W&M Homepage
This calendar presented by
William & Mary
[PAST EVENT] RadioSense: Exploiting Wireless Communication Patterns for Body Sensor Network Activity Recognition
October 5, 2012
3pm - 4pm
Automatically recognizing human activities in a body sensor network (BSN) enables many human-centric applications. Many current works recognize human activities through collecting and analyzing sensor readings from on-body sensor nodes. These sensing-based solutions face a dilemma. On the one hand, to guarantee data availability and recognition accuracy, sensing-based solutions have to either utilize a high transmission power or involve a packet retransmission mechanism. On the other hand, enhancing the transmission power increases a sensor node's energy overheads and communication range. The enlarged communication range in consequence increases privacy risks. A packet retransmission mechanism complicates on-body sensor nodes' MAC layer and hence increases energy overheads.
In contrast to the sensing-based solutions, we build RadioSense, a prototype system that exploits wireless communication patterns for BSN activity recognition. Using RadioSense, we benchmark three system parameters (transmission (TX) power, packet sending rate, and smoothing window size) to design algorithms for system parameter selection. The algorithms aim to balance accuracy, latency, and energy overheads. In addition, we investigate the minimal amount of training data needed for reliable performance. We evaluate our RadioSense system with multiple subjects' data collected over a two-week period and demonstrate that RadioSense achieves reliable performance in terms of accuracy, latency and battery lifetime.
Bio:
Xin Qi is a Ph.D. candidate supervised by Professor Gang Zhou. He received his M.Eng. in Pattern Recognition and Intelligent Systems in June 2010 from the National Laboratory of Pattern Recognition at the Institute of Automation, CAS, and his B.Sc. degree in Computer Science in June 2007 from Nanjing University. His research mainly focuses on applying machine learning in ubiquitous environment.
In contrast to the sensing-based solutions, we build RadioSense, a prototype system that exploits wireless communication patterns for BSN activity recognition. Using RadioSense, we benchmark three system parameters (transmission (TX) power, packet sending rate, and smoothing window size) to design algorithms for system parameter selection. The algorithms aim to balance accuracy, latency, and energy overheads. In addition, we investigate the minimal amount of training data needed for reliable performance. We evaluate our RadioSense system with multiple subjects' data collected over a two-week period and demonstrate that RadioSense achieves reliable performance in terms of accuracy, latency and battery lifetime.
Bio:
Xin Qi is a Ph.D. candidate supervised by Professor Gang Zhou. He received his M.Eng. in Pattern Recognition and Intelligent Systems in June 2010 from the National Laboratory of Pattern Recognition at the Institute of Automation, CAS, and his B.Sc. degree in Computer Science in June 2007 from Nanjing University. His research mainly focuses on applying machine learning in ubiquitous environment.
Contact
Department of Computer Science