Makine öğrenmesi algoritmaları kullanılarak elektromiyografi tabanlı el hareketi sınıflandırması ve özellik çıkarımı

Öz

El hareketlerinin sınıflandırılması özellikle ortez ve protez kontrolü, insan-makine etkileşimi ve telerehabilitasyon uygulamaları için önem arz etmektedir. Görüntü işleme tekniklerine dayalı hareket analizi yöntemleri ile el hareketlerinin belirlenmesi uzun yıllardır uygulanmaktadır. Günümüzde üzerinde durulan araştırma alanlarından biri kas kasılmasından faydalanarak el hareketlerinin belirlenmesidir. Son yıllarda el ve kol kaslarından alınan sEMG (yüzey elektromiyografi) verileri yardımıyla el hareketlerinin sınıflandırılması üzerine çalışmalar hız kazanmıştır. Bizim çalışmamızda 4 gönüllü katılımcı üzerinden toplanan Ekstansör digitorum ve Fleksör carpi radialis kaslarının EMG verileri kullanılarak elin açık (parmakların ekstansiyonu) ve kapalı (parmakların fleksiyonu) konumları tahmin edilmiştir. EMG sinyallerini doğru bir şekilde ayırt etmek için varyans, standart sapma, kök ortalama kare, ortalama enerji, minimum ve maksimum özellikler gibi çeşitli istatistiksel ölçütler kullanılmıştır. Bu ilave özelliklerle birlikte elde edilen veri seti Destek Vektör Makinesi (SVM), K-En Yakın Komşu (KNN), Karar Ağacı (DT) ve Gaussian Naive Bayes (GNB) algoritmalarına uygulanmış ve elin açık-kapalı konumları sınıflandırılmıştır. Sınıflandırma başarısı en yüksek algoritmanın SVM (max. 73.1%), en düşük algoritmanın ise KNN (min. 55.9%) olduğu görülmüştür. Gelecekteki çalışmalarda tahmin doğruluğunu daha da artırmak için daha fazla kas grubundan veri toplanması önerilmektedir.

Anahtar Kelimeler

• EMG
• el kasları
• ikili sınıflandırma
• destek vektör makineleri

Electromyography based hand movement classification and feature extraction using machine learning algorithms

Öz

The categorization of hand gestures holds significant importance in controlling orthotic and prosthetic devices, enabling human-machine interaction, and facilitating telerehabilitation applications. For many years, methods of motion analysis based on image processing techniques have been employed to detect hand motions. However, recent research has focused on utilizing muscle contraction for detecting hand movements. Specifically, there has been an increase in studies that classify hand movements using surface electromyography (sEMG) data from the muscles of the hand and arm. In our study, we estimated the open (extension of the fingers) and closed (flexion of the fingers) positions of the hand by analyzing EMG data obtained from 4 volunteer participants' Extensor digitorum and Flexor carpi radialis muscles. In order to accurately discriminate EMG signals, various statistical measures such as variance, standard deviation, root mean square, average energy, minimum and maximum features were utilized. The dataset containing these additional features was then subjected to classification algorithms including Support Vector Machines (SVM), K Nearest Neighbour (KNN), Decision Tree (DT), and Gaussian Naive Bayes (GNB) for the purpose of classifying hand positions into open or closed states. Among the tested algorithms, SVM achieved the highest success rate with a maximum accuracy of 73.1%, while KNN yielded the lowest success rate at a minimum accuracy of 55.9%. To further enhance prediction accuracy in future studies, it is suggested that data from a larger set of muscles be collected.

Anahtar Kelimeler

• EMG
• hand mucle
• binary classification
• support vector machines (SVM)

Kaynakça

1. [1] Kang S., Kim H., Park C., Sim Y., Lee S. and Jung Y., “sEMG-Based Hand Gesture Recognition Using Binarized Neural Network”, Sensors, 23(3): 1436, (2023).
2. [2] Jarosz J., Gołaś A., Krzysztofik M., Matykiewicz P., Strońska K., Zając A. and Maszczyk A., “Changes in muscle pattern activity during the asymmetric flat bench press (offset training)”, International Journal of Environmental Research and Public Health, 17(11): 3912, (2020).
3. [3] Borysiuk Z., Blaszczyszyn M., Piechota K., Konieczny M. and Cynarski W.J., “Correlations between the EMG Structure of Movement Patterns and Activity of Postural Muscles in Able-Bodied and Wheelchair Fencers”, Sensors, 23(1): 135, (2022).
4. [4] Xie Z., “Fatigue Monitoring and Recognition During Basketball Sports via Physiological Signal Analysis”, International Journal of Information System Modeling and Design, 13(2): 1-11, (2022).
5. [5] Phillips D.A., Del Vecchio A.R., Carroll K. and Matthews E.L., “Developing a Practical Application of the Isometric Squat and Surface Electromyography”, Biomechanics, 1(1): 145-151, (2021).
6. [6] Jochumsen M., Niazi I.K., Zia ur Rehman M., Amjad I., Shafique M., Gilani S.O., and Waris A., “Decoding attempted hand movements in stroke patients using surface electromyography”, Sensors, 20(23): 6763, (2020).
7. [7] Fu Y.L., Liang K.C., Song W. and Huang J., “A hybrid approach to product prototype usability testing based on surface EMG images and convolutional neural network classification”, Computer Methods and Programs in Biomedicine, 221: 106870, (2022).
8. [8] Karnam N.K., Dubey S.R., Turlapaty A.C., and Gokaraju B., “EMGHandNet: A hybrid CNN and Bi-LSTM architecture for hand activity classification using surface EMG signals”, Biocybernetics and biomedical engineering, 42(1): 325-340, (2022).

