Brain State Intelligence and Cognitive Health Through EEG Date Modeling

Introduction

Using electroencephalographic (EEG) data, cognitive psychologists can visualize and observe correlations between different active brain states. It is desirable to create an application that takes EEG data and exposes it to various analytical techniques so the resultant brain states can be studied and predicted. We present explanations of the design and implementation offered herein.

An EEG device can record the electric signals from a human scalp. EEG devices used to be only available in professional health care institutions for clinic use. Last decade witnessed the development of cheap EEG devices, for example, EPOC from Emotiv (http://www.neurosky.com/), and increasing interest in EEG based brain-computer interfaces (BCI). EEG signals characterize the result of the neuron activities inside of a human brain. Naturally, they are used to study and understand human brain activities. In particular, EEG signals indicate that neural patterns of meanings in each brain occur in trajectories of discrete steps, whist the amplitude modulation in EEG wave is the mode of expressing meanings (Freeman, 2000). Zhou et al (2008) have proposed some novel features for EEG signals to be used in brain-computer interface (BCI) system to classify left and right hand motor imagery. The experimental results have shown that based on the proposed features, the classifiers using linear discriminant analysis, support vector machines and neural network achieve better classification performance than the BCI-competition 2003 winner on the same data set in terms of the criteria of either mutual information or misclassification rate. Dressler et al studied the anaesthetics on the brain and the level of sedation (Dressler et al, 2004). Lin et al (2010) studied the change of human emotion during music listening through EEG signals.

The vast implications of using EEG data to analyze brain states include designing brain-computer interfaces (BCI) where users can operate on a machine via brain activities, and using brain state models in healthcare related activities. As an example, we present a case study in transcendental meditation (Schreiber et al, 2017), a spiritual development technique, which was popularized by former Hindu ascetic Mharishi Mahesh Yogi and gained popularity in the west during the 1960’s (Holzel et al, 2010). The concurrent brain states associated with transcendental meditation have been viewed as something outside of the world of physical measurement and objective evaluation by most scientific communities. Scientists now have the ability to measure and register electric potential of the human brain through the use of electroencephalographic technologies. One approach is to study finite differences within the minds of those practicing meditation, and those who do not. Such an endeavor is an avenue towards modeling a wide range of brain states (Lin, 2010). The combination of electroencephalographic data with modeling methods in fields such as data mining and bioinformatics could be used to prove that subjects in a state of transcendental meditation are in a verifiable and observable state of mind that can be monitored and predicted (Schreiber et al, 2017). Experiments found that cancer patients that practiced meditation experienced higher well-being levels, better cognitive function and lower levels of inflammation than a control group (Oh et al, 2009).