Klasifikasi Gelombang Otot Lengan Pada Robot Manipulator Menggunakan Support Vector Machine

Muhammad Ja'far Ubaidillah; Ii Munadhif; Noorman Rinanto

doi:10.21107/rekayasa.v12i2.5406

Klasifikasi Gelombang Otot Lengan Pada Robot Manipulator Menggunakan Support Vector Machine

Muhammad Ja'far Ubaidillah, Ii Munadhif, Noorman Rinanto

Abstract

Teknologi robotika semakin berkembang. Banyak orang berinovasi untuk membantu aktivitas mereka, diantaranya membuat robot manipulator untuk mengambil barang di tempat berbahaya atau memindah barang dengan presisi yang sangat tinggi. Pada penelitian ini telah dirancang robot manipulator untuk membantu pasien yang diamputasi pergelangan tangannya agar dapat memegang dan tidak memegang. Sensor Electromyography (EMG) dapat merekam aktivitas listrik yang dihasilkan oleh otot rangka dalam bentuk sinyal yang mempresentasikan gerakan otot. Pada penelitian ini, elektromiogram diekstraksi untuk mendapatkan fitur Root Mean Square (RMS) dan Mean Absolute Value (MAV) kemudian diklasifikasi menggunakan Support Vector Machine (SVM). Metode SVM dipilih karena mampu menemukan hyperplane terbaik sebagai pemisah. Pengendali yang digunakan adalah Arduino yang memerintahkan motor servo untuk menggerakkan robot manipulator sesuai dengan hasil klasifikasi. Penerapan metode Support Vector Machine (SVM) yang bertipe linier memiliki akurasi yang cukup baik dengan keberhasilan 80% pada pengujian dengan subjek yang telah diambil data sampel dan keberhasilan 60% pada pengujian dengan subjek yang tidak diambil data sampel.

Classification of Muscle Wave Arm on Manipulator Robot Using Support Vector Machine

ABSTRACT

Robotics technology is growing. Many people innovate to help their activities, including making manipulator robots to take items in dangerous places or move items with very high precision. In this study a manipulator robot was designed to help patients who amputated their wrists to grip and un-grip. Electromyography (EMG) sensors can record electrical activity produced by skeletal muscles in the form of signals that present muscle movements. In this study, the electromyogram was extracted to get the Root Mean Square (RMS) and Mean Absolute Value (MAV) features then classified using Support Vector Machine (SVM). The SVM method was chosen because it was able to find the best hyperplane as a separator. The controller used is Arduino which instructs the servo motor to move the manipulator robot according to the classification results. The application of the Support Vector Machine (SVM) method which has a linear type has a fairly good accuracy with 80% success in testing with subjects who have taken sample data and 60% success in testing with subjects who are not taken sample data.

Keywords: EMG Sensor, Arm Muscle, MAV, RMS, SVM, Classification.

Keywords

Sensor EMG; Otot Lengan; MAV; RMS; SVM; Klasifikasi

Full Text:

PDF (Bahasa Indonesia)

References

Bhavsar, H., Mahesh H. P. (2012).”Review on Support Vector Machine for Data Classification”. Vol 1, Issue 10.

Falih, A. D. I. (2017).“Klasifikasi Sinyal EMG Dari Otot Lengan Sebagai Media Kontrol Menggunakan Naïve Bayes” (Tesis). Surabaya. Institut Teknologi Sepuluh Nopember.

Fiska, R. R. (2017). Penerapan Teknik Data Mining dengan Metode Support Vector Machine (SVM) untuk Memprediksi Siswa yang Berpeluang Drop Out. Jaringan Sistem Informasi Robotik Vol. 1,No. 01, 42-51.

Lee, J., Kim J., Park J. (2013). "Classification of grip configuration using surface EMG", in 2013 13th International Conference on Control, Automation and Systems (ICCAS 2013).

Muis, I. A., Muhammad A. (2015). “Penerapan Metode Support Vector Machine (SVM) Menggunakan Kernel Radial Basis Function (RBF) Pada Klasifikasi Tweet”, Vol.12 No.2

Mustiadi, I., Thomas S. W., Indah S., (2012). “Analisis Ekstraksi Ciri Sinyal EMG Menggunakan Wavelet Discrete Transform”, Yogyakarta.

Nugraha, D.W. (2011). "Pengendalian Robot Yang Memiliki Lima Derajat Kebebasan", Ilmiah Foristek, 1(1): p. 22.

Padillah, H. A., Arif G., Wahyuni K. (2013). “Kontrol Wireless Bionik Robot Jari Tangan Menggunakan Arduino”, Vol I, No. 2.

Paul, Y., Goyal V., Jaswal R.A. (2017). "Comparative analysis between SVM & KNN classifier for EMG signal classification on elementary time domain features", in 2017 4th International Conference on Signal Processing, Computing and Control (ISPCC).

Phinyomark, A., Phukpattaranont P., Limsakul C. (2012). "Feature Reduction and Selection for EMG Signal Classification", Vol. 39. 7420–7431.

Rahman, M.M., Rosly M.H.M. (2016). "Gripping Motion of Artificial Hand Using EMG Signal", in 2016 International Conference on Computer and Communication Engineering (ICCCE).

Rekhi, N. S., Arora A. S., Singh S., Singh D. (2009). "Multi-Class SVM Classification of Surface EMG Signal for Upper Limb Function", in 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

Rusmanto. (2016). “Akuisisi Data Sinyal EMG di Lengan Tangan dengan Sensor Surface Electrode Menggunakan Mikrokontroler Arduino Uno” (Tugas Akhir). Semarang: Universitas Dian Nuswantoro.

She, Q., Luo Z., Meng M. Xu P. (2010). "Multiple kernel learning SVM-based EMG pattern classification for lower limb control", in 2010 11th International Conference on Control Automation Robotics & Vision.

Subhash, K.M., Pournami P.N., Joseph P.K. (2017). "Census transform based feature extraction of EMG signals for neuromuscular disease classification", in 2017 IEEE 15th Student Conference on Research and Development (SCOReD).

Wibawa, A. D., Verdonschot N., Burgerhof J. G. M., Purnama I. K. E., Andersen M. S., Halbertsma J. P. K., Diercks R. L., Verkerke G. J. (2013) "A validation study on muscle activity prediction of a lower limb musculoskeletal model using EMG during normal walking", in 2013 3rd International Conference on Instrumentation, Communications, Information Technology and Biomedical Engineering (ICICI-BME).

Technologies, A. (2013). “Three-lead Differential Muscle/ Electromyography Sensor for Microcontroller Applications” (Datasheet).

Tong, S., Daphne K. (2001). “Support Vector Machine Active Learning with Applications to Text Classification”. USA.