DocumentCode :
617569
Title :
Software reliability prediction model based on ICA algorithm and MLP neural network
Author :
Noekhah, Shirin ; Hozhabri, Ali Akbar ; Rizi, Hamideh Salimian
Author_Institution :
Soft Comput. Res. Group (SCRG), Univ. Technol. Malaysia, Skudai, Malaysia
fYear :
2013
fDate :
17-18 April 2013
Firstpage :
1
Lastpage :
15
Abstract :
To achieve the high performance system without any failure, we should provide the high reliability level of software. Soft computing models for software reliability prediction suffer from low accuracy during predicting the number of faults. Moreover, the models have some problems like no solid mathematical foundation for analysis, being trapped in local minima, and convergence problem. This paper introduces Imperialist Competitive Algorithm (ICA) to overcome the weaknesses of previous models and improve the efficiency of training process of Multi-Layer Perceptron (MLP) neural network. Therefore, the network can predict the number of faults precisely. The results show that the proposed predicting model is more efficient than the existing techniques in prediction performance.
Keywords :
convergence; evolutionary computation; learning (artificial intelligence); multilayer perceptrons; optimisation; software fault tolerance; ICA algorithm; MLP neural network; convergence problem; fault prediction; high performance system; high software reliability level; imperialist competitive algorithm; local minima; multilayer perceptron neural network; soft computing models; software reliability prediction model; training process efficiency improvement; Computational modeling; Neural networks; Prediction algorithms; Predictive models; Software; Software algorithms; Software reliability; ICA algorithm; MLP; Neural network; software reliability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
e-Commerce in Developing Countries: With Focus on e-Security (ECDC), 2013 7th Intenational Conference on
Conference_Location :
Kish Island
Print_ISBN :
978-1-4799-0394-8
Type :
conf
DOI :
10.1109/ECDC.2013.6556733
Filename :
6556733
Link To Document :
بازگشت