismic intensities and geographical locations. We shall conduct several experiments on the data gathered to eventually discuss the most promising conditions for the Poisson distribution in this forecasting context. Journal: Int. J. of Data Science Pages: 1-18 Issue: 1 Volume: 3 Year: 2018 Keywords: probabilistic inference; data analysis; sensor network; earthquake; K-NET; KiK-net. File-URL: http://www.inderscience.com/link.php?id=90627 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:1-18 Template-Type: ReDIF-Article 1.0 Author-Name: P.M.K. Prasad Author-X-Name-First: P.M.K. Author-X-Name-Last: Prasad Author-Name: G. Sasibhushana Rao Author-X-Name-First: G. Sasibhushana Author-X-Name-Last: Rao Author-Name: M.N.V.S.S. Kumar Author-X-Name-First: M.N.V.S.S. Author-X-Name-Last: Kumar Author-Name: K. Chiranjeevi Author-X-Name-First: K. Author-X-Name-Last: Chiranjeevi Title: Design and implementation of non-perfect reconstruction biorthogonal wavelets for edge detection of X-ray images Abstract: The X-ray bone images are extensively used by the medical practitioners to detect the minute fractures as they are painless and economical compared with other imaging modalities. Edge detection of X-ray bone image is very useful for the medical practitioners as it provides important information for diagnosis which, in turn, enables them to give better treatment decisions to the patients. This paper proposes design and implementation of non-perfect reconstruction biorthogonal wavelet for the edge detection of X-ray images. The non-perfect reconstruction biorthogonal wavelet NPR Zbo6.5 wavelet performs well in detecting the edges with better quality. The simulation results show that the non-prefect reconstruction biorthogonal wavelet is effective and accurate. The non-perfect reconstruction biorthogonal wavelet is superior to perfect reconstruction (PR) biorthogonal wavelet for edge detection of X-ray images. The various performance metrics like ratio of edge pixels to size of an image (REPS), peak signal to noise ratio (PSNR) and computation time are compared for various biorthogonal wavelets. Journal: Int. J. of Data Science Pages: 50-67 Issue: 1 Volume: 3 Year: 2018 Keywords: filter-banks; non-perfect reconstruction; symmetry; biorthogonal; edge detection; threshold; edge points; peak signal to noise ratio; support interval; vanishing moments. File-URL: http://www.inderscience.com/link.php?id=90628 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:1:p:50-67 Template-Type: ReDIF-Article 1.0 Author-Name: Deepak K. Agarwalla Author-X-Name-First: Deepak K. Author-X-Name-Last: Agarwalla Title: Damage identification of composite beam structure using fuzzy logic-based model Abstract: Damage identification of beam structures has been in practice for last few decades. The methodologies adopted were upgraded over the time depending upon the complexities of the damage or crack and the desired accuracy. The utilisation of artificial intelligence (AI) techniques has also been considered by many researchers. In the current research, damage detection of a glass fibre-reinforced composite cantilever beam subjected to vibration has been carried out. A fuzzy-based model using triangular, trapezoidal and Gaussian membership functions has been developed separately to predict the damage characteristics, i.e., relative damage position (RDP) and relative damage severity (RDS). The inputs required for the fuzzy-based model, i.e., first three relative natural frequencies and first three mode shape differences have been determined by finite element analysis of the damaged cantilever beam subjected to the natural vibration. An experimental setup has been used to justify the robustness of the proposed technique for damage identification. Journal: Int. J. of Data Science Pages: 170-187 Issue: 2 Volume: 3 Year: 2018 Keywords: damage; glass fibre-reinforced composite cantilever beam; fuzzy model; triangular membership function; trapezoidal membership function; Gaussian membership function; relative natural frequency; mode shape difference; RDP; relative damage position; RDS; relative damage severity. File-URL: http://www.inderscience.com/link.php?id=92281 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:2:p:170-187 Template-Type: ReDIF-Article 1.0 Author-Name: Marko Robnik-Šikonja Author-X-Name-First: Marko Author-X-Name-Last: Robnik-Šikonja Title: Dataset comparison workflows Abstract: To assess similarity of two datasets