Article: Software fault prediction using BP-based crisp artificial neural networks Journal: International Journal of Intelligent Information and Database Systems (IJIIDS) 2015 Vol.9 No.1 pp.15 - 31 Abstract: Early fault detection for software reduces the cost of developments. Fault level can be predicted through learning mechanisms. Conventionally, precise metrics measure the fault level and crisp artificial neural networks (CANNs) perform the learning. However, the performance of CANNs depends on complexities of data and learning algorithm. This paper considers these two complexities to predict the fault level of software. We apply the principle component analysis (PCA) to reduce the dimensionality of data, and employ the correlation-based feature selection (CFS) to select the best features. CANNs, then, predict the fault level of software using back propagation (BP) algorithm as a learning mechanism. To investigate the performance of BP-based CANNs, we analyse varieties of dimensionality reduction. The results reveal the superiority of PCA to CFS in terms of accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Software fault prediction using BP-based crisp artificial neural networks

Authors: Golnoush Abaei; M. Reza Mashinchi; Ali Selamat

Addresses: UTM-IRDA Center of Excellence UTM, Faculty of Computing, Universiti Teknologi Malaysia, UTM Johor Bahru, 81310, Johor, Malaysia ' UTM-IRDA Center of Excellence UTM, Faculty of Computing, Universiti Teknologi Malaysia, UTM Johor Bahru, 81310, Johor, Malaysia ' UTM-IRDA Center of Excellence UTM, Faculty of Computing, Universiti Teknologi Malaysia, UTM Johor Bahru, 81310, Johor, Malaysia

Abstract: Early fault detection for software reduces the cost of developments. Fault level can be predicted through learning mechanisms. Conventionally, precise metrics measure the fault level and crisp artificial neural networks (CANNs) perform the learning. However, the performance of CANNs depends on complexities of data and learning algorithm. This paper considers these two complexities to predict the fault level of software. We apply the principle component analysis (PCA) to reduce the dimensionality of data, and employ the correlation-based feature selection (CFS) to select the best features. CANNs, then, predict the fault level of software using back propagation (BP) algorithm as a learning mechanism. To investigate the performance of BP-based CANNs, we analyse varieties of dimensionality reduction. The results reveal the superiority of PCA to CFS in terms of accuracy.

Keywords: fault prediction; crisp ANNs; artificial neural networks; CANNs; correlation-based feature selection; CFS; principle component analysis; PCA; class-level metrics; dimensionality reduction; recall; accuracy; precision; F-measure; software faults; software errors; software development; back propagation; dimensionality reduction.

DOI: 10.1504/IJIIDS.2015.070825

International Journal of Intelligent Information and Database Systems, 2015 Vol.9 No.1, pp.15 - 31

Received: 23 Oct 2013
Accepted: 20 Jan 2015
Published online: 28 Jul 2015 *

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

Title: Software fault prediction using BP-based crisp artificial neural networks

Keep up-to-date