Mental workload (MWL) monitoring is increasingly relevant in safety-critical and high-demand domains. Excessive mental workload can impair attention, decision-making, and task performance, increasing the likelihood of human error and, in critical scenarios, contributing to accidents. Therefore, reliable systems capable of assessing an operator’s cognitive state represent an important research challenge with clear practical implications. Several approaches have been proposed to estimate MWL, including subjective questionnaires, behavioural measures, performance-based indices, and physiological monitoring. Among these, physiological methods are particularly promising, as they provide continuous and objective information about the user’s state and can potentially be applied across different tasks and contexts. Among physiological signals, electroencephalography (EEG) is one of the most informative techniques for cognitive-state assessment, as it directly measures the electrical activity of the brain.