Development of Pi Sigma Neural Network Model for the Prediction of Software Reliability Using 5 NASA Failure Datasets

Barka Piyinkir Ndahi; Opeyemi Aderike Abisoye; Hamzat Olanrewaju Aliyu; Oluwaseun Adeniyi Ojerinde

doi:10.37284/eajit.6.1.1366

Barka Piyinkir Ndahi Federal University of Technology
Opeyemi Aderike Abisoye, PhD Federal University of Technology
Hamzat Olanrewaju Aliyu, PhD Federal University of Technology
Oluwaseun Adeniyi Ojerinde, PhD Federal University of Technology

DOI: https://doi.org/10.37284/eajit.6.1.1366

Keywords: Software Reliability, Feedforward Neural Networks, Pi Sigma Neural Networks, Software Fault, Soft Computing, Ensembles

Share Article:

Abstract

Software reliability models are usually used to model the failure of software systems and prediction of its reliability potential. These models are however plagued with less accuracy, efficiency, and resource-effectiveness. Some soft computing methods have not yet been implemented to investigate their effectiveness and robustness for software fault prediction. Pi Sigma Neural Network (PSNN) software reliability prediction model was developed in this study for a better understanding of the modelling of software systems defects and reliability validated on 5 NASA promise datasets after carrying out data analysis using Seaborn on Python, working with raw data, pre-processed data with min-max normalization, Synthetic Minority Oversampling Technique (SMOTE) to overcome class imbalance problem between defective and non-defective modules, and then correlational analysis with varying thresholds (0.8, 0.85, 0.9 and 0.95) to reduce noise and get key features. The results obtained using the PSNN model showed for all the datasets good average performance for recall being highest at 79.8% based on no threshold, precision at 76.2% on 0.9 threshold, f1-score with 75.6% on 0.95 threshold and accuracy at 74.8% with the same 0.95 threshold. A model based on recall is good at fault finding. Modifying the structure and architecture of the PSNN, like using a voting ensemble algorithm of varied combinations of PSNNs and using a firefly algorithm to optimize in the future, will improve the Neural Network technique

Downloads

Download data is not yet available.

References

Acheampong, M. (2023). Overpromising and Underdelivering? Digital Technology in Nigeria’s 2023 Presidential Elections.

Alsop, T. (2021). Global PC unit shipments 2006-2020. https://www.statista.com

Arasteh, B. (2018). Software Fault-Prediction using Combination of Neural Network and Naive Bayes Algorithm. Journal of Networking Technology, 9(3), 94-101. DOI: 10.6025/jnt/2018/9/3/94-101

Bharany, S., Sharma, S., Khalaf, O. I., Abdulsahib, G. M., Al Humaimeedy, A. S., Aldhyani, T. H., ... & Alkahtani, H. (2022). A systematic survey on energy-efficient techniques in sustainable cloud computing. Sustainability, 14(10), 6256.

Burney, S. A., Ali, S. M., and Burney, S. (2017). A survey of soft computing applications for decision making in supply chain management. In IEEE 3rd International Conference on Engineering Technologies and Social Sciences (pp. 1–6). https://doi.org/10.1109/ICETSS.2017.8324158

Ceci, L. (2021). Number of apps available in leading app stores 2021. https://www.statista.com/

Charette, R. N. (2005). Why software fails. IEEE spectrum, 42(9), 36.

Dhavakumar, P., Shankar, S., Vikram, P. M. (2018, April). Soft computing techniques for enhancing software reliability. International Journal of Latest Trends in Engineering and Technology, 133-140. https://www.ijltet.org

Diwekar, U. M. (2020). Introduction to applied optimization (Vol. 22). Springer Nature.

Gill, P. E., Murray, W., & Wright, M. H. (2019). Practical optimization. Society for Industrial and Applied Mathematics.

Henderi, H., Wahyuningsih, T., & Rahwanto, E. (2021). Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer. International Journal of Informatics and Information Systems, 4(1), 13-20.

