Power Theft Detection Using Novel Linear SVM Algorithm and Compared With Convolutional SVM Algorithm For Accuracy

Abstract

The aim of the study is to eliminate the electricity loss of individual customers and to overcome the economic crisis. A novel Linear Support Vector Machine (SVM) algorithm is proposed over a Convolutional Support Vector Machine (SVM) Algorithm. It is used to improve the accuracy of power theft detection. Materials and Methods: There are two groups in this study each with a sample size of 10 per group. The analysis was done with the pretest power 0.8. Results: The mean value for accuracy of power theft detection in Novel Linear SVM method is 90.242 which is high when compared to Convolutional SVM whose accuracy is 81.842. Obtained significance value is 0.05 ( <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$p$</tex> = 0.05). Conclusion: The study shows that the novel Linear SVM algorithm has more significant and reliable accuracy of power theft detection compared to the Convolutional SVM model.