The DOI matches its Crossref record; 69 of the 71 references it cites were found in a registry or an index.
Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands
Open accessAbstract
Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Pattern recognition control of myoelectric prostheses is also getting popularity due to its better classification of EMG signals (user intentions) using various methods, i.e., linear discriminant analysis classifier, tacit learning system, deep learning with convolutional neural network (Adewuyi et al., 2016; Atzori et al., 2016; Fani et al., 2016; Oyama et al., 2016), etc.”
From Selectivity and Longevity of Peripheral-Nerve and Machine Interfaces: A Review. (2017) · cites this paper as Atzori et al., 2016
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“They include: random Forests (Breiman, 2001), SVM (Cristianini and Shawe-Taylor, 2000) and k-Nearest Neighbors (Duda et al., 2001).”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“However, in the field of computer vision in 2012, deep learning approaches won one of the largest object recognition challenges (the ILSVRC) decreasing the previous top-5 error rate by more than 10% (Krizhevsky and Hinton, 2010; Goodfellow et al., 2016).”
BackgroundHuman-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 1×
“Moreover, they have also improved the performance of reinforcement learning, where a machine or software agent is able to maximize its performance by itself performing trials and errors (Mnih et al., 2015; Goodfellow et al., 2016).”
BackgroundDelving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“Since then, only techniques based on convolutional neural networks have won this competition, leading to top-5 error rates lower than 5% (He et al., 2015; Goodfellow et al., 2016).”
BackgroundThe pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 1×
“The usefulness of benchmark databases has been demonstrated repeatedly in other fields, e.g., in the machine vision and image analysis communities (Müller et al., 2009; Everingham et al., 2010).”
BackgroundSeel, N. M. (2012) · Springer eBooks · doi:10.1007/978-1-4419-1428-6_5195 · Cited by 19,482
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
Cristianini, N., & Shawe-Taylor, J. (2000) · doi:10.1017/cbo9780511801389 · Cited by 13,855
(2016) · Cited by 11,679
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“Since 2010, the application of deep learning techniques to speech recognition has allowed a quick and impressive reduction of error rate (Dahl et al., 2010; Deng et al., 2010b, 2013; Hinton et al., 2012; Goodfellow et al., 2016).”
BackgroundRussell, E. L., Chiang, L. H., & Braatz, R. D. (2000) · Advances in industrial control · doi:10.1007/978-1-4471-0409-4_3 · Cited by 7,938
Flagged first, then by citations
2 of the 71 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- Feix, 2009, A comprehensive grasp taxonomy, 2
- Goodfellow, 2016, Deep Learning (Book in preparation).
Cited by
Sorted by citations
Deep learning for healthcare applications based on physiological signals: A review
Faust, O., Hagiwara, Y., Hong, T. J., Lih, O. S., & Acharya, U. R. (2018) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2018.04.005 · Cited by 1,081
“, 2016 [65] Hand movement classification CNN NinaPro DB [62] accuracy: 66.”
BackgroundApplications of deep learning and reinforcement learning to biological data
Mahmud, M., Kaiser, M. S., Hussain, A., & Vassanelli, S. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2790388 · Cited by 765
“[184] and Park and Lee [185] decoded hand movements from EMG signals.”
Deep Learning for Electromyographic Hand Gesture Signal Classification Using Transfer Learning
Côté‐Allard, U., Fall, C. L., Drouin, A., Campeau‐Lecours, A., Gosselin, C., Glette, K., Laviolette, F., & Gosselin, B. J. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2896269 · Cited by 789
“Recently, researchers have proposed deep learning approaches [4], [5], [6], shifting the paradigm from feature engineering to feature learning.”
BackgroundMethodDeep Learning in Mining Biological Data
Mahmud, M., Kaiser, M. S., McGinnity, T. M., & Hussain, A. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09773-x · Cited by 478
Comparison of six electromyography acquisition setups on hand movement classification tasks
Pizzolato, S., Tagliapietra, L., Cognolato, M., Reggiani, M., Müller, H., & Atzori, M. (2017) · PLoS ONE · doi:10.1371/journal.pone.0186132 · Cited by 429
“Offline data analysis on public benchmark datasets on the other hand can be performed by any researcher worldwide (including a wide community of scientists that are highly specialized in machine learning) and it allows the immediate comparison of different methods (including very recent ones [8]) and setups.”
