EMG SİNYALLERİ İLE DERİN ÖĞRENME YÖNTEMLERİNİ KULLANARAK EL/PARMAK HAREKETİ TANIMA

Mehmet İsmail Gürsoy

doi:10.17780/ksujes.1532693

EN TR

HAND/FINGER GESTURE RECOGNITION USING DEEP LEARNING METHODS WITH EMG SIGNALS

Abstract

Electromyography(EMG) signals and hand/finger gesture recognition systems have an important place in fields such as human-computer interaction, virtual reality and prostheses. In recent years, various deep learning methods have been developed for hand/finger gesture recognition with EMG signals. In this study, bioelectric signals containing five finger gesture from 10 different people were used with a 10-channel EMG device obtained from the NinaPRO DB1 dataset. The data was divided into 500 ms long windows and the sliding window method was used at a rate of 70%. Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) deep learning methods were used for hand/finger gesture classification. Accuracy, Precision, Sensitivity and F-score statistical parameters were used to evaluate the performance of the developed models. The developed CNN and LSTM models were repeated 40 times and statistical parameters were obtained. As a result, the system developed with the CNN model showed superior performance with the best classification values of 100% accuracy, 100% precision, 100% sensitivity and 100% F-score. With the LSTM model, 99% accuracy, 98% precision, 98% sensitivity and 98% F-score classification metrics were obtained. The deep learning model presented in this study explains its strong potential and effectiveness in hand/finger gesture recognition or classification with EMG signals.

Keywords

EMG SİNYALLERİ İLE DERİN ÖĞRENME YÖNTEMLERİNİ KULLANARAK EL/PARMAK HAREKETİ TANIMA

Öz

Elektromiyografi (EMG) sinyalleri ile el/parmak hareketi tanıma sistemleri, insan – bilgisayara etkileşimi, sanal gerçeklik ve protezler gibi alanlarda önemli bir yere sahiptir. Son yıllarda, EMG sinyalleri ile el/parmak hareketi tanıma için çeşitli derin öğrenme yöntemleri geliştirilmiştir. Bu çalışmada, NinaPRO DB1 veri setinden alınan 10 kanallı EMG cihazı ile 10 farklı kişiden beş parmak hareketini içeren biyoelektrik sinyaller kullanılmıştır. Veriler 500 ms uzunluğunda pencerelere bölünerek %70 oranında kayan pencere yöntemi kullanılmıştır. El/parmak sınıflandırma için Evrişimli Sinir Ağları (CNN) ve Uzun Kısa Dönem Hafıza (LSTM) derin öğrenme yöntemleri kullanılmıştır. Geliştirilen modellerin performansını değerlendirmek için Doğruluk, Kesinlik, Duyarlılık ve F-skor istatistiksel parametreleri kullanılmıştır. Geliştirilen CNN ve LSTM ile modeller 40 defa tekrar edilerek istatistiksel parametreler elde edilmiştir. Sonuç olarak CNN model ile geliştirilen sistemde; doğruluk %100, Kesinlik %100, Duyarlılık %100 ve F-skor %100 en iyi sınıflandırma değerleri ile üstün performansa sahip olduğunu göstermiştir. LSTM modeli ile de doğruluk %99, Kesinlik %98, Duyarlılık %98 ve F-skor %98 sınıflandırma metrikleri elde edilmiştir. Bu çalışmada sunulan derin öğrenme modeli, EMG sinyalleri ile el/parmak hareketi tanıma veya sınıflandırmada güçlü potansiyel ve etkinliğini açıklamaktadır.

