Tom Van Steenkiste
Disentangled Variational Auto-Encoders for Explaining ECG Beat Embeddings
An important aspect of analyzing ECG data is identifying and classifying heartbeats. Advancements in neural networks and deep learning have led to high classification accuracy. However, adoption of such models into clinical practice is limited due to the black-box nature of the classification method. In this work, the use of variational auto encoders to learn human-interpretable encodings of the beat types is analyzed.
Tom Van Steenkiste received his M. Sc. degree in Computer Science Engineering from Ghent university in 2016. Since August 2016, he is active as a PhD researcher in the IDLab research group where he is working on machine learning techniques for medical time series analysis.