Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility
A feature subset discernibility hybrid evaluation method using Fisher score based on joint feature and support vector machine is proposed for the feature selection problem of the upper limb rehabilitation training motion of Brunnstrom 4–5 stage patients. In this method, the joint feature is introduc...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-03-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147719838467 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547802827194368 |
|---|---|
| author | Guoyu Zuo Zhaokun Xu Jiahao Lu Daoxiong Gong |
| author_facet | Guoyu Zuo Zhaokun Xu Jiahao Lu Daoxiong Gong |
| author_sort | Guoyu Zuo |
| collection | DOAJ |
| description | A feature subset discernibility hybrid evaluation method using Fisher score based on joint feature and support vector machine is proposed for the feature selection problem of the upper limb rehabilitation training motion of Brunnstrom 4–5 stage patients. In this method, the joint feature is introduced to evaluate the discernibility between classes due to the joint effect of both candidate and selected features. A feature subset search strategy is used to search a set of candidate feature subsets. The Fisher score based on joint feature method is used to evaluate the candidate feature subsets and the best subset is selected as a new selected feature subset. From these selected subsets such as obtained by the above process, the subset with the best performance of support vector machine classification is finally selected as the optimal feature subset. Experiments were carried out on the upper limb routine rehabilitation training samples of the Brunnstrom 4–5 stage. Compared with both the F -score and the discernibility of feature subset methods, the experimental results show the effectiveness and feasibility of the proposed method which can obtain the feature subsets with higher accuracy and smaller feature dimension. |
| format | Article |
| id | doaj-art-b7f3ffaaca46466498429dcdce156f77 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2019-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-b7f3ffaaca46466498429dcdce156f772025-02-03T06:43:15ZengWileyInternational Journal of Distributed Sensor Networks1550-14772019-03-011510.1177/1550147719838467Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibilityGuoyu Zuo0Zhaokun Xu1Jiahao Lu2Daoxiong Gong3Beijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, ChinaBeijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, ChinaBeijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, ChinaBeijing Key Laboratory of Computing Intelligence and Intelligent Systems, Beijing, ChinaA feature subset discernibility hybrid evaluation method using Fisher score based on joint feature and support vector machine is proposed for the feature selection problem of the upper limb rehabilitation training motion of Brunnstrom 4–5 stage patients. In this method, the joint feature is introduced to evaluate the discernibility between classes due to the joint effect of both candidate and selected features. A feature subset search strategy is used to search a set of candidate feature subsets. The Fisher score based on joint feature method is used to evaluate the candidate feature subsets and the best subset is selected as a new selected feature subset. From these selected subsets such as obtained by the above process, the subset with the best performance of support vector machine classification is finally selected as the optimal feature subset. Experiments were carried out on the upper limb routine rehabilitation training samples of the Brunnstrom 4–5 stage. Compared with both the F -score and the discernibility of feature subset methods, the experimental results show the effectiveness and feasibility of the proposed method which can obtain the feature subsets with higher accuracy and smaller feature dimension.https://doi.org/10.1177/1550147719838467 |
| spellingShingle | Guoyu Zuo Zhaokun Xu Jiahao Lu Daoxiong Gong Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility International Journal of Distributed Sensor Networks |
| title | Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| title_full | Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| title_fullStr | Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| title_full_unstemmed | Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| title_short | Feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| title_sort | feature subset evaluation method for upper limb rehabilitation training based on joint feature discernibility |
| url | https://doi.org/10.1177/1550147719838467 |
| work_keys_str_mv | AT guoyuzuo featuresubsetevaluationmethodforupperlimbrehabilitationtrainingbasedonjointfeaturediscernibility AT zhaokunxu featuresubsetevaluationmethodforupperlimbrehabilitationtrainingbasedonjointfeaturediscernibility AT jiahaolu featuresubsetevaluationmethodforupperlimbrehabilitationtrainingbasedonjointfeaturediscernibility AT daoxionggong featuresubsetevaluationmethodforupperlimbrehabilitationtrainingbasedonjointfeaturediscernibility |