Emotiv EPOC BCI com Python em uma Raspberry Pi

Autores

  • José Salgado Patrón Universidad Surcolombiana, Neiva
  • Cristian Raúl Barrera Monje Universidad Surcolombiana, Neiva

DOI:

https://doi.org/10.18046/syt.v14i36.2217

Palavras-chave:

BCI, EEG, EPOC, Python, Raspberry Pi, máquina de vetores de suporte.

Resumo

O sistema BCI híbrido dá uma visão sobre o desenvolvimento de interfaces úteis para usuários com diferentes formações, desde aplicações médicas até jogos de vídeo, onde autônomo e portátil significam acessibilidade para o usuário. Sistemas como EPOC oferecem uma solução simples para a aquisição de sinais de EEG e EMG com preço baixo e configuração rápida, em comparação com equipamentos médicos de alta tecnologia. Do ponto de vista do processamento, um computador oferece sempre a fonte principal para resolver qualquer problema, tal como o Raspberry Pi [RPi] faz, que fornece o suficiente poder computacional para implementar  uma BCI e um sistema operacional de código aberto, como Raspbian. Certamente uma comunicação sem fio é uma obrigação entre o robô e o RPi, onde um módulo Xbee permite uma conexão bidirecional simples. Python é a principal ferramenta usada no projeto com múltiplas bibliotecas para o processamento de sinais cerebrais e musculares, não só para a sua preparação, mas também para a sua classificação, a partir de funções multithreading, extração de características, tais como Densidade de Potência Espectral [PSD] e Parámetros Hjorth, e uma Máquina de Vetores de Suporte [SVM] classificadora.

Biografia do Autor

  • José Salgado Patrón, Universidad Surcolombiana, Neiva
    Electronic Engineer; Master in Computing and Electronic Engineering; professor at the Universidad Surcolombiana (Neiva, Colombia): Electronic Engineering Program. His professional interest areas are: biomedical instrumentation, biomedical signal processing, robotics, and computational vision.
  • Cristian Raúl Barrera Monje, Universidad Surcolombiana, Neiva
    Student of Electronic Engineering at the Universidad Surcolombiana (Neiva, Colombia). His professional interest areas are: biomedical signal processing [EEG], learning machine, embedded systems and brain computer interfaces.

Referências

Bao, F., Liu, X., Zhang, C. (2011). PyEEG: An Open Source Python Module for EEG / MEG Feature Extraction. Computational Intelligence and Neuroscience. 2001(Art. 406391). doi: 10.1155/2011/406391.

Emotiv (2014). Emotiv EPOC: Brain Computer Interface & Scientific contextual EEG [blog]. Retrieved from: https://emotiv.com/product-specs/Emotiv%20EPOC%20Specifications%202014.pdf

Goh, C., Hamadicharef, B., Henderson, G., & Ifeachor, E. (2005). Comparison of fractal dimension algorithms for the computation of EEG biomarkers for dementia. In 2nd International Conference on Computational Intelligence in Medicine and Healthcare (CIMED2005), (pp.464-471). Retrieved from: https://hal.inria.fr/inria-00442374

Grude, S., Freeland, M., Yang, C., & Ma, H. (2013). Controlling mobile Spykee robot using Emotiv neuro headset. In 2013 32nd Chinese Control Conference (CCC), (pp. 5927-5932). IEEE.

Guneysu, A., & Akin, H. (2013). An SSVEP based BCI to control a humanoid robot by using portable EEG device. In 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), (pp. 6905-6908). IEEE. doi: 10.1109/EMBC.2013.6611145.

Joblib (2009). Joblib: running Python functions as pipeline jobs [blog]. Retrieved from: https://pythonhosted.org/joblib/generated/joblib.dump.html

Kaysa, W. A. & Widyotriatmo, A. (2013). Design of Brain-computer interface platform for semi real-time commanding electrical wheelchair simulator movement. In 2013 3rd International Conference on Instrumentation Control and Automation (ICA), (pp. 39-44). IEEE. doi: 10.1109/ICA.2013.6734043.

