Pattern analysis using lower body human walking data to identify the gaitprint
All people have a fingerprint that is unique to them and persistent throughout life. Similarly, we propose that people have a gaitprint, a persistent walking pattern that contains unique information about an individual. To provide evidence of a unique gaitprint, we aimed to identify individuals base...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037024000977 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846116093184180224 |
|---|---|
| author | Tyler M. Wiles Seung Kyeom Kim Nick Stergiou Aaron D. Likens |
| author_facet | Tyler M. Wiles Seung Kyeom Kim Nick Stergiou Aaron D. Likens |
| author_sort | Tyler M. Wiles |
| collection | DOAJ |
| description | All people have a fingerprint that is unique to them and persistent throughout life. Similarly, we propose that people have a gaitprint, a persistent walking pattern that contains unique information about an individual. To provide evidence of a unique gaitprint, we aimed to identify individuals based on basic spatiotemporal variables. 81 adults were recruited to walk overground on an indoor track at their own pace for four minutes wearing inertial measurement units. A total of 18 trials per participant were completed between two days, one week apart. Four methods of pattern analysis, a) Euclidean distance, b) cosine similarity, c) random forest, and d) support vector machine, were applied to our basic spatiotemporal variables such as step and stride lengths to accurately identify people. Our best accuracy (98.63%) was achieved by random forest, followed by support vector machine (98.40%), and the top 10 most similar trials from cosine similarity (98.40%). Our results clearly demonstrate a persistent walking pattern with sufficient information about the individual to make them identifiable, suggesting the existence of a gaitprint. |
| format | Article |
| id | doaj-art-3efced4b12c8420f8149e4e2dd0dae82 |
| institution | Kabale University |
| issn | 2001-0370 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj-art-3efced4b12c8420f8149e4e2dd0dae822024-12-19T10:53:21ZengElsevierComputational and Structural Biotechnology Journal2001-03702024-12-0124281291Pattern analysis using lower body human walking data to identify the gaitprintTyler M. Wiles0Seung Kyeom Kim1Nick Stergiou2Aaron D. Likens3Department of Biomechanics at the University of Nebraska at Omaha, 6160 University Dr S, Omaha, NE 68182, USADepartment of Biomechanics at the University of Nebraska at Omaha, 6160 University Dr S, Omaha, NE 68182, USADepartment of Biomechanics at the University of Nebraska at Omaha, 6160 University Dr S, Omaha, NE 68182, USA; Department of Physical Education and Sport Science, Aristotle University, Thermi, AUTH DPESS, Thessaloniki 57001, GreeceDepartment of Biomechanics at the University of Nebraska at Omaha, 6160 University Dr S, Omaha, NE 68182, USA; Corresponding author.All people have a fingerprint that is unique to them and persistent throughout life. Similarly, we propose that people have a gaitprint, a persistent walking pattern that contains unique information about an individual. To provide evidence of a unique gaitprint, we aimed to identify individuals based on basic spatiotemporal variables. 81 adults were recruited to walk overground on an indoor track at their own pace for four minutes wearing inertial measurement units. A total of 18 trials per participant were completed between two days, one week apart. Four methods of pattern analysis, a) Euclidean distance, b) cosine similarity, c) random forest, and d) support vector machine, were applied to our basic spatiotemporal variables such as step and stride lengths to accurately identify people. Our best accuracy (98.63%) was achieved by random forest, followed by support vector machine (98.40%), and the top 10 most similar trials from cosine similarity (98.40%). Our results clearly demonstrate a persistent walking pattern with sufficient information about the individual to make them identifiable, suggesting the existence of a gaitprint.http://www.sciencedirect.com/science/article/pii/S2001037024000977BiometricsGait RecognitionVariabilityRandom ForestsSupport Vector MachinesInertial Measurement Units |
| spellingShingle | Tyler M. Wiles Seung Kyeom Kim Nick Stergiou Aaron D. Likens Pattern analysis using lower body human walking data to identify the gaitprint Computational and Structural Biotechnology Journal Biometrics Gait Recognition Variability Random Forests Support Vector Machines Inertial Measurement Units |
| title | Pattern analysis using lower body human walking data to identify the gaitprint |
| title_full | Pattern analysis using lower body human walking data to identify the gaitprint |
| title_fullStr | Pattern analysis using lower body human walking data to identify the gaitprint |
| title_full_unstemmed | Pattern analysis using lower body human walking data to identify the gaitprint |
| title_short | Pattern analysis using lower body human walking data to identify the gaitprint |
| title_sort | pattern analysis using lower body human walking data to identify the gaitprint |
| topic | Biometrics Gait Recognition Variability Random Forests Support Vector Machines Inertial Measurement Units |
| url | http://www.sciencedirect.com/science/article/pii/S2001037024000977 |
| work_keys_str_mv | AT tylermwiles patternanalysisusinglowerbodyhumanwalkingdatatoidentifythegaitprint AT seungkyeomkim patternanalysisusinglowerbodyhumanwalkingdatatoidentifythegaitprint AT nickstergiou patternanalysisusinglowerbodyhumanwalkingdatatoidentifythegaitprint AT aarondlikens patternanalysisusinglowerbodyhumanwalkingdatatoidentifythegaitprint |