A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition
Abnormal gait recognition is important for detecting body part weakness and diagnosing diseases. The abnormal gait hides a considerable amount of information. In order to extract the fine, spatial feature information in the abnormal gait and reduce the computational cost arising from excessive netwo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-02-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023349?viewType=HTML |
| _version_ | 1827990163615121408 |
|---|---|
| author | Xiaoguang Liu Yubo Wu Meng Chen Tie Liang Fei Han Xiuling Liu |
| author_facet | Xiaoguang Liu Yubo Wu Meng Chen Tie Liang Fei Han Xiuling Liu |
| author_sort | Xiaoguang Liu |
| collection | DOAJ |
| description | Abnormal gait recognition is important for detecting body part weakness and diagnosing diseases. The abnormal gait hides a considerable amount of information. In order to extract the fine, spatial feature information in the abnormal gait and reduce the computational cost arising from excessive network parameters, this paper proposes a double-channel multiscale depthwise separable convolutional neural network (DCMSDSCNN) for abnormal gait recognition. The method designs a multiscale depthwise feature extraction block (MDB), uses depthwise separable convolution (DSC) instead of standard convolution in the module and introduces the Bottleneck (BK) structure to optimize the MDB. The module achieves the extraction of effective features of abnormal gaits at different scales, and reduces the computational cost of the network. Experimental results show that the gait recognition accuracy is up to 99.60%, while the memory size of the model is reduced 4.21 times than before optimization. |
| first_indexed | 2024-04-10T00:31:05Z |
| format | Article |
| id | doaj.art-9d1b532f1e694ef1b8349c7ec5c40a77 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-10T00:31:05Z |
| publishDate | 2023-02-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-9d1b532f1e694ef1b8349c7ec5c40a772023-03-15T01:17:31ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-02-012058049806710.3934/mbe.2023349A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognitionXiaoguang Liu 0Yubo Wu1Meng Chen2Tie Liang3Fei Han 4Xiuling Liu 51. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China 1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, China1. College of Electronic and Information Engineering, Hebei University, Baoding, China 2. Key Laboratory of Digital Medical Engineering of Hebei Province, Hebei University, Baoding, ChinaAbnormal gait recognition is important for detecting body part weakness and diagnosing diseases. The abnormal gait hides a considerable amount of information. In order to extract the fine, spatial feature information in the abnormal gait and reduce the computational cost arising from excessive network parameters, this paper proposes a double-channel multiscale depthwise separable convolutional neural network (DCMSDSCNN) for abnormal gait recognition. The method designs a multiscale depthwise feature extraction block (MDB), uses depthwise separable convolution (DSC) instead of standard convolution in the module and introduces the Bottleneck (BK) structure to optimize the MDB. The module achieves the extraction of effective features of abnormal gaits at different scales, and reduces the computational cost of the network. Experimental results show that the gait recognition accuracy is up to 99.60%, while the memory size of the model is reduced 4.21 times than before optimization.https://www.aimspress.com/article/doi/10.3934/mbe.2023349?viewType=HTMLabnormal gait recognitionconvolutional neural network (cnn)mdbbk structuredouble-channel network |
| spellingShingle | Xiaoguang Liu Yubo Wu Meng Chen Tie Liang Fei Han Xiuling Liu A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition Mathematical Biosciences and Engineering abnormal gait recognition convolutional neural network (cnn) mdb bk structure double-channel network |
| title | A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| title_full | A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| title_fullStr | A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| title_full_unstemmed | A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| title_short | A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| title_sort | double channel multiscale depthwise separable convolutional neural network for abnormal gait recognition |
| topic | abnormal gait recognition convolutional neural network (cnn) mdb bk structure double-channel network |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023349?viewType=HTML |
| work_keys_str_mv | AT xiaoguangliu adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT yubowu adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT mengchen adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT tieliang adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT feihan adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT xiulingliu adoublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT xiaoguangliu doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT yubowu doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT mengchen doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT tieliang doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT feihan doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition AT xiulingliu doublechannelmultiscaledepthwiseseparableconvolutionalneuralnetworkforabnormalgaitrecognition |