A Neuro-Fuzzy Hybridized Approach for Software Reliability Prediction

Context: Reliability prediction is critical for software engineers in the current challenging scenario of increased demand high-quality software. Even though various reliability models have been established so far, there always a need more accurate model today's competitive environment producing Objective: This paper proposes neuro-fuzzy hybridized method by integrating self-organized- map (SOM) and fuzzy time series (FTS) forecasting system. Methodology: In proposed approach, well-known supervised clustering algorithm SOM incorporated with FTS developing hybrid prediction. To validate an experimental study done applying on failure dataset. addition, comparative was conducted evaluating performance comparing it some existing models. Results: Experimental outcomes show that approach performs better than Conclusion: The results can be used efficiently industry