Multiclass Fuzzy Time-Delay Common Spatio-Spectral Patterns With Fuzzy Information Theoretic Optimization for EEG-Based Regression Problems in Brain–Computer Interface (BCI)

Abstract

Electroencephalogram (EEG) signals are one of the most widely used non-invasive signals in Brain Computer Interfaces (BCI). Large dimensional EEG recordings suffer from poor SNR (Signal to Noise Ratio). These signals are very much prone to artifacts and noise, so sufficient preprocessing is done on raw EEG signals before using them for classification or regression. Properly selected spatial filters enhance the signal quality and subsequently improve the rate and accuracy of classifiers, but their applicability to solve regression problems is quite an unexplored objective. This paper extends Common Spatial Patterns (CSP) to EEG state-space using fuzzy time delay and thereby proposes a novel approach for spatial filtering. The approach also employs a novel fuzzy information theoretic framework for filter selection. Experimental performance on EEG based reaction time prediction from a Lane-keeping task data from 12 subjects, demonstrated that the proposed spatial filters can significantly increase the EEG signal quality. A comparison based on Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE) and correlation to true responses is made for all the subjects. In comparison to the baseline fuzzy CSPROVR (Common Spatial Patterns Regression One Versus Rest), the proposed Fuzzy Time-delay Common Spatio-Spectral (FTDCSSP) filters reduced the RMSE on an average by 9.94%, increased the correlation to true reaction time on an average by 7.38% and reduced the MAPE by 7.09%.

Current Status, Challenges, and Possible Solutions of EEG-Based Brain-Computer Interface: A Comprehensive Review

“…To overcome this issue, numerous changes have been applied to the CSP. The common spatio-spectral pattern approach (CSSP) combines an FIR filter with a CSP algorithm and was observed to improve performance relative to pure CSP (Reddy et al, 2019). Common sparse spatio-spectral patterns (CSSSP) (Dornhege et al, 2006) are a comparatively more advanced procedure where the common spectral patterns across channels are investigated.…”

A novel EEG channel selection and classification methodology for multi‐class motor imagery‐based BCI system design

“…A brain–computer interface (BCI) system provides a potential communication medium between the human and external world by transforming brain activity into control commands 1 . Electroencephalogram (EEG) signals are the potential input to the BCI system since it alters mainly with the human brain's distinct physiological and neurological conditions 2 . Motor imagery (MI) BCI activity refers to performing limb, tongue, or leg movements mentally without performing the task in reality 3 .…”

“…For instance, it is reported that there is an increase in oscillatory beta power and a decrease in alpha power of EEG activity due to limb movement 5 . The capability to detect MI activity through EEG signals enables a BCI system to control assistive applications to support disabled people or patients suffering from motor impairments such as multiple sclerosis, amyotrophic lateral sclerosis, etc 2,6 . However, intrinsic nonstationarity and nonlinearity within EEG activity make processing and information extraction a tedious task 3 .…”

Motor-Imagery-Based Brain Computer Interface using Signal Derivation and Aggregation Functions

“…Some of the most common procedures include using the Fast Fourier transform (FFt) to transform the EEG signals to the frequency domain [8], [9], [10] and the Meyer wavelet transformation [11], [12]. There have also been many different fuzzy approaches to the BCI problem [13], [14], [15].…”