Real-Time Hand Gesture Recognition Model Using Deep Learning Techniques and EMG Signals
Abstract
Gesture recognition has multiple applications in medicine, engineering and robotics. It also allows us to develop new and more natural approaches to human-machine interaction. Real-time hand gesture recognition consists of identifying, with no perceivable delay, a given gesture performed by the hand at any moment. In this paper, we propose a model for real-time hand gesture recognition. The proposed model takes as input electromyographic (EMG) signals measured on the forearm, using the commercial sensor Myo Armband. We use an autoencoder for automatic feature extraction, and an artificial feed-forward neural network for classification. The proposed model can recognize the same 5 gestures as the proprietary recognition system of the Myo Armband, achieving an average recognition accuracy of 85.08% ± 15.21%, with an average response time of 3 ± 1 ms. The proposed model is general, which implies that it can recognize the gestures from any user, even when his\her data are not included in the training dataset. Finally, for reproducing this work, we make publicly available the code that implements the proposed model.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Autoencoders are most commonly used for feature extraction and dimensionality reduction.
“As such, autoencoders are most commonly used for feature extraction and dimensionality reduction [120,122,123,124,125,126,133,134,135,136,137,138,139,140,141].”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [136]
Cites
Approximation capabilities of multilayer feedforward networks
Hornik, K. (1991) · Neural Networks · doi:10.1016/0893-6080(91)90009-t · Cited by 6,091 · see citing works
Hand gesture recognition with leap motion and kinect devices
Marin, G., Dominio, F., & Zanuttigh, P. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025313 · Cited by 447 · see citing works
EMG-based hand gesture recognition for realtime biosignal interfacing
Kim, J., Mastnik, S., & André, E. (2008) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/1378773.1378778 · Cited by 222 · see citing works
Hand gesture recognition using machine learning and the Myo armband
Benalcázar, M. E., Jaramillo, A. G., Jonathan, J., Zea, A., Paez, A., & Andaluz, V. H. (2017) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2017.8081366 · Cited by 142 · see citing works
Real-time hand gesture recognition using the Myo armband and muscle activity detection
Benalcázar, M. E., Motoche, C., Zea, J. A., Jaramillo, A. G., Anchundia, C. E., Zambrano, P., Segura, M., Palácios, F., & Pérez, M. (2017) · IEEE Ecuador Technical Chapters Meeting (ETCM) · doi:10.1109/etcm.2017.8247458 · Cited by 124 · see citing works
Hand Motion Recognition from Single Channel Surface EMG Using Wavelet & Artificial Neural Network
Mane, S., Kambli, R., Kazi, F., & Singh, N. M. (2015) · Procedia Computer Science · doi:10.1016/j.procs.2015.04.227 · Cited by 88 · see citing works
Surface Electromyography signal processing and application: a review
Norali, A. N., & Hanafi, M. S. M. (2009) · Cited by 36 · see citing works
Forearm motion discrimination technique using real-time EMG signals
Mizuno, H., TSUJIUCHI, N., & KOIZUMI, T. (2011) · doi:10.1109/iembs.2011.6091100 · Cited by 34 · see citing works
Benatti, S., Rovere, G., Bosser, J., Montagna, F., Farella, E., Glaser, H., Schönle, P., Burger, T., Fateh, S., Huang, Q., et al. (2017) · International Workshop on Advances in Sensors and Interfaces (IWASI) · doi:10.1109/iwasi.2017.7974234 · Cited by 32 · see citing works
Ganiev, A., Shin, H.-S., & Lee, K. (2016) · International Journal of Applied Engineering Research · Cited by 28 · see citing works
Intuitive muscle-gesture based robot navigation control using wearable gesture armband
Luh, G.-C., Lin, H., Ma, Y.-H., & Yen, C. J. (2015) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2015.7340953 · Cited by 27 · see citing works
A portable artificial robotic hand controlled by EMG signal using ANN classifier
Wang, J., Ren, H., Chen, W., & Zhang, P. (2015) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2015.7279744 · Cited by 24 · see citing works
Human-computer interaction system design based on surface EMG signals
Li, H., Chen, X., & Li, P.-F. (2014) · doi:10.1109/icmic.2014.7020734 · Cited by 12 · see citing works
