Hybrid deep architecture for software defect prediction with improved feature set

The software Defect Prediction (SDP) model uses previously learned data to predict whether a future example (such as a file, class, or module) will be defective or not. Accurate forecast results can help software testers arrange testing resources more efficiently. Nonetheless, there are still difficulties in more exact and reliable defect predictions. This study presents the SDP-CMPOA framework, which stands for Software Defect Prediction Crossover with Brownian Motion-based Pelican Optimization Algorithm. The stages of the approach are pre-processing, feature extraction, feature selection, and detection. The preprocessing stage involves improved data normalization. Higher-order statistical features, enhanced statistical features, and raw features are all taken from the pre-processed data. The primary barrier to precise software defect detection and hence adhering to the ideal feature selection method will be the curse of dimensionality. This research proposes a novel Crossover with the Brownian motion-based Pelican Optimization Algorithm for selecting the best features (CMPOA). Finally, hybrid classifiers like Improved Bidirectional Long Short Term Memory (Bi-LSTM and) Deep Max out models are employed for defect prediction. The classifier analysis of KCI/SDP dataset accuracy of the projected model is 9.17%, 9.6%, 7.20%, 13.3%, and 5.7% better than the other methods such as DBN, SVM, CNN, RF, RNN, and SDP- CMPOA respectively at the 60th learning percentage. The efficiacy of the SDP-CMPOA is examined in comparison to other extant schemes with respect to certain measures.