International Journal of

Soft Computing and Software Engineering [JSCSE]

ISSN: 2251-7545

Prefix DOI : 10.7321/jscse

URL: http://JSCSE.com

A Peer-Reviewed Journal

The International Journal of

Soft Computing and Software Engineering [JSCSE]

UserName:

Password:

Publication Year:

[ 2011 ] [ 2012 ] [ 2013 ] [ 2014 ] [ 2015 ] [ 2016 ] [ 2017 ]

[Vol. 4, No.1, Jan] [Vol. 4, No.2, Feb] [Vol. 4, No.3, Mar] [Vol. 4, No.4, Apr] [Vol. 4, No.5, May] [Vol. 4, No.6, Jun] [Vol. 4, No.7, Jul] [Vol. 4, No.8, Aug] [Vol. 4, No.12, Dec]

Advance Search
Table of Contents [Vol. 4, No.1, Jan]

Multi-view Gait Based Biometric System

Hu Ng, Wooi-Haw Tan, Junaidi Abdullah
Doi : 10.7321/jscse.v4.n1.1
Page : 1 - 12

Show Summary

Abstract . This paper presents a multi-view gait based biometric system that able to work well in various walking trajectories and covariate factors such as clothing, load carrying and speed of walking. Our approach first applies perspective correction to alter the silhouettes from oblique view to side-view plane. Next, joint locations of hip, knees and ankles are estimated based on a priori information of human body proportion. Dynamic and static gait features are then extracted by the proposed extraction technique. Gaussian filter is applied to smooth the features in order to reduce the influence of outliers. Feature normalization and selection are subsequently applied before the classification process. The experiments were carried out on SOTON Oblique Database and SOTON Covariate Database from University of Southampton. From the experimental results, the proposed system achieved 92.5% and 96.0% correct classification rates for both databases respectively.
Keyword : gait recognition, biometrics, covariate factors

Applying Genetic Evolutionary, Bacteriological and Quantum Evolutionary Algorithm for Improving Performance Optimization Segment of Test Data Sets in Mutation Testing Method

Mohsen Falah Rad, Sajjad Bahrekazemi
Doi : 10.7321/jscse.v4.n1.2
Page : 13 - 26

Show Summary

Abstract . Due to computer progress, computer systems became bigger and their function area expanded too. So, software testing, as a part of software engineering, has gained great importance. The goal of software testing is improving software quality and being sure about the accuracy of the final product; moreover the programmers test it for evaluating software accuracy. There are a variety of methods for software testing, among which, the mutation testing is the most famous one. In this method, high range mutants are made from the original program, and then attempts are made to discover mutants by the help of testing data collections. Whenever necessary, testing data can be improved or software deficiency can be found in the process of making and discovering mutant. This is done through algorithm of genetic evolutionary, bacteriological, particle swarm optimization, and evolutionary quantum, which have a high quality for research and can be done automatically. In these methods, test data can be improved by using the properties of the above evolutionary algorithms and without any human intervention in optimization part of the test data of mutation testing system, which consequently leads to a huge reduction in mutation testing costs. In these methods, test data can be improved by using the properties of the above evolutionary algorithms and without any human intervention in optimization part of the test data of mutation testing system, which consequently leads to a huge reduction in mutation testing costs. In this article, four methods of algorithm of genetic evolutionary, bacteriological, particle swarm optimization, and evolutionary quantum have been studied for improving testing data in mutation.
Keyword : software testing ; mutation testing ; genetic algorithm ; evolutionary quantum ; bacteriological algorithm