Arie Sapta Nugraha
ULM

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

DEEP NEURAL NETWORK ON SOFTWARE DEFECT PREDICTION Arie Sapta Nugraha; Mohammad Reza Faisal; Friska Abadi; Radityo Adi Nugroho; Rudy Herteno
Journal of Data Science and Software Engineering Vol 2 No 02 (2021)
Publisher : Fakultas MIPA Universitas Lambung Mangkurat

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (272.911 KB)

Abstract

Software defect prediction is often performed in research to determine the performance, accuracy, precision, and performance of the prediction model or method used in research, using various software metric datasets such as NASA MDP. In this research, we used Deep Neural Network to classify the software metrics dataset modules into Defective and Non-Defective. The data validation technique used to validate the model is Stratified 10-Fold Cross Validation. Performance of the Deep Neural Network model is reported using Area Under the Curve (AUC) for evaluation measurement. AUC of Deep Neural Network is obtained as 0.815 on MC1 dataset and 0.889 on PC1 dataset. Both AUC values obtained in the MC1 and PC1 datasets are included in Good Classification category.