Anxiety disorders are commonly assessed using instruments such as HAM-A and GAD-7. These tools rely on patient self-report and clinician interpretation, which may introduce variability. This study proposes an EEG-based computational framework for estimating anxiety levels using portable EEG recordings from the Unicorn Hybrid Black device. These data were harmonized with the DASPS public dataset to ensure methodological consistency. After standardized preprocessing and multi-domain feature extraction, three classifiers—logistic regression, multilayer perceptron (MLP), and k-nearest neighbors (KNN)—were trained and evaluated. Logistic regression achieved 81.25% accuracy (F1 = 0.8247), while the MLP reached 87.5% accuracy (F1 = 0.859). ROC analysis (AUC = 0.98 for logistic regression and 0.92 for MLP) confirmed that both classifiers reliably separated non-anxious from moderate participants. Severe anxiety could not be classified, reflecting the extremely limited number of participants in this category. Predicted anxiety probabilities showed significant correlations with HAM-A scores (r up to 0.71, p < 0.01), supporting the external validity of the proposed approach.

This paper investigates how neuronal networks modify their functional organization according to cognitive demands, using the percolation threshold as an indicator of the distance from the critical state. Based on EEG recordings collected during rest and two cognitive tasks (working memory and inhibitory control), functional networks were constructed, and variations in the giant cluster were analyzed in relation to the connectivity threshold. Results show that under high cognitive load, the neuronal network approaches a near-critical zone, characterized by efficient integration and functional dynamism. Moreover, lower percolation threshold values correlate with better cognitive performance, suggesting that optimal information processing occurs near criticality. The study confirms the relevance of the critical brain theory and highlights the potential of pc as a functional biomarker for assessing cognitive flexibility. Keywords: percolation, EEG, neuronal networks, criticality, giant cluster, connectivity, working memory, synchronization, cognitive performance

Major depressive disorder requires scalable, low-burden screening tools. We examined whether three-channel resting-state EEG can support reliable discrimination between major depressive disorder and healthy controls using a lightweight model compatible with portable implementations. This work makes three main contributions: (i) a compact hybrid fusion model combining raw-window Conv1D embeddings with per-channel spectral–statistical descriptors for three-channel resting-state EEG, (ii) a leakage-resistant subject-independent (cross-subject) evaluation protocol with subject-level inference via majority voting, and (iii) a preliminary external feasibility test on an independent portable three-channel cohort without fine-tuning. The proposed model fuses a Conv1D encoding of raw ≈15 s eyes-closed windows (3840 samples; 15.36 s at 250 Hz) with per-channel spectral and statistical descriptors. Training uses subject-independent splits to avoid leakage, class weighting, and data augmentation (including MixUp); hyperparameters are selected via randomized search with refinement. The model is trained on a publicly available MDD dataset and subsequently applied, without fine-tuning, on an independent acquisition of 20 subjects recorded with a portable three-channel device; we report both window-level and subject-level (majority-vote) performance. On the held-out test subjects from the public dataset, the hybrid model attains 93.43% window-level accuracy. The independent evaluation is reported as a preliminary external feasibility analysis; given the small cohort, we report subject-level performance with 95% confidence intervals to reflect uncertainty and avoid over-interpreting cross-device generalization. The model occupies approximately 40.19 MB on disk, and the architecture is compatible with post-training int8 (TFLite) quantization for resource-constrained hardware. These results, obtained on limited samples, support the feasibility of three-channel EEG for major depressive disorder detection using a lightweight hybrid architecture and motivate prospective clinical validation, on-device inference and quantization studies, and broader evaluation across centers and devices.