DAGAN-Based Gait Features Augmentation for Ankle Instability Detection
We developed a computer-aided program for the diagnosis of ankle ligament injury. This study used the Heidelberg Foot Measurement Method (HFMM) to obtain the specific gait kinematic characteristics. To address the issue of insufficient available medical samples, an Attention Dual Generative Adversar...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11075723/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849245889958248448 |
|---|---|
| author | Xin Liu Yao Zhang Yuwei Jiao Bin Zheng Qinwei Guo Yuanyuan Yu Aziguli Wulamu |
| author_facet | Xin Liu Yao Zhang Yuwei Jiao Bin Zheng Qinwei Guo Yuanyuan Yu Aziguli Wulamu |
| author_sort | Xin Liu |
| collection | DOAJ |
| description | We developed a computer-aided program for the diagnosis of ankle ligament injury. This study used the Heidelberg Foot Measurement Method (HFMM) to obtain the specific gait kinematic characteristics. To address the issue of insufficient available medical samples, an Attention Dual Generative Adversarial Network (Attention-DualGAN) is proposed to augment the gait feature set. We used a Convolutional Long Short-Term Memory (ConvLSTM) Network-based and Time Convolution Network (TCN)-based detection model to observe the impact of the extended dataset. The results show that the accuracy of the ConvLSTM model after data enhancement improves by 2.4%, and the accuracy of the TCN model after data enhancement improves by 7.47%. Through the visualization of Pearson correlation coefficient, histogram, and scatter plot, it is proved that Attention-DualGAN produces high-quality gait kinematics characteristics. This study shows that Attention-DualGAN generates synthetic gait features with high correlation to real data, and the performance of the detection model in the diagnosis of ankle ligament injury can be improved by adding appropriate synthetic data. |
| format | Article |
| id | doaj-art-d8355a3a4b8c4fe09b98c665b30c769f |
| institution | Kabale University |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-d8355a3a4b8c4fe09b98c665b30c769f2025-08-20T03:58:40ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01332793280510.1109/TNSRE.2025.358723311075723DAGAN-Based Gait Features Augmentation for Ankle Instability DetectionXin Liu0https://orcid.org/0000-0001-7909-9012Yao Zhang1Yuwei Jiao2Bin Zheng3https://orcid.org/0000-0003-3476-5936Qinwei Guo4https://orcid.org/0000-0003-3600-9544Yuanyuan Yu5Aziguli Wulamu6https://orcid.org/0000-0001-7228-7838School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaDepartment of Surgery, Surgical Simulation Research Laboratory, University of Alberta, Edmonton, CanadaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaDepartment of Surgery, Surgical Simulation Research Laboratory, University of Alberta, Edmonton, CanadaInstitute of Sports Medicine, Peking University Third Hospital, Beijing, ChinaInstitute of Sports Medicine, Peking University Third Hospital, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaWe developed a computer-aided program for the diagnosis of ankle ligament injury. This study used the Heidelberg Foot Measurement Method (HFMM) to obtain the specific gait kinematic characteristics. To address the issue of insufficient available medical samples, an Attention Dual Generative Adversarial Network (Attention-DualGAN) is proposed to augment the gait feature set. We used a Convolutional Long Short-Term Memory (ConvLSTM) Network-based and Time Convolution Network (TCN)-based detection model to observe the impact of the extended dataset. The results show that the accuracy of the ConvLSTM model after data enhancement improves by 2.4%, and the accuracy of the TCN model after data enhancement improves by 7.47%. Through the visualization of Pearson correlation coefficient, histogram, and scatter plot, it is proved that Attention-DualGAN produces high-quality gait kinematics characteristics. This study shows that Attention-DualGAN generates synthetic gait features with high correlation to real data, and the performance of the detection model in the diagnosis of ankle ligament injury can be improved by adding appropriate synthetic data.https://ieeexplore.ieee.org/document/11075723/Gait analysisankle instabilitydual attention generative adversarial networks (DAGAN)convolutional long short-term memory network (ConvLSTM)temporal convolutional network (TCN) |
| spellingShingle | Xin Liu Yao Zhang Yuwei Jiao Bin Zheng Qinwei Guo Yuanyuan Yu Aziguli Wulamu DAGAN-Based Gait Features Augmentation for Ankle Instability Detection IEEE Transactions on Neural Systems and Rehabilitation Engineering Gait analysis ankle instability dual attention generative adversarial networks (DAGAN) convolutional long short-term memory network (ConvLSTM) temporal convolutional network (TCN) |
| title | DAGAN-Based Gait Features Augmentation for Ankle Instability Detection |
| title_full | DAGAN-Based Gait Features Augmentation for Ankle Instability Detection |
| title_fullStr | DAGAN-Based Gait Features Augmentation for Ankle Instability Detection |
| title_full_unstemmed | DAGAN-Based Gait Features Augmentation for Ankle Instability Detection |
| title_short | DAGAN-Based Gait Features Augmentation for Ankle Instability Detection |
| title_sort | dagan based gait features augmentation for ankle instability detection |
| topic | Gait analysis ankle instability dual attention generative adversarial networks (DAGAN) convolutional long short-term memory network (ConvLSTM) temporal convolutional network (TCN) |
| url | https://ieeexplore.ieee.org/document/11075723/ |
| work_keys_str_mv | AT xinliu daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT yaozhang daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT yuweijiao daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT binzheng daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT qinweiguo daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT yuanyuanyu daganbasedgaitfeaturesaugmentationforankleinstabilitydetection AT aziguliwulamu daganbasedgaitfeaturesaugmentationforankleinstabilitydetection |