Estimating EMG signals to drive neuromusculoskeletal models in cyclic rehabilitation movements
Tagliapietra, L., Vivian, M., Sartori, M., Farina, D., & Reggiani, M. (2015) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2015.7319174 · Cited by 9 · see citing works
A wireless surface EMG acquisition and gesture recognition system
Wu, Z., & Li, X. (2016) · International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) · doi:10.1109/cisp-bmei.2016.7852985 · Cited by 9 · see citing works
Virtual Rehabilitation System for Fine Motor Skills Using a Functional Hand Orthosis
León, M. A. R., Romero, P. A., Quevedo, W. X., Arteaga, Ó., Terán, C., Benalcázar, M. E., & Andaluz, V. H. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-95282-6_6 · Cited by 7 · see citing works
Gaikwad, V. T., & Sardeshmukh, M. M. (2014) · Cited by 4 · see citing works
Flagged first, then by citations
2 of the 19 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625 · see citing works
“As such, autoencoders are most commonly used for feature extraction and dimensionality reduction [18, 27, 53, 73, 74, 80, 103, 137, 171, 172, 194, 234, 283, 287, 296, 298].”
MethodA survey on deep learning in medicine: Why, how and when?
Piccialli, F., Somma, V. D., Giampaolo, F., Cuomo, S., & Fortino, G. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.09.006 · Cited by 352 · see citing works
Jaramillo, A. G., Benalcázar, M. E., & Mena-Maldonado, E. (2020) · Sensors · doi:10.3390/s20092467 · Cited by 268 · see citing works
“SPS 35 Real-Time Hand Gesture Recognition Model Using Deep Learning Techniques and EMG Signals [85] Conference”
MethodLi, W., Shi, P. A., & Yu, H. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.621885 · Cited by 220 · see citing works
“, 2019), threshold (Chung and Benalcázar, 2019; Yang and Zhang, 2019), and Bayesian Fusion (Khushaba et al.”
BackgroundCNN-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 64 · see citing works
Real-Time Classification of EMG Myo Armband Data Using Support Vector Machine
Tepe, C., & DEMİR, M. C. (2022) · IRBM · doi:10.1016/j.irbm.2022.06.001 · Cited by 56 · see citing works
Tateno, S., Liu, H., & Ou, J. (2020) · Sensors · doi:10.3390/s20205807 · Cited by 48 · see citing works
“On the other hand, although the study of [42] needed only 3 ms, the accuracy is 85.”
BackgroundLópez, L. I. B., Caraguay, Á. L. V., Vimos, V. H., Zea, J. A., Vásconez, J. P., Álvarez, M., & Benalcázar, M. E. (2020) · Sensors · doi:10.3390/s20216327 · Cited by 33 · see citing works
“Feature extraction can be carried out using automatic feature extractors such as convolutional neural networks (CNNs) or autoencoders [29–35].”
BackgroundVásconez, J. P., López, L. I. B., Caraguay, Á. L. V., & Benalcázar, M. E. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106327 · Cited by 31 · see citing works
Deep learning for understanding multilabel imbalanced Chest X-ray datasets
Liz, H., Huertas‐Tato, J., Sánchez-Montañés, M. A., Ser, J. D., & Camacho, D. (2023) · Future Generation Computer Systems · doi:10.1016/j.future.2023.03.005 · Cited by 29 · see citing works
ViT-LLMR: Vision Transformer-based lower limb motion recognition from fusion signals of MMG and IMU
Zhang, H., Yang, K., Cao, G., & Xia, C. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.104508 · Cited by 28 · see citing works
Khan, M. U., Khan, H., Muneeb, M., Abbasi, Z. A., Abbasi, U. B., & Baloch, N. K. (2021) · International Conference on Applied and Engineering Mathematics (ICAEM) · doi:10.1109/icaem53552.2021.9547148 · Cited by 20 · see citing works
“Two phases of data collection were carried out, the first phase is with 2 EMG electrodes and the second is with 4 electrodes and used simplest type flow analysis (TFA) technique of Short-Time Fourier Transform (STFT) [9] employed Yule-Walker technique and Learning Vector Quantization (LVQ) for pattern identification o…”
MethodLee, H., Jiang, M. X., Yang, J., Yang, Z., & Zhao, Q. (2024) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2024.3523943 · Cited by 18 · see citing works
“…such as transfer learning [40], [41], [42], [43], reinforcement learning [37], [38], [39], [50], attention-based model [17], [48], unsupervised learning [44], [45], [58], temporal convolution-based learning [14], [15], [46], [47], [49], multi-view learning [19], and few-shot learning [35].”
