Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units
This paper develops Deep Neural Network (DNN) models that can recognize stroke gaits. Stroke patients usually suffer from partial disability and develop abnormal gaits that can vary widely and need targeted treatments. Evaluation of gait patterns is crucial for clinical experts to make decisions abo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/5/1864 |
| _version_ | 1797412664232640512 |
|---|---|
| author | Fu-Cheng Wang Szu-Fu Chen Chin-Hsien Lin Chih-Jen Shih Ang-Chieh Lin Wei Yuan You-Chi Li Tien-Yun Kuo |
| author_facet | Fu-Cheng Wang Szu-Fu Chen Chin-Hsien Lin Chih-Jen Shih Ang-Chieh Lin Wei Yuan You-Chi Li Tien-Yun Kuo |
| author_sort | Fu-Cheng Wang |
| collection | DOAJ |
| description | This paper develops Deep Neural Network (DNN) models that can recognize stroke gaits. Stroke patients usually suffer from partial disability and develop abnormal gaits that can vary widely and need targeted treatments. Evaluation of gait patterns is crucial for clinical experts to make decisions about the medication and rehabilitation strategies for the stroke patients. However, the evaluation is often subjective, and different clinicians might have different diagnoses of stroke gait patterns. In addition, some patients may present with mixed neurological gaits. Therefore, we apply artificial intelligence techniques to detect stroke gaits and to classify abnormal gait patterns. First, we collect clinical gait data from eight stroke patients and seven healthy subjects. We then apply these data to develop DNN models that can detect stroke gaits. Finally, we classify four common gait abnormalities seen in stroke patients. The developed models achieve an average accuracy of 99.35% in detecting the stroke gaits and an average accuracy of 97.31% in classifying the gait abnormality. Based on the results, the developed DNN models could help therapists or physicians to diagnose different abnormal gaits and to apply suitable rehabilitation strategies for stroke patients. |
| first_indexed | 2024-03-09T05:06:23Z |
| format | Article |
| id | doaj.art-d0db94f39b554a2f92bb74c0c10bb855 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:06:23Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d0db94f39b554a2f92bb74c0c10bb8552023-12-03T12:55:03ZengMDPI AGSensors1424-82202021-03-01215186410.3390/s21051864Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement UnitsFu-Cheng Wang0Szu-Fu Chen1Chin-Hsien Lin2Chih-Jen Shih3Ang-Chieh Lin4Wei Yuan5You-Chi Li6Tien-Yun Kuo7Department of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanDepartment of Physical Medicine and Rehabilitation, Cheng Hsin General Hospital, Taipei 112, TaiwanDepartment of Neurology, National Taiwan University Hospital, Taipei 100, TaiwanDepartment of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanDepartment of Physical Medicine and Rehabilitation, Cheng Hsin General Hospital, Taipei 112, TaiwanDepartment of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanDepartment of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanDepartment of Mechanical Engineering, National Taiwan University, Taipei 106, TaiwanThis paper develops Deep Neural Network (DNN) models that can recognize stroke gaits. Stroke patients usually suffer from partial disability and develop abnormal gaits that can vary widely and need targeted treatments. Evaluation of gait patterns is crucial for clinical experts to make decisions about the medication and rehabilitation strategies for the stroke patients. However, the evaluation is often subjective, and different clinicians might have different diagnoses of stroke gait patterns. In addition, some patients may present with mixed neurological gaits. Therefore, we apply artificial intelligence techniques to detect stroke gaits and to classify abnormal gait patterns. First, we collect clinical gait data from eight stroke patients and seven healthy subjects. We then apply these data to develop DNN models that can detect stroke gaits. Finally, we classify four common gait abnormalities seen in stroke patients. The developed models achieve an average accuracy of 99.35% in detecting the stroke gaits and an average accuracy of 97.31% in classifying the gait abnormality. Based on the results, the developed DNN models could help therapists or physicians to diagnose different abnormal gaits and to apply suitable rehabilitation strategies for stroke patients.https://www.mdpi.com/1424-8220/21/5/1864gait recognitiondeep learningneural networkstroke gaitIMU (inertial measurement unit) |
| spellingShingle | Fu-Cheng Wang Szu-Fu Chen Chin-Hsien Lin Chih-Jen Shih Ang-Chieh Lin Wei Yuan You-Chi Li Tien-Yun Kuo Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units Sensors gait recognition deep learning neural network stroke gait IMU (inertial measurement unit) |
| title | Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units |
| title_full | Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units |
| title_fullStr | Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units |
| title_full_unstemmed | Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units |
| title_short | Detection and Classification of Stroke Gaits by Deep Neural Networks Employing Inertial Measurement Units |
| title_sort | detection and classification of stroke gaits by deep neural networks employing inertial measurement units |
| topic | gait recognition deep learning neural network stroke gait IMU (inertial measurement unit) |
| url | https://www.mdpi.com/1424-8220/21/5/1864 |
| work_keys_str_mv | AT fuchengwang detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT szufuchen detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT chinhsienlin detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT chihjenshih detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT angchiehlin detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT weiyuan detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT youchili detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits AT tienyunkuo detectionandclassificationofstrokegaitsbydeepneuralnetworksemployinginertialmeasurementunits |