A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction
Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used t...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/19/6446 |
_version_ | 1797515759134441472 |
---|---|
author | Tahjid Ashfaque Mostafa Sara Soltaninejad Tara L. McIsaac Irene Cheng |
author_facet | Tahjid Ashfaque Mostafa Sara Soltaninejad Tara L. McIsaac Irene Cheng |
author_sort | Tahjid Ashfaque Mostafa |
collection | DOAJ |
description | Freezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, its detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on a publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University. |
first_indexed | 2024-03-10T06:51:49Z |
format | Article |
id | doaj.art-1f2113fb031e411db2b6c798d913e0bf |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T06:51:49Z |
publishDate | 2021-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-1f2113fb031e411db2b6c798d913e0bf2023-11-22T16:46:12ZengMDPI AGSensors1424-82202021-09-012119644610.3390/s21196446A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and PredictionTahjid Ashfaque Mostafa0Sara Soltaninejad1Tara L. McIsaac2Irene Cheng3Multimedia Research Center, Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, CanadaMultimedia Research Center, Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, CanadaArizona School of Health Sciences, A.T. Still University, 5850 E. Still Circle, Mesa, AZ 85206, USAMultimedia Research Center, Department of Computing Science, University of Alberta, Edmonton, AB T6G 2E8, CanadaFreezing of Gait (FOG) is an impairment that affects the majority of patients in the advanced stages of Parkinson’s Disease (PD). FOG can lead to sudden falls and injuries, negatively impacting the quality of life for the patients and their families. Rhythmic Auditory Stimulation (RAS) can be used to help patients recover from FOG and resume normal gait. RAS might be ineffective due to the latency between the start of a FOG event, its detection and initialization of RAS. We propose a system capable of both FOG prediction and detection using signals from tri-axial accelerometer sensors that will be useful in initializing RAS with minimal latency. We compared the performance of several time frequency analysis techniques, including moving windows extracted from the signals, handcrafted features, Recurrence Plots (RP), Short Time Fourier Transform (STFT), Discreet Wavelet Transform (DWT) and Pseudo Wigner Ville Distribution (PWVD) with Deep Learning (DL) based Long Short Term Memory (LSTM) and Convolutional Neural Networks (CNN). We also propose three Ensemble Network Architectures that combine all the time frequency representations and DL architectures. Experimental results show that our ensemble architectures significantly improve the performance compared with existing techniques. We also present the results of applying our method trained on a publicly available dataset to data collected from patients using wearable sensors in collaboration with A.T. Still University.https://www.mdpi.com/1424-8220/21/19/6446Parkinson’s diseasefreeze of gaitdeep learningensemble learningwearable sensor datadetection and predication |
spellingShingle | Tahjid Ashfaque Mostafa Sara Soltaninejad Tara L. McIsaac Irene Cheng A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction Sensors Parkinson’s disease freeze of gait deep learning ensemble learning wearable sensor data detection and predication |
title | A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction |
title_full | A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction |
title_fullStr | A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction |
title_full_unstemmed | A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction |
title_short | A Comparative Study of Time Frequency Representation Techniques for Freeze of Gait Detection and Prediction |
title_sort | comparative study of time frequency representation techniques for freeze of gait detection and prediction |
topic | Parkinson’s disease freeze of gait deep learning ensemble learning wearable sensor data detection and predication |
url | https://www.mdpi.com/1424-8220/21/19/6446 |
work_keys_str_mv | AT tahjidashfaquemostafa acomparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT sarasoltaninejad acomparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT taralmcisaac acomparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT irenecheng acomparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT tahjidashfaquemostafa comparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT sarasoltaninejad comparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT taralmcisaac comparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction AT irenecheng comparativestudyoftimefrequencyrepresentationtechniquesforfreezeofgaitdetectionandprediction |