from the point of view of data science, univariate statistical comparisons are mostly insufficient. We present a methodology which estimates similarity of datasets from the point of view of data mining tasks. For example, we provide a relevant information for a decision if a new/related dataset can be used with an existing supervised or unsupervised model or not. We propose several workflows which cover: (a) statistical properties of generated data; (b) distance based structural similarity and (c) predictive similarity of two datasets. We evaluate the proposed workflows on random splits of several datasets and by comparing original datasets with datasets produced by a generator of semi-artificial data. The results show that the proposed workflows can reveal relevant similarity information about datasets needed in many data mining scenarios. Journal: Int. J. of Data Science Pages: 126-145 Issue: 2 Volume: 3 Year: 2018 Keywords: data analytics; data mining; machine learning; data similarity; clustering; classification. File-URL: http://www.inderscience.com/link.php?id=92282 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:2:p:126-145 Template-Type: ReDIF-Article 1.0 Author-Name: Anthony Scime Author-X-Name-First: Anthony Author-X-Name-Last: Scime Title: Classification diversity measurement Abstract: Interesting classification rules can be determined by a number of measures. When searching a domain for a characterisation of unique, different, but important data an appropriate measurement is diversity. Diversity as a measure of a classification rule is based on the relative distinctness of the rule to the other rules in the rule-set. The diversity measure is the sum of the inverse of commonness of a rule's items. In this paper, diversity is derived from the simplest classification trees using techniques from statistics and information retrieval, and demonstrated using sample datasets. Journal: Int. J. of Data Science Pages: 107-125 Issue: 2 Volume: 3 Year: 2018 Keywords: classification data mining; diversity; interestingness measurement; classification tree measurement; classification trees; data mining; classification rules; rule diversity; rule sets; interestingness. File-URL: http://www.inderscience.com/link.php?id=92283 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:2:p:107-125 Template-Type: ReDIF-Article 1.0 Author-Name: Sherief Abdallah Author-X-Name-First: Sherief Author-X-Name-Last: Abdallah Author-Name: Rasha Abdelsalam Author-X-Name-First: Rasha Author-X-Name-Last: Abdelsalam Author-Name: Rania Seliem Author-X-Name-First: Rania Author-X-Name-Last: Seliem Title: Using Bayesian inference to measure the proximity of flow cytometry data Abstract: Flow cytometry (FCM) is a widely used technique in health-related fields, including cancer diagnosis and HIV monitoring. Measuring and quantifying the proximity between two patients based on the FCM data is challenging, yet crucial in most data mining tasks. Not only does each file contain thousands of features (representing different cells), but also the features are unordered. Furthermore, the data of a single patient can be divided over multiple FCS files due to technical limitations of FCM machines. We propose in this paper the use of Bayesian inference, along with Binning, to represent and measure the proximity between two patients using FCM data. We verify the effectiveness of our approach by comparing the performance of several classification algorithms in predicting leukaemia cases. Journal: Int. J. of Data Science Pages: 188-201 Issue: 2 Volume: 3 Year: 2018 Keywords: FCM; flow cytometry; data mining; leukaemia; Bayesian inference. File-URL: http://www.inderscience.com/link.php?id=92284 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:2:p:188-201 Template-Type: ReDIF-Article 1.0 Author-Name: Sikha Bagui Author-X-Name-First: Sikha Author-X-Name-Last: Bagui Author-Name: Sean Spratlin Author-X-Name-First: Sean Author-X-Name-Last: Spratlin Title: A review of data mining algorithms on Hadoop's MapReduce Abstract: This paper is a review of the most frequently used data mining algorithms on Hadoop's MapReduce. We describe the algorithms with respect to their implementation and performance on Hadoop's MapReduce. We also discuss the similarities and differences between MapReduce's parallel or distributed implementations and the original standard sequential implementations. Journal: Int. J. of Data Science Pages: 146-169 