Puthankattil Subha Dharmapalan

Subject-independent emotion recognition from electroencephalography (EEG) is constrained by nonlinear neural dynamics and inter-subject variability. This study characterises nine bispectral quadratic phase coupling (QPC) descriptors extracted from frontal EEG rhythms of the DEAP dataset, selects a compact subset via a genetic algorithm under nested leave-one-subject-out (LOSO) cross-validation, and evaluates classification with an explainable boosting machine (EBM). Under matched preprocessing, the bispectral features outperform power spectral density and differential entropy baselines by 2.7–3.8 points F 1 for arousal and 2.0–2.8 points F 1 for valence (paired Wilcoxon, p < 0.05 after Bonferroni correction), supporting their utility as compact nonlinear descriptors. The pipeline achieves 70.39% accuracy for arousal (19 features) and 69.98% for valence (25 features) on DEAP, statistically comparable to GRU-Conv and BiDCNN under matched LOSO evaluation, while using approximately an order-of-magnitude faster inference and a substantially smaller model footprint. Application of the identical pipeline to the independent DREAMER dataset yields comparable within-dataset performance, while direct DEAP → DREAMER cross-dataset transfer remains challenging. The additive structure of the EBM provides per-feature shape functions and pairwise interactions that are consistent with established frontal asymmetry and cross-frequency coupling literature. Bispectral QPC descriptors under an inherently interpretable modelling framework thus offer a compact, transparent alternative to higher-dimensional black-box approaches for subject-independent EEG emotion classification.

Analyzing Alzheimer’s disease (AD) and mild cognitive impairment (MCI) is crucial for early diagnosis and intervention. AD is the most common form of dementia and is characterized by a progressive decline in cognitive abilities, behavioral functions and memory. Analyzing the texture of the fornix can offer valuable insights for diagnosing MCI and AD. In this study, the fornix structure is segmented, and multifractal spectral features are analyzed for texture changes to distinguish between MCI and AD conditions. The images obtained from a public domain database undergo pre-processing steps such as removal of non-brain tissues, including skull stripping, spatial registration and contrast enhancement. Further, the fornix structure is delineated from the pre-processed images using the FreeSurfer pipeline. The slice image with the maximum area is selected for analysis. Subsequently, the 2-dimensional images are converted into a representative 1-dimensional using the Euclidean distance approach. The mass exponent, fluctuation function and generalized Hurst exponent are evaluated using the multifractal detrended moving average (MFDMA) algorithm in order to analyze the multifractal features of the fornix structure. The multifractal spectrum is used to generate characteristics that aid in differentiating between MCI and AD conditions. The results demonstrate that the FreeSurfer pipeline effectively segments the fornix structure in all considered images. The mass exponent shows a nonlinear trend, while the generalized Hurst exponent decreases with order, and the fluctuation function exhibits a linear relationship with scale, highlighting the multifractal nature of the fornix region. The singularity spectral features, such as the minimum Hölder exponent, strength of multifractality and singularity strength, are most effective in distinguishing between normal cognitive (NC) versus MCI and NC versus AD in subject groups. Multifractal analysis appears to be effective in assessing the progressive changes associated with MCI and AD conditions. Therefore, the proposed approach is effective for the early diagnosis of neurocognitive conditions.

Automated emotion recognition is crucial in identifying and monitoring psychological disorders. Although several electroencephalography (EEG)-based methods have been explored for emotion recognition, capturing the subtle oscillations within EEG signals associated with distinct emotional states remains a persistent challenge. Nonlinear phase-based functional connectivity (FC) can capture the intricate time-varying patterns of brain activity during the processing of emotions. In this work, an attempt has been made to characterize the EEG-based emotional states using nonlinear phase-based FC techniques. For this, the EEG signals are obtained from the publicly available DEAP database and decomposed into four frequency bands: Theta (4–7[ ]Hz), alpha (8–12[ ]Hz), beta (13–30[ ]Hz) and gamma (30–45[ ]Hz). Three nonlinear phase-based FC measures, namely phase lag index (PLI), phase locking value (PLV) and Rho index, are extracted from individual frequency bands. Two types of features, namely network features and FC indices, are fed to three classifiers, namely random forest (RF), extreme gradient boosting (XGB) and K-Nearest Neighbors (KNN). The results reveal that the proposed approach can capture EEG dynamics to characterize emotional states. The gamma band-based Rho index demonstrated prominence in discriminating arousal and valence emotional states. The utilization of the Rho index-based FC feature effectively reveals interactions among cortical brain regions in response to audio-visual stimuli. Thus, the proposed approach could be extended to classifying various emotional states in clinical settings.

