Discriminating cognitive performance using biomarkers extracted from linear and nonlinear analysis of EEG signals by machine learning

Abstract

Nonlinear dynamics and chaos theory are being widely used nowadays in neuroscience to characterize complex systems within which the change of the output isn’t proportional to the change of the input. Nonlinear systems compared to linear systems, often appear chaotic, unpredictable, or counterintuitive, and yet their behaviour isn’t random. The importance of the time series analysis, which exhibits a typical complex dynamics, within the area of nonlinear analysis can’t be undermined. Hidden important dynamical properties of the physiological phenomenon can be detected by many features of these approaches. Nonlinear dynamics and chaos theory are being employed in neurophysiology with the aim to elucidate the complex brain activity from electroencephalographic (EEG) signals. The brain is a chaotic dynamical system and further, their generated EEG signals are generally chaotic in another sense, because, with respect to time, the amplitude changes continuously. A reliable and non-invasive measurement of memory load which will be made continuously while performing a cognitive task would be very helpful for assessing cognitive function, crucial for the prevention of decision-making errors, and also the development of adaptive user interfaces. Such a measurement could help to keep up the efficiency and productivity in task completion, work performance, and to avoid cognitive overload, especially in critical/high mental load workplaces like traffic control, military operations, and rescue commands. We have measured the linear and nonlinear dynamics of the EEG signals in subjects undergoing mental arithmetic task and measured the cognitive load on the brain continuously. We have also differentiated the subjects who can perform a mental task good and bad and developed a system using support vector machine to differentiate rest and task states.