BackgroundA novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition
Hu, Y., Wong, Y., Wei, W., Du, Y., Kankanhalli, M., & Geng, W. (2018) · PLoS ONE · doi:10.1371/journal.pone.0206049 · Cited by 403
Deep Learning for EMG-based Human-Machine Interaction: A Review
Xiong, D., Zhang, D., Zhao, X., & Zhao, Y. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1003865 · Cited by 428
“[81] developed a TCN-based network named TEMPONet, which runs on an embedded system.”
BackgroundMethodSurface EMG-Based Inter-Session Gesture Recognition Enhanced by Deep Domain Adaptation
Du, Y., Jin, W., Wei, W., Hu, Y., & Geng, W. (2017) · Sensors · doi:10.3390/s17030458 · Cited by 367
“[49] also employed a ConvNet-based gesture classifier to recognize hand gestures from a 150 ms window of sEMG signals in the NinaPro database.”
MethodZhai, X., Jelfs, B., Chan, R. H. M., & Tin, C. (2017) · Frontiers in Neuroscience · doi:10.3389/fnins.2017.00379 · Cited by 365
“Atzori et al. (2016) applied a CNN classifier on the NinaPro dataset, which reached an average accuracy of 60.27% on DB2 taking a total training time of 1 h and 42min.”
MethodInfluentialWei, W., Wong, Y., Du, Y., Hu, Y., Kankanhalli, M., & Geng, W. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.12.005 · Cited by 278
EMG Pattern Recognition in the Era of Big Data and Deep Learning
Phinyomark, A., & Scheme, E. (2018) · Big Data and Cognitive Computing · doi:10.3390/bdcc2030021 · Cited by 272
“When short time windows of the raw EMG signal (150–200 ms) have been used as inputs to CNNs with very simple architectures, however, the reported accuracies have been below those of classical classification methods (i.e., RF for Ninapro 1 and 2, and SVM for Ninapro 3) [114].”
MethodSurface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning
Wei, W., Dai, Q., Wong, Y., Hu, Y., Kankanhalli, M., & Geng, W. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2899222 · Cited by 261
“ing [6], [8], [9], [13], x usually takes the form of raw sEMG signals.”
BackgroundInfluentialMultiday EMG-Based Classification of Hand Motions with Deep Learning Techniques
Rehman, M. Z. U., Waris, A., Gilani, S. O., Jochumsen, M., Niazi, I. K., Jamil, M., Farina, D., & Kamavuako, E. N. (2018) · Sensors · doi:10.3390/s18082497 · Cited by 226
“They found that classification accuracy improved significantly as compared with random forests, AtzoriNet [21], and GengNet [37].”
BackgroundMethodResultInfluentialXia, P., Hu, J., & Peng, Y. (2017) · Artificial Organs · doi:10.1111/aor.13004 · Cited by 232
Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals
Chen, L., Fu, J., Wu, Y., Li, H., & Zheng, B. (2020) · Sensors · doi:10.3390/s20030672 · Cited by 227
“Using CNN to classify sEMG signals, literature [12,17,18] took the raw signals as input space.”
MethodFleming, A., Stafford, N. E., Huang, S., Hu, X., Ferris, D. P., & Huang, H. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/ac1176 · Cited by 236
Li, W., Shi, P. A., & Yu, H. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.621885 · Cited by 228
“Atzori et al. (2016) introduced a modified version of the well-known CNN architecture, called LeNet, to classify an average of 50 hand movements in NinaPro database.”
BackgroundMethodInfluentialDeep Learning in the Biomedical Applications: Recent and Future Status
Zemouri, R. M., Noureddine Zerhouni, A., & Racoceanu, D. (2019) · Applied Sciences · doi:10.3390/app9081526 · Cited by 200
Furui, A., Eto, S., Nakagaki, K., Shimada, K., Nakamura, G., Masuda, A., Chin, T., & Tsuji, T. (2019) · Science Robotics · doi:10.1126/scirobotics.aaw6339 · Cited by 185
Transfer learning for sEMG hand gestures recognition using convolutional neural networks
Côté‐Allard, U., Fall, C. L., Campeau‐Lecours, A., Gosselin, C., Laviolette, F., & Gosselin, B. J. (2017) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2017.8122854 · Cited by 174
“fact, it has recently been suggested for classification in the time domain [7], [8] and time-frequency domain [2].”