Anahtar Kelimeler

References

Abdelaziz, M. H., Mohamed, W. A., & Selmy, A. S. (2024). Hand Gesture Recognition Based on Electromyography Signals and Deep Learning Techniques. Journal of Advances in Information Technology, 15(2), 255–263. https://doi.org/10.12720/jait.15.2.255-263
Atzori, M., Gijsberts, A., Castellini, C., Caputo, B., Hager, A. G. M., Elsig, S., Giatsidis, G., Bassetto, F., & Müller, H. (2014). Electromyography data for non-invasive naturally-controlled robotic hand prostheses. Scientific Data, 1, 1–13. https://doi.org/10.1038/sdata.2014.53
Bargellesi, N., Carletti, M., Cenedese, A., Susto, G. A., & Terzi, M. (2019). A Random Forest-based Approach for Hand Gesture Recognition with Wireless Wearable Motion Capture Sensors. IFAC-PapersOnLine, 52(11), 128–133. https://doi.org/10.1016/j.ifacol.2019.09.129
Barona López, L. I., Ferri, F. M., Zea, J., Valdivieso Caraguay, Á. L., & Benalcázar, M. E. (2024). CNN-LSTM and post-processing for EMG-based hand gesture recognition. Intelligent Systems with Applications, 22(February), 200352. https://doi.org/10.1016/j.iswa.2024.200352
Benalcázar, M. E., Caraguay, Á. L. V., & López, L. I. B. (2020). A user-specific hand gesture recognition model based on feed-forward neural networks, emgs, and correction of sensor orientation. Applied Sciences (Switzerland), 10(23), 1–21. https://doi.org/10.3390/app10238604
Benalcazar, M. E., Motoche, C., Zea, J. A., Jaramillo, A. G., Anchundia, C. E., Zambrano, P., Segura, M., Benalcazar Palacios, F., & Perez, M. (2018). Real-time hand gesture recognition using the Myo armband and muscle activity detection. 2017 IEEE 2nd Ecuador Technical Chapters Meeting, ETCM 2017, 2017-Janua, 1–6. https://doi.org/10.1109/ETCM.2017.8247458
Chen, X., Li, Y., Hu, R., Zhang, X., & Chen, X. (2021). Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning Method. IEEE Journal of Biomedical and Health Informatics, 25(4), 1292–1304. https://doi.org/10.1109/JBHI.2020.3009383
Chen, Y., Wang, H., Zhang, D., Zhang, L., & Tao, L. (2023). Multi-feature fusion learning for Alzheimer’s disease prediction using EEG signals in resting state. Frontiers in Neuroscience, 17. https://doi.org/10.3389/fnins.2023.1272834

