Classification of motor imagery electroencephalography signals using spiking neurons with different input encoding strategies

Motor imagery-based brain–computer interfaces decode users’ intentions from the electroencephalogram; however, poor spatial resolution makes automatic recognition of these intentions a challenging task. New classification approaches with low computational costs and high classification performances need to be developed in order to increase the number of users benefitted by these systems. On the other hand, spiking neuron models, which are mathematical abstractions of real neurons, have shown good performances in several classification tasks, making these models suitable for motor imagery classification. In this work, two different encoding strategies for spiking neuron models, applied to the classification of motor imagery time–frequency features of stroke patients and healthy subjects, were evaluated. Classification performances and computational costs of spiking neuron models were compared against those of linear discriminant analysis, support vector machines and artificial neural networks. Results showed that a time-varying encoding strategy is more suitable for motor imagery classification, and its implementation computational cost is low. Therefore, a spiking neuron model with a time-varying encoding strategy could increase the number of potential users of brain–computer interfaces.