Real-time Gait Analysis
Smartphones have a wealth of sensors in them. As part of my master's work, I helped develop algorithms that use smartphone accelerometers to measure information about gait (how a person walks).
We've developed the RRACE algorithm that can sense a user's cadence (step frequency) without any training on the person. We also used machine learning to classify different gaits to provide input to an exercise game or other active application. We have working implementations of both systems that run on Android. (cadence paper) (classification paper)
Collaborators: Idin Karuei, Karon MacLean