BackgroundHuman-Robot Interaction in Rehabilitation and Assistance: a Review
Mohebbi, A. (2020) · Current Robotics Reports · doi:10.1007/s43154-020-00015-4 · Cited by 175
Karnam, N. K., Dubey, S. R., Turlapaty, A. C., & Gokaraju, B. (2022) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2022.02.005 · Cited by 181
“In [25], Atzori et al. performed the sEMG classification task over NinaPro DB1, NinaPro DB2 and NinaPro DB3 datasets with a deep Convolutional Neural Network (CNN) architecture consisting of two convolutional layers.”
MethodAmeri, A., Akhaee, M. A., Scheme, E., & Englehart, K. B. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2962189 · Cited by 180
“CNNs have been successfully applied for amputee subjects in offline tests [18].”
Regression convolutional neural network for improved simultaneous EMG control
Ameri, A., Akhaee, M. A., Scheme, E., & Englehart, K. B. (2019) · Journal of Neural Engineering · doi:10.1088/1741-2552/ab0e2e · Cited by 178
Panwar, M., Biswas, D., Bajaj, H., Jobges, M., Turk, R., Maharatna, K., & Acharyya, A. (2019) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2899927 · Cited by 158
A Review of Hand Gesture Recognition Systems Based on Noninvasive Wearable Sensors
Tchantchane, R., Zhou, H., Zhang, S., & Alıcı, G. (2023) · Advanced Intelligent Systems · doi:10.1002/aisy.202300207 · Cited by 181
Surface Electromyography as a Natural Human–Machine Interface: A Review
Zheng, M., Crouch, M. S., & Eggleston, M. S. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3165988 · Cited by 171
“A similar architecture has also been used for analyzing sparse sEMG signals through an entire time window, using a 2-dimensional convolution that looks for patterns over both the time and space axes [130], [147], [149], [156]–[158].”
MethodZanghieri, M., Benatti, S., Burrello, A., Kartsch, V., Conti, F., & Benini, L. (2019) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2019.2959160 · Cited by 168
“[36] also proposed a CNN-based approach to recognize the 52 hand gestures from the NinaPro DB1, DB2 andDB3 (taking 150ms-windows of RMS, acting on time×channels), reaching classification accuracy comparable to classical methods such as RF.”
MethodA CNN-LSTM Hybrid Model for Wrist Kinematics Estimation Using Surface Electromyography
Bao, T., Zaidi, S. A. R., Xie, S. Q., Yang, P., & Zhang, Z. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3036654 · Cited by 152
“Compared with CNN architectures in many previous studies [15], [16], [21], the dimension of our last FC block is smaller since we empirically found that a too large dimension might not be able to benefit the performances of CNN and CNN-LSTM significantly.”
MethodResultInfluentialMukhopadhyay, A. K., & Samui, S. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.101669 · Cited by 148
Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG
Asif, A. R., Waris, A., Gilani, S. O., Jamil, M., Ashraf, H., Shafique, M., & Niazi, I. K. (2020) · Sensors · doi:10.3390/s20061642 · Cited by 150
“Atzori et al. [11] showed CNN’s potential compared to traditional techniques (KNN, SVM and LDA).”
MethodFS-HGR: Few-Shot Learning for Hand Gesture Recognition via Electromyography
Rahimian, E., Zabihi, S., Asif, A. A., Farina, D., Atashzar, S. F., & Mohammadi, A. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3077413 · Cited by 135
“Following the pre-processing procedure established in previous studies [16], [19], [22], [23], we used a 1st order low-pass Butterworth filter to smooth the electrical activities”
BackgroundMethodInfluentialsEMG-Based Gesture Recognition with Convolution Neural Networks
Ding, Z., Yang, C., Tian, Z., Yi, C., Fu, Y., & Jiang, F. (2018) · Sustainability · doi:10.3390/su10061865 · Cited by 138
“[35] achieved a recognition accuracy of”
BackgroundMethodInfluentialKyranou, I., Vijayakumar, S., & Erden, M. S. (2018) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2018.00058 · Cited by 144
Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
Côté-Allard, U., Campbell, E., Phinyomark, A., Laviolette, F., Gosselin, B. J., & Scheme, E. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00158 · Cited by 139
“In the last few years, however, researchers have started to leverage deep learning (Atzori et al., 2016; Allard et al., 2016; Phinyomark and Scheme, 2018a), shifting the paradigm from feature engineering to feature learning.”
BackgroundAdvances and Disturbances in sEMG-Based Intentions and Movements Recognition: A Review
Xu, H., & Xiong, A. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3068521 · Cited by 127
“in real-life environments [5], [6], [19].”
