An Enhanced Conventional Neural Network Schema for Structural Class-based Software Fault Prediction

An Enhanced Conventional Neural Network Schema for Structural Class-based Software Fault Prediction

Malicious software detection is the most prominent process required by various industries to avoid server failure. It is required to detect malicious software accurately to avoid time and cost wastage. Various research works have been introduced earlier for the detection of malicious software. In the existing work Support Vector Machine (SVM) is introduced for malicious software detection. However, existing works cannot perform well where there are error modules in the software. It is addressed in this suggested study by developing Coupling and Cohesion Metrics-based Fault Detection (CCMFD). In this research work, structural measures are mainly examined which come under the cohesion measures and comprise deficient cohesion in approaches (LCOM), and Conceptual Coupling between Object Classes (CCBO). Failure situations and measures relating to information flow are used in other techniques. A high-quality service has a low coupling and a high cohesiveness. These extracted features will be given as input to the enhanced Conventional Neural Network (CNN) for software mistake forecasting. A complete study analysis is done in a Java simulator, indicating that the suggested approach tends to have superior fault prediction outcomes than the current method.

The accessible file is the accepted version of the paper. Please refer to the URL for the published version.