9. [9] Sahu P., Singh B. K. and Nirala N., “An improved feature selection approach using global best guided Gaussian artificial bee colony for EMG classification”, Biomedical Signal Processing and Control, 80: 104399, (2023).
10. [10] Fajardo J.M., Gomez O. and Prieto F., “EMG hand gesture classification using handcrafted and deep features”, Biomedical Signal Processing and Control, 63: 102210, (2021).
11. [11] Tepe C. and Demir M.C., “Real-Time Classification of EMG Myo Armband Data Using Support Vector Machine” IRBM, 43(4): 300-308, (2022).
12. [12] Klein Breteler M.D., Simura K.J. and Flanders M., “Timing of muscle activation in a hand movement sequence”, Cerebral Cortex, 17(4): 803-815, (2007).
13. [13] Khushaba R.N, Kodagoda S., Takruri M. and Dissanayake G., “Toward improved control of prosthetic using surface electromyogram (EMG) signals” Expert Systems with Applications 39:10731-10738, (2012).
14. [14] Roldan-Vasco S., Orozco-Duque A. and Orozco-Arroyave J.R., “Swallowing disorders analysis using surface EMG biomarkers and classification models”, Digital Signal Processing, 133: 103815, (2023).
15. [15] Torres-Castillo J.R., Lopez-Lopez C.O. and Padilla-Castaneda M.A., “Neuromuscular disorders detection through time-frequency analysis and classification of multi-muscular EMG signals using Hilbert-Huang transform”, Biomedical Signal Processing and Control, 71: 103037, (2022).
16. [16] Putra D.S. and Weru Y.U.W., “Pattern recognition of electromyography (EMG) signal for wrist movement using learning vector quantization (LVQ)”, In IOP Conference Series: Materials Science and Engineering, 50681):, p. 012020, (2019).
17. [17] López L.I.B., Caraguay Á.L.V., Vimos V.H., Zea J.A., Vásconez J.P., Álvarez M. and Benalcázar M.E., “An energy-based method for orientation correction of EMG bracelet sensors in hand gesture recognition systems”, Sensors, 20(21): 6327, (2020).
18. [18] Kısa D.H., Özdemir M.A., Güren O. and Alaybeyoğlu, A., “A decision-making mechanism based on EMG signals and adaptive neural fuzzy inference system (ANFIS) for hand gesture prediction”, Journal of the Faculty of Engineering and Architecture of Gazi University, 38(3): 1417-1430, (2023).
19. [19] Vapnik V.N., “The nature of statistical learning theory”, Springer science & business media, (2000).
20. [20] Yiğit H., Köylü H. and Eken, S., “Estimation of road surface type from brake pressure pulses of ABS”, Expert Systems with Applications, 212: 118726, (2023).
21. [21] Ay Ş., Ekinci E. and Garip Z., “A comparative analysis of meta-heuristic optimization algorithms for feature selection on ML-based classification of heart-related diseases”, The Journal of Supercomputing, 1-30, (2023).
22. [22] Şengür D., “EEG, EMG and ECG based determination of psychosocial risk levels in teachers based on wavelet extreme learning machine autoencoders”, Politeknik Dergisi, 25(3): 985-989, (2022).
23. [23] Cica D., Sredanovic B., Tesic S. and Kramar, D., “Predictive modeling of turning operations under different cooling/lubricating conditions for sustainable manufacturing with machine learning techniques”, Applied Computing and Informatics, 1-19, (2020).
24. [24] Atban F., Ekinci E. and Garip Z., “Traditional machine learning algorithms for breast cancer image classification with optimized deep features”, Biomedical Signal Processing and Control, 81: 104534, (2023).
25. [25] Han J., “System optimization of talent Life cycle management platform based on decision tree model”, Journal of Mathematics, 2022: 1-12, (2022).
26. [26] Latash M.L., “Muscle coactivation: definitions, mechanisms, and functions”, Journal of neurophysiology, 120(1): 88-104, (2018).