Hand gesture classification using time–frequency images and transfer learning based on CNN
Özdemir, M. A., Kisa, D. H., Güren, O., & Akan, A. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103787 · Cited by 118
A Subject-Transfer Framework Based on Single-Trial EMG Analysis Using Convolutional Neural Networks
Kim, K.-T., Guan, C., & Lee, S. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2946625 · Cited by 116
“the recognition of user intention in several myoelectric interface studies [23], [24].”
BackgroundA Novel Deep Learning Bi-GRU-I Model for Real-Time Human Activity Recognition Using Inertial Sensors
Tong, L., Ma, H., Lin, Q., He, J., & Peng, L. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3148431 · Cited by 121
Gautam, A., Panwar, M., Biswas, D., & Acharyya, A. (2020) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2020.2972523 · Cited by 121
“that the signal to noise ratio of the augmented data equals to 25 based on the study conducted by [34].”
BackgroundMethodDynamic Gesture Recognition Using Surface EMG Signals Based on Multi-Stream Residual Network
Yang, Z., Jiang, D., Sun, Y., Tao, B., Tong, X., Jiang, G., Xu, M., Yun, J., Liu, Y., Chen, B., et al. (2021) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2021.779353 · Cited by 115
“The surface electromyography signal (sEMG) contains a lot of information and can be used for gesture recognition and force prediction (Ma et al., 2020; Atzori et al., 2016; Sadikoglu et al., 2017; Baldacchino et al., 2018).”
BackgroundCurrent Solutions and Future Trends for Robotic Prosthetic Hands
Mendez, V., Iberite, F., Shokur, S., & Micera, S. (2021) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-071020-104336 · Cited by 116
Deep Learning and Big Data in Healthcare: A Double Review for Critical Beginners
Bote-Curiel, L., Muñoz-Romero, S., Guerrero-Curieses, A., & Rojo‐Álvarez, J. L. (2019) · Applied Sciences · doi:10.3390/app9112331 · Cited by 112
“For example, see limb movement estimation in [137], neuroprosthesis control in [138], movement intention decoding in [139], hand movement classification in [140], gesture recognition in [141], robotics and guidance in [142], and speech recognition with gestures in [143].”
BackgroundGesture recognition based on surface electromyography ‐feature image
Cheng, Y., Li, G., Yu, M., Jiang, D., Yun, J., Liu, Y., Liu, Y., & Chen, D. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6051 · Cited by 103
Intuitive neuromyoelectric control of a dexterous bionic arm using a modified Kalman filter
George, J. A., Davis, T. S., Brinton, M. R., & Clark, G. A. (2019) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2019.108462 · Cited by 100
Song, W., Han, Q., Lin, Z., Yan, N., Luo, D., Liao, Y., Zhang, M., Wang, Z., Xie, X., Wang, A., et al. (2019) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2019.2953998 · Cited by 101
“The precision of the hand gesture recognition algorithm is highly related to the number of gestures to be classified [40].”
BackgroundNasri, N., Orts‐Escolano, S., & Cazorla, M. (2020) · Sensors · doi:10.3390/s20226451 · Cited by 96
Selectivity and Longevity of Peripheral-Nerve and Machine Interfaces: A Review.
Ghafoor, U., Kim, S., & Hong, K.-S. (2017) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2017.00059 · Cited by 88
“, linear discriminant analysis classifier, tacit learning system, deep learning with convolutional neural network (Adewuyi et al., 2016; Atzori et al., 2016; Fani et al., 2016; Oyama et al., 2016), etc.”
Improved Gesture Recognition Based on sEMG Signals and TCN
Tsinganos, P., Cornelis, B., Cornelis, J. P., Jansen, B., & Skodras, A. N. (2019) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2019.8683239 · Cited by 93
“In [15], a simple model consisting of five blocks of convolutional and average pooling layers resulted in accuracy figures comparable, though not higher, to what was obtained with classical ML methods.”
MethodResultSpiking Neural Network (SNN) With Memristor Synapses Having Non-linear Weight Update
Kim, T.-Y., Hu, S., Kim, J., Kwak, J. Y., Park, J., Lee, S., Kim, I., Park, J., & Jeong, Y. (2021) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2021.646125 · Cited by 93
“…and industrial interests in artificial intelligence (AI) represented by machine learning (ML) was appearing in the various tasks from recognition of images (Liu et al., 2020) and sounds (Jung et al., 2020) to behavioral controls of autonomous cars and robots (Atzori et al., 2016; Gao et al., 2019).”
