Etd

Smartphone TBI Sensing using Deep Embedded Clustering and Extreme Boosted Outlier Detection

Public

Downloadable Content

open in viewer

Traumatic Brain Injury (TBI) can have long-lasting effects and possibly cause life-long disability of patients, creating a huge economic and social burden. Many TBI patients do not get early and adequate medical care. Sensor-rich, ubiquitously owned smartphones can now be used to passively sense a wide range of ailments, facilitating continuous monitoring of patients and high-risk groups in the real world. In this thesis, we propose a Deep learning approach for distinguishing smartphone users with TBI from health controls within 24-hours of the injury. Our method analyzes smartphone sensor data by first utilizing Deep embedded clustering to identify user clusters with similar smart-phone sensed behaviors. Extreme Gradient based outlier detection is then employed on each of the identified clusters to predict users with TBI. In rigorous evaluation, our method achieves a balanced accuracy of 88% and a sensitivity of 74%. Our proposed method can flag smartphone users with TBI, enabling them to receive early medical attention and improve their prognostic outlook.

Creator
Contributors
Degree
Unit
Publisher
Identifier
  • etd-23186
Advisor
Orcid
Defense date
Year
  • 2021
Date created
  • 2021-05-06
Resource type
Rights statement

Relations

In Collection:

Items

Items

Permanent link to this page: https://digital.wpi.edu/show/qr46r365q