IoT-based freezing of gait detection using grey relational analysis

With the massive progress of Internet of Things based technologies, the importance of remote monitoring has increased by many folds especially for the assistance of patients suffering from life threatening diseases. This work deals with the detection of Freezing of Gait in patients having Parkinson's disease with the help of wearable acceleration sensors placed on their legs and hips which consequently results in their real-time remote monitoring. This work proposes a FoG detection method based on Grey Relational Analysis which uses the readings from the sensors to predict the presence or absence of freezing in a patient. Additionally, an ensemble learning approach that uses Grey Relational Analysis as the base classification model has also been illustrated for FoG detection. The proposed approaches have been applied on benchmark Daphnet Freezing of Gait data set to verify their feasibility. The simulation results show that the proposed approaches have better accuracy when compared to other existing machine learning techniques. (C) 2019 Elsevier B.V. All rights reserved.

Automated summary

This study focuses on real-time monitoring of Freezing of Gait in Parkinson's disease patients using wearable acceleration sensors, and proposes a FoG detection method based on Grey Relational Analysis. An ensemble learning approach is also illustrated. The simulation results demonstrate that the proposed methods have superior accuracy compared to other machine learning techniques.