Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities
This study aimed to develop and evaluate a new step-count algorithm, StepMatchDTWBA, for the accurate measurement of physical activity using wearable devices in both healthy and pathological populations. We conducted a study with 30 healthy volunteers wearing a wrist-worn MOX accelerometer (Maastric...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/22/9061 |
| _version_ | 1797457822367088640 |
|---|---|
| author | Valeria Filippou Michael R. Backhouse Anthony C. Redmond David C. Wong |
| author_facet | Valeria Filippou Michael R. Backhouse Anthony C. Redmond David C. Wong |
| author_sort | Valeria Filippou |
| collection | DOAJ |
| description | This study aimed to develop and evaluate a new step-count algorithm, StepMatchDTWBA, for the accurate measurement of physical activity using wearable devices in both healthy and pathological populations. We conducted a study with 30 healthy volunteers wearing a wrist-worn MOX accelerometer (Maastricht Instruments, NL). The StepMatchDTWBA algorithm used dynamic time warping (DTW) barycentre averaging to create personalised templates for representative steps, accounting for individual walking variations. DTW was then used to measure the similarity between the template and accelerometer epoch. The StepMatchDTWBA algorithm had an average root-mean-square error of 2 steps for healthy gaits and 12 steps for simulated pathological gaits over a distance of about 10 m (GAITRite walkway) and one flight of stairs. It outperformed benchmark algorithms for the simulated pathological population, showcasing the potential for improved accuracy in personalised step counting for pathological populations. The StepMatchDTWBA algorithm represents a significant advancement in accurate step counting for both healthy and pathological populations. This development holds promise for creating more precise and personalised activity monitoring systems, benefiting various health and wellness applications. |
| first_indexed | 2024-03-09T16:28:25Z |
| format | Article |
| id | doaj.art-5f61e3911f2c467dbd6622de9eaee8d8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T16:28:25Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5f61e3911f2c467dbd6622de9eaee8d82023-11-24T15:05:11ZengMDPI AGSensors1424-82202023-11-012322906110.3390/s23229061Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking ActivitiesValeria Filippou0Michael R. Backhouse1Anthony C. Redmond2David C. Wong3Institute of Medical and Biological Engineering, University of Leeds, Leeds LS2 9JT, UKWarwick Clinical Trials Unit, University of Warwick, Coventry CV4 7AL, UKLeeds Institute of Rheumatic and Musculoskeletal Medicine, University of Leeds, Leeds LS2 9JT, UKLeeds Institute of Health Informatics, University of Leeds, Leeds LS2 9JT, UKThis study aimed to develop and evaluate a new step-count algorithm, StepMatchDTWBA, for the accurate measurement of physical activity using wearable devices in both healthy and pathological populations. We conducted a study with 30 healthy volunteers wearing a wrist-worn MOX accelerometer (Maastricht Instruments, NL). The StepMatchDTWBA algorithm used dynamic time warping (DTW) barycentre averaging to create personalised templates for representative steps, accounting for individual walking variations. DTW was then used to measure the similarity between the template and accelerometer epoch. The StepMatchDTWBA algorithm had an average root-mean-square error of 2 steps for healthy gaits and 12 steps for simulated pathological gaits over a distance of about 10 m (GAITRite walkway) and one flight of stairs. It outperformed benchmark algorithms for the simulated pathological population, showcasing the potential for improved accuracy in personalised step counting for pathological populations. The StepMatchDTWBA algorithm represents a significant advancement in accurate step counting for both healthy and pathological populations. This development holds promise for creating more precise and personalised activity monitoring systems, benefiting various health and wellness applications.https://www.mdpi.com/1424-8220/23/22/9061accelerometrydynamic time warpingphysical activitystep counting |
| spellingShingle | Valeria Filippou Michael R. Backhouse Anthony C. Redmond David C. Wong Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities Sensors accelerometry dynamic time warping physical activity step counting |
| title | Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities |
| title_full | Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities |
| title_fullStr | Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities |
| title_full_unstemmed | Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities |
| title_short | Person-Specific Template Matching Using a Dynamic Time Warping Step-Count Algorithm for Multiple Walking Activities |
| title_sort | person specific template matching using a dynamic time warping step count algorithm for multiple walking activities |
| topic | accelerometry dynamic time warping physical activity step counting |
| url | https://www.mdpi.com/1424-8220/23/22/9061 |
| work_keys_str_mv | AT valeriafilippou personspecifictemplatematchingusingadynamictimewarpingstepcountalgorithmformultiplewalkingactivities AT michaelrbackhouse personspecifictemplatematchingusingadynamictimewarpingstepcountalgorithmformultiplewalkingactivities AT anthonycredmond personspecifictemplatematchingusingadynamictimewarpingstepcountalgorithmformultiplewalkingactivities AT davidcwong personspecifictemplatematchingusingadynamictimewarpingstepcountalgorithmformultiplewalkingactivities |