The extraction of relevant and distinct features from the electroencephalogram (EEG) signals is one of the most challenging task when implementing Brain Computer Interface (BCI) based systems. Frequency analysis techniques are recognised as one of the most suitable methods to have distinct information from EEG signals. However, existing studies use mostly classical approaches assuming that the signal is Gaussian, stationary and linear. These properties are not verified in the EEG case considering the complexity of the brain electrical activity.

This paper proposes two new spectral estimators that are robust against non-Gaussian, non-linear and non-stationary signals. These two approaches use quantile regression and L₁-norm regularisation to estimate the spectrum of the motor imagery (MI) related EEG.

A dataset collected during a study of BCI motor imagery project conducted at Tshwane University of Technology (TUT), Pretoria, South Africa, is used to validate the proposed estimators. Experimental results demonstrate that the newly proposed approaches help improve the classification performance of MI.

In order to show the effectiveness of the proposed estimators, a comparative study is conducted, considering classical commonly used techniques such as FFT and Welch periodogram through 5 classification algorithms.

The proposed Quantile-based spectral estimators are potential methods to improve the classification performance of the EEG-Based motor imagery systems.