WPI – Computer Science
Tuesday, May 4, 2021
Time: 12:00 p.m. – 1:00 p.m.
Zoom Link: https://wpi.zoom.us/j/9328254177
Advisor: Prof. Emmanuel Agu
Reader: Prof. Michael Gennert
In United States, Traumatic Brain Injury (TBI) has become a major cause of death and disability. Violent blow, sudden jerk to the head or the body are few causes of TBI. The effects of TBI depend widely on the severity level. Mild TBI may temporarily affect the brain cells whereas severe TBI may result in more severe impact such as physical damage. Determining ways to detect TBI at an early stage can help reduce emergency visits and even create life-saving experiences.
Smartphones being ubiquitous with powerful in-built sensors, it gets easier to share the information real-time along with quantification and monitoring. This thesis focuses on smartphone sensors to compare three approaches namely, i) computing hand-crafted features on raw sensor data; ii) computing hand-crafted features on pre-processed sensor data; iii) using auto-encoder based approach using location, GAIT and balance to understand how the patterns of TBI differ from that of Non-TBI users.