Title: Wavelet Transform Based Finger Movement Recognition

Abstract: Electromyography has been used for Human-Computer interactions (HCI). Gesture recognition such as hand and finger movements is helpful to have a better HCI experience. This study investigates methods used on a publicly available dataset. To the best of our knowledge, this dataset has never been used with wavelets previously. This study uses Discrete Wavelet Transforms (DWT) with three different wavelets such as Symlet 4, Daubechies 4, and Haar wavelets. The time and frequency domain features have been extracted from the result of the DWT which uses three different wavelets. The features have been tested with a proposed Convolutional Neural Network (CNN) model. To the best of our knowledge, this CNN architecture hasn't been used before. The results with different metrics and confusion matrix for each trial are given in the results section. The highest and the lowest accuracy rates have been achieved with the Symlet 4 wavelet and Haar wavelet, respectively. The performance ranking of the reported wavelets is Symlet 4, Daubechies, and Haar with accuracy rates of 91.56%, 90.66%, and 90.02%, respectively.

Keywords: finger movement recognition, surface electromyography, convolutional neural networks, discrete wavelet transforms

Başlık: Dalgacık Dönüşümü Tabanlı Parmak Hareketi Tanıma

Özet: Elektromiyografi (EMG), İnsan-Bilgisayar Etkileşimleri (IBE) için kullanılmaktadır. El ve parmak hareketlerini içeren jest tanıma, daha iyi bir HCI deneyimi sunmak için faydalı olabilmektedir. Bu çalışma, topluluğa açık bir veri seti üzerinde dalgacıkların kullanımını araştırmaktadır. Bildiğimiz kadarıyla, bu veri seti daha önce dalgacık yöntemi uygulanarak kullanılmamıştır. Bu çalışmada, Symlet 4, Daubechies 4 ve Haar dalgacıkları olmak üzere üç farklı dalgacıkla Ayrık Dalgacık Dönüşümlerini (ADD) kullanılmıştır. Zaman ve frekans alanı öznitelikleri ADD'nin sonuçlarından çıkarılmıştır. Önerilen Evrişimli Sinir Ağı (Convolutional Neural Networks - CNN) modeli ile öznitelikler test edilmiştir. Bildiğimiz kadarıyla, bu CNN mimarisi daha önce kullanılmamıştır. Farklı metrikler ve her denemeye ait karmaşıklık matrisleri sonuçlar bölümünde sunulmuştur. En yüksek ve en düşük doğruluk oranları sırasıyla Symlet 4 dalgacığı ve Haar dalgacığı ile elde edilmiştir. Rapor edilen dalgacıkların performans sıralaması Symlet 4, Daubechies ve Haar olup, sırasıyla %91,56, %90,66 ve %90,02 doğruluk oranlarına sahiptirler.

Anahtar kelimeler: parmak hareketi tanınması, yüzey elektromiyografisi, evrişimsel sinir ağları, ayrık dalgacık dönüşümleri

