Tuesday 30 January 2024 at 3:00 PM CET, 9:00 AM EST

By Mohamed Benbouzid (University of Brest, France)

Register now using the link below:

https://attendee.gotowebinar.com/register/8995107261184803935


Abstract:

The increase in electricity theft has become one of the main concerns of power distribution networks. Indeed, electricity theft could not only lead to financial losses, but also leads to reputation damage by reducing the quality of supply. With advanced sensing technologies of metering infrastructures, data collection of electricity consumption enables data-driven methods to emerge in such non-technical loss detection as an alternative to traditional experience-based human-centric approaches. In this context, predicting instances of fraud poses various challenges, such as identifying missing patterns, handling class imbalance, and managing a high level of cardinality, where a single feature can have numerous possible values. Therefore, this webinar aims to address the problem of data representation and enhance the distinction between different data classes. To achieve this, deeper representations are proposed, going beyond the capabilities of deep learning networks. These deeper representations involve recurrent expansion, where the learning models themselves are repeatedly merged into a more complex architecture.

Presenter’s bio:

Mohamed Benbouzid completed his Ph.D. in electrical at the National Polytechnic Institute of Grenoble, Grenoble, France, in 1994. He further earned his Habilitation à Diriger des Recherches degree from the University of Amiens, Amiens, France, in 2000.
Following the completion of his Ph.D., Dr. Benbouzid joined the University of Amiens, where he held the position of Associate Professor in electrical engineering. Since September 2004, he has been affiliated with the University of Brest, Brest, France, where he currently serves as a Full Professor in electrical engineering. Additionally, he holds the distinguished positions of a Distinguished Professor and a 1000 Talent Expert at the Shanghai Maritime University in Shanghai, China. Prof. Benbouzid primary research interests and expertise include control of electric machines, variable-speed drives for traction, propulsion, and renewable energy applications, and fault diagnosis of electric machines.
Prof. Benbouzid is an IEEE Fellow and a Fellow of the IET. He is the Editor-in-Chief of the International Journal on Energy Conversion and the Applied Sciences (MDPI) Section on Electrical, Electronics and Communications Engineering. He is a Subject Editor for the IET Renewable Power Generation.