Fast and Efficient Four- Class Motor Imagery EEG Signals Analysis Using CSP-Ridge Regression Algorithm for the Purpose of Brain Computer Interface

Brain–computer interfaces (BCIs) enable users to control devices with electroencephalographic (EEG) activity from the scalp or with single-neuron activity from within the brain.Undoubtedly, one of the most challenging issues in this regard is the balancing between accuracy of given brain signals from patients as well as the speed of interpreting them into machine language. The main objective of the paper is to perform analysis of different approaches to achieve the method by more speed and better performance. Forreduction ocular artifacts, SYM-WHITE Independent Component Analysis (ICA)algorithm evaluatedwhich has the lowest run time as well as the lowest signal to interference (SIR) indexwithout destroying original signal. After quick eliminating of undesirable signals,two successful feature extractors, Log-band power algorithm andcommon spatial patterns are used to extract features. The emphasis is on identifying discriminative properties of the feature sets representing EEG trials recorded during imagination of tongue, feet and left- right hand movement.At last but not least, three well-known classifiers are evaluated which Ridge Regression classifier and common spatial patternsas feature extractor have the highest accuracy classification rate about 83.06%with a standard division of 1.22% counter-posing the latest studies.