Iftikhar, A., Musa, S., Alam, M., Su’ud, M. M., Ali, S. M. (2018, October). Application of Soft Computing Techniques in Global Software Development: state-of-the-art Review. International Journal of Engineering & Technology, 7(4.15), 304-310. DOI: 10.14419/ijet.v7i4.15.23015

Kather, P., Duran, R., & Vahrenhold, J. (2021). Through (tracking) their eyes: Abstraction and complexity in program comprehension. ACM Transactions on Computing Education (TOCE), 22(2), 1-33.

Kaur, G., & Bahl, K. (2014, May). Software Reliability, Metrics, Reliability Improvement Using Agile Process. IJISET - International Journal of Innovative Science, Engineering & Technology, 1(3). http://www.ijiset.com

Kaur, R., & Sharma, S. (2018, July). An ANN based approach for software fault prediction using object-oriented metrics. In International Conference on Advanced Informatics for Computing Research (pp. 341-354). Springer, Singapore.

Khan, A. W., Hussain, I., & Zamir, M. (2021). Analytic hierarchy process‐based prioritization framework for vendor’s reliability challenges in global software development. Journal of Software: Evolution and Process, 33(3), e2310.

Minow, J. I. Spacecraft Anomalies and Failures Workshop 2023: NASA Introductory Comments. In Spacecraft Anomalies and Failures 2023 Workshop.

Nayak, J., Naik, B., & Behera, H. S. (2016). A novel nature inspired firefly algorithm with higher order neural network: performance analysis. Engineering Science and Technology, an International Journal, 19(1), 197-211.

Nayak, J., Naik, B., Pelusi, D., & Krishna, A. V. (2020). A comprehensive review and performance analysis of firefly algorithm for artificial neural networks. Nature-Inspired Computation in Data Mining and Machine Learning, 137-159.

O’Dea, S. (2021). Global smartphone sales to end users 2007-2021. Retrieved from https://www.statista.com

Pandey, S. K., Mishra, R. B., & Tripathi, A. K. (2021). Machine learning based methods for software fault prediction: A survey. Expert Systems with Applications, 172, 114595.

Prasad, R. S., & Sangeetha, Y. (2012). SPC for Software Reliability using Inflection S-Shaped Model. International Journal of Computer Applications, 60(2).

Prasetiyo, B., Muslim, M. A., & Baroroh, N. (2021, June). Evaluation performance recall and F2 score of credit card fraud detection unbalanced dataset using SMOTE oversampling technique. In Journal of Physics: Conference Series (Vol. 1918, No. 4, p. 042002). IOP Publishing.

Sahu, K., Alzahrani, F. A., Srivastava, R. K., & Kumar, R. (2021). Evaluating the impact of prediction techniques: Software reliability perspective. Computers, Materials & Continua, 67(2), 1471-1488.

Shirabad, J. S., & Menzies, T. J. (2005). The PROMISE Repository of Software Engineering Databases. School of Information Technology and Engineering, University of Ottawa, Canada. http://promise.site.uottawa.ca/SERepository

Sharma, D., & Chandra, P. (2019). A comparative analysis of soft computing techniques in software fault prediction model development. International Journal of Information Technology, 11(1), 37-46.

Shin, Y., & Ghosh, J. (1991, July). The pi-sigma network: An efficient higher-order neural network for pattern classification and function approximation. In IJCNN-91-Seattle international joint conference on neural networks (Vol. 1, pp. 13-18). IEEE.

Son, L. H., Pritam, N., Khari, M., Kumar, R., Phuong, P. T. M., & Thong, P. H. (2019). Empirical study of software defect prediction: a systematic mapping. Symmetry, 11(2), 212.

Wu, X., Zheng, W., Chen, X., Zhao, Y., Yu, T., & Mu, D. (2021). Improving high-impact bug report prediction with combination of interactive machine learning and active learning. Information and Software Technology, 133, 106530.