The Detection of Gait Events Based on Smartphones and Deep Learning
This study aims to detect gait events using a smartphone combined with deep learning and evaluate the remote effects and clinical significance of this method in different elderly populations and patients with cerebral small vessel disease (CSVD). In total, 150 healthy individuals aged 20–70 years we...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/5/491 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850257950681071616 |
|---|---|
| author | Kaiyue Xu Wenqiang Yu Shui Yu Minghui Zheng Hao Zhang |
| author_facet | Kaiyue Xu Wenqiang Yu Shui Yu Minghui Zheng Hao Zhang |
| author_sort | Kaiyue Xu |
| collection | DOAJ |
| description | This study aims to detect gait events using a smartphone combined with deep learning and evaluate the remote effects and clinical significance of this method in different elderly populations and patients with cerebral small vessel disease (CSVD). In total, 150 healthy individuals aged 20–70 years were asked to attach a smartphone to their thighs and walk six gait cycles at self-selected low, normal, and high speeds, using an insole pressure sensor as the reference standard for gait events. A deep learning model was then established using BiTCN-BiGRU-CrossAttention, and two models (TCN-GRU and BiTCN-BiGRU) were compared. In total, 48 elderly (25 healthy, 12 with mild cognitive impairment, 11 with Parkinson’s disease) participated in an online home assessment, completing single-task and cognitive dual-task walking. Overall, 35 CSVD patients participated in an offline clinical assessment, completing single-task, cognitive dual-task, and physical dual-task walking. The BiTCN-BiGRU-CrossAttention model had the lowest MAE for detecting gait events compared to the other models. All models had lower MAEs for detecting heel strikes than toe-offs, and the MAE for low and high walking was higher than for normal speed walking. There were significant differences (<i>p</i> < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Swing time, Stride length, and walking speed) between single-task and cognitive dual-task walking for all online elderly participants. CSVD patients showed significant differences (<i>p</i> < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Stride length, and walking speed) between single-task and cognitive dual-task and between single-task and physical dual-task walking. |
| format | Article |
| id | doaj-art-175b8f5ea5b6497dbd6bf8b17ad5fb08 |
| institution | OA Journals |
| issn | 2306-5354 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-175b8f5ea5b6497dbd6bf8b17ad5fb082025-08-20T01:56:17ZengMDPI AGBioengineering2306-53542025-05-0112549110.3390/bioengineering12050491The Detection of Gait Events Based on Smartphones and Deep LearningKaiyue Xu0Wenqiang Yu1Shui Yu2Minghui Zheng3Hao Zhang4College of Mechanical Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaCollege of Mechanical Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaCollege of Mechanical Engineering, Shandong Huayu University of Technology, Dezhou 253034, ChinaCollege of Information Engineering, Dalian University, Dalian 116622, ChinaThis study aims to detect gait events using a smartphone combined with deep learning and evaluate the remote effects and clinical significance of this method in different elderly populations and patients with cerebral small vessel disease (CSVD). In total, 150 healthy individuals aged 20–70 years were asked to attach a smartphone to their thighs and walk six gait cycles at self-selected low, normal, and high speeds, using an insole pressure sensor as the reference standard for gait events. A deep learning model was then established using BiTCN-BiGRU-CrossAttention, and two models (TCN-GRU and BiTCN-BiGRU) were compared. In total, 48 elderly (25 healthy, 12 with mild cognitive impairment, 11 with Parkinson’s disease) participated in an online home assessment, completing single-task and cognitive dual-task walking. Overall, 35 CSVD patients participated in an offline clinical assessment, completing single-task, cognitive dual-task, and physical dual-task walking. The BiTCN-BiGRU-CrossAttention model had the lowest MAE for detecting gait events compared to the other models. All models had lower MAEs for detecting heel strikes than toe-offs, and the MAE for low and high walking was higher than for normal speed walking. There were significant differences (<i>p</i> < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Swing time, Stride length, and walking speed) between single-task and cognitive dual-task walking for all online elderly participants. CSVD patients showed significant differences (<i>p</i> < 0.05) in gait parameters (Cadence, Stride time, Stance phase, Swing phase, Stance time, Stride length, and walking speed) between single-task and cognitive dual-task and between single-task and physical dual-task walking.https://www.mdpi.com/2306-5354/12/5/491gait analysisgait eventsmartphonedeep learningmobile health |
| spellingShingle | Kaiyue Xu Wenqiang Yu Shui Yu Minghui Zheng Hao Zhang The Detection of Gait Events Based on Smartphones and Deep Learning Bioengineering gait analysis gait event smartphone deep learning mobile health |
| title | The Detection of Gait Events Based on Smartphones and Deep Learning |
| title_full | The Detection of Gait Events Based on Smartphones and Deep Learning |
| title_fullStr | The Detection of Gait Events Based on Smartphones and Deep Learning |
| title_full_unstemmed | The Detection of Gait Events Based on Smartphones and Deep Learning |
| title_short | The Detection of Gait Events Based on Smartphones and Deep Learning |
| title_sort | detection of gait events based on smartphones and deep learning |
| topic | gait analysis gait event smartphone deep learning mobile health |
| url | https://www.mdpi.com/2306-5354/12/5/491 |
| work_keys_str_mv | AT kaiyuexu thedetectionofgaiteventsbasedonsmartphonesanddeeplearning AT wenqiangyu thedetectionofgaiteventsbasedonsmartphonesanddeeplearning AT shuiyu thedetectionofgaiteventsbasedonsmartphonesanddeeplearning AT minghuizheng thedetectionofgaiteventsbasedonsmartphonesanddeeplearning AT haozhang thedetectionofgaiteventsbasedonsmartphonesanddeeplearning AT kaiyuexu detectionofgaiteventsbasedonsmartphonesanddeeplearning AT wenqiangyu detectionofgaiteventsbasedonsmartphonesanddeeplearning AT shuiyu detectionofgaiteventsbasedonsmartphonesanddeeplearning AT minghuizheng detectionofgaiteventsbasedonsmartphonesanddeeplearning AT haozhang detectionofgaiteventsbasedonsmartphonesanddeeplearning |