题目：Activity Recognition using Wireless Body Sensor Networks: A Pattern Mining Approach
报告人：顾涛 南丹麦大学
地点：东五楼二楼210学术报告厅
时间：6月18日上午9：00

报告摘要：
　　Recognizing human activity using Wireless Body Sensor Networks has recently attracted much research interest. This task is particularly challenging because real-life activities are often performed in not only a simple (i.e., sequential), but also a complex (i.e., interleaved and concurrent) manner. Little work has been done in addressing complex issues arising in such a situation. The existing models for interleaved and concurrent activities are typically learning-based. Such models lack of flexibility because activities can be usually interleaved and performed concurrently in many different ways. In this paper, we propose a novel pattern mining approach to recognize sequential, interleaved and concurrent activities. We exploit Emerging Pattern as a powerful discriminator to differentiate activities. We conduct our empirical studies by collecting real-world activity traces in a real smart home, evaluate the performance of our algorithm, and compare our algorithm with both the state-of-the-art models.

报告人简介：
　　Dr. Tao Gu is currently an Assistant Professor in the Department of Mathematics and Computer Science at University of Southern Denmark. He received his Bachelor degree from Huazhong University of Science and Technology, and M.Sc. from Nanyang Technological University, Singapore, and Ph.D. in computer science from National University of Singapore. His current research interest includes pervasive computing and wireless sensor networks.