Handwritten Character Recognition System using Gabor Filter and SVM Classifier
Abstract: The selection of features is an important step in any pattern recognition system. This selection of features is considered a combinatorial optimization problem and made the object of research in many disciplines. The main objective of the selection of features is to reduce the number of them by eliminating redundant and irrelevant features recognition system. The second objective of this feature selection is also to maintain and/or improve the performance of the classifier used by the recognition system. In this paper, support vector machine (SVM) based approach is proposed to solve this type of problem in the recognition of handwritten character. This work is capable of recognizing handwritten character with the help of morphological operation, edge detection, feature extraction using Gabor filter and support vector machine (SVM) based classifier

Authors: Sandli Bansal, Komal Paliwal

File Name: Sandli_68000-18-105.pdf
 Download Abstract | Download Full Paper

Comparative Analysis of Community Detection Algorithms on Social Network
Abstract: Networks are very important structures. As modern humans, we are surrounded by them every minute. Therefore, the detection and aggregation of data and users in communities in social networks are important and complex activities. In this paper, we consider a method of analyzing the network, which is known as community detection. The detection of the community can be useful for identifying communities of common interests, which would be done for the benefit of the youth so that they are involved in things that interest them. There are several types of networks for community identification, like social networks and biological networks. Several different approaches have been proposed to solve the problem and one of these is the Louvain method based on maximality of modularity. As the social networks evolve, the network community structure changes. How can the community structure be updated efficiently? In this, we provide two methods based on the Louvain algorithm, to determine the community structure to update, that is the Edge-distribution-Analysis Algorithm, this decides and adds of new edges, modularity-change algorithms analyze the rate of modularity and provides whether an update is necessary.

Authors: Priya Chaudhary, Nisha Pandey, Dinesh Singh

File Name: Priya_68000-18-106.pdf
 Download Abstract | Download Full Paper

A Novel Approach of Cluster Heads Selection by Fuzzy Logic to Enhance the Reliability of WSN
Abstract: Sensor nodes in WSN are powered by a battery. Sensor nodes consume the battery power mainly in the tasks like data transmission, data reception, and sensing. Sometimes it is impractical to replace a battery in WSN because humans cannot reach. Therefore once energy or computational resources are consumed, immediate recovery of these resources is a complex task so it is necessary to make use of battery power efficiently to increase the lifetime of the sensor nodes that will also increase the lifetime of the whole network. To make WSN energy efficient and to increase the lifetime of the network we design a Fuzzy Logic based clustering approach in the heterogeneous environment. The execution and demonstration of this work are performed with the help of MATLAB 2014a. The performance comparison metrics are; network lifetime, network throughput and the number of alive nodes.

Authors: Ankita Luhan, Prof. Y. S. Thakur, Dr. D. K. Sakravdia

File Name: Ankita_69000-18-102.pdf
 Download Abstract | Download Full Paper