Draft:Stefano Frizzo Stefenon

Researcher in the field of artificial intelligence with a focus on applying solutions to electrical power systems. He currently is a researcher at Fondazione Bruno Kessler in Italy. His interests include artificial intelligence for fault identification in electrical power systems, deep learning, computer vision, and wavelet transform.

He received the B.E. and M.E. degrees in Electrical Engineering (Power Systems) from the Regional University of Blumenau, Brazil, in 2012 and 2015 respectively. In 2021 received his Ph.D. in Electrical Engineering from the State University of Santa Catarina, Brazil. During his doctoral period, he developed a research project in the field of deep learning applied to computer vision at the Faculty of Engineering and Applied Science, University of Regina, Canada.

His research initially took place at the High Voltage Laboratory of the Regional University of Blumenau (FURB). During his master's degree, he investigated faults in medium-voltage distribution networks exposed to natural and artificial contamination. . During his investigation, he used ultrasound equipment to classify insulators. After inspecting the electrical system, with insulators in various conditions, he carried out laboratory analysis under controlled conditions.

To improve the ability to identify faults in the electrical power grids, he began his doctorate where, in his first work he focused on applying machine learning techniques to power systems was focused on the classification of defects in distribution insulators. This work relied on a combination of various techniques such as bottom-up segmentation, wavelet energy coefficient, principal component analysis, and particle swarm optimization associated with an ensemble extreme learning machine. This work had superior results to other classification models and motivated him to do more in-depth research on the subject.

Some of the topics have shown promise and have prompted specific research into their application. Focusing on the use of the wavelet transform to noise reduction in time series, the following works were explored by the author, such as:, , and. Combining of the wavelet transform with forecasting models has been extended to collaborative work with other authors, such as the doctoral work of Nathielle Waldrigues Branco.

The exploration of noise attenuation models resulted in research into other techniques such as the Hodrick–Prescott filter, empirical wavelet transform , and Christiano–Fitzgerald random walk filter