Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation
BackgroundFor rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and mach...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2021-09-01
|
| Series: | JMIR mHealth and uHealth |
| Online Access: | https://mhealth.jmir.org/2021/9/e24402 |
| _version_ | 1797735762601443328 |
|---|---|
| author | Qiaoqin Li Yongguo Liu Jiajing Zhu Zhi Chen Lang Liu Shangming Yang Guanyi Zhu Bin Zhu Juan Li Rongjiang Jin Jing Tao Lidian Chen |
| author_facet | Qiaoqin Li Yongguo Liu Jiajing Zhu Zhi Chen Lang Liu Shangming Yang Guanyi Zhu Bin Zhu Juan Li Rongjiang Jin Jing Tao Lidian Chen |
| author_sort | Qiaoqin Li |
| collection | DOAJ |
| description |
BackgroundFor rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and machine learning algorithms. Time-domain and frequency-domain features are extracted from original time series data collected by sensor nodes. For high-dimensional data, feature selection plays an important role in improving the performance of motion recognition. Existing feature selection methods can be categorized into filter and wrapper methods. Wrapper methods usually achieve better performance than filter methods; however, in most cases, they are computationally intensive, and the feature subset obtained is usually optimized only for the specific learning algorithm.
ObjectiveThis study aimed to provide a feature selection method for motion recognition of upper-limb exercises and improve the recognition performance.
MethodsMotion data from 5 types of upper-limb exercises performed by 21 participants were collected by a customized inertial measurement unit (IMU) node. A total of 60 time-domain and frequency-domain features were extracted from the original sensor data. A hybrid feature selection method by combining filter and wrapper methods (FESCOM) was proposed to eliminate irrelevant features for motion recognition of upper-limb exercises. In the filter stage, candidate features were first selected from the original feature set according to the significance for motion recognition. In the wrapper stage, k-nearest neighbors (kNN), Naïve Bayes (NB), and random forest (RF) were evaluated as the wrapping components to further refine the features from the candidate feature set. The performance of the proposed FESCOM method was verified using experiments on motion recognition of upper-limb exercises and compared with the traditional wrapper method.
ResultsUsing kNN, NB, and RF as the wrapping components, the classification error rates of the proposed FESCOM method were 1.7%, 8.9%, and 7.4%, respectively, and the feature selection time in each iteration was 13 seconds, 71 seconds, and 541 seconds, respectively.
ConclusionsThe experimental results demonstrated that, in the case of 5 motion types performed by 21 healthy participants, the proposed FESCOM method using kNN and NB as the wrapping components achieved better recognition performance than the traditional wrapper method. The FESCOM method dramatically reduces the search time in the feature selection process. The results also demonstrated that the optimal number of features depends on the classifier. This approach serves to improve feature selection and classification algorithm selection for upper-limb motion recognition based on wearable sensor data, which can be extended to motion recognition of more motion types and participants. |
| first_indexed | 2024-03-12T13:03:48Z |
| format | Article |
| id | doaj.art-c140e79bf16b409f8884cc10dc0d2f46 |
| institution | Directory Open Access Journal |
| issn | 2291-5222 |
| language | English |
| last_indexed | 2024-03-12T13:03:48Z |
| publishDate | 2021-09-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR mHealth and uHealth |
| spelling | doaj.art-c140e79bf16b409f8884cc10dc0d2f462023-08-28T18:59:43ZengJMIR PublicationsJMIR mHealth and uHealth2291-52222021-09-0199e2440210.2196/24402Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and ValidationQiaoqin Lihttps://orcid.org/0000-0001-9225-307XYongguo Liuhttps://orcid.org/0000-0002-4906-7025Jiajing Zhuhttps://orcid.org/0000-0002-5916-3141Zhi Chenhttps://orcid.org/0000-0002-5159-1280Lang Liuhttps://orcid.org/0000-0001-7724-3375Shangming Yanghttps://orcid.org/0000-0001-7227-3698Guanyi Zhuhttps://orcid.org/0000-0001-5526-8256Bin Zhuhttps://orcid.org/0000-0002-8412-5577Juan Lihttps://orcid.org/0000-0002-8530-9001Rongjiang Jinhttps://orcid.org/0000-0002-4733-9955Jing Taohttps://orcid.org/0000-0001-9751-5294Lidian Chenhttps://orcid.org/0000-0002-8699-0839 BackgroundFor rehabilitation training systems, it is essential to automatically record and recognize exercises, especially when more than one type of exercise is performed without a predefined sequence. Most motion recognition methods are based on feature engineering and machine learning algorithms. Time-domain and frequency-domain features are extracted from original time series data collected by sensor nodes. For high-dimensional data, feature selection plays an important role in improving the performance of motion recognition. Existing feature selection methods can be categorized into filter and wrapper methods. Wrapper methods usually achieve better performance than filter methods; however, in most cases, they are computationally intensive, and the feature subset obtained is usually optimized only for the specific learning algorithm. ObjectiveThis study aimed to provide a feature selection method for motion recognition of upper-limb exercises and improve the recognition performance. MethodsMotion data from 5 types of upper-limb exercises performed by 21 participants were collected by a customized inertial measurement unit (IMU) node. A total of 60 time-domain and frequency-domain features were extracted from the original sensor data. A hybrid feature selection method by combining filter and wrapper methods (FESCOM) was proposed to eliminate irrelevant features for motion recognition of upper-limb exercises. In the filter stage, candidate features were first selected from the original feature set according to the significance for motion recognition. In the wrapper stage, k-nearest neighbors (kNN), Naïve Bayes (NB), and random forest (RF) were evaluated as the wrapping components to further refine the features from the candidate feature set. The performance of the proposed FESCOM method was verified using experiments on motion recognition of upper-limb exercises and compared with the traditional wrapper method. ResultsUsing kNN, NB, and RF as the wrapping components, the classification error rates of the proposed FESCOM method were 1.7%, 8.9%, and 7.4%, respectively, and the feature selection time in each iteration was 13 seconds, 71 seconds, and 541 seconds, respectively. ConclusionsThe experimental results demonstrated that, in the case of 5 motion types performed by 21 healthy participants, the proposed FESCOM method using kNN and NB as the wrapping components achieved better recognition performance than the traditional wrapper method. The FESCOM method dramatically reduces the search time in the feature selection process. The results also demonstrated that the optimal number of features depends on the classifier. This approach serves to improve feature selection and classification algorithm selection for upper-limb motion recognition based on wearable sensor data, which can be extended to motion recognition of more motion types and participants.https://mhealth.jmir.org/2021/9/e24402 |
| spellingShingle | Qiaoqin Li Yongguo Liu Jiajing Zhu Zhi Chen Lang Liu Shangming Yang Guanyi Zhu Bin Zhu Juan Li Rongjiang Jin Jing Tao Lidian Chen Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation JMIR mHealth and uHealth |
| title | Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation |
| title_full | Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation |
| title_fullStr | Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation |
| title_full_unstemmed | Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation |
| title_short | Upper-Limb Motion Recognition Based on Hybrid Feature Selection: Algorithm Development and Validation |
| title_sort | upper limb motion recognition based on hybrid feature selection algorithm development and validation |
| url | https://mhealth.jmir.org/2021/9/e24402 |
| work_keys_str_mv | AT qiaoqinli upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT yongguoliu upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT jiajingzhu upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT zhichen upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT langliu upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT shangmingyang upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT guanyizhu upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT binzhu upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT juanli upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT rongjiangjin upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT jingtao upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation AT lidianchen upperlimbmotionrecognitionbasedonhybridfeatureselectionalgorithmdevelopmentandvalidation |