Background: The current study analyses metastability, a feature of brain dynamics in subjects experiencing mild cognitive impairment Alzheimer’s disease (MCI-AD) under eyes open (EO) and eyes closed (EC) conditions. Alzheimer’s disease is a critically prolonged brain disorder that alters brain connectivity through changes in neural synchronization and desynchronization. Metastable states occur when functional connectivity patterns changes as a consequence of temporal dynamics of brain. Thus, studying metastability under EO and EC would help in understanding the cortical dynamics and its impact in early-stage Alzheimer’s disease. Methods: The study estimated metastability from three methods namely frequency variance analysis, Kuramoto order parameter and through meta-state activation patterns. Frequency variance estimated from 21 EEG channels were clustered into three regions namely anterior, central and posterior to study the regional metastability analysis. Global metastability was assessed from Kuramoto order parameter and meta-state activation patterns by collating the 21 EEG channels. Results: Reduction in metastability was observed in central regions of MCI-AD subjects through the study of frequency variance analysis. There was a marked reduction in global metastability in the patient group under resting EO condition. Reduction in meta-state activation properties such as TAS complexity, modularity and leap size in MCI-AD condition under EO condition indicates an overall reduction in brain flexibility. Conclusion: Taken together, the study infers an underlying structural change in neuronal dynamics influencing the reduction of metastability under MCI-AD condition. The study further revealed that this reduction in metastability is more pronounced in EO condition.

Background: Functional connectivity and complexity analysis has been discretely studied to understand intricate brain dynamics. The current study investigates the interplay between functional connectivity and complexity using the Kuramoto mean-field model. Method: Functional connectivity matrices are estimated using the weighted phase lag index and complexity measures through popularly used complexity estimators such as Lempel-Ziv complexity (LZC), Higuchi's fractal dimension (HFD), and fluctuation-based dispersion entropy (FDispEn). Complexity measures are estimated on real and simulated electroencephalogram (EEG) signals of patients with mild cognitive-impaired Alzheimer's disease (MCI-AD) and controls. Complexity measures are further applied to simulated signals generated from lesion-induced connectivity matrix and studied its impact. It is a novel attempt to study the relation between functional connectivity and complexity using a neurocomputational model. Results: Real EEG signals from patients with MCI-AD exhibited reduced functional connectivity and complexity in anterior and central regions. A simulation study has also displayed significantly reduced regional complexity in the patient group with respect to control. A similar reduction in complexity was further evident in simulation studies with lesion-induced control groups compared with non-lesion-induced control groups. Conclusion: Taken together, simulation studies demonstrate a positive influence of reduced connectivity in the model imparting a reduced complexity in the EEG signal. The study revealed the presence of a direct relation between functional connectivity and complexity with reduced connectivity, yielding a decreased EEG complexity.

Over the last two decades, there has been a tremendous increase in research activity on brain connectivity studies and its application in different neurological disorders. Studies have been focused on different connectivity patterns generated and potential biomarkers that could be derived to find the etymology of the disorder. In this review, the focus is on the utilization of wireless electroencephalogram monitoring system for functional connectivity analysis and its capacity for deciphering neurological disorders. The paper reviews different methods adopted to estimate connectivity and the possible convergence of connectivity patterns in four neurological disorders: epilepsy, autism spectrum disorder, Alzheimer and Parkinson's disease. The paper reviews the current status of connectivity research in the aforementioned neurological disorders and its potential in developing a smart e‐health service.