Self-organizing Maps for Motor Tasks Recognition from Electrical Brain Signals
Recently, there has been a relevant progress and interest for brain–computer interface (BCI) technology as a potential channel of communication and control for the motor disabled, including post-stroke and spinal cord injury patients. Different mental tasks, including motor imagery, generate changes in the electro-physiological signals of the brain, which could be registered in a non-invasive way using electroencephalography (EEG). The success of the mental motor imagery classification depends on the choice of features used to characterize the raw EEG signals, and of the adequate classifier. As a novel alternative to recognize motor imagery tasks for EEG-based BCI, this work proposes the use of self-organized maps (SOM) for the classification stage. To do so, it was carried out an experiment aiming to predict three-class motor tasks (rest versus left motor imagery versus right motor imagery) utilizing spectral power-based features of recorded EEG signals. Three different pattern recognition algorithms were applied, supervised SOM, SOM+k-means and k-means, to classify the data offline. Best results were obtained with the SOM trained in a supervised way, where the mean of the performance was 77% with a maximum of 85% for all classes. Results indicate potential application for the development of BCIs systems.
KeywordsElectroencephalogram Brain-computer interfaces Motor imagery Classification Self-organized maps
The authors thank to Universidad Antonio Nariño under project 2016207 and publication PI/UAN-2017-611GIBIO for the support in this work. J.M. Antelis thanks the financial support of CONACYT through grants 268958 and PN2015-873.
- 3.Vega, R., Sajed, T., Mathewson, K.W., Khare, K., Pilarski, P.M., Greiner, R., Sánchez-Ante, G., Antelis, J.M.: Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals. Artif. Intell. Res. 6(1), 37 (2017)Google Scholar
- 5.Carino-Escobar, R.I., Cantillo-Negrete, J., Gutierrez-Martinez, J.: Decodificación de imaginación motora en la señal de electroencefalografía mediante mapas auto-organizados. Revista del Centro de Investigación de la Universidad La Salle 12, 107–125 (2016)Google Scholar
- 11.Kohavi, R., et al.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: IJCAI, vol. 14, Stanford, CA, pp. 1137–1145 (1995)Google Scholar
- 12.Ojeda, L., Vega, R., Falcon, L.E., Sanchez-Ante, G., Sossa, H., Antelis, J.M.: Classification of hand movements from non-invasive brain signals using lattice neural networks with dendritic processing. In: Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Sossa-Azuela, J.H., Olvera López, J.A., Famili, F. (eds.) MCPR 2015. LNCS, vol. 9116, pp. 23–32. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-19264-2_3 CrossRefGoogle Scholar
- 13.Gudiño-Mendoza, B., Sanchez-Ante, G., Antelis, J.M.: Detecting the intention to move upper limbs from electroencephalographic brain signals. Comput. Math. Methods Med. 2016 (2016)Google Scholar