ADAPTIVE DIMENSIONAL PARTICLE SWARM OPTIMIZATION BASED HYPER BASIS FUNCTION NEURAL NETWORK CLASSIFICATION FOR SOFTWARE FAILURE CAUSE PREDICTION
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 9, Pages 956-969
AbstractIn software engineering, Detection of software root cause failure is a considerable issue to be resolved for increasing the reliability. Few research works are introduced for predicting the software failure causes with help of diverse classification algorithm. However, False Positive Rate (FPR) of failure detection process was higher. Therefore, a novel software failure cause prediction model called Adaptive Dimensional Particle Swarm Optimization Based Hyper Basis Function Neural Network (ADPSO-HBFNN) Model is proposed to increase the software reliability through predicting the root cause of software failure at an early stage. ADPSO-HBFNN Model initially gets number of event log files as input. Next, ADPSO-HBFNN Model applies Hyper Basis Function Neural Networks (HBFNNs) for discovering the software fault root cause by means of classifying the event log files. Subsequently, ADPSO-HBFNN Model applies Adaptive Dimensional Search Based Particle Swarm Optimization (ADS-PSO) algorithm where it considers the cost sensitive factor such as expected cost of software failure misclassification. The ADS-PSO algorithm lessen mean square error (MSE) during the learning process by optimizing the weights of network. From that, ADPSO-HBFNN Model correctly find outs the root cause of software failure with higher accuracy. Simulation outcome of ADPSO-HBFNN Model increase the accuracy and lessen time required for software fault root cause prediction as compared to conventional works.
- Article View: 92
- PDF Download: 140