FB LinkEdIn Instagram

Relevant Projects

Photo of Arielle Fischer
Assistant Professor
Predicting kinetic force data from wearable motion sensors

This research aims to develop an algorithm to predict ground reaction forces and knee moments by using only subject body parameters and kinematic data from Inertial measurement units. This research aims to improve the prediction compared to existing algorithms by focusing on the pre-processing stage (feature extraction). This algorithm will provide additional information on healthy subjects, post knee replacement, and subjects with advanced knee OA motion patterns, which can help achieve a better understanding of subject’s gait analysis and thus allow to improve their gait pattern if necessary.

Parkinson's disease classification from wearable sensors

Application of a machine learning framework to classify gait and Parkinson’s disease from a single IMU worn for 24 hours for 7 days out side of the lab. Develop a robust and reliable methodology for validation of algorithm in daily living to quantify motor symptoms in patients with PD.

professional athlete motion and video analysis

Literature gap in windsurfing biomechanics analysis at top speed. Markerless motion tracking in real life (at sea) environment was collected from professional windsurfers.
Single GoPro Footage with built in IMU’s. AIM: Investigate videos in order to extract insights regarding the athlete/board movement.