Performance Analysis on Datasets and Heterogenous Defect Prediction through Machine Learning
Y Prasanth1, B Yamini Supriya2, M Tharun Kumar3, P Y S Surya Teja4
1Dr. Y Prasanth, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (A.P), India.
2B Yamini Supriya, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (A.P), India.
3M Tharun Kumar, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (A.P), India.
4P Y S Surya Teja, Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram (A.P), India.
Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1878-1882 | Volume-8 Issue-4, April 2019 | Retrieval Number: D7010048419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Software defect prediction is an important factor which maintains high grade of software and reduces the cost of software development.In General, defect prediction identifies the modules that are defect-prone and then proceed for the testing phases.Literature survey is performed on Software defect prediction which is based on different machine learning techniques such as decision trees, neural network, Naive Bayes etc., This project presents the survey of various techniques to identify defects which also shows the accuracy between one defect to the other defect.To perform this experiment four NASA datasets have been used(defect data sets).These datasets are different in size and number of defective data. Finally, we end up with identifying which technique gives us more accuracy and less number of defects.
Keywords: Software Defect Prediction, Software Reliability, Fault Prediction, Defect Data Sets, Accuracy.
Scope of the Article: Machine Learning