The determination of brain age based on electroencephalography (EEG) data has become widely developed with the spread of machine learning in recent years. In this research paper, we analyzed 21 articles published no earlier than 2015, focusing particularly on features, machine learning and deep learning models, and the validation process. The studies reviewed presented model performance on EEG data using machine learning or deep learning techniques. Deep convolutional and transformer-based models trained on well-curated features forecasted chronological age most precisely. In newborns, time–frequency and entropy-based characteristics showed good predictive power for the brain age index (BAI) and functional brain age (FBA). Consistently, spectral and nonlinear descriptors ranked among the most informative characteristics. Methodological rigor, meanwhile, differed: only a small number of studies used bias correction techniques, addressed statistical assumptions, or reported external validation. Preprocessing techniques also showed significant variation. Although EEG-based models have good accuracy, problems of interpretability and generalizability restrict their clinical and developmental use. Advancing this discipline will call for biologically based outcome definitions, uniform evaluation systems, and open source processing pipelines.
30 September 2026 in Scientific Journal of Astana IT University
Electroencephalography (EEG) provides a non-invasive means to investigate the dynamic behavior of the brain through electrical activity. Traditional linear analysis methods tend to be insufficient in capturing the complexity of neural signals. This study applies nonlinear dynamic analysis - the Largest Lyapunov Exponent (LLE) - to EEG data recorded during an emotional conflict task in children and young adults. The aim of the study was to define age and sex differences during emotional conflict task performance in Lyapunov exponent of EEG signal. EEG were recorded as participants performed task with viewing facial expressions and hearing auditory words corresponding to four emotions: angry, sad, happy and fearful. EEG preprocessing included filtering, artifact removal by using Independent Component Analysis (ICA). Electrodes were grouped into functional brain networks: anterior, posterior, executive, z-network and left and right hemispheres. LLE was computed from each epoch for broadband to quantify the underlying chaotic dynamics of brain activity, and separately for alpha and theta bands as emotional features. Repeated-measures ANOVA revealed significant differences across brain networks, and interactions with age, sex, and emotions. Machine learning classification found that sex-stratified emotion decoding revealed band-dependent asymmetries: in broadband features, male participants showed higher four-way emotion decoding accuracy (~30.1%) than female participants (~23.5%), while the pattern reversed in the alpha band, where females outperformed males (~27.6% vs. ~19.8%). These interactions suggest that sex differences in LLE-based emotion separability are spectrally specific.
Emotion recognition from electroencephalography (EEG) signals is a central problem in affective computing. This study benchmarks seven classical machine learning models—XGBoost, LightGBM, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, and Logistic Regression—for multiclass EEG emotion classification on the FACED dataset, which provides fine-grained labels across nine emotion categories (amusement, inspiration, joy, tenderness, anger, fear, disgust, sadness, and neutral) from 123 participants. We extract Differential Entropy (DE) features across five frequency bands and, using an identical feature-and-preprocessing pipeline, evaluate all models under three distinct protocols that differ only in how the data are partitioned: (i) an intra-subject protocol, in which a separate model is trained and tested within each participant and the per-participant scores are averaged; (ii) a pooled segment-level protocol, in which segments from all participants are mixed so that segments from the same participant may fall in both training and test sets; and (iii) a strict subject-independent protocol, in which all segments from any given participant are kept together on one side of the training and test split, so that test participants are never seen during training. Under the intra-subject protocol, the best model (LightGBM) reaches 85.4% accuracy; under the pooled segment-level protocol the best model reaches 56.4%; and under the subject-independent protocol the best model (SVM with an RBF kernel) achieves only 18.2% accuracy—above the 11.1% chance level but far below the other two settings. We provide reproducible baselines under all three protocols and argue that subject-independent evaluation is essential for meaningful benchmarking on FACED.