I Ketut Eddy Purnama, Mochamad Ashari, Mauridhi Hery Purnomo : Data Mining Based ROC for Fault Detection and Diagnosis in Radial Distribution System

Dr. I Ketut Eddy Purnama ST.,M.Kom.
Prof. Dr. Ir. Mochamad Ashari M.Eng.
Prof.Dr.Ir. Mauridhi Hery Purnomo M.Eng.

External link



Jurnal Nasional Terakreditasi




This paper discusses data mining applications, especially the use of support vector machines to identify a fault in the 13 nodes radial distribution system of IEEE standard. The identification process was carried out with support vector machine (SVM). Prior to the identification process by SVM, feature extraction was carried out using wavelet transformation for signal decomposition and signal size reduction. To determine the performance of the identification, ROC (Receiver Operating Characteristic) analysis was used. Based on the curve formed by the ROC a fault in the radial distribution can be identified by SVM with ‚??good‚?? performance This is indicated by the value of the best cut-off point is 0.8 and area under the curve is 0.85854.