Nonlinear, Multivariate Computational Methods to Measure Complexity of Movement and Back Pain Recovery

With over 100,000 mobile health applications currently available and the volume of data collected using them, developing novel automated approaches to learn from biophysical large-scale data is critical. Wearables have become affordable; mobile devices are display-rich and the flow of information from sensors to mobile devices is sufficiently accessible for enthusiasts. A key question here is how ubiquitous wearable sensing can be used to improve user health monitoring. In this data-intensive context, merely storing data about daily activities and vital recordings (e.g., heart rate) are no longer sufficient. New tools are needed that not only track data, but that also allow the users to understand their biophysical data. The ubiquity of mobile and sensor based wearable applications has brought the design and improvement of algorithms that learn from the large-scale, distributed data collected by them into the research spot light. This investigation focuses on measuring complexity of movement in human motion using large-scale data collected by Backtrack’s sensing device, and it studies the design of learning algorithms that can be used to self-track recovery for back pain patients.

Faculty Supervisor:

Doina Precup

Student:

Ladan Mahabadi

Partner:

TandemLaunch Technologies Inc.

Discipline:

Computer science

Sector:

Information and communications technologies

University:

McGill University