• Jaramillo-Yanez A, Benalcazar ME, Mena-Maldonado E. Real-time hand gesture recognition using surface electromyography and machine learning: A systematic literature review. Sensors 2020; 20(9): 2467.
• Sayilgan E, Yuce YK, Isler Y. Evaluation of mother wavelets on steady-state visually-evoked potentials for triple-command brain-computer interfaces. Turkish Journal of Electrical Engineering & Computer Sciences 2021; 29(5): 2263-2279.
• Sayilgan E, Yuce YK, Isler Y. Evaluation of wavelet features selected via statistical evidence from steady-state visually-evoked potentials to predict the stimulating frequency. Journal of the Faculty of Engineering and Architecture of Gazi University 2021; 36(2): 593-605.
• Sayilgan E, Yuce YK, Isler Y. Investigating the effect of flickering frequency pair and mother wavelet selection in steady-state visually-evoked potentials on two-command brain-computer interfaces. Innovation and Research in BioMedical Engineering 2022; 43(6): 594-603.
• Yesilkaya B, Sayilgan E, Yuce YK, Perc M, Isler Y. Principal component analysis and manifold learning techniques for the design of brain-computer interfaces based on steady-state visually evoked potentials. Journal of Computational Science 2023; 68: 102000.
• Sayilgan E, Yuce YK, Isler Y. Frequency recognition from temporal and frequency depth of the brain-computer interface based on steady-state visual evoked potentials. Journal of Intelligent Systems with Applications 2021; 4(1): 68-73.
• Degirmenci M, Sayilgan E, Isler Y. Evaluation of Wigner-Ville distribution features to estimate steady-state visual evoked potentials' stimulation frequency. Journal of Intelligent Systems with Applications 2021; 4(2): 133-136.
• Avci MB, Hamurcu R, Bozbas OA, Gurman E, Cetin AE, Sayilgan E. Design of steady-state visually-evoked potential based brain-computer interface system. Journal of Intelligent Systems with Applications 2022; 5(2): 86-89.
• Degirmenci M, Yuce YK, Perc M, Isler Y. Statistically significant features improve binary and multiple motor imagery tasks predictions from EEGs. Frontiers in Human Neuroscience 2023; 17: 1223307.
• Degirmenci M, Yuce YK, Isler Y. Classification of finger movements from statistically-significant time-domain EEG features. Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 39(3), 1597-1609, 2024.
• Degirmenci M, Yuce YK, Perc M, Isler Y. EEG-based finger movement classification with intrinsic time-scale decomposition. Frontiers in Human Neuroscience 2024; 18: 1362135.
• Isler Y, Isler O. Design of expert systems using surface EMG signal for movements of multi-function prosthetic hand. Karaelmas Science and Engineering Journal 2019; 9(2): 237-243.
• Isler Y, Isler O. EMG controlled 3D printed bionic hand. Natural and Engineering Sciences 2019; 4(3): 59-64.
• Kumar DK, Pah ND, Bradley A. Wavelet analysis of surface electromyography. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2003; 11(4): 400-406.
• Hu Y, Wong Y, Wei W, Du Y, Kankanhalli M, Geng W. A novel attention-based hybrid CNN-RNN architecture for sEMG-based gesture recognition. PloS One 2018; 13(10): e0206049.
• Haris M, Chakraborty P, Rao BV. EMG signal based finger movement recognition for prosthetic hand control. In 2015 Communication, Control and Intelligent Systems (CCIS) November, 2015, Mathura, India, pp. 194-198
• Naseer N, Ali F, Ahmed S, Iftikhar S, Khan RA, Nazeer H. EMG based control of individual fingers of robotic hand. In 2018 International Conference on Sustainable Information Engineering and Technology (SIET) November, 2018, pp. 6-9.
• Chen X, Zhang X, Zhao ZY, Yang JH, Lantz V, Wang KQ. Multiple hand gesture recognition based on surface EMG signal. In 2007 1st International conference on Bioinformatics and Biomedical Engineering, July, 2007, pp. 506-509.
• Arteaga MV, Castiblanco JC, Mondragon IF, Colorado JD, Alvarado-Rojas C. EMG-driven hand model based on the classification of individual finger movements. Biomedical Signal Processing and Control 2020; 58: 101834.
• Peleg D, Braiman E, Yom-Tov E, Inbar GF. Classification of finger activation for use in a robotic prosthesis arm. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2002; 10(4): 290-293.
• Zhang Z, Yu X, Qian J. Classification of Finger Movements for Prosthesis Control with Surface Electromyography. Sensors and Materials 20202; 32.
• Too J, Abdullah AR, Zawawi TT, Saad NM, Musa H. Classification of EMG signal based on time domain and frequency domain features. International Journal of Human and Technology Interaction (IJHaTI) 2017; 1(1): 25-30.
• Altin C, Er O. Comparison of different time and frequency domain feature extraction methods on elbow gesture’s EMG. European Journal of Interdisciplinary Studies 2016; 2(3): 25-34.
• Zhou T, Omisore OM, Du W, Wang L, Zhang Y. Adapting random forest classifier based on single and multiple features for surface electromyography signal recognition. In 2019 12th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI), October, 2019, pp. 1-6.
• Wahid MF, Tafreshi R, Langari R. A multi-window majority voting strategy to improve hand gesture recognition accuracies using electromyography signal. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2019; 28(2): 427-436.
• Geng W, Du Y, Jin W, Wei W, Hu Y, Li J. Gesture recognition by instantaneous surface EMG images. Scientific Reports 2016; 6(1): 36571.
• Duque CJG, Munoz LD, Mejia JG, Trejos ED. Discrete wavelet transform and k-nn classification in EMG signals for diagnosis of neuromuscular disorders. In 2014 XIX Symposium on Image, Signal Processing and Artificial Vision, November, 2014, pp. 1-5.
• Phinyomark A, Nuidod A, Phukpattaranont P, Limsakul C. Feature extraction and reduction of wavelet transform coefficients for EMG pattern classification. Elektronika ir Elektrotechnika 2012; 122(6): 27-32.
• Electro-Myography-EMG-Dataset. 13 May 2024. [Online] Retrieved from https://www.kaggle.com/datasets/nccvector/electromyography-emg-dataset
• PyWave Python Library. 15 May 2024. [Online]. Retrieved from https://pypi.org/project/PyWave/
• Lalitharatne TD, Hayashi Y, Teramoto K, Kiguchi K. A study on effects of muscle fatigue on EMG-based control for human upper-limb power-assist. In 2012 IEEE 6th International Conference on Information and Automation for Sustainability, November, 2012, pp. 124-128.
• Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Systems with Applications 2012; 39(8): 7420-7431.
• Phinyomark A, Hirunviriya S, Limsakul C, Phukpattaranont P. Evaluation of EMG Feature Extraction for Hand Movement Recognition Based on Euclidean Distance and Standard Deviation. ECTI-CON2010: The 2010 ECTI International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, Chiang Mai, Thailand, 2010, pp. 856-860.
• Daud WMBD, Yahya AB, Horng CS, Sulaima MF, Sudirman R. Features extraction of electromyography signals in time domain on biceps brachii muscle. International Journal of Modeling and Optimization 2013; 3(6): 515.
• Abdelouahad A, Belkhou A, Jbari A, Bellarbi L. Time and frequency parameters of sEMG signal—force relationship. In 2018 4th International Conference on Optimization and Applications (ICOA), April, 2018, pp. 1-5.