RFID BASED DRIVING FATIGUE DETECTION πŸ—“

Sponsor: San Diego Section Chapter, COM19
San Diego Section
San Diego Section Chapter, VT06
San Diego Section Chapter, CIS11
Atlanta Section Chapter, COM19
Speaker: Prof. SHIWEN MAO
register
Meeting Date: July 1, 2021
Time: 6PM
Cost:
Reservations: IEEE

Summary:
With the increasing number of vehicles and traffic accidents, driving safety has become an important factor that affects our daily lives. As the primary cause of driving accidents, driving fatigue could be prevented by a sensing and alarm system built in the vehicle. In this talk, we propose to exploit radio frequency identification (RFID) tags as low-cost wearable sensors for driving fatigue detection. Unlike traditional video camera based solutions, this approach does not require lighting in the driving environment and can effectively protect the privacy of users. We first present the NodTrack system, which sense the driver’s nodding movements using commodity RFID. To accurately extract nodding features, we propose an effective approach to mitigate the environment noise, the interference caused by surrounding movements, and the cumulative error caused by the frequency hopping offset in FCC-compliant RFID systems. A long short-term memory (LSTM) autoencoder is utilized to detect nodding movements using calibrated data. The second part of the talk presents an RFID based respiration monitoring system for driving environments. Since breathing rate is a key indicator of drowsy state, respiration monitoring in the noisy driving environment is useful for developing an effective driving fatigue detection system. The system estimates the respiration rate of a driver based on phase values sampled from multiple RFID tags attached to the seat belt, exploiting tag diversity to combat the strong noise in the driving environment. The proposed systems are implemented with commodity RFID devices. Their accurate and robust performances are demonstrated with extensive experiments conducted in a moving car. The highly accurate detection performances of the proposed systems are validated by extensive experiments in various real driving scenarios.

Bio: Prof. SHIWEN MAO , Earle C. Williams Eminent Scholar Chair, and Director of the Wireless Engineering Research and Education Center at Auburn University, a Fellow of the IEEE, Distinguished Lecturer of IEEE Communications Society and Distinguished Speaker of IEEE Vehicular Technology Society.

Scheduled Webinar