学术交流

人工智能研究院学术报告 第2020-06-10-(1)期

发布时间:2020-06-10动态浏览次数:15

Title

Enhancing Human Health and Safety via Smart Sensing Techniques

Lecture & Organization

LANDU JIANG

Mitacs Accelerate industrial postdoc at Aerial Technologies and McGill University

Date & Time

Sat 10/6/2020 9:30-10:30am

Beijing time

Mode

Zoom ID:  574 459 9066

Password: 001234

Bio

LANDU JIANG is currently a Mitacs Accelerate industrial postdoc at Aerial Technologies and McGill University. He received his Ph.D. in the School of Computer Science at McGill University and MSc in Computer Science from University of Nebraska-Lincoln. Previously, He received his BEng in Information Security Engineering from Shanghai Jiao Tong University. His research interests include ubiquitous computing, machine learning and computer vision applications, smart home and healthcare systems and green energy solutions.

Abstract

With the development of communication technologies and rapid growth of the Internet of Things (IoT), understanding human behaviors to support their daily living has become an important and emerging subject in both research and industry communities. In this talk, I will introduce our recent work on enhancing driving safety and human healthcare by leveraging smart sensing techniques. Specifically, several studies are presented: 1. analyzing intersection-related driver behaviors using smartphone sensors; 2. monitoring distracted driving behaviors using wrist-worn devices; 3.  energy-efficient route planning for solar-powered EVs; and 4. occupancy and activity monitoring using commodity Wi-Fi. 

The first study focuses on intersection safety which is a critical issue in current roadway systems. In the United States, nearly one-quarter of traffic fatalities and half of all traffic injuries are attributed to intersections. We design a safety application that uses embedded sensors (i.e., inertial sensors and cameras) on the smartphone to track vehicle dynamics while at the same time adopts computer vision algorithms to recognize traffic control information (e.g., traffic lights and stop signs). The system is able to detect dangerous driving events not only on roads but also at intersections including speeding, lane waving, unsafe turns, running stop signs and running red lights. Our second study discusses the driving distraction problem which has been considered as a major threat to traffic safety. It is estimated that roughly 30% of vehicle fatalities involve distracted drivers, which cause thousands of injuries and deaths every year in the United States. We propose SafeDrive, a driving safety system that leverages the wrist-worn (i.e., smartwatch) sensors to prevent driver distractions. By tracking driver's hand motion and utilizing machine learning algorithms, SafeDrive can detect five most common distracting activities including fiddling with the control (e.g., infotainment systems), drinking/eating, using smartphones, searching items at the passenger side and reaching back seats. The third study aims to provide alternative solutions for EV range anxiety problems. A route planning method for solar-powered EVs is provided to balance the energy harvesting and consumption subject to time constraint. The idea behind our solution is to offer power-aware optimal routing, which maximizes the on-road energy input given solar availability on each road segment. We first build a solar access estimation model using 3D geographic data and then employ a multi-criteria search method to generate a set of candidate routes for drivers with better solar availability. Finally, we address human activity monitoring problems in the fourth study. This project aims to provide a non-intrusive device-free approach for occupancy and activity monitoring by using the already deployed commodity Wi-Fi infrastructures. We exploit the correlation between CSI dynamics and human motion by using deep learning techniques to not only count/estimate the number of people but also track human daily living motion. We are able to provide a non-intrusive solution for analyzing the living status of the people (especially for elderly people)  such as whether their living habits are good and healthy, do caregivers come and serve properly, are there many friends or relatives visiting frequently, etc.