Benalcázar, M. E., Caraguay, Á. L. V., & López, L. I. B. (2020) · Applied Sciences · doi:10.3390/app10238604 · Cited by 14 · see citing works
“Moreover, to develop a system with acceptable portability and usability characteristics, it needs to be able to work with limited computational resources [2,7,8].”
BackgroundChen, S.-L., & Huang, L.-W. (2021) · International Journal of Engineering and Technology Innovation · doi:10.46604/ijeti.2021.7342 · Cited by 12 · see citing works
“Similar gesture recognition methods are also investigated in the studies of Pinzón-Arenas et al. [19] and Chung et al. [20].”
ResultMyo Transformer Signal Classification for an Anthropomorphic Robotic Hand
Nunez-Montoya, B., Añazco, E. V., Guerrero, S., Anazco, M. V., Espin-Ramos, D., & Farfán, C. J. (2023) · Prosthesis · doi:10.3390/prosthesis5040088 · Cited by 11 · see citing works
Deep Feature Learning From Electromyographic Signals for Gesture Recognition Systems
Zhong, W., Jiang, X., Szymaniak, K., Jabbari, M., Ma, C., & Nazarpour, K. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3635419 · Cited by 10 · see citing works
“Deep learning models such as fully connected neural networks (FCNNs) [140], MLPs [141], [142], and deep forest (DF) [143], [144] typically process sEMG signals in this unrestricted format.”
Alam, M. S. B., Lameesa, A., Sharmin, S., Afrin, S., Ahmed, S. F., Nikoo, M. R., & Gandomi, A. H. (2025) · Digital Communications and Networks · doi:10.1016/j.dcan.2025.04.001 · Cited by 9 · see citing works
Deep Convolutional Spiking Neural Network Based Hand Gesture Recognition
Ke, W., Xing, Y., Caterina, G. D., Petropoulakis, L., & Soraghan, J. J. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207040 · Cited by 9 · see citing works
Benalcázar, M. E., González, J. L., Jaramillo, A. G., Anchundia, C. E., Zambrano, P., & Segura, M. (2020) · IEEE ANDESCON · doi:10.1109/andescon50619.2020.9271979 · Cited by 8 · see citing works
“A general EMG classification model based on automatic feature extraction using autoencoders is presented in [11].”
MethodInfluentialsEMG-Based Gesture Classifier Through DTW and Enhanced Muscle Activity Detection
Chaves, G. S., Vieira, A. S., & Lima, M. V. S. (2024) · IEEE Access · doi:10.1109/access.2024.3448410 · Cited by 5 · see citing works
“In [29], the authors reported an average recognition accuracy of 85 .”
