Discriminating the different human brain states with EEG signals using Fractal dimension: A nonlinear approach

EEG signals are measured on scalp of the human brain and are widely used to address the clinical as well as in modern application like brain computer interfacing (BCI) and gaming. Feature extraction plays a fundamental role for good classification purposes. EEG features commonly extracted are linear as well as nonlinear. Nonlinear approaches are used when the complexity of EEG signals increases. Nonlinear features like correlation dimension (CD), Lyapunov exponents, approximate entropy requires higher computational complexity. On other hand Fractal dimension (FD) requires less computations. Therefore, Fractal dimension are widely used in engineering and biological sciences. In our paper, Fractal dimension has been selected to discriminate the different brain states. EEG data from 08 healthy participants have been acquired during eyes open, eyes close and during IQ task. Fractal dimensions have been computed on the EEG data acquired. Using Fractal dimension, we have successfully discriminated the different brain conditions/states like eyes open, eyes close and IQ task. Results have shown better discrimination between mental task and active brain conditions with 91.66 % accuracy using SVM classifier as compared to other classifiers. This approach can be used for fast decision making and pattern matching based on the selected epoch of the EEG signal using nonlinear approach.

I. Introduction

Different neuroimaging modalities like EEG, MEG, fMRI and PET etc. are widely used by researchers to understand the human brain dynamics and its functionality. However, EEG is the most cost effective and non-invasive approach as compared to the others. Electroencephalography (EEG) is a valuable and unique measure of neural activity of the brain. EEG records the scalp potentials generated due to neural activities or neuron firing on the surface of the human brain [1]. First EEG recording from the human scalp was done in 1920 by Hans Berger, a German scientist. The amplitude and frequency content of EEG signals gives ample information about the brain dynamics [2]–[3]. EEG signals can be divided into different frequency bands starting from 1Hz to 100 Hz e.g. deep sleep has a dominant frequency approximately 1 Hz. Eyes close during active state has 10 Hz dominant frequency called alpha state of the human brain. Therefore, EEG signals can be categorizes into different frequency bands i.e., delta (1–4Hz), theta (4–12), alpha, beta and gamma band.