Klasifikasi Gerakan Tangan Berbasis Sinyal sEMG Menggunakan Deep Learning
DOI:
https://doi.org/10.26418/jp.v11i1.88663Keywords:
sEMG, klasifikasi gerakan, deep learning, 1D CNN, MLPAbstract
Penelitian ini mengkaji penggunaan sinyal elektromiografi permukaan (sEMG) untuk klasifikasi 10 jenis gerakan tangan menggunakan klasifikasi berbasis pembelajaran mesin. Dalam penelitian ini, sebuah metode berbasis deep learning, Convolutional Neural Network satu dimensi (1D CNN) dengan fitur yang diekstraksi secara otomatis, dibandingkan dengan kinerja sebuah Multi-Layer Perceptron (MLP) dengan ekstraksi fitur manual berbasis domain waktu. Penggunaan CNN dan MLP dalam klasifikasi sinyal sEMG dilakukan untuk mengetahui efektivitas penggunaan fitur otomatis dan yang diekstraksi secara manual. Dataset yang digunakan mencakup 10 gerakan tangan yang dilakukan sebanyak 5 kali repetisi dan direkam dari 40 partisipan dengan jumlah total adalah 2000 data. Proses penelitian meliputi pre-processing, ekstraksi fitur, klasifikasi, dan evaluasi. Hasil menunjukkan bahwa 1D CNN memberikan akurasi pengujian terbaik sebesar 78% dengan skenario pelatihan yang memanfaatkan early stopping. Sebaliknya, MLP mencapai akurasi tertinggi sebesar 61,5% dengan pengaturan learning rate optimal. Performa superior 1D CNN dibandingkan MLP terutama disebabkan oleh kemampuannya melakukan ekstraksi fitur secara otomatis tanpa tergantung pada seleksi fitur manual, yang menjadi faktor kunci pada MLP. Penelitian ini mengindikasikan bahwa 1D CNN lebih efektif untuk klasifikasi sinyal sEMG dalam pengembangan teknologi asistif, khususnya untuk pengenalan gerakan tangan. Hasil ini memberikan kontribusi signifikan dalam pengembangan aplikasi berbasis sEMG, seperti teknologi rehabilitasi dan antarmuka mesin-manusia, dengan potensi meningkatkan akurasi dan efisiensi sistem yang dihasilkan.References
J. O. Pinzón-Arenas, R. Jiménez-Moreno, and A. Rubiano, “Percentage estimation of muscular activity of the forearm by means of EMG signals based on the gesture recognized using CNN,†Sens. Bio-Sensing Res., vol. 29, no. February, p. 100353, 2020, doi: 10.1016/j.sbsr.2020.100353.
M. del Olmo and R. Domingo, “EMG Characterization and Processing in Production Engineering,†Materials (Basel)., vol. 13, no. 24, 2020.
D. Wu, J. Yang, and M. Sawan, “Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond,†IEEE Trans. Neural Syst. Rehabil. Eng., vol. 31, pp. 3015–3034, 2023, doi: 10.1109/TNSRE.2023.3295453.
N. Nasri, S. Orts-Escolano, and M. Cazorla, “An semg-controlled 3d game for rehabilitation therapies: Real-time time hand gesture recognition using deep learning techniques,†Sensors (Switzerland), vol. 20, no. 22, pp. 1–12, 2020, doi: 10.3390/s20226451.
A. Sadiq, S. G. Khawaja, M. U. Akram, N. S. Alghamdi, A. Khan, and A. Shaukat, “Machine Learning and Signal Processing Based Analysis of sEMG Signals for Daily Action Classification,†IEEE Access, vol. 10, pp. 40506–40516, 2022, doi: 10.1109/ACCESS.2022.3166885.
X. Song, S. S. Van De Ven, L. Liu, F. J. Wouda, H. Wang, and P. B. Shull, “Activities of Daily Living-Based Rehabilitation System for Arm and Hand Motor Function Retraining after Stroke,†IEEE Trans. Neural Syst. Rehabil. Eng., vol. 30, pp. 621–631, 2022, doi: 10.1109/TNSRE.2022.3156387.
L. I. Barona López, F. M. Ferri, J. Zea, Ã. L. Valdivieso Caraguay, and M. E. Benalcázar, “CNN-LSTM and post-processing for EMG-based hand gesture recognition,†Intell. Syst. with Appl., vol. 22, no. March, p. 200352, 2024, doi: 10.1016/j.iswa.2024.200352.
Z. Li, K. Li, and N. Wei, “A sEMG-Based Hand Gesture Recognition Using Mulit-channel CNN and MLP,†Proc. - 2020 13th Int. Congr. Image Signal Process. Biomed. Eng. Informatics, CISP-BMEI 2020, no. 62073195, pp. 867–871, 2020, doi: 10.1109/CISP-BMEI51763.2020.9263646.