BackgroundNeamah, H. A., Khudhair, M. A., & Dhaiban, M. S. (2024) · International Power Electronics and Motion Control Conference (EPE-PEMC) · doi:10.1109/pemc61721.2024.10726353 · Cited by 4 · see citing works
“…(ANN) with the MyoWare™ Muscle Sensor (AT-04-001) to classify between 5 hand movements which got an accuracy of 80% or Edison A. Chung et. al study [36], in 2019 that used an artificial feed-forward neural network for the classification with the Myo armband by Thalmic Labs for signal acquisition…”
MethodFarag, H. O., Awad, M. I., Baioumy, A. M., Shawky, A., Taha, A. A., Hassan, A. A., Elqess, Y. A., Ismail, O. I., El-Shazly, B. T., Mohamed, Y. A., et al. (2021) · International Conference on Computer Engineering & Systems (ICCES) · doi:10.1109/icces54031.2021.9686171 · Cited by 4 · see citing works
Hand Sign Recognition using Deep Convolutional Neural Network
Naveenkumar, M., Srithar, S., Kalyan, G. R., Vetrimani, E., & Alagumuthukrishnan, S. (2022) · International Conference on Inventive Research in Computing Applications (ICIRCA) · doi:10.1109/icirca54612.2022.9985691 · Cited by 4 · see citing works
“The system can recognize the system with five gestures and an average recognition rate of 85.08 percent accuracy with an average response time of three milliseconds [19].”
BackgroundInfluentialAnbalagan, N., Akilandeswari, J., Mathangi, P. R., Kavya, P., Prabhu, S. D., & Kumar, V. A. (2023) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc57686.2023.10192582 · Cited by 3 · see citing works
“An efficient hand-gesture based browsing system[5] was built for radiologist-surgeons by utilizing two individual neural network, denoising autoencoder[9] and convolution neural network.”
MethodInfluentialA Control System of SEMG Signal Based on Deep Learning
(2020) · International Journal of Circuits Systems and Signal Processing · doi:10.46300/9106.2020.14.52 · Cited by 3 · see citing works
CAN: Communicator Assistance Network for Deaf-Dumb-Blind People
Deekshitulu, A. T. R. S., Cheethirala, A. V., Phutke, R., Bhargav, A., Gupta, V. K., & Prakash, S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10725466 · Cited by 3 · see citing works
Gupta, A., Kumar, S., & Kumar, S. (2023) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405620666230530093026 · Cited by 3 · see citing works
Raw sEMG-based Real-time Gesture Recognition with Recurrent Neural Networks
Wang, Y., Xue, J., & Duan, F. (2021) · International Conference on Robotics and Automation Engineering (ICRAE) · doi:10.1109/icrae53653.2021.9657777 · Cited by 2 · see citing works
Bastidas, C. G., Pérez, K. A., Caraguay, Á. L. V., López, L. I. B., & Benalcázar, M. E. (2024) · IEEE Latin American Conference on Computational Intelligence (LA-CCI) · doi:10.1109/la-cci62337.2024.10814786 · Cited by 2 · see citing works
Towards Discriminant Analysis Classifiers Using Online Active Learning via Myoelectric Interfaces
Jaramillo, A. G., Benalcázar, M. E., Sardiña, S., & Zambetta, F. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20658 · Cited by 2 · see citing works
“We use five sEMG datasets that are: NinaPro5 (Atzori et al. 2014; Pizzolato et al. 2017), CapgMyo dbb (Du et al. 2017), MyoArmband (Cˆot´e-Allard et al. 2019), Long-Term 3DC (Cote-Allard et al. 2021), and EMG-EPN-120 (Chung and Benalc´azar 2019).”
MethodKhorram, A., Lin, H., & Peng, W. (2024) · International Conference on Industrial, Manufacturing, and Process Engineering (ICIMP) · doi:10.3390/engproc2024076052 · Cited by 2 · see citing works
Santillán, L. G. M., Zea, J. A., López, L. I. B., Caraguay, Á. L. V., & Benalcázar, M. E. (2025) · Mathematical and Computational Applications · doi:10.3390/mca30050101 · Cited by 1 · see citing works
“According to Chung et al. in their research [32] used ANN to achieve a accuracy recognition of 85.08 ± 15.21%.”
