Abstract

: Cognitive load modeling and analysis are foundational to intelligent human–machine interaction (HMI), where system performance and user effectiveness hinge on optimal allocation of cognitive resources. With the proliferation of adaptive interfaces, autonomous agents, and complex decision support systems, understanding how cognitive load influences human performance is critical for designing resilient, efficient, and usable systems. Cognitive load refers to the mental effort required to process information, and its improper management can lead to reduced task performance, increased error rates, and user disengagement. This research synthesizes theoretical and empirical advancements in cognitive load theory, elaborates on established modeling techniques—including physiological measures, computational cognitive models, and real‑time assessment frameworks—and examines their integration into intelligent HMI systems. By conducting a systematic literature review and comparative analysis, the study highlights the strengths and limitations of current methodologies, evaluates multimodal measurement approaches, and discusses how adaptive systems mitigate cognitive overload. Results indicate that effective cognitive load modeling significantly enhances situational awareness, decision accuracy, and user satisfaction but also presents challenges in real‑time measurement fidelity, model generalization across domains, and the interpretability of cognitive metrics. Future research directions emphasize advanced machine learning integration, cross‑modal fusion techniques, and personalized adaptive models to improve predictive accuracy and system responsiveness.