Deep learning transforming sleep research: from labs to home

Topic: Deep learning transforming sleep research: from labs to home

Time: 15h00, August 12-th, 2021

Speaker: Dr. Huy PhanSchool of Electronic Engineering and Computer ScienceQueen Mary University of London (UK)

📌 Location: MS Teams.

✅ Link: MS Teams

Abstract:

Automatic sleep staging, a long-standing and fundamental problem in research, is vital in sleep medicine and longitudinal sleep monitoring in home environments. This talk will discuss the recent methodological development towards automating sleep staging based on deep learning paradigms that recently outperform human experts’ scoring. State-of-the-art results on conventional PSG data as well as on modern wearable devices (e.g. around-the-ear EEG and in-ear EEG) for home-based longitudinal sleep monitoring will be presented. This talk will envision the future of machine learning / deep learning in sleep medicine.

Speaker Bio:

Huy Phan is a Lecturer in AI at the School of Electronic Engineering and Computer Science, Queen Mary University of London since April 2020 after a postdoc position at the University of Oxford and a Lecturer position at the University of Kent. His research focuses on developing machine learning algorithms for temporal signal analysis, particularly audio/speech and biosignal. He is strongly interested in healthcare applications.

Following the Computer Science education at the University of Science at Ho Chi Minh City, Vietnam and the Computer Engineering education at Nanyang Technological University, Singapore, Huy Phan received a PhD degree with summa cum laude in Computer Science from the University of Lübeck, Germany. His PhD thesis was awarded the Bernd Fischer award by the University of Lübeck in 2018. In 2021, he was awarded Benelux’s IEEE-EMBS Best Paper Award 2019-2020.

Slides: Sleep Staging_Huy Phan

Recording: https://web.microsoftstream.com/video/b0abb9f0-75d3-42c1-883c-96b985418d45

Leave a Reply

Your email address will not be published. Required fields are marked *