Raw Electroencephalogram-Based Cognitive Workload Classification Using Directed and Nondirected Functional Connectivity Analysis and Deep Learning.

With the phenomenal rise in internet-of-things devices, the use of electroencephalogram (EEG) based brain-computer interfaces (BCIs) can empower individuals to control equipment with thoughts. These allow BCI to be used and pave the way for pro-active health management and the development of internet-of-medical-things architecture. However, EEG-based BCIs have low fidelity, high variance, and EEG signals are very noisy. These challenges compel researchers to design algorithms that can process big data in real-time while being robust to temporal variations and other variations in the data. Another issue in designing a passive BCI is the regular change in user's cognitive state (measured through cognitive workload). Though considerable amount of research has been conducted on this front, methods that could withstand high variability in EEG data and still reflect the neuronal dynamics of cognitive state variations are lacking and much needed in literature. In this research, we evaluate the efficacy of a combination of functional connectivity algorithms and state-of-the-art deep learning algorithms for the classification of three different levels of cognitive workload. We acquire 64-channel EEG data from 23 participants executing the n-back task at three different levels; 1-back (low-workload condition), 2-back (medium-workload condition), and 3-back (high-workload condition). We compared two different functional connectivity algorithms, namely phase transfer entropy (PTE) and mutual information (MI). PTE is a directed functional connectivity algorithm, whereas MI is non-directed. Both methods are suitable for extracting functional connectivity matrices in real-time, which could eventually be used for rapid, robust, and efficient classification. For classification, we use the recently proposed BrainNetCNN deep learning model, designed specifically to classify functional connectivity matrices. Results reveal a classification accuracy of 92.81% with MI and BrainNetCNN and a staggering 99.50% with PTE and BrainNetCNN on test data. PTE can yield a higher classification accuracy due to its robustness to linear mixing of the data and its ability to detect functional connectivity across a range of analysis lags.

Effective Stress Management through Meditation: An Electroencephalograph-Based Study.

Introduction: Stress among college students is a common health problem that is directly correlated with poor cognitive health. For instance, cognitive mechanisms required for sustenance can be affected due to stress caused by daily mundane events, not necessarily by chronic events. Thus, it becomes essential to manage stress effectively especially for college students. Meditation is one of the useful techniques that facilitates cognitive flexibility and has consequences at the molecular and endocrinal level to treat stress. Objectives: The present study attempts to understand the effect of meditation on the brain waves when participants face stressful events. Methods: A randomized controlled pre-post experimental design was used. Total 18 subjects were randomly assigned to control group and experimental group. Subsequently, Electroencephalograph (EEG) data were recorded during the determination test (DT) before and after the meditation. The Control group underwent relaxation music while the experimental group practiced Sudarshan Kriya Yoga (SKY) (a type of meditation). Non-linear EEG signal processing algorithm was applied to capture dynamics and complexity in brain waves. Results: Results indicated that the efficacy of meditation was reflected with the improved information processing in the brain. Improved performance and reduced errors were reported in DT Scores in the experimental group. Increased complexity of beta band was observed for non-linear features, signifying efficient utilization of cognitive resources while performing the task. Conclusion: Findings implicated the usefulness of the meditation process for effective stress management.

Effect of Complexity on Frontal Event Related Desynchronisation in Mental Rotation Task.

A complexity (orientation and shape of stimuli) in the mental rotation (MR) task often affects reaction time (RT) and response accuracy, but the nature of such reflections in neuroscientific research is commonly undocumented. A number of studies have explored the effect of complexity and subsequently noted down the differences in performance. However, a few studies explored complexity (in the term of angular disparity) and cognitive strategies with respect to correct responses only. In contrast, the present study investigated frontal alpha desynchronization with reference to the complexity and proportions of correct and incorrect responses. Behavioral and neurophysiological responses were investigated to understand the switching between strategies (Analytic vs. Holistic). Results showed longer response time with respect to increased complexity. Frontal alpha desynchronization increased for difficult trials and incorrect responses, suggesting a higher utilization of cognitive resources at the frontal region during the MR task. Higher left frontal desynchronization reflected a trading off between strategies for difficult trials. Taken together, these findings suggest that the effect of stimuli complexity is more nuanced than implied by a simple hemispheric dichotomy for frontal cortex and discuss possible future directions to better understand the multitudinous brain mechanisms involved in MR.