Amputee Gait Phase Recognition Using Multiple GMM-HMM
Gait analysis helps clinical assessment and achieves comfortable prosthetic designs for lower limb amputees, in which accurate gait phase recognition is a key component. However, gait phase detection remains a challenge due to the individual nature of prosthetic sockets and limbs. For the first time...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10795137/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536167694041088 |
|---|---|
| author | Wenyao Zhu Zhenbang Liu Yizhi Chen Dejiu Chen Zhonghai Lu |
| author_facet | Wenyao Zhu Zhenbang Liu Yizhi Chen Dejiu Chen Zhonghai Lu |
| author_sort | Wenyao Zhu |
| collection | DOAJ |
| description | Gait analysis helps clinical assessment and achieves comfortable prosthetic designs for lower limb amputees, in which accurate gait phase recognition is a key component. However, gait phase detection remains a challenge due to the individual nature of prosthetic sockets and limbs. For the first time, we present a gait phase recognition approach for transfemoral amputees based on intra-socket pressure measurement. We proposed a multiple GMM-HMM (Hidden Markov Model with Gaussian Mixture Model emissions) method to label the gait events during walking. For each of the gait phases in the gait cycle, a separate GMM-HMM model is trained from the collected pressure data. We use gait phase recognition accuracy as a primary metric. The evaluation of six human subjects during walking shows a high accuracy of over 99% for single-subject, around 97.4% for multiple-subject, and up to 84.5% for unseen-subject scenarios. We compare our approach with the widely used CHMM (Continuous HMM) and LSTM (Long Short-term Memory) based methods, demonstrating better recognition accuracy performance across all scenarios. |
| format | Article |
| id | doaj-art-3e9b3b3801ab433e80a939056e20b733 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-3e9b3b3801ab433e80a939056e20b7332025-01-15T00:02:11ZengIEEEIEEE Access2169-35362024-01-011219379619380610.1109/ACCESS.2024.351652010795137Amputee Gait Phase Recognition Using Multiple GMM-HMMWenyao Zhu0https://orcid.org/0000-0002-4911-0257Zhenbang Liu1Yizhi Chen2https://orcid.org/0000-0001-8488-3506Dejiu Chen3https://orcid.org/0000-0001-7048-0108Zhonghai Lu4https://orcid.org/0000-0003-0061-3475Department of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, SwedenDepartment of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, SwedenDepartment of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, SwedenDepartment of Engineering Design, KTH Royal Institute of Technology, Stockholm, SwedenDepartment of Electrical Engineering, KTH Royal Institute of Technology, Stockholm, SwedenGait analysis helps clinical assessment and achieves comfortable prosthetic designs for lower limb amputees, in which accurate gait phase recognition is a key component. However, gait phase detection remains a challenge due to the individual nature of prosthetic sockets and limbs. For the first time, we present a gait phase recognition approach for transfemoral amputees based on intra-socket pressure measurement. We proposed a multiple GMM-HMM (Hidden Markov Model with Gaussian Mixture Model emissions) method to label the gait events during walking. For each of the gait phases in the gait cycle, a separate GMM-HMM model is trained from the collected pressure data. We use gait phase recognition accuracy as a primary metric. The evaluation of six human subjects during walking shows a high accuracy of over 99% for single-subject, around 97.4% for multiple-subject, and up to 84.5% for unseen-subject scenarios. We compare our approach with the widely used CHMM (Continuous HMM) and LSTM (Long Short-term Memory) based methods, demonstrating better recognition accuracy performance across all scenarios.https://ieeexplore.ieee.org/document/10795137/Gait phase recognitionGaussian mixture modelhidden Markov modellower limb prosthesis |
| spellingShingle | Wenyao Zhu Zhenbang Liu Yizhi Chen Dejiu Chen Zhonghai Lu Amputee Gait Phase Recognition Using Multiple GMM-HMM IEEE Access Gait phase recognition Gaussian mixture model hidden Markov model lower limb prosthesis |
| title | Amputee Gait Phase Recognition Using Multiple GMM-HMM |
| title_full | Amputee Gait Phase Recognition Using Multiple GMM-HMM |
| title_fullStr | Amputee Gait Phase Recognition Using Multiple GMM-HMM |
| title_full_unstemmed | Amputee Gait Phase Recognition Using Multiple GMM-HMM |
| title_short | Amputee Gait Phase Recognition Using Multiple GMM-HMM |
| title_sort | amputee gait phase recognition using multiple gmm hmm |
| topic | Gait phase recognition Gaussian mixture model hidden Markov model lower limb prosthesis |
| url | https://ieeexplore.ieee.org/document/10795137/ |
| work_keys_str_mv | AT wenyaozhu amputeegaitphaserecognitionusingmultiplegmmhmm AT zhenbangliu amputeegaitphaserecognitionusingmultiplegmmhmm AT yizhichen amputeegaitphaserecognitionusingmultiplegmmhmm AT dejiuchen amputeegaitphaserecognitionusingmultiplegmmhmm AT zhonghailu amputeegaitphaserecognitionusingmultiplegmmhmm |