TY - GEN
T1 - Utilizing neural networks to predict freezing of gait in Parkinson's patients
AU - Zia, Jonathan
AU - Tadayon, Arash
AU - McDaniel, Troy
AU - Panchanathan, Sethuraman
PY - 2016/10/23
Y1 - 2016/10/23
N2 - With the appropriate mathematical models, data from wearable devices can be used to help Parkinson's patients live safer and more independent lives. Inspired by this idea, the purpose of this study was to determine the viability of neural networks in predicting Freezing of Gait (FoG), a symptom of Parkinson's disease in which the patient's legs are suddenly rendered unable to move. A class of neural networks known as layered recurrent networks (LRNs) was applied to an open-source FoG experimental dataset donated to the Machine Learning Repository of the University of California at Irvine. The independent variables in this experiment -The subject being tested, neural network architecture, and down sampling of the majority classes - were each varied and compared against the performance of the neural network in predicting impending FoG events. It was determined that single-layered recurrent networks are a viable method of predicting FoG events given the volume of the training data available, though results varied between patients.
AB - With the appropriate mathematical models, data from wearable devices can be used to help Parkinson's patients live safer and more independent lives. Inspired by this idea, the purpose of this study was to determine the viability of neural networks in predicting Freezing of Gait (FoG), a symptom of Parkinson's disease in which the patient's legs are suddenly rendered unable to move. A class of neural networks known as layered recurrent networks (LRNs) was applied to an open-source FoG experimental dataset donated to the Machine Learning Repository of the University of California at Irvine. The independent variables in this experiment -The subject being tested, neural network architecture, and down sampling of the majority classes - were each varied and compared against the performance of the neural network in predicting impending FoG events. It was determined that single-layered recurrent networks are a viable method of predicting FoG events given the volume of the training data available, though results varied between patients.
KW - Freezing of gait
KW - Machine learning
KW - Parkinson's disease
KW - Wearable devices
UR - http://www.scopus.com/inward/record.url?scp=85006710391&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85006710391&partnerID=8YFLogxK
U2 - 10.1145/2982142.2982194
DO - 10.1145/2982142.2982194
M3 - Conference contribution
AN - SCOPUS:85006710391
T3 - ASSETS 2016 - Proceedings of the 18th International ACM SIGACCESS Conference on Computers and Accessibility
SP - 333
EP - 334
BT - ASSETS 2016 - Proceedings of the 18th International ACM SIGACCESS Conference on Computers and Accessibility
PB - Association for Computing Machinery, Inc
T2 - 18th International ACM SIGACCESS Conference on Computers and Accessibility, ASSETS 2016
Y2 - 24 October 2016 through 26 October 2016
ER -