Cognitive Load Monitoring in Control Room Operations Using Principal Component Analysis
Аннотация
Cognitive load monitoring plays a vital role in ensuring safety and efficiency in control room operations, where operators are continuously exposed to high-pressure decisionmaking environments. Accurate assessment of mental workload enables better task management and supports human reliability in critical infrastructures. Existing methods for cognitive load evaluation often rely on single-modal indicators such as EEG, eye-tracking, or self-reported measures. However, these approaches suffer from noise sensitivity, redundancy, and limited interpