Study of Software Defect Prediction using Forward Pass RNN with Hyperbolic Tangent Function

For the IT sector and software specialists, software failure prediction and proneness have long been seen as crucial issues. Conventional methods need prior knowledge of errors or malfunctioning modules in order to identify software flaws inside an application. By using machine learning approaches, automated software fault recovery models allow the program to substantially forecast and recover from software problems. This feature helps the program operate more efficiently and lowers errors, time, and expense. Using machine learning methods, a software fault prediction development model was presented, which might allow the program to continue working on its intended mission. Additionally, we assessed the models performance using a variety of optimization assessment benchmarks, including accuracy, f1 measure, precision, recall, and specificity. Convolutional neural networks and its hyperbolic tangent functions are the basis of the deep learning prediction model FPRNN HTF Forward Pass RNN with Hyperbolic Tangent Function technique. The assessment procedure demonstrated the high accuracy rate and effective application of CNN algorithms. Moreover, a comparative measure is used to evaluate the suggested prediction model against other methodologies. The gathered data demonstrated the superior performance of the FPRNN HTF technique. Swati Rai | Dr. Kirti Jain "Study of Software Defect Prediction using Forward Pass RNN with Hyperbolic Tangent Function" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-7 | Issue-6 , December 2023, URL: https://www.ijtsrd.com/papers/ijtsrd60159.pdf Paper Url: https://www.ijtsrd.com/humanities-and-the-arts/education/60159/study-of-software-defect-prediction-using-forward-pass-rnn-with-hyperbolic-tangent-function/swati-rai