Hindi Character Recognition using HOG and Bayesian Optimized SVM Classifier
Abstract: The massive digitization of paper documents has revealed the need for highly efficient writing recognition systems. Digitizing these documents allows you to perform operations such as keyword searches or retrieval of high-level information (title, author, addresses, and.). However the recognition of writing and in particular the handwriting are not yet at the level of human performance on complex documents, which restricts or harms some applications. 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 character. Hindi character recognition system which is capable of recognizing Hindi character with the help of morphological operation, edge detection, HOG feature extraction and Bayesian optimized support vector machine (SVM) based classifier

Authors: Durgesh Dixit, Dr. Saroj Hiranwal

File Name: Durgesh_90300-20-101.pdf
 Download Abstract | Download Full Paper

Fuzzy Logic based Relay Selection & Particle Swarm Optimization based Power Allocation Scheme in Cooperative Communication Network
Abstract: The term diversity is based on supplying a lot of duplicates of the similar signal to the receiver over all individual fading channels. There are a few approaches to provide the autonomously fading replications of the information signal to the recipient. The major diversity techniques are frequency, temporal and spatial diversities. Among all, spatial diversity is most popular form of diversity technique which is widely used to overcome the fading impacts in wireless channels. Spatial diversity is obtained by deploying many antennas at sufficient spacing between them to produce multiple independent fading path for transmitted signal. Multiple-input multiple-output (MIMO) technique is kind of spatial diversity, widely adopted in multi antenna communication techniques to enhance their performance. To provide the benefits of MIMO technique in single antenna devices, where use of multiple antennas is restricted due size and power limitations, cooperative communication is proposed. It is often the case that number of sources and number of relays cooperate to send their data to destination. For the cooperative systems, selection of appropriate relay node is of very important. This paper is focused towards the Fuzzy Logic based relay selection and power allocation (PA) using Particle Swarm Optimization (PSO) algorithm in cooperative communication system.

Authors: Vineeta Singh, Ashish Duvey

File Name: Vineeta_90300-20-102.pdf
 Download Abstract | Download Full Paper

© 2016 IJDACR Journal. All rights reserved.