BackgroundA Human–Machine Interface Using Electrical Impedance Tomography for Hand Prosthesis Control
Wu, Y., Jiang, D., Liu, X., Bayford, R. H., & Demosthenous, A. (2018) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2018.2878395 · Cited by 92
“using support vector machine [16] and neural networks [17]; 4) myoelectric actuator control profiles such as on-off, and proportional schemes [18] as well as grasp force feedback control [19].”
MethodHigh-Density Surface EMG-Based Gesture Recognition Using a 3D Convolutional Neural Network
Chen, J., Bi, S., Zhang, G., & Cao, G. (2020) · Sensors · doi:10.3390/s20041201 · Cited by 98
“The sEMG image was spatially composed of instant values of raw HD-sEMG data according to the arrangement of the electrodes, while the sEMG map was composed of values of time windowed features [7,8,10–13].”
BackgroundMethodReviewing methods of deep learning for intelligent healthcare systems in genomics and biomedicine
Zafar, I., Anwar, S., kanwal, F., Yousaf, W., Nisa, F. U., Kausar, T., Ain, Q. U., Unar, A., Kamal, M. A., Rashid, S., et al. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105263 · Cited by 104
Montazerin, M., Rahimian, E., Naderkhani, F., Atashzar, S. F., Yanushkevich, S. N., & Mohammadi, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-36490-w · Cited by 95
Machine Learning in Electromagnetics With Applications to Biomedical Imaging: A Review
Li, M., Guo, R., Zhang, K., Lin, Z., Yang, F., Xu, S., Chen, X., Massa, A., & Abubakar, A. (2021) · IEEE Antennas and Propagation Magazine · doi:10.1109/map.2020.3043469 · Cited by 93
“Biomedical signal classification is useful in a number of applications, such as the detection of certain diseases [41]–[48], recognition of limb or body movement [49]–[52], mental tasks classification [53], and fall motion detection [14].”
BackgroundTraHGR: Transformer for Hand Gesture Recognition via Electromyography
Zabihi, S., Rahimian, E., Asif, A. A., & Mohammadi, A. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3324252 · Cited by 100
“The window size of 200ms is a well-established value in previous works [5], [6], [14], [23], [32], [33], [59], [60] in sEMG-based hand gesture recognition.”
BackgroundMethodInfluentialA Transfer Learning Model for Gesture Recognition Based on the Deep Features Extracted by CNN
Zou, Y., & Cheng, L. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3098253 · Cited by 89
Duan, N., Liu, L., Yu, X., Li, Q., & Yeh, S. (2018) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2018.09.001 · Cited by 84
Deep Learning on 1-D Biosignals: a Taxonomy-based Survey
Ganapathy, N., Swaminathan, R., & Deserno, T. (2018) · Yearbook of Medical Informatics · doi:10.1055/s-0038-1667083 · Cited by 83
“, [81] proposed to classify the movements of a prosthetic hand using a CNN model.”
Real-time, simultaneous myoelectric control using a convolutional neural network
Ameri, A., Akhaee, M. A., Scheme, E., & Englehart, K. B. (2018) · PLoS ONE · doi:10.1371/journal.pone.0203835 · Cited by 82
Benatti, S., Montagna, F., Kartsch, V., Rahimi, A., Rossi, D., & Luca Benini, C. (2019) · IEEE Transactions on Biomedical Circuits and Systems · doi:10.1109/tbcas.2019.2914476 · Cited by 82
“Recently, a few works have investigated the use of deep neural networks, such as CNN [13] or combinations of CNN and Recurrent Neural Networks (RNN) [38].”
MethodInfluentialBetthauser, J. L., Krall, J. T., Bannowsky, S. G., Levay, G., Kaliki, R. R., Fifer, M. S., & Thakor, N. V. (2020) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2019.2943309 · Cited by 73
“In ideal cases, such as during steady-state muscle contractions, prediction models like linear discriminant analysis [2], support vector machines [3], and spatial convolutional networks [4] can reliably decode many movement class patterns from EMG feature representations [5].”
BackgroundParkinson’s Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer
Zanini, R. A., & Colombini, E. L. (2020) · Sensors · doi:10.3390/s20092605 · Cited by 79
“The protocol includes six repetitions of 49 different actions (plus rest) performed by 40 intact subjects [15].”
