back Back to all Seminars

CS Seminar| Modeling Interaction-Behavior with Wrist-Worn Devices

Start Date: February 14, 2018
End Date: February 14, 2018

By Professor Chao Shen, School of Electronic and Information Engineering of Xi’an Jiaotong University, China
The growing trend of using wearable devices for con-text-aware computing and pervasive sensing systems has raised its potentials for quick and reliable authentication techniques, especially in the mobile computing field. In this talk, we present a non-intrusive user verification system through wrist-worn devices by analyzing the interaction behavior with users, which is both accurate and efficient for future usage. For each hand motion, sensory data from wrist-worn device are analyzed to obtain kinematic sequences. These sequences are then characterized by statistic-, frequency-, and wave-let-domain features for providing accurate and fine-grained characterization of users’ hand motions. Then a multiple decision procedure is developed to perform the verification, in which one-class learning algorithms are employed for fast and reliable classification. Analyses are conducted on three sets of wristband-interaction data collected from 237 participants with diversity in gender, age, and height. Extensive experimental results show that the proposed system can identify users in a timely and accurate manner, with lightweight system overhead.
Biography: Dr. Chao Shen received his B.S. degree in automatic control from Xi’an Jiaotong University, Xi’an, China, in 2007, and his Ph.D. degree in system engineering from Xi’an Jiaotong University, Xi’an, China, in 2014. He worked as a research scholar in Computer Science Department of Carnegie Mellon University from 2011 to 2013. He is currently is a Professor in School of Electronic and Information Engineering of Xi’an Jiaotong University. His research interests are at the intersection of computer and mobile security, insider/intrusion detection, big data analysis, and machine learning. Specifically, he is currently working on human-computer interaction behavior analysis/forensics, and mobile security analysis/applications.

More Information:

For more info contact: Prof. Xiangliang Zhang: email:
Date: Wednesday 14th Feb 2018
Time:12:00 PM - 01:30 PM
Location: Building1-Level 3-Room 3422
Refreshments: Light lunch will be available at 11:45 AM