Lin, K., Chen, X., Huang, X., Ding, Q., & Gao, X. (2015). A Hybrid BCI speller based on the combination of EMG envelopes and SSVEP. Applied Informatics, 2(1). doi: 10.1186/s40535-014-0004-0

Liu, N., Chiang, C., & Chu, H. (2013). Recognizing the degree of human attention using EEG signals from mobile sensors. Sensors, 13(8). 10273-10286. doi: 10.3390/s130810273.

Oh, S. H., Lee, Y. R., & Kim, H. N. (2014). A novel EEG feature extraction method using Hjorth parameter. International Journal of Electronics and Electrical Engineering, 2(2), 106-110. doi: 10.12720/ijeee.2.2.106-110.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Vanderplas, J. (2011). Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 12, 2825-2830.

Pololu Corporation (2014). Pololu maestro servo controller: user's guide [on line] Retrieved from: https://www.pololu.com/docs/pdf/0J40/maestro.pdf

Qt Company. (2016). Qt Designer Manual [blog]. Retrieved from: http://doc.qt.io/qt-4.8/designer-manual.html

Rechy-Ramirez, E. J., Hu, H., & McDonald-Maier, K. (2012). Head movements based control of an intelligent wheelchair in an indoor environment. In 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO), (pp. 1464-1469). IEEE. doi: 10.1109/ROBIO.2012.6491175.

Scikit Learn (2014b). Standardize features by removing the mean and scaling to unit variance [blog]. Retrieved from: http://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html

Scikit Learn. (2014a). C-Support vector classification [blog]. Retrieved from: http://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html

Sinyukov, D. A., Li, R., Otero, N. W., Gao, R., & Padir, T. (2014). Augmenting a voice and facial expression control of a robotic wheelchair with assistive navigation. In 2014 IEEE International Conference on
Systems, Man and Cybernetics (SMC), (pp. 1088-1094). IEEE. doi:10.1109/SMC.2014.6974059.

Tahmasebzadeh, A., Bahrani, M., & Setarehdan, S. K. (2013). Development of a robust method for an online P300 speller brain computer interface. In 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER), (pp. 1070-1075). IEEE. doi: 10.1109/NER.2013.6696122.

The Python Software Foundation (2016a). 16.2. threading — Higher-level threading interface. In The Python Standard Library [blog]. Retrieved from: https://docs.python.org/2/library/threading.html

The Python Software Foundation (2016b). 16.6. multiprocessing — Process-based “threading” interface. In The Python Standard Library [blog]. Retrieved from: https://docs.python.org/2/library/multiprocessing.html

Upton, L. (2015). Benchmarking raspberry Pi 2 [blog]. Retrieved from: https://www.raspberrypi.org/blog/benchmarking-raspberry-pi-2/

Van Der Walt, S., Colbert, S. C., & Varoquaux, G. (2011). The NumPy array: a structure for efficient numerical computation. Computing in Science & Engineering, 13(2), 22-30. doi:10.1109/MCSE.2011.37.

Wang, Q., & Sourina, O. (2013). Real-time mental arithmetic task recognition from EEG signals. IEEE Transactions on Neural Systems and Rehabilitation Engineering 21(2), 225-232. doi: 10.1109/TNSRE.2012.2236576.

Yao, L., Meng, J., Zhang, D., Sheng, X., & Zhu, X. (2014). Combining motor imagery with selective sensation toward a hybrid-modality BCI. IEEE Transactions on Biomedical Engineering, 61(8), 2304-2312. doi: 10.1109/TBME.2013.2287245.

Downloads

Publicado

2016-03-30

Edição

v. 14 n. 36 (2016)

Seção

Original Research

Licença

Esta publicação está licenciada sob os termos da licença CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/deed.pt_BR).