Issue: 2 Volume: 3 Year: 2018 Keywords: Hadoop; MapReduce; Classification; Clustering; KNN; SVM; Regression; Association Rule Mining. File-URL: http://www.inderscience.com/link.php?id=92285 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:2:p:146-169 Template-Type: ReDIF-Article 1.0 Author-Name: Dharmpal Singh Author-X-Name-First: Dharmpal Author-X-Name-Last: Singh Author-Name: J. Paul Choudhury Author-X-Name-First: J. Paul Author-X-Name-Last: Choudhury Author-Name: Mallika De Author-X-Name-First: Mallika Author-X-Name-Last: De Title: An enhance DE algorithm for analysis in dataset Abstract: Differential evolution (DE) is a simple, powerful optimisation algorithm widely used to solve constrained optimisation problems, multi objective global optimisations and complex real-world applications. However, the choices of the best mutation, search strategies, long training time and lower classification accuracy are difficult for authors to know the appropriate encoding schemes and evolutionary operators. Otherwise, it may be lead to demanding computational costs of the time consuming trial and error parameter and operator tuning process. Moreover, mutation and crossover plays an important role in the DE optimisation and several functions are available for it may leads a different result for the same dataset. Therefore, an enhance DE has been proposed to improve searching ability, crossover and mutation strategy to efficiently guide the evolution of the population towards the global optimum in less time. Journal: Int. J. of Data Science Pages: 203-235 Issue: 3 Volume: 3 Year: 2018 Keywords: data mining; association rule; data preprocessing; factor analysis; fuzzy logic; neural network; PSO; particle swarm optimisation; artificial bee colony; DEA; differential evolution algorithm. File-URL: http://www.inderscience.com/link.php?id=94503 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:3:p:203-235 Template-Type: ReDIF-Article 1.0 Author-Name: B. Jaya Lakshmi Author-X-Name-First: B. Jaya Author-X-Name-Last: Lakshmi Author-Name: M. Shashi Author-X-Name-First: M. Author-X-Name-Last: Shashi Author-Name: K.B. Madhuri Author-X-Name-First: K.B. Author-X-Name-Last: Madhuri Title: Summarisation of subspace clusters based on similarity connectedness Abstract: Subspace clustering is an emerging area which explores clusters of objects in various subspaces. The existing subspace clustering algorithms are computationally expensive as they generate a large number of possibly redundant subspace clusters limiting the interpretability of the results. The problem gets even worse with the increase in data's dimensionality. So, this demands for efficient summarisation framework that generates limited number of interesting subspace clusters. A novel algorithm, Similarity Connectedness Based clustering on subspace clusters (SCoC) is proposed to form natural grouping of lower-dimensional subspace clusters. The concept of similarity connectedness is introduced to group and merge the subspace clusters formed in different lower-dimensional subspaces leaping through the lattice of dimensions. The resulted compact and summarised high-dimensional subspace clusters would easily be interpreted for making sound decisions. The SCoC algorithm is thoroughly tested on various benchmark datasets and found that it outperforms PCoC and SUBCLU both in cluster quality and execution time. Journal: Int. J. of Data Science Pages: 255-265 Issue: 3 Volume: 3 Year: 2018 Keywords: subspace clusters; summarisation; similarity; similarity connectedness; similarity threshold; groups of subspace clusters. File-URL: http://www.inderscience.com/link.php?id=94504 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:3:p:255-265 Template-Type: ReDIF-Article 1.0 Author-Name: Priyangika R. Piyasinghe Author-X-Name-First: Priyangika R. Author-X-Name-Last: Piyasinghe Author-Name: J. Morris Chang Author-X-Name-First: J. Morris Author-X-Name-Last: Chang Title: Community detection in dynamic networks with spark Abstract: Detecting the evolution of communities within dynamically changing networks is important to understand the latent structure of complex large graphs. In this paper, we present an algorithm to detect real-time communities in dynamically changing networks. We demonstrate the proposed methodology through a case study in peer-to-peer (P2P) botnet detection which is one of the major threats to network security for serving as the infrastructure