Neurodegenerative diseases such as Parkinson's Disease (PD), Huntington Disease (HD), and Amyotrophic Lateral Sclerosis (ALS) affect the lives of thousands of people around the world. One of the consequences of such diseases occurs in the motor neurons of the patients, resulting in problems in movement, causing a change in gait pattern. Force sensitive resistors can be used to measure the force/pressure between the shoe and the patient's foot, providing information about the gait dynamics when the patient walks. This project uses signals from the Gait Dynamics in Neuro-Degenerative Disease database to extract features for classification of neurodegenerative diseases (NDD). Manually labelled features from the database are used for comparison with previous studies. Time series signals is also used, where algorithms for signal reliability, feature extraction and feature selection are implemented, allowing real-time signal processing and classification. Multiple feature sets are used for classification with algorithms such as K-nearest neighbor, Support Vector Machines, and Decision Trees, and the performance of these algorithms are then reported. This study presents a realtime system with accuracy exceeding 82% for the aforementioned diseases. Finally, a discussion about possible improvements for future studies are presented.

, , , ,
2018 IEEE Life Sciences Conference, LSC 2018
Department of Systems and Computer Engineering

Selzler, R. (Roger), Green, J, & Goubran, R. (2018). Neurodegenerative disease prediction based on gait analysis signals acquired with force-sensitive resistors. In 2018 IEEE Life Sciences Conference, LSC 2018 (pp. 122–125). doi:10.1109/LSC.2018.8572063