BackgroundYang, W. P., Yang, D., Liu, Y., & Liu, H. (2019) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2019.2925191 · Cited by 77
“pattern recognition, and recent studies have verified that a wide variety of hand gestures can be classified precisely using convolutional neural networks (CNNs) [20]–[23].”
Shoulder muscle activation pattern recognition based on sEMG and machine learning algorithms
Jiang, Y., Chen, C., Zhang, X., Chen, C., Zhou, Y. C., Ni, G., Muh, S. J., & Lemos, S. E. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105721 · Cited by 82
Hand medical monitoring system based on machine learning and optimal EMG feature set
Yu, M., Li, G., Jiang, D., Jiang, G., Tao, B., & Chen, D. (2019) · Personal and Ubiquitous Computing · doi:10.1007/s00779-019-01285-2 · Cited by 76
“The selection of features is mainly to reduce the number of features, make the generalization ability of the model stronger, and enhance the understanding between features and eigenvalues [12].”
sEMG-Based Gesture Recognition Using Deep Learning From Noisy Labels
Fatayer, A., Gao, W., & Fu, Y. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3179630 · Cited by 75
“Deep learning methods, such as CNNs, have lately been used in sEMG-based gesture recognition systems [18], [19].”
BackgroundMethodInfluentialLearning Effective Spatial–Temporal Features for sEMG Armband-Based Gesture Recognition
Zhang, Y., Chen, Y., Yu, H., Yang, X., & Wang, L. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2979328 · Cited by 73
“In [16], convolutional neural networks (CNNs) are used as a classifier to control robotic hands naturally via the sEMG signal.”
MethodA Methodological and Structural Review of Hand Gesture Recognition Across Diverse Data Modalities
Shin, J., Miah, A. S. M., Kabir, M. H., Rahim, M., & Shiam, A. A. (2024) · IEEE Access · doi:10.1109/access.2024.3456436 · Cited by 83
“Adhering to the preprocessing methodology out-lined in earlier investigations [173], [239], a 1st-order low-pass Butterworth filter was employed to dampen electrical activity data of muscles.”
MethodRezaee, K., Savarkar, S., Yu, X., & Zhang, J. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103161 · Cited by 72
Exploration of Chinese Sign Language Recognition Using Wearable Sensors Based on Deep Belief Net
Yu, Y., Chen, X. '., Cao, S., Zhang, X., & Chen, X. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2941535 · Cited by 71
“adopted a simplified convolutional neural network to recognize 50 gestures with sEMG signals as the input [14].”
MethodA Global and Local Feature fused CNN architecture for the sEMG-based hand gesture recognition
Xiong, B., Chen, W., Niu, Y., Gan, Z., Mao, G., & Xu, Y. N. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107497 · Cited by 70
Movements Classification of Multi-Channel sEMG Based on CNN and Stacking Ensemble Learning
Shen, S., Gu, K., Chen, X., Yang, M., & Wang, R. (2019) · IEEE Access · doi:10.1109/access.2019.2941977 · Cited by 70
“[9] used a convolutional network to classify an average of 50 handmovements of 67 intact subjects and 11 transradial amputees.”
MethodXceptionTime: Independent Time-Window Xceptiontime Architecture for Hand Gesture Classification
Rahimian, E., Zabihi, S., Atashzar, S. F., Asif, A. A., & Mohammadi, A. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054586 · Cited by 70
“Preprocessing Step Following the proposed preprocessing procedure in the previous studies [4, 5, 8, 10], we adopted a 1 order 1Hz low-pass Butterworth filter to preprocess the electrical activities of muscles.”
MethodInfluentialDeep learning for processing electromyographic signals: A taxonomy-based survey
Buongiorno, D., Cascarano, G. D., Feudis, I. D., Brunetti, A., Carnimeo, L., Dimauro, G., & Bevilacqua, V. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.139 · Cited by 75
BBO-BPNN and AMPSO-BPNN for multiple-criteria inventory classification
Cui, L., Tao, Y., Deng, J., Liu, X., Xu, D., & Tang, G. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114842 · Cited by 70
SeNic: An Open Source Dataset for sEMG-Based Gesture Recognition in Non-Ideal Conditions
Zhu, B., Zhang, D., Chu, Y., Gu, Y.-L., & Zhao, X. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3173708 · Cited by 72
Yang, D., Gu, Y., Thakor, N. V., & Liu, H. (2018) · Experimental Brain Research · doi:10.1007/s00221-018-5441-x · Cited by 70
Selection of Features and Classifiers for EMG-EEG-Based Upper Limb Assistive Devices—A Review
Khan, S. M., Khan, A. A., & Farooq, O. (2019) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2019.2950897 · Cited by 69
“resulted in a higher but comparable classification rate by convolutional neural network techniques as compared to random forest [101].”
