Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification
The acquisition of bio-signal from the human body requires a strict experimental setup and ethical approvements, which leads to limited data for the training of classifiers in the era of big data. It will change the situation if synthetic data can be generated based on real data. This article propos...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-07-01
|
| Series: | Frontiers in Bioengineering and Biotechnology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fbioe.2022.909653/full |
| _version_ | 1811214830511587328 |
|---|---|
| author | Zihan Chen Yaojia Qian Yuxi Wang Yinfeng Fang |
| author_facet | Zihan Chen Yaojia Qian Yuxi Wang Yinfeng Fang |
| author_sort | Zihan Chen |
| collection | DOAJ |
| description | The acquisition of bio-signal from the human body requires a strict experimental setup and ethical approvements, which leads to limited data for the training of classifiers in the era of big data. It will change the situation if synthetic data can be generated based on real data. This article proposes such a kind of multiple channel electromyography (EMG) data enhancement method using a deep convolutional generative adversarial network (DCGAN). The generation procedure is as follows: First, the multiple channels of EMG signals within sliding windows are converted to grayscale images through matrix transformation, normalization, and histogram equalization. Second, the grayscale images of each class are used to train DCGAN so that synthetic grayscale images of each class can be generated with the input of random noises. To evaluate whether the synthetic data own the similarity and diversity with the real data, the classification accuracy index is adopted in this article. A public EMG dataset (that is, ISR Myo-I) for hand motion recognition is used to prove the usability of the proposed method. The experimental results show that adding synthetic data to the training data has little effect on the classification performance, indicating the similarity between real data and synthetic data. Moreover, it is also noted that the average accuracy (five classes) is slightly increased by 1%–2% for support vector machine (SVM) and random forest (RF), respectively, with additional synthetic data for training. Although the improvement is not statistically significant, it implies that the generated data by DCGAN own its new characteristics, and it is possible to enrich the diversity of the training dataset. In addition, cross-validation analysis shows that the synthetic samples have large inter-class distance, reflected by higher cross-validation accuracy of pure synthetic sample classification. Furthermore, this article also demonstrates that histogram equalization can significantly improve the performance of EMG-based hand motion recognition. |
| first_indexed | 2024-04-12T06:12:11Z |
| format | Article |
| id | doaj.art-df50825cf6944aed864ab5550dc63e0e |
| institution | Directory Open Access Journal |
| issn | 2296-4185 |
| language | English |
| last_indexed | 2024-04-12T06:12:11Z |
| publishDate | 2022-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Bioengineering and Biotechnology |
| spelling | doaj.art-df50825cf6944aed864ab5550dc63e0e2022-12-22T03:44:41ZengFrontiers Media S.A.Frontiers in Bioengineering and Biotechnology2296-41852022-07-011010.3389/fbioe.2022.909653909653Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion ClassificationZihan ChenYaojia QianYuxi WangYinfeng FangThe acquisition of bio-signal from the human body requires a strict experimental setup and ethical approvements, which leads to limited data for the training of classifiers in the era of big data. It will change the situation if synthetic data can be generated based on real data. This article proposes such a kind of multiple channel electromyography (EMG) data enhancement method using a deep convolutional generative adversarial network (DCGAN). The generation procedure is as follows: First, the multiple channels of EMG signals within sliding windows are converted to grayscale images through matrix transformation, normalization, and histogram equalization. Second, the grayscale images of each class are used to train DCGAN so that synthetic grayscale images of each class can be generated with the input of random noises. To evaluate whether the synthetic data own the similarity and diversity with the real data, the classification accuracy index is adopted in this article. A public EMG dataset (that is, ISR Myo-I) for hand motion recognition is used to prove the usability of the proposed method. The experimental results show that adding synthetic data to the training data has little effect on the classification performance, indicating the similarity between real data and synthetic data. Moreover, it is also noted that the average accuracy (five classes) is slightly increased by 1%–2% for support vector machine (SVM) and random forest (RF), respectively, with additional synthetic data for training. Although the improvement is not statistically significant, it implies that the generated data by DCGAN own its new characteristics, and it is possible to enrich the diversity of the training dataset. In addition, cross-validation analysis shows that the synthetic samples have large inter-class distance, reflected by higher cross-validation accuracy of pure synthetic sample classification. Furthermore, this article also demonstrates that histogram equalization can significantly improve the performance of EMG-based hand motion recognition.https://www.frontiersin.org/articles/10.3389/fbioe.2022.909653/fullEMGDCGANdata enhancementinter-class distanceclassification accuracyhistogram equalization |
| spellingShingle | Zihan Chen Yaojia Qian Yuxi Wang Yinfeng Fang Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification Frontiers in Bioengineering and Biotechnology EMG DCGAN data enhancement inter-class distance classification accuracy histogram equalization |
| title | Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification |
| title_full | Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification |
| title_fullStr | Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification |
| title_full_unstemmed | Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification |
| title_short | Deep Convolutional Generative Adversarial Network-Based EMG Data Enhancement for Hand Motion Classification |
| title_sort | deep convolutional generative adversarial network based emg data enhancement for hand motion classification |
| topic | EMG DCGAN data enhancement inter-class distance classification accuracy histogram equalization |
| url | https://www.frontiersin.org/articles/10.3389/fbioe.2022.909653/full |
| work_keys_str_mv | AT zihanchen deepconvolutionalgenerativeadversarialnetworkbasedemgdataenhancementforhandmotionclassification AT yaojiaqian deepconvolutionalgenerativeadversarialnetworkbasedemgdataenhancementforhandmotionclassification AT yuxiwang deepconvolutionalgenerativeadversarialnetworkbasedemgdataenhancementforhandmotionclassification AT yinfengfang deepconvolutionalgenerativeadversarialnetworkbasedemgdataenhancementforhandmotionclassification |