An Optimized Software Defect Prediction Model Based on PSO - ANFIS

Introduction The Software defect prediction (SDP) model plays a very important role in today’s software industry. SDP models can provide either only a list of defect-prone classes as output or the number of defects present in each class. This output can then be used by quality assurance teams to effectively allocate limited resources for validating software products by putting more effort into these defect-prone classes. The study proposes an OANFIS-SDP model that gives the number of defects as an output to software development teams. Development teams can then use this data for better allocation for their scarce resources such as time and manpower. Methods: OANFIS is a novel approach based on the Adaptive neuro-fuzzy inference system (ANFIS), which is optimized using Particle swarm optimization (PSO). OANFIS model combines the flexibility of ANFIS model with the optimization capabilities of PSO for better performance. Results: The proposed model is tested using the dataset from open source java projects of varied sizes (from 176 to 745 classes). Conclusion: The study proposes an SDP model-based OANFIS that gives the number of defects as an output to software development teams. Development teams can then use this data for better allocation for their scarce resources such as time and manpower. OANFIS is a novel approach that uses the flexibility provided by the ANFIS model and optimizes the same using PSO. The results given by OANFIS are very good and it can also be concluded that the performance of the SDP model based on OANFIS might be influenced by the size of the projects. Discussion: The performance of the SDP model based on OANFIS is better than the ANFIS model. It can also be concluded that the performance of the SDP model might be influenced by the size of projects.