ResultLong short-term memory (LSTM) recurrent neural network for muscle activity detection
Ghislieri, M., Cerone, G. L., Knaflitz, M., & Agostini, V. (2021) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-021-00945-w · Cited by 78
From deep learning to transfer learning for the prediction of skeletal muscle forces
Dao, T. T. (2018) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-018-1940-y · Cited by 71
Improved Multi-Stream Convolutional Block Attention Module for sEMG-Based Gesture Recognition
Wang, S., Huang, L., Jiang, D., Sun, Y., Jiang, G., Li, J., Zou, C., Fan, H., Xie, Y., Xiong, H., et al. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.909023 · Cited by 68
“Random Forest (Atzori et al., 2014b) 75.2 Atzori_Net (Atzori et al., 2016) 66.6 Geng_Net (Geng et al., 2016) 77.8 CNN (Du et al., 2017) 79.5 ELM (Cene et al., 2019) 75.1 MSFusionNet (Wei et al., 2019) 85.0 MCBAM-GRU (ours) 89.7 From the comparison of the results in the above table, it is obvious that with the applicat…”
BackgroundMethodInfluentialBurns, A., Adeli, H., & Buford, J. A. (2020) · Journal of Medical Systems · doi:10.1007/s10916-020-01639-x · Cited by 67
“Recent algorithms such as random forest classification [6, 61], particle swarm optimization [2, 55], deep learning [23, 60], and convolutional neural networks [4, 33, 35, 37, 50, 51, 57 – 59] have outperformed earlier methods such as the support vector machine [5, 65], principal component analysis…”
BackgroundMethodInfluentialSimultaneous sEMG Recognition of Gestures and Force Levels for Interaction With Prosthetic Hand
Fang, B., Wang, C., Sun, F., Chen, Z., Shan, J., Liu, H., Ding, W., & Liang, W. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3199809 · Cited by 70
“Reference [26] and [27] transmitted raw sEMG signals as an input vector to a CNN classifier and achieved good results.”
MethodRecent trends and challenges of surface electromyography in prosthetic applications
Yadav, D., & Veer, K. (2023) · Biomedical Engineering Letters · doi:10.1007/s13534-023-00281-z · Cited by 66
Deep Learning in EMG-based Gesture Recognition
Tsinganos, P., Cornelis, B., Cornelis, J. P., Jansen, B., & Skodras, A. N. (2018) · International Conference on Physiological Computing Systems (PhyCS) · doi:10.5220/0006960201070114 · Cited by 71
“Figure 1: The proposed model architecture is based on the work of (Atzori et al., 2016) with modifications that were found to improve the classification accuracy.”
BackgroundMethodInfluentialSurface EMG Pattern Recognition Using Long Short-Term Memory Combined with Multilayer Perceptron
He, Y., Fukuda, O., Bu, N., Okumura, H., & Yamaguchi, N. (2018) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2018.8513595 · Cited by 65
“The recogniton approaches used to be compared with include k-nearest neighbors (KNN), support vector machines (SVM), random forests and convolutional neural network (CNN) [3], [10].”
BackgroundMethodCNN-LSTM and post-processing for EMG-based hand gesture recognition
López, L. I. B., Ferri, F. M., Zea, J. A., Caraguay, Á. L. V., & Benalcázar, M. E. (2024) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2024.200352 · Cited by 77
Rehman, M. Z. U., Gilani, S. O., Waris, A., Niazi, I. K., Slabaugh, G., Farina, D., & Kamavuako, E. N. (2018) · Applied Sciences · doi:10.3390/app8071126 · Cited by 64
A Prosthetic Hand Body Area Controller Based on Efficient Pattern Recognition Control Strategies
Benatti, S., Milosevic, B., Farella, E., Gruppioni, E., & Luca Benini, C. (2017) · Sensors · doi:10.3390/s17040869 · Cited by 62
Gautam, A., Panwar, M., Wankhede, A., Arjunan, S. P., Naik, G. R., Acharyya, A., & Kumar, D. (2020) · IEEE Journal of Translational Engineering in Health and Medicine · doi:10.1109/jtehm.2020.3023898 · Cited by 63
“The recent study by [9] done the analysis on effect of normalization on”
InfluentialClassification of Transient Myoelectric Signals for the Control of Multi-Grasp Hand Prostheses
Kanitz, G., Cipriani, C., & Edin, B. B. (2018) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2018.2861465 · Cited by 61
“Researchers have demonstrated that these classifiers are able to discriminate up to 12 hand/wrist movements from forearm EMGs, with accuracies >95% both offline and in constrained laboratory environments [14]–[17].”
