Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Soumma, Shovito Barua, Mangipudi, Kartik, Peterson, Daniel, Mehta, Shyamal, Ghasemzadeh, Hassan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909367860723712
author Soumma, Shovito Barua
Mangipudi, Kartik
Peterson, Daniel
Mehta, Shyamal
Ghasemzadeh, Hassan
author_facet Soumma, Shovito Barua
Mangipudi, Kartik
Peterson, Daniel
Mehta, Shyamal
Ghasemzadeh, Hassan
contents LIFT-PD is an innovative self-supervised learning framework developed for real-time detection of Freezing of Gait (FoG) in Parkinson's Disease (PD) patients, using a single triaxial accelerometer. It minimizes the reliance on large labeled datasets by applying a Differential Hopping Windowing Technique (DHWT) to address imbalanced data during training. Additionally, an Opportunistic Inference Module is used to reduce energy consumption by activating the model only during active movement periods. Extensive testing on publicly available datasets showed that LIFT-PD improved precision by 7.25% and accuracy by 4.4% compared to supervised models, while using 40% fewer labeled samples and reducing inference time by 67%. These findings make LIFT-PD a highly practical and energy-efficient solution for continuous, in-home monitoring of PD patients.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20715
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning
Soumma, Shovito Barua
Mangipudi, Kartik
Peterson, Daniel
Mehta, Shyamal
Ghasemzadeh, Hassan
Signal Processing
Machine Learning
LIFT-PD is an innovative self-supervised learning framework developed for real-time detection of Freezing of Gait (FoG) in Parkinson's Disease (PD) patients, using a single triaxial accelerometer. It minimizes the reliance on large labeled datasets by applying a Differential Hopping Windowing Technique (DHWT) to address imbalanced data during training. Additionally, an Opportunistic Inference Module is used to reduce energy consumption by activating the model only during active movement periods. Extensive testing on publicly available datasets showed that LIFT-PD improved precision by 7.25% and accuracy by 4.4% compared to supervised models, while using 40% fewer labeled samples and reducing inference time by 67%. These findings make LIFT-PD a highly practical and energy-efficient solution for continuous, in-home monitoring of PD patients.
title Wearable-Based Real-time Freezing of Gait Detection in Parkinson's Disease Using Self-Supervised Learning
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2410.20715