Title: Software credibility assessment model based on back propagation network

Authors: Mingxun Zhu; Xiaohong Chen; Xinxing Luo; Fujun Liu

Addresses: School of Business, Central South University, Changsha, Hunan 410083, China; Department of Information Technology, Hunan Women's University, Changsha, Hunan 410002, China ' School of Business, Central South University, Changsha, Hunan 410083, China; Hunan University of Commerce, Changsha, Hunan 410082, China ' School of Business, Central South University, Changsha, Hunan 410083, China ' School of Business, Central South University, Changsha, Hunan 410083, China

Abstract: Regarding the problem on ignoring the mutual influence between trustworthy attributes in software trustworthy evaluation process, first, the relation between trustworthy attributes is qualitatively divided into promotion, inhibition, and no effect on the three. Second, combined with users' expectation, a software trustworthy evaluation model based on back propagation (BP) network is proposed, and qualitative relation between software attributes carries out quantitative conversion and obtains differences in degree of different software attribute effect software trustworthiness. Finally, this paper uses a web software case to verify the validity and rationality of the proposed model. The results show that the proposed model can be more accurate and comprehensive in software trustworthy evaluation.

Keywords: software credibility assessment; back propagation networks; trustworthy attributes; user expectations; software trustworthiness; software evaluation; neural networks.

DOI: 10.1504/IJCSYSE.2015.077069

International Journal of Computational Systems Engineering, 2015 Vol.2 No.2, pp.66 - 75

Received: 03 Mar 2015
Accepted: 01 Jan 2016
Published online: 20 Jun 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article