BackgroundPancholi, S., & Joshi, A. M. (2019) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2019.2946536 · Cited by 62
“system [24].”
Data Augmentation of Surface Electromyography for Hand Gesture Recognition
Tsinganos, P., Cornelis, B., Cornelis, J. P., Jansen, B., & Skodras, A. N. (2020) · Sensors · doi:10.3390/s20174892 · Cited by 64
“These are a modified version of the simple model of [13] denoted as AtzoriNet* described in [22], and an implementation of the bigger network of [19] called WeiNet to evaluate how well augmentation works in overparameterized networks.”
BackgroundMethodInfluentialTransfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond
Wu, D., Yang, J., & Sawan, M. (2023) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2023.3295453 · Cited by 62
“We summarize common EMG datasets [6], [48], [51], [108], [109], [110], [111], [112], [113] that could be used for transfer learning and provide dataset statistics in Table I, including task category, number of subjects, number of recording device channel, sampling frequency, number of gesture classes, and correspondin…”
MethodsEMG-based consecutive estimation of human lower limb movement by using multi-branch neural network
Wang, X., Dong, D., Chi, X., Wang, S., Miao, Y., An, M., & Gavrilov, A. I. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102781 · Cited by 60
Extraction of Multi-Labelled Movement Information from the Raw HD-sEMG Image with Time-Domain Depth
Olsson, A. E., Sager, P., Andersson, E., Björkman, A., Malešević, N., & Antfolk, C. (2019) · Scientific Reports · doi:10.1038/s41598-019-43676-8 · Cited by 62
“…our experiments and tested on the same subject, EMR values close to, and sometimes higher than, accuracies of single-label approaches were produced 26,46,47 , despite our method being able to represent many more movements (65 unique movements as demonstrated in this study, and possibly many more…”
He, J., & Jiang, N. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00058 · Cited by 59
R-CNN and wavelet feature extraction for hand gesture recognition with EMG signals
Shanmuganathan, V., Yesudhas, H. R., Khan, M. S., Khari, M., & Gandomi, A. H. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05349-w · Cited by 59
“Currently, these have been focused on deep neural networks that correspond to a model inspired by the brain’s functioning, which analyzes information as a deep framework [17], for example, 5–10 layers of processing for visual information.”
BackgroundEMG-Based Hand Gesture Classification with Long Short-Term Memory Deep Recurrent Neural Networks
Jabbari, M., Khushaba, R. N., & Nazarpour, K. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9175279 · Cited by 64
“Atzori et al. [18] performed classification of 50 hand movements for both intact and trans-radial subjects using a Convolutional Neural Network (CNN) and achieved comparable results to the other methods like SVM, and k-NN.”
Result
Metadata
- Authors
- Atzori, M., Cognolato, M., & Müller, H.
- Affiliations
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- Corresponding author
- Atzori, Manfredo
- Venue
- Frontiers in Neurorobotics
- Publisher
- Frontiers Media SA
- Published
- 2016-09-07
- Volume
- 10
- Pages
- 9-9
- ISSN
- 1662-5218 (ISSN-L)
- PMC
- PMC5013051
- OpenAlex
- W2516710120
- Cited by
- 684
- References
- 71
- Citations by year
- 2026: 53 · 2025: 70 · 2024: 72 · 2023: 92 · 2022: 93 · 2021: 96 · 2020: 77 · 2019: 74 · 2018: 42 · 2017: 15
- FWCI
- 20.96
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Frontiers in Neurorobotics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- ArODES (HES-SO (https://www.hes-so.ch/)) (submittedVersion, cc-by)
- Padua Research Archive (University of Padova) (submittedVersion, cc-by)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (#132700, #160837)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
- Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
- Keywords
- surface electromyography, hand movement classification, prosthetic hand control, convolutional neural networks, transradial amputees, data augmentation, neural network architecture, classification accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