A. Turgunov, K. Zohirov, A. Ganiyev, and B. Sharopova, “Defining the Features of EMG Signals on the Forearm of the Hand Using SVM, RF, k-NN Classification Algorithms,†2020 Inf. Commun. Technol. Conf. ICTC 2020, pp. 260–264, 2020, doi: 10.1109/ICTC49638.2020.9123287.
D. C. Toledo-Perez, M. Aviles, R. A. Gomez-Loenzo, and J. Rodriguez-Resendiz, “Feature Set to sEMG Classification Obtained with Fisher Score,†IEEE Access, vol. 12, no. November 2023, pp. 13962–13970, 2024, doi: 10.1109/ACCESS.2024.3353044.
M. A. Ozdemir, D. H. Kisa, O. Guren, A. Onan, and A. Akan, “EMG based Hand Gesture Recognition using Deep Learning,†TIPTEKNO 2020 - Tip Teknol. Kongresi - 2020 Med. Technol. Congr. TIPTEKNO 2020, no. 1919, pp. 3–6, 2020, doi: 10.1109/TIPTEKNO50054.2020.9299264.
S. Kiranyaz, O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman, “1D convolutional neural networks and applications: A survey,†Mech. Syst. Signal Process., vol. 151, p. 107398, 2021, doi: 10.1016/j.ymssp.2020.107398.
O. Cheikhrouhou, R. Mahmud, R. Zouari, M. Ibrahim, A. Zaguia, and T. N. Gia, “One-Dimensional CNN Approach for ECG Arrhythmia Analysis in Fog-Cloud Environments,†IEEE Access, vol. 9, pp. 103513–103523, 2021, doi: 10.1109/ACCESS.2021.3097751.
A. A. Ahmed, W. Ali, T. A. A. Abdullah, and S. J. Malebary, “Classifying Cardiac Arrhythmia from ECG Signal Using 1D CNN Deep Learning Model,†Mathematics, vol. 11, no. 3, pp. 1–16, 2023, doi: 10.3390/math11030562.
K. D. Manalo, N. B. Linsangan, and J. L. Torres, “Classification of Myoelectric Signals Using Multilayer Perceptron Neural Network with Back Propagation Algorithm in a Wireless Surface Myoelectric Prosthesis,†Int. J. Inf. Educ. Technol., vol. 6, no. 9, pp. 686–690, 2016, doi: 10.7763/ijiet.2016.v6.774.
S. Savalia and V. Emamian, “Cardiac arrhythmia classification by multi-layer perceptron and convolution neural networks,†Bioengineering, vol. 5, no. 2, 2018, doi: 10.3390/bioengineering5020035.
Y. Narayan, “Motor-imagery based EEG signals classification using MLP and KNN classifiers,†Int. J. Eng. Trends Technol., vol. 69, no. 1, pp. 121–125, 2021, doi: 10.14445/22315381/IJETT-V69I1P219.
W. Ke, Y. Xing, G. Di Caterina, L. Petropoulakis, and J. Soraghan, “Intersected EMG Heatmaps and Deep Learning Based Gesture Recognition,†ACM Int. Conf. Proceeding Ser., pp. 73–78, 2020, doi: 10.1145/3383972.3383982.
D. Kumar and A. Ganesh, “A Critical Review on Hand Gesture Recognition using sEMG: Challenges, Application, Process and Techniques,†J. Phys. Conf. Ser., vol. 2327, no. 1, 2022, doi: 10.1088/1742-6596/2327/1/012075.
J. Naskath, G. Sivakamasundari, and A. A. S. Begum, “A Study on Different Deep Learning Algorithms Used in Deep Neural Nets: MLP SOM and DBN,†Wirel. Pers. Commun., vol. 128, no. 4, pp. 2913–2936, 2023, doi: 10.1007/s11277-022-10079-4.
M. A. Ozdemir, D. H. Kisa, O. Guren, and A. Akan, “Dataset for multi-channel surface electromyography (sEMG) signals of hand gestures,†Data Br., vol. 41, 2022, doi: 10.1016/j.dib.2022.107921.
M. A. Ozdemir, D. H. Kisa, O. Guren, and A. Akan, “Dataset for multi-channel surface electromyography (sEMG) signals of hand gestures,†Mendeley Data, V2, 2021, doi: 10.17632/ckwc76xr2z.2.
O. Ali, M. Saif-ur-Rehman, T. Glasmachers, I. Iossifidis, and C. Klaes, “ConTraNet: A hybrid network for improving the classification of EEG and EMG signals with limited training data,†Comput. Biol. Med., vol. 168, no. November 2023, p. 107649, 2024, doi: 10.1016/j.compbiomed.2023.107649.
