Aplicação da Análise Discriminante Linear (LDA) para Classificação de Sinais Eletromiográficos (EMG) de Movimentos da Mão
Resumo
A eletromiografia (EMG) fornece informações valiosas acerca da atividade e morfologia muscular. A classificação e reconhecimento de padrões dos sinais EMG são passos importantes na detecção de anormalidades, análise de desempenho muscular e controle de prótese. A análise discriminante linear (LDA) é um método estatístico usado para separação de duas ou mais classes de objetos. Propõe-se um método baseado em LDA, pré-processamento dos dados de entrada e aplicação de técnica de votação (Moda) das saídas para realizar classificação de sinais EMG de movimentos da mão de um indivíduo. O método proposto apresentou taxa de acerto de até 97,85% na fase de teste das amostras, apontando o potencial e eficiência do LDA na classificação dos sinais.
Palavras-chave:
Eletromiografia (EMG), morfologia muscular, método, análise
Referências
Alpaydin, E. (2010). Introduction to Machine Learning. MIT Press.
Basmajian, J. and De Luca, C. (1985). Muscle Alive: Their Functions Revealed by Elec- tromyography, volume 5. William and Wilkins, Baltimore.
De Luca, C. J. (1997). The use of surface electromyography in biomechanics. Journal of applied biomechanics, 13(2):135–163.
Dideriksen, J. L., Gianfelici, F., Maneski, L. Z. P., and Farina, D. (2011). Emg-based cha- racterization of pathological tremor using the iterated hilbert transform. IEEE Tran- sactions on Biomedical Engineering, 58(10):2911–2921.
Khushaba, R. N., Kodagoda, S., Liu, D., and Dissanayake, G. (2013). Muscle computer interfaces for driver distraction reduction. Computer methods and programs in biome- dicine, 110(2):137–149.
Kotsiantis, S. B., Zaharakis, I., and Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160:3–24.
Phinyomark, A., Hu, H., Phukpattaranont, P., and Limsakul, C. (2012a). Application of linear discriminant analysis in dimensionality reduction for hand motion classification. Measurement Science Review, 12(3):82–89.
Phinyomark, A., Phukpattaranont, P., and Limsakul, C. (2012b). Feature reduction and selection for emg signal classification. Expert systems with applications, 39(8):7420– 7431.
Raez, M. (2006). Techniques of emg signal analysis: detection, classification and appli- cations. 8:11–35.
Raurale, S., McAllister, J., and del Rincon, J. M. (2018). Emg acquisition and hand pose classification for bionic hands from randomly-placed sensors. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1105–1109. IEEE.
Robertson, G. E., Caldwell, G. E., Hamill, J., Kamen, G., and Whittlesey, S. (2013).
Research methods in biomechanics. Human kinetics.
Shenoy, P., Miller, K. J., Crawford, B., and Rao, R. P. (2008). Online electromyo- graphic control of a robotic prosthesis. IEEE transactions on biomedical engineering, 55(3):1128–1135.
Too, J., Abdullah, A., Zawawi, T. T., Saad, N. M., and Musa, H. (2017). Classification of emg signal based on time domain and frequency domain features. International Journal of Human and Technology Interaction (IJHaTI), 1(1):25–30.
Yousefi, J. and Hamilton-Wright, A. (2014). Characterizing emg data using machine- learning tools. Computers in biology and medicine, 51:1–13.
Zhang, D., Xiong, A., Zhao, X., and Han, J. (2012). Pca and lda for emg-based control of bionic mechanical hand. In 2012 IEEE International Conference on Information and Automation, pages 960–965. IEEE.
Basmajian, J. and De Luca, C. (1985). Muscle Alive: Their Functions Revealed by Elec- tromyography, volume 5. William and Wilkins, Baltimore.
De Luca, C. J. (1997). The use of surface electromyography in biomechanics. Journal of applied biomechanics, 13(2):135–163.
Dideriksen, J. L., Gianfelici, F., Maneski, L. Z. P., and Farina, D. (2011). Emg-based cha- racterization of pathological tremor using the iterated hilbert transform. IEEE Tran- sactions on Biomedical Engineering, 58(10):2911–2921.
Khushaba, R. N., Kodagoda, S., Liu, D., and Dissanayake, G. (2013). Muscle computer interfaces for driver distraction reduction. Computer methods and programs in biome- dicine, 110(2):137–149.
Kotsiantis, S. B., Zaharakis, I., and Pintelas, P. (2007). Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160:3–24.
Phinyomark, A., Hu, H., Phukpattaranont, P., and Limsakul, C. (2012a). Application of linear discriminant analysis in dimensionality reduction for hand motion classification. Measurement Science Review, 12(3):82–89.
Phinyomark, A., Phukpattaranont, P., and Limsakul, C. (2012b). Feature reduction and selection for emg signal classification. Expert systems with applications, 39(8):7420– 7431.
Raez, M. (2006). Techniques of emg signal analysis: detection, classification and appli- cations. 8:11–35.
Raurale, S., McAllister, J., and del Rincon, J. M. (2018). Emg acquisition and hand pose classification for bionic hands from randomly-placed sensors. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1105–1109. IEEE.
Robertson, G. E., Caldwell, G. E., Hamill, J., Kamen, G., and Whittlesey, S. (2013).
Research methods in biomechanics. Human kinetics.
Shenoy, P., Miller, K. J., Crawford, B., and Rao, R. P. (2008). Online electromyo- graphic control of a robotic prosthesis. IEEE transactions on biomedical engineering, 55(3):1128–1135.
Too, J., Abdullah, A., Zawawi, T. T., Saad, N. M., and Musa, H. (2017). Classification of emg signal based on time domain and frequency domain features. International Journal of Human and Technology Interaction (IJHaTI), 1(1):25–30.
Yousefi, J. and Hamilton-Wright, A. (2014). Characterizing emg data using machine- learning tools. Computers in biology and medicine, 51:1–13.
Zhang, D., Xiong, A., Zhao, X., and Han, J. (2012). Pca and lda for emg-based control of bionic mechanical hand. In 2012 IEEE International Conference on Information and Automation, pages 960–965. IEEE.
Publicado
22/11/2019
Como Citar
REZENDE, Ana Cláudia Barbosa; LOPES FILHO, Gilberto ; VIEIRA, Flávio Henrique Teles .
Aplicação da Análise Discriminante Linear (LDA) para Classificação de Sinais Eletromiográficos (EMG) de Movimentos da Mão. In: ESCOLA REGIONAL DE INFORMÁTICA DE GOIÁS (ERI-GO), 7. , 2019, Goiânia.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 351-360.
