Tuesday, Feb 26, 2019
2 PM - 3 PM
The proliferation of the mobile devices (e.g., smartphones, smartwatches and fitness trackers) have brought great convenience to our daily lives. Mobile users can enjoy online access anytime and anywhere through WiFi or cellular services, monitor daily activities (e.g., walking steps) via wearable devices, or flexibly access the devices via touch screens and microphones. The mobile technologies can further benefit the public sector, such as providing real-time data for public transportation, emergency and public safety protection. In this talk, I will show our efforts in developing intelligent mobile sensing systems aiming to improve public safety and facilitate well- being monitoring by using fine-grained signal features extracted from prevalent mobile technologies.
The first part of my talk focuses on detecting in-baggage suspicious object detection using commodity WiFi. This work targets to provide a low-cost and easy-to-scale solution to address the ever-increasing public safety concerns caused by dangerous objects (e.g., lethal weapons, chemical explosives and home-made bombs) in public places such as museums, stadiums, theme parks and schools. Our proposed detection system utilizes the fine-grained channel state information (CSI) from existing WiFi networks to detect the existence of suspicious objects hidden inside of baggage and further identify the dangerous material type without penetrating the user’s privacy through physically opening the baggage. Comparing to the existing X-ray based object scanning infrastructure, this detection system based on commodity WiFi could become a game-changer and significantly reduce the deployment cost and is easy to set up in public venues (e.g., museums, stadiums, theme parks and schools).
Turning to look at individual wellbeing, sleep monitoring has drawn great attention these years, because inadequate and irregular sleep are associated with serious health problems such as sleep apnea, depression and cardiovascular diseases. The traditional sleep monitoring systems such as Polysomnography are intrusive, expensive and mostly limited to clinical usage. My second part of the talk will demonstrate how to use the smartphone earphone (i.e., a standard accessory in smartphone sales package) to capture sleep events (e.g., snoring and coughing) and vital signs such as breathing sound. Our intelligent learning system based on extracted acoustic features could provide noninvasive and continuous fine-grained sleep monitoring, having the potential to be largely used in home environments.
Chen Wang is currently a Ph.D. candidate in Computer Engineering at Rutgers University and works in Wireless Information Network Laboratory (WINLAB) under the supervision of Prof. Yingying Chen. Chen Wang received his bachelor’s and master’s degrees from the University of Electronic Science and Technology of China (UESTC) in 2009 and 2012. His research interests include cyber security and privacy, smart healthcare, mobile sensing and computing, Internet of Things and machine learning. He is the recipient of three Best Paper Awards from the top security conferences, IEEE Conference on Communications and Network Security (IEEE CNS) 2018, IEEE CNS 2014 and ACM Conference on Information, Computer and Communications Security (ASIACCS) 2016. His recent research won the Best Poster Runner-up from ACM MobiCom 2018. From 2014 to 2018, his research studies have been widely reported by over 150 media outlets, including Rutgers News, Stevens News, IEEE Spectrum, NSF Science 360, CBS TV, BBC News, NBC, IEEE Engineering 360, Fortune, ABC News, MIT Technology Review, USA Today, Daily Mail, Science Daily, CTV News, etc.
Prof. Alex Liu