An Activity Recognition Framework for Continuous Monitoring of Non-Steady-State Locomotion of Individuals with Parkinson's Disease

TL;DR

This study develops an activity recognition framework for non-steady-state locomotion in Parkinson's disease, utilizing LSTM neural networks with fewer sensors, improving classification accuracy over traditional methods.

Contribution

Introduces a novel approach combining LSTM neural networks with limited sensor data for recognizing complex locomotion tasks in Parkinson's patients.

Findings

LSTM outperforms LDA in task recognition accuracy.

Feet data alone can achieve F1 scores above 0.8 in subject-independent training.

Limited sensor setups can effectively classify non-steady-state activities.

Abstract

Fundamental knowledge in activity recognition of individuals with motor disorders such as Parkinson's disease (PD) has been primarily limited to detection of steady-state/static tasks (sitting, standing, walking). To date, identification of non-steady-state locomotion on uneven terrains (stairs, ramps) has not received much attention. Furthermore, previous research has mainly relied on data from a large number of body locations which could adversely affect user convenience and system performance. Here, individuals with mild stages of PD and healthy subjects performed non-steady-state circuit trials comprising stairs, ramp, and changes of direction. An offline analysis using a linear discriminant analysis (LDA) classifier and a Long-Short Term Memory (LSTM) neural network was performed for task recognition. The performance of accelerographic and gyroscopic information from varied lower/upper-body segments were tested across a set of user-independent and user-dependent training paradigms. Comparing the F1 score of a given signal across classifiers showed improved performance using LSTM compared to LDA. Using LSTM, even a subset of information (e.g., feet data) in subject-independent training appeared to provide F1 score > 0.8. However, employing LDA was shown to be at the expense of being limited to using a subject-dependent training and/or biomechanical data from multiple body locations. The findings could inform a number of applications in the field of healthcare monitoring and developing advanced lower-limb assistive devices by providing insights into classification schemes capable of handling non-steady-state and unstructured locomotion in individuals with mild Parkinson's disease.