that is responsible for various cyber crimes. Our method considers online community structure from time to time and improves efficiency by maintaining the same level of accuracy of community detection over time. Experimental evaluation on Apache Spark implementation of the method showed that the execution time improves over dynamic version of Girvan-Newman community detection algorithm while having a higher accuracy level. Journal: Int. J. of Data Science Pages: 236-254 Issue: 3 Volume: 3 Year: 2018 Keywords: dynamic networks; community detection; Girvan-Newman algorithm; large graphs; spark. File-URL: http://www.inderscience.com/link.php?id=94505 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:3:p:236-254 Template-Type: ReDIF-Article 1.0 Author-Name: R. Sumithra Author-X-Name-First: R. Author-X-Name-Last: Sumithra Author-Name: Sujni Paul Author-X-Name-First: Sujni Author-X-Name-Last: Paul Title: Incorporating security and integrity into the mining process of hybrid weighted-hashT apriori algorithm using Hadoop Abstract: This paper talks about the best algorithms of association rule mining (ARM), weighted and hash tree apriori algorithms in a distributed cloud platform and its enhancement as a hybrid weighted-hashT apriori algorithm and its implementation in a eucalyptus platform. Then, this research work handles the integrity and security issues of data during the process of mining. The algorithm is experimented in a cloud environment using Eucalyptus platform with VMware workstation and Hadoop distributed file system (HDFS). And also, the work evaluated how distributed implementation goes better than stand-alone implementations of weighted and hash tree apriori algorithms as well as distributed implementation. The work further studies the effectiveness of using eucalyptus Hadoop nodes and the performance changes with respect to the use of the security protocol for ensuring the security of data in the mining process. Journal: Int. J. of Data Science Pages: 266-287 Issue: 3 Volume: 3 Year: 2018 Keywords: data mining; weighted apriori; hashT; Hadoop; cloud; data integrity; data security; eucalyptus; apriori; distributed mining. File-URL: http://www.inderscience.com/link.php?id=94506 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:3:p:266-287 Template-Type: ReDIF-Article 1.0 Author-Name: D. Ashok Kumar Author-X-Name-First: D. Ashok Author-X-Name-Last: Kumar Author-Name: S. Murugan Author-X-Name-First: S. Author-X-Name-Last: Murugan Title: Performance analysis of NARX neural network backpropagation algorithm by various training functions for time series data Abstract: This study seeks to investigate the various training functions with non-linear auto regressive eXogenous neural network (NARXNN) to forecasting the closing index of the stock market. An iterative approach strives to adjust the number of hidden neurons of a NARXNN model. This approach systematically constructs different NARXNN models from simple architecture to complex architecture with different training functions and finds the optimum NARXNN model. The effectiveness of the proposed approach was seen to be a step ahead of Bombay Stock Exchange (BSE100) closing stock index of the Indian stock market. This approach has identified optimum neuron counts in the hidden layer for every training function with NARXNN, which reduces neural network (NN) structure and training time and increases the convergence speed. The experimental result reveals that neuron counts in the hidden layer cannot be identified by some rule of thumb. Journal: Int. J. of Data Science Pages: 308-325 Issue: 4 Volume: 3 Year: 2018 Keywords: NARX neural network; time series data; training functions; stock index; forecasting; performance analysis. File-URL: http://www.inderscience.com/link.php?id=96265 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:4:p:308-325 Template-Type: ReDIF-Article 1.0 Author-Name: Tengku Adil Tengku Izhar Author-X-Name-First: Tengku Adil Tengku Author-X-Name-Last: Izhar Author-Name: Torab Torabi Author-X-Name-First: Torab Author-X-Name-Last: Torabi Author-Name: Trieu Minh Nhut Le Author-X-Name-First: Trieu Minh Nhut Author-X-Name-Last: Le Title: Managing data using an ontology for enterprise decision making: a case of the World Bank Abstract: People have access to more data in single day than most people that have access to data in the previous decade. This data is created in many forms and it highlights the development of