University Events

Description: TOPIC: WHEREISOUTLIER: A CRITICAL EVENT DETECTION PLATFORM FOR REAL-TIME WEARABLE BIOSENSOR

LOCATION: Lester W. Cory Conference Room, Science & Engineering Building (Group II), Room 213A

ABSTRACT:
Recently, biosensors have been widely used for remote monitoring of human body vital sign, such as heart beat, blood pressure etc. Real-time mining these biosensor data is very important, especially for real-time critical events detection. These critical events usually describe some kinds of body anomaly, such as cardiac abnormal. Finding these abnormal body symptoms in advance would be helpful for preventive healthcare. The existing critical event detection methods usually aim at static data stored in memory or disk. Yet, it is impractical to deal with the evolving biosensor data. Moreover, the biosensor data is usually uncertain, including various noises. How to find critical events from the noisy data is challenging.

This project built up a real-time critical event detection platform based on Spark for wearable biosensor data. Spark is a known big data analytical platform, yet no critical event detection module found on it. We implemented two typical critical event detection methods on our platform, and adopted some real public datasets to test the performance of our platform in terms of the metrics of CPU usage and memory usage. As the experimental results demonstrated, the proposed methods can efficiently detect critical events in real-time.

NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.

Advisor: Dr. Honggang Wang
Committee Members: Dr. Liudong Xing, Department of Electrical & Computer Engineering
and Dr. Donghui Yan, Department of Mathematics

*For further information, please contact Dr. Honggang Wang at 508.999.8469, or via email at hwang1@umassd.edu.