2014年电气论坛第12次活动 - 美国罗格斯，新泽西州立大学张燕咏副教授讲座
报告摘要:Learning human contexts is critical to the development of many applications, ranging from healthcare, business, to social sciences. Most existing work, however, acquires contextual information in an obtrusive manner -- they may require the subjects to carry mobile devices to be monitored, or rely on self or peer report to report the data.
In this talk, we will present two unobtrusive techniques that can help us learn important human contextual information including the count, location, trajectory, and speech. We first present SCPL, a RF based device free localization technique. SCPL is able to count how many people are in an indoor setting and track their locations by observing how they disturb the wireless radio links in the environment. Second, we present Crowd++, a smartphone based speech sensing technique. Crowd++ records a conversation and automatically counts the number of people in the conversation without prior knowledge of their speech characteristics. Crowd++ can also calculate the percentage of each person's speech, as well as the turn-taking behavior of the speakers. Both techniques are unobtrusive, low-cost, and private, which can thus enable a large array of important applications that rely upon the knowledge of human contextual information.
教授介绍:Yanyong Zhang is currently an Associate Professor in the Electrical and Computer Engineering Department at Rutgers University. She is also a member of the Wireless Information Networks Laboratory (Winlab). Her current research interests are in future Internet and pervasive computing. Her research is mainly funded by the National Science Foundation, including an NSF CAREER award.