Towards Acoustic Sensing in Human-centered Enhanced Interaction

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Towards Acoustic Sensing in Human-centered Enhanced Interaction"

By

Mr. Linfei GE


Abstract:

In recent years, the spread of smart devices has led to big growth and fast 
improvements in technology. As a result, the interaction between humans and 
computers has become very important. Researchers have looked into many ways to 
create connections between smart devices and humans, aiming to make 
interactions that are focused on the human user and improve comfort and 
convenience. However, using these methods and systems in real-world settings is 
still very challenging. This thesis looks at acoustic sensing and aims to 
create practical systems that can be easily used in daily life. Firstly, we 
create a strength-based acoustic tracking system that works well in small 
spaces. Unlike traditional systems that need localization beacons to be placed 
far apart for better accuracy, our system lets us place beacons close together, 
giving us high tracking accuracy. Secondly, we suggest a way to guess human 
attention by watching head movement. By keeping an eye on the movement of the 
earphones, we can accurately follow the motion of the user's head, letting us 
guess their attention. Then, we deal with the limits set by the Bluetooth Low 
Energy protocol by using the nonlinearity properties of wireless earphones. 
This helps us get past the limits of low sampling rates and BLE compression, 
letting us effectively track earphones within the framework of commercial 
wireless earphones. Lastly, we extend the ability of acoustic touch sensing to 
underwater settings, where normal touch screens don't work at all. This makes 
it possible for smartphones to take better underwater photos. Through these 
contributions, we aim to push the field of acoustic sensing forward and develop 
practical systems that can be used in various real-world settings to improve 
the interaction between humans and computers.


Date:                   Tuesday, 11 June 2024

Time:                   10:00am - 12:00noon

Venue:                  Room 3494
                        Lifts 25/26

Chairman:               Dr. Kristiaan HELSEN (MARK)

Committee Members:      Prof. Qian ZHANG (Supervisor)
                        Dr. Jin ZHANG (Co-supervisor, SUSTech)
                        Prof. Song GUO
                        Dr. Xiaojuan MA
                        Dr. Hongyu YU (MAE)
                        Prof. Dan WANG (PolyU)