big data. The challenge is how to capture this data and analyse this data into useful information for the specific organisation activities because determining relevant data is a key to delivering value of information. In this paper, we describe big data in information spectrum to identify relevant data from large collection of big data to assist information professionals with useful information for decision-making process. We illustrate the relationship between big data and information spectrum using an ontology. Case study is applied using data from the World Bank. The results from the case study demonstrate how we incorporate big data and information spectrum using an ontology to provide a platform to extra value from large datasets. Journal: Int. J. of Data Science Pages: 326-352 Issue: 4 Volume: 3 Year: 2018 Keywords: big data; information professionals; information spectrum; ontologies; organisational goals; the World Bank. File-URL: http://www.inderscience.com/link.php?id=96266 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:4:p:326-352 Template-Type: ReDIF-Article 1.0 Author-Name: Bala Brahmeswara Kadaru Author-X-Name-First: Bala Brahmeswara Author-X-Name-Last: Kadaru Author-Name: B. Raja Srinivasa Reddy Author-X-Name-First: B. Raja Srinivasa Author-X-Name-Last: Reddy Title: A novel ensemble decision tree classifier using hybrid feature selection measures for Parkinson's disease prediction Abstract: Parkinson's disease and Alzheimer's disease are the most critical health issues in current days. In neurology, Parkinson disease affects the dopamine receptors of central nervous system. It affects the movement of patients. Dopamine cells are degenerated in this disease progressively, which leads to rapid growth of severity. Extensive amount of research works were done since years for prediction of Parkinson's disease in the early stage. Till date, there is no significant approach, which will provide optimised performance for prediction. Alzheimer's disease is another neurological disease, which generally leads to dementia in most cases Machine learning approaches are more promising approaches for the prediction of these above-said diseases. We presented a novel ensemble-based feature selection measure and decision tree model to predict Parkinson's disease. Experimental results proved that the proposed model has high computational accuracy and true positive rate compared with traditional feature selection measures and ensemble decision trees. Journal: Int. J. of Data Science Pages: 289-307 Issue: 4 Volume: 3 Year: 2018 Keywords: feature selection measures; ensemble decision tree; disease prediction. File-URL: http://www.inderscience.com/link.php?id=96267 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:4:p:289-307 Template-Type: ReDIF-Article 1.0 Author-Name: Gautam M. Borkar Author-X-Name-First: Gautam M. Author-X-Name-Last: Borkar Author-Name: A.R. Mahajan Author-X-Name-First: A.R. Author-X-Name-Last: Mahajan Title: A review on propagation of secure data, prevention of attacks and routing in mobile ad-hoc networks (MANETs) Abstract: Wireless communication is considered as a significant part in our modern innovation for transmitting the packets from source node to destination node. In the developing current situation of wireless communications mobile ad-hoc network (MANET) assumes a major part. In this paper, we have built up a definite review about the algorithms and systems utilised for fathoming the different issues such as security, authentication and routing. We have clarified three different classifications of issues that happen during broadcasting the packets by contrasting each and the past advancements in this paper. To acquire precise solutions to issues such as authentication, protection and security a vast number of protocols, routing strategy and algorithms have been utilised, however, it is exceptionally testing to discover the ideal and proficient technique that can be utilised internationally. In this paper, we have displayed an overview of different existing procedures and afterward basically investigated the work done by the different scientists in the field of MANETs. Journal: Int. J. of Data Science Pages: 353-389 Issue: 4 Volume: 3 Year: 2018 Keywords: wireless networks; MANET; mobile ad-hoc network; communication. File-URL: http://www.inderscience.com/link.php?id=96268 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijdsci:v:3:y:2018:i:4:p:353-389