Defesa de mestrado do discente Guilherme Lopes Silva, dia 07/03/2023, as 14:00.

Defesa de mestrado do discente Guilherme Lopes Silva, dia 07/03/2023, as 14:00.

link (Meet): meet.google.com/tze-bwot-mdk

Title: Self-Supervised Learning for Arrhythmia Classification

Abstract: Arrhythmias, heart diseases that are commonly diagnosed through electrocardiograms (ECG), require computational methods for detection and classification. Although there is abundant literature on the subject, the high intra-patient variability and noise of ECG signals pose challenges in developing practical machine learning models. To address this, we propose a customized adjustment of machine learning models through self-supervised learning with human-in-the-loop. Our approach introduces a pretext task called ECGWavePuzzle, which improves classification performance through better generalization. Evaluation metrics on the MIT-BIH database demonstrate the effectiveness of our approach.

Discente: Guilherme Silva

Banca Avaliadora: Prof. Dr. Eduardo Luz (UFOP - orientador); Prof. Dr. Pedro Silva (UFOP coorientador); Prof. Dr. Ivan Meneghini (IFMG); Prof. Dr. Vander Freitas (UFOP)