Jump to the main content block
TITLE

[2021-Apr-07] Development of Reliable and Applicable Sleep Monitoring and Enhancement Systems

ImgDesc
ImgDesc
ImgDesc

Institute of Information Systems and Applications

Speaker:

Prof. Sheng-Fu Liang 梁勝富教授

Department of Computer Science and Information Engineering & Institute of Medical Informatics, National Cheng Kung University, Taiwan.

AI Biomedical Research Center at NCKU, Ministry of Science and Technology, Taiwan.

Topic:

Development of Reliable and Applicable Sleep Monitoring and Enhancement Systems

Date:

13:30-15:00 Wednesday 07-Apr-2021

Locate:

Delta R104

QR code:

Link:

https://meet.google.com/oxa-smvh-dmk

Hosted by:

Prof. Po-Chih Kuo

Abstract

Advances in artificial intelligence and information technologies support the development of new diagnostics and treatments to the healthcare. The physiological data are usually taken from the patients and the recordings are scored by well-trained experts. The reliable computer-assisted tools for clinical staff to increase the efficiency of data scoring are desired because manual scoring is a time consuming and subjective process. A human-computer collaborative sleep scoring system developed based on small data by combining expert knowledge and machine learning is introduced. The reliability level of each epoch is analyzed based on physiological patterns during sleep and the characteristics of various stage changes. The experts would only need to rescore epochs with a low-reliability level to fine-tune the results. It can ensure the final scoring results are reliable and accepted by experts and the manual scoring time can be greatly reduced. In addition, a series of AIoT devices with edge computing for the in-home screening of objective sleep measurements and sleep environment enhancement are also presented. Finally, a wearable neurofeedback training system with on-line neurosensing, processing and feedback for effective neuromodulation is proposed and the feasibility of applying this system to sleep quality enhancement is also demonstrated.

Bio

http://www.csie.ncku.edu.tw/ncku_csie/depmember/teacherdetail/id/26

All faculty and students are welcome to join.

Click Num: