@article{Salah Albermany, Loay E. George_2022, title={Energy Theft Detection and Preventive Measures for IoT Using Machine Learning}, volume={71}, url={https://www.philstat.org/index.php/MSEA/article/view/357}, DOI={10.17762/msea.v71i3s3.357}, abstractNote={<p> Electricity theft is a big challenge for utilities. The smart grid infrastructure collects and sends out a huge amount of data, Using this data, algorithms for machine learning and deep learning may be able to reliably detect electrical thieves. Automatic power theft detection was carried out using CNNs, and convolution neural networks. CNN with some layers to extract features map by convolution layer and is classified by a softmax layer. State Grid Corporation of China (SGCC) dataset is used, and it handles missing values by linear interpolation, removes an empty record from a dataset, and orders the dataset by date. Then, the slope, average, and moment for each month are determined and entered into the CNN model. Finally, the attained computed accuracy reached 100, which is encouraging compared to previously published classification systems</p>}, number={3s3}, journal={Mathematical Statistician and Engineering Applications}, author={Salah Albermany, Loay E. George, Mali H. Alameady,}, year={2022}, month={Aug.}, pages={155–168} }