InfluentialShukla, P. K., Abbas, J. K. K., Ali, I. R., & Ansari, M. S. (2023) · IEEE International Conference on Innovations in High Speed Communication and Signal Processing (IHCSP) · doi:10.1109/ihcsp56702.2023.10127181 · Cited by 1 · see citing works
RetractedDíaz, D., Benalcázar, M. E., López, L. I. B., & Caraguay, Á. L. V. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-33258-6_34 · Cited by 1 · see citing works
Brain tumour detection using deep learning
Balajee, A., Bharat, Mounica, N., & Mandava, S. (2024) · AIP conference proceedings · doi:10.1063/5.0189795 · Cited by 1 · see citing works
Sakinala, U. C., & Abinaya, S. (2025) · IEEE Access · doi:10.1109/access.2025.3559182 · Cited by 1 · see citing works
“Similarly, [9] achieved an accuracy of 85.08% with a model aimed at real-time hand gesture recognition for applications that include VR or prosthetic control.”
InfluentialAssessing the Influence of Lstm and Post-Processing in Cnn Based Hand Gesture Recognition Using EmgPreprint
Barona, L., Ferri, F. M., Zea, J. A., Valdivieso, Á., & Benalcázar, M. E. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4670147
Parlak, E., & Başpınar, U. (2024) · Gazi Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi · doi:10.17341/gazimmfd.1135737
Shah, M. A., Arbab, M. A., KHAN, S., & Ullah, A. (2025) · Research Square · doi:10.21203/rs.3.rs-6268608/v1
Çetin, E., İlayda, K. A. Y. A., Erat, K., & Durdu, P. O. (2025) · Karadeniz Fen Bilimleri Dergisi · doi:10.31466/kfbd.1553565
Online hand gesture recognition by sEMG: a system for Myo armband based on machine learning
Carneiro, M. T., Inafuco, A. T. P., Lourenção, J. P. M., Dias, T. S., Campos, D. P., & Mendes, J. J. A. (2025) · Research on Biomedical Engineering · doi:10.1007/s42600-025-00426-2
“Myo was chosen due to its use in several works that employ gesture recognition with sEMG signals (Tepe and Demir (2022); Kobylarz et al. (2020); Chung and Benalcázar (2019); Raurale et al. (2019)).”
Mathew, A., & Rajalakshmy, P. (2025) · Multimedia Tools and Applications · doi:10.1007/s11042-025-21071-y
“Out of those, EMG sensors are mostly employed because they will not be affected by the hand orientation, location, and the light differences [ 8, 9].”
EMG-Based Fatigue Detection System for Robotic Collaboration: A Deep Learning Approach
Debache, M., Hatem, Y., Benahmed, S., & Akli, I. (2025) · International Conference on Pattern Analysis and Intelligent Systems (PAIS) · doi:10.1109/pais66004.2025.11126517
“[8] highlight the importance of dataset preprocessing and validation techniques in ensuring robust performance.”
Comparative Machine Learning Models for Sign Language Detection
Dwivedi, A., Nithya, P., & Goenka, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6906-6_14
Vijay, M., Nagavenkat, N., Reddy, Y. V. S., Sree, K. K., Tejasree, M., & Gobika, K. (2025) · International Conference on Sustainable Computing and Smart Systems (ICSCSS) · doi:10.1109/icscss64956.2025.11500788
“Khamis and Khedher [8] demonstrated the viability of real-time gesture recognition using deep neural networks.”
HAND GESTURE RECOGNITION FOR EMG SIGNAL BASED ON DIFFERENT MACHINE LEARNING METHODS
Alhade, B. A. (2026) · Journal of Digital Security and Forensics · doi:10.29121/digisecforensics.v3.i1.2026.99
- Authors
- Chung, E. A., & Benalcazar, M. E.
- Affiliations
- National Polytechnic School (EC)
- Venue
- 2019 27th European Signal Processing Conference (EUSIPCO)
- Publisher
- IEEE
- Published
- 2019-09
- Pages
- 1-5
- OpenAlex
- W2984329907
- Cited by
- 47
- References
- 19
- Citations by year
- 2026: 1 · 2025: 11 · 2024: 9 · 2023: 9 · 2022: 4 · 2021: 5 · 2020: 8
- FWCI
- 3.44
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- European Signal Processing Conference (EUSIPCO) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- hand gesture recognition, real-time recognition, electromyography, Myo armband, autoencoder feature extraction, feedforward neural networks, human-machine interaction
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
