Estudo Preliminar do Uso de Meta-heurísticas para Seleção de Canais em Sistemas BCI-SSVEP

• Raquel Queiroz UFABC
• Denis G. Fantinato UFABC

DOI: https://doi.org/10.5753/ercas.2021.17440

Abstract

Classification of electroencephalography (EEG) signals is a crucial problem in Brain-Computer Interfaces (BCI) systems. The EEG signals can be seen as a set of temporal series, being the use of Recurrent Neural Networks (RNNs) interesting for their processing, particularly the Long Short-Term Memory (LSTM) network. In this work, we propose the use of a LSTM classifier along with the Genetic Algorithm (GA) or the Clonal Selection Algorithm (CSA) for selection of electrodes in a set of artificial EEG data.

References

Bablani, A., Edla, D., Tripathi, D., and Cheruku, R. (2019). Survey on brain-computer interface: An emerging computational intelligence paradigm. ACM Computing Surveys, 52(1):1–32.

Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M. A. (2020). Multi-sequence lstm-rnn deep learning and metaheuristics for electric load forecasting. Energies, 13(2):391.

Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, volume 1. MIT press Cambridge.

Nam, C. S., Nijholt, A., and Lotte, F. (2018). Brain–Computer Interfaces Handbook: Technological and Theoretical Advances. CRC Press.

Pang, W., Wang, K., Wang, Y., Ou, G., Li, H., and Huang, L. (2015). Clonal selection algorithm for solving permutation optimisation problems: a case study of travelling salesman problem. In International Conference on Logistics Engineering, Management and Computer Science (LEMCS 2015), pages 575–580. Atlantis Press.