Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data
Changes in gait patterns provide important information about individuals’ health. To perform sensor based gait analysis, it is crucial to develop methodologies to automatically segment single strides from continuous movement sequences. In this study we developed an algorithm based on time-invariant...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/15/3/6419 |
| _version_ | 1811279898791116800 |
|---|---|
| author | Jens Barth Cäcilia Oberndorfer Cristian Pasluosta Samuel Schülein Heiko Gassner Samuel Reinfelder Patrick Kugler Dominik Schuldhaus Jürgen Winkler Jochen Klucken Björn M. Eskofier |
| author_facet | Jens Barth Cäcilia Oberndorfer Cristian Pasluosta Samuel Schülein Heiko Gassner Samuel Reinfelder Patrick Kugler Dominik Schuldhaus Jürgen Winkler Jochen Klucken Björn M. Eskofier |
| author_sort | Jens Barth |
| collection | DOAJ |
| description | Changes in gait patterns provide important information about individuals’ health. To perform sensor based gait analysis, it is crucial to develop methodologies to automatically segment single strides from continuous movement sequences. In this study we developed an algorithm based on time-invariant template matching to isolate strides from inertial sensor signals. Shoe-mounted gyroscopes and accelerometers were used to record gait data from 40 elderly controls, 15 patients with Parkinson’s disease and 15 geriatric patients. Each stride was manually labeled from a straight 40 m walk test and from a video monitored free walk sequence. A multi-dimensional subsequence Dynamic Time Warping (msDTW) approach was used to search for patterns matching a pre-defined stride template constructed from 25 elderly controls. F-measure of 98% (recall 98%, precision 98%) for 40 m walk tests and of 97% (recall 97%, precision 97%) for free walk tests were obtained for the three groups. Compared to conventional peak detection methods up to 15% F-measure improvement was shown. The msDTW proved to be robust for segmenting strides from both standardized gait tests and free walks. This approach may serve as a platform for individualized stride segmentation during activities of daily living. |
| first_indexed | 2024-04-13T01:04:08Z |
| format | Article |
| id | doaj.art-3a8cec07a41f42a090194dc4afe01368 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T01:04:08Z |
| publishDate | 2015-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3a8cec07a41f42a090194dc4afe013682022-12-22T03:09:23ZengMDPI AGSensors1424-82202015-03-011536419644010.3390/s150306419s150306419Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor DataJens Barth0Cäcilia Oberndorfer1Cristian Pasluosta2Samuel Schülein3Heiko Gassner4Samuel Reinfelder5Patrick Kugler6Dominik Schuldhaus7Jürgen Winkler8Jochen Klucken9Björn M. Eskofier10ASTRUM IT GmbH, Am Wolfsmantel 2, Erlangen D-91058, GermanyASTRUM IT GmbH, Am Wolfsmantel 2, Erlangen D-91058, GermanyDigital Sports Group, Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen D-91058, GermanyGeriatrics Centre Erlangen, Waldkrankenhaus St. Marien, Rathsberger Straße 57, Erlangen D-91054, GermanyDepartment of Molecular Neurology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Schwabachanlage 6, Erlangen D-91054, GermanyDigital Sports Group, Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen D-91058, GermanyDigital Sports Group, Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen D-91058, GermanyDigital Sports Group, Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen D-91058, GermanyDepartment of Molecular Neurology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Schwabachanlage 6, Erlangen D-91054, GermanyDepartment of Molecular Neurology, Universitätsklinikum Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Schwabachanlage 6, Erlangen D-91054, GermanyDigital Sports Group, Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen D-91058, GermanyChanges in gait patterns provide important information about individuals’ health. To perform sensor based gait analysis, it is crucial to develop methodologies to automatically segment single strides from continuous movement sequences. In this study we developed an algorithm based on time-invariant template matching to isolate strides from inertial sensor signals. Shoe-mounted gyroscopes and accelerometers were used to record gait data from 40 elderly controls, 15 patients with Parkinson’s disease and 15 geriatric patients. Each stride was manually labeled from a straight 40 m walk test and from a video monitored free walk sequence. A multi-dimensional subsequence Dynamic Time Warping (msDTW) approach was used to search for patterns matching a pre-defined stride template constructed from 25 elderly controls. F-measure of 98% (recall 98%, precision 98%) for 40 m walk tests and of 97% (recall 97%, precision 97%) for free walk tests were obtained for the three groups. Compared to conventional peak detection methods up to 15% F-measure improvement was shown. The msDTW proved to be robust for segmenting strides from both standardized gait tests and free walks. This approach may serve as a platform for individualized stride segmentation during activities of daily living.http://www.mdpi.com/1424-8220/15/3/6419inertial sensorsstride segmentationaccelerometergyroscopedynamic time warpingfree walkgait analysisParkinson’s diseasegeriatric patientsmovement impairments |
| spellingShingle | Jens Barth Cäcilia Oberndorfer Cristian Pasluosta Samuel Schülein Heiko Gassner Samuel Reinfelder Patrick Kugler Dominik Schuldhaus Jürgen Winkler Jochen Klucken Björn M. Eskofier Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data Sensors inertial sensors stride segmentation accelerometer gyroscope dynamic time warping free walk gait analysis Parkinson’s disease geriatric patients movement impairments |
| title | Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data |
| title_full | Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data |
| title_fullStr | Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data |
| title_full_unstemmed | Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data |
| title_short | Stride Segmentation during Free Walk Movements Using Multi-Dimensional Subsequence Dynamic Time Warping on Inertial Sensor Data |
| title_sort | stride segmentation during free walk movements using multi dimensional subsequence dynamic time warping on inertial sensor data |
| topic | inertial sensors stride segmentation accelerometer gyroscope dynamic time warping free walk gait analysis Parkinson’s disease geriatric patients movement impairments |
| url | http://www.mdpi.com/1424-8220/15/3/6419 |
| work_keys_str_mv | AT jensbarth stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT caciliaoberndorfer stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT cristianpasluosta stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT samuelschulein stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT heikogassner stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT samuelreinfelder stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT patrickkugler stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT dominikschuldhaus stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT jurgenwinkler stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT jochenklucken stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata AT bjornmeskofier stridesegmentationduringfreewalkmovementsusingmultidimensionalsubsequencedynamictimewarpingoninertialsensordata |