Dobbin, K. K., & Simon, R. M. (2011). Optimally splitting cases for training and testing high dimensional classifiers. BMC Medical Genomics, 4. https://doi.org/10.1186/1755-8794-4-31
Elsayed, R. A., Sayed, M. S., & Abdalla, M. I. (2017). Hand gesture recognition based on dimensionality reduction of histogram of oriented gradients. 2017 Proceedings of the Japan-Africa Conference on Electronics, Communications and Computers, JAC-ECC 2017, 2018-Janua, 119–122. https://doi.org/10.1109/JEC-ECC.2017.8305792
Garcia-Vellisca, M. A., Matran-Fernandez, A., Poli, R., & Citi, L. (2021). Hand-movement Prediction from EMG with LSTM-Recurrent Neural Networks. Pan American Health Care Exchanges, PAHCE, 2021-May. https://doi.org/10.1109/GMEPE/PAHCE50215.2021.9434840
Günay, M., & Alkan, A. (2010). Spektral Yöntemler ve DVM Sınıflandırıcı ile EMG İş aretlerinin Tasnifi Classification of EMG Signals by Spectral Methods and SVM Classifier. KSU Journal of Engineering Sciences, 13(2), 63–69.
Gursoy, M. I. (2024). Biometric Authentication Based on EMG Hand Gestures Signals Using CNN. Elektronika Ir Elektrotechnika, 30(2), 54–62. https://doi.org/10.5755/j02.eie.33777
Gürsoy, M. İ., & Alkan, A. (2022). Investigation Of Diabetes Data with Permutation Feature Importance Based Deep Learning Methods. Karadeniz Fen Bilimleri Dergisi, 12(2), 916–930. https://doi.org/10.31466/kfbd.1174591
Hahne, J. M., Farina, D., Jiang, N., & Liebetanz, D. (2016). A novel percutaneous electrode implant for improving robustness in advanced myoelectric control. Frontiers in Neuroscience, 10(MAR), 1–10. https://doi.org/10.3389/fnins.2016.00114
Hochreiter, S., & Schmindhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1–32.
Icel, Y., Mamis, M. S., Bugutekin, A., & Gursoy, M. I. (2019). Photovoltaic Panel Efficiency Estimation with Artificial Neural Networks: Samples of Adiyaman, Malatya, and Sanliurfa. International Journal of Photoenergy, 2019, 1–12. https://doi.org/10.1155/2019/6289021
Karnam, N. K., Dubey, S. R., Turlapaty, A. C., & Gokaraju, B. (2022). EMGHandNet: A hybrid CNN and Bi-LSTM architecture for hand activity classification using surface EMG signals. Biocybernetics and Biomedical Engineering, 42(1), 325–340. https://doi.org/10.1016/j.bbe.2022.02.005
Li, Z., Zuo, J., Han, Z., Han, X., Sun, C., & Wang, Z. (2020). Intelligent classification of multi-gesture EMG signals based on LSTM. International Conference on Artificial Intelligence and Electromechanical Automation, AIEA 2020, 2020, 62–65. https://doi.org/10.1109/AIEA51086.2020.00020
Lin, Y., Palaniappan, R., De Wilde, P., & Li, L. (2022). Reliability Analysis for Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional Networks. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30, 96–107. https://doi.org/10.1109/TNSRE.2022.3141593
Miron, C., Pasarica, A., Costin, H., Manta, V., Timofte, R., & Ciucu, R. (2019). Hand gesture recognition based on SVM classification. 7th E-Health and Bioengineering Conference, EHB 2019, 2–7. https://doi.org/10.1109/EHB47216.2019.8969921
O’Shea, K., & Nash, R. (2015). An Introduction to Convolutional Neural Networks. http://arxiv.org/abs/1511.08458
Ozdemir, M. A., Kisa, D. H., Guren, O., Onan, A., & Akan, A. (2020). EMG based Hand Gesture Recognition using Deep Learning. 2020 Medical Technologies Congress, TIPTEKNO 2020, 1919, 1–4. https://doi.org/10.1109/TIPTEKNO50054.2020.9299264
Özerdem, M. S., & Bamwenda, J. (2019). Recognition of static hand gesture with using ANN and SVM. DÜMF Mühendislik Dergisi, 10(2), 561–568. https://doi.org/10.24012/dumf.569357
Pallotti, A., Orengo, G., & Saggio, G. (2021). Measurements comparison of finger joint angles in hand postures between an sEMG armband and a sensory glove. Biocybernetics and Biomedical Engineering, 41(2), 605–616. https://doi.org/10.1016/j.bbe.2021.03.003
Saggio, G., Cavallo, P., Ricci, M., Errico, V., Zea, J., & Benalcázar, M. E. (2020). Sign language recognition using wearable electronics: Implementing K-nearest neighbors with dynamic time warping and convolutional neural network algorithms. Sensors (Switzerland), 20(14), 1–14. https://doi.org/10.3390/s20143879
Shanmuganathan, V., Yesudhas, H. R., Khan, M. S., Khari, M., & Gandomi, A. H. (2020). R-CNN and wavelet feature extraction for hand gesture recognition with EMG signals. Neural Computing and Applications, 32(21), 16723–16736. https://doi.org/10.1007/s00521-020-05349-w
Shi, H., Jiang, X., Dai, C., & Chen, W. (2024). EMG-based Multi-User Hand Gesture Classification via Unsupervised Transfer Learning Using Unknown Calibration Gestures. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32, 1119–1131. https://doi.org/10.1109/TNSRE.2024.3372002
Shi, W. T., Lyu, Z. J., Tang, S. T., Chia, T. L., & Yang, C. Y. (2018). A bionic hand controlled by hand gesture recognition based on surface EMG signals: A preliminary study. Biocybernetics and Biomedical Engineering, 38(1), 126–135. https://doi.org/10.1016/j.bbe.2017.11.001
Toro-Ossaba, A., Jaramillo-Tigreros, J., Tejada, J. C., Peña, A., López-González, A., & Castanho, R. A. (2022). LSTM Recurrent Neural Network for Hand Gesture Recognition Using EMG Signals. Applied Sciences (Switzerland), 12(19). https://doi.org/10.3390/app12199700
Tuncer, S. A., & Alkan, A. (2022). Classification of EMG signals taken from arm with hybrid CNN‐SVM architecture. Concurrency and Computation: Practice and Experience, 34(5), 16723–16736. https://doi.org/10.1002/cpe.6746
Wang, H., Yi, H., Peng, J., Wang, G., Liu, Y., Jiang, H., & Liu, W. (2017). Deterministic and probabilistic forecasting of photovoltaic power based on deep convolutional neural network. Energy Conversion and Management, 153, 409–422. https://doi.org/10.1016/j.enconman.2017.10.008
Wang, L., Fu, J., Chen, H., & Zheng, B. (2023). Hand gesture recognition using smooth wavelet packet transformation and hybrid CNN based on surface EMG and accelerometer signal. Biomedical Signal Processing and Control, 86(PB), 105141. https://doi.org/10.1016/j.bspc.2023.105141
Zhang, K., Badesa, F. J., Liu, Y., & Ferre Pérez, M. (2024). Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition. Sensors, 24(11), 1–18. https://doi.org/10.3390/s24113631

Details

Primary Language

Turkish

Subjects

Circuits and Systems

Journal Section

Research Article

Authors

Mehmet İsmail Gürsoy ^*
0000-0002-2285-5160
Türkiye

Publication Date

March 3, 2025

Submission Date

August 13, 2024

Acceptance Date

October 22, 2024

Published in Issue

Year 2025 Volume: 28 Number: 1

DOI

https://doi.org/10.17780/ksujes.1532693

IZ

https://izlik.org/JA34GG62PK

Cite

RIS / Bibtex

APA

Gürsoy, M. İ. (2025). EMG SİNYALLERİ İLE DERİN ÖĞRENME YÖNTEMLERİNİ KULLANARAK EL/PARMAK HAREKETİ TANIMA. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28(1), 179-188. https://doi.org/10.17780/ksujes.1532693

Cited By

Epileptik Nöbet Tespitinde Derin Öğrenme Yaklaşımlarının ve Dalgacık Dönüşümlerinin Rolü

International Journal of Pure and Applied Sciences

https://doi.org/10.29132/ijpas.1748452