[CCoE Notice] Dissertation Announcement: Tanapol Kosolwattana, "Adaptive, Federated and Resilient Health Monitoring via Novel Online Collaborative Learning Algorithms"

[Greenwell, Stephen J]

[Dissertation Defense Announcement at the Cullen College of Engineering]
Adaptive, Federated and Resilient Health Monitoring via Novel Online Collaborative Learning Algorithms

Tanapol Kosolwattana
February 5, 2025; 2:30 p.m. to 4:30 p.m. (CST)
Location: Mechanical Engineering Conference Room 202
Microsoft Teams Link:  Join the meeting<https://urldefense.com/v3/__https://teams.microsoft.com/l/meetup-join/19*3ameeting_Mjk0Njk2MzYtZTJiZi00ZmE0LWIxYjItMGE0NzI3ZDc0Njdk*40thread.v2/0?context=*7b*22Tid*22*3a*22170bbabd-a2f0-4c90-ad4b-0e8f0f0c4259*22*2c*22Oid*22*3a*2258acac18-0128-4198-b4a0-29a441635034*22*7d__;JSUlJSUlJSUlJSUlJSUl!!LkSTlj0I!AVfuOS0BXr0HeuBpFvCjRsiZxQ6wU0UuVAw0zg20pl588xDRw3XJ8X6SqG5satFrFtn2aDaXLTb0nN9CI1B-M5jeKb8$ >
Committee Chair:
Ying Lin, Ph.D.
Committee Members:
Gino Lim, Ph.D. | Qianmei (May) Feng, Ph.D. | Renjie Hu, Ph.D. | Huazheng Wang, Ph.D.
Abstract
Adaptive monitoring of a large population of dynamic processes is critical for the timely detection of abnormal events under limited resources. This issue is pervasive in various sectors, including healthcare and engineering systems, due to the disparity between available monitoring resources and the large population of units, and the uncertain and heterogeneous dynamics of unit progression. To effectively address this problem, in this dissertation, we introduce advanced methodologies for designing adaptive monitoring strategies. We first develop an online collaborative learning framework that efficiently models and monitors a population of dependent units under resource constraints. We then develop a decentralized online collaborative framework that enables online modeling and monitoring of units with latent dynamics while preserving data privacy. Finally, we develop a novel online robust collaborative algorithm designed to capture latent structures inherent in the population from sequentially observed data corrupted by adversarial attacks. We have demonstrated the effectiveness of the proposed methods through rigorously proven theoretical analysis and experiments, including simulation studies and real-world world applications including cognitive degradation monitoring in Alzheimer's Disease (AD) and battery degradation monitoring.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20250131/71804068/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 28058 bytes
Desc: image001.png
Url : http://Bug.EGR.UH.EDU/pipermail/engi-dist/attachments/20250131/71804068/attachment-0001.png