Electricity Theft Detection System

Authors

  • Snehal Sanjay Vipradas Student, Department of Computer Engineering, Marathwada Mitra Mandal's College of Engineering, Pune, India
  • Prathamesh Ramesh Bendre Student, Department of Computer Engineering, Marathwada Mitra Mandal's College of Engineering, Pune, India
  • Apurva Shripad Upasani Student, Department of Computer Engineering, Marathwada Mitra Mandal's College of Engineering, Pune, India
  • Geetha Chillarge Assistant Professor, Department of Computer Engineering, Marathwada Mitra Mandal's College of Engineering, Pune, India
  • Anisha Shitole Student, Department of Computer Engineering, Marathwada Mitra Mandal's College of Engineering, Pune, India

Keywords:

OCR (Optical Character Recognition), Machine Learning, Smart grid meter

Abstract

Most of theft detection issues are observed in multiple areas. So, this system is proposed to detect the electricity theft, in which reading of electric meter through images are used and preprocessing done with the help of OCR and XGboost. User’s monthly electric meter is captured in the camera and stored into the dataset. Upon successful completion of comparison between the meter unit values and its monthly meter average if we get difference between them then theft is detected. The values which actually goes under computation are trained and the results are displayed over the screen.

Downloads

Download data is not yet available.

Downloads

Published

15-05-2022

Issue

Vol. 5 No. 5 (2022)

Section

Articles

License

Copyright (c) 2022 Snehal Sanjay Vipradas, Prathamesh Ramesh Bendre, Apurva Shripad Upasani, Geetha Chillarge, Anisha Shitole

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
S. S. Vipradas, P. R. Bendre, A. S. Upasani, G. Chillarge, and A. Shitole, “Electricity Theft Detection System”, IJRESM, vol. 5, no. 5, pp. 87–89, May 2022, Accessed: Dec. 21, 2024. [Online]. Available: https://journal.ijresm.com/index.php/ijresm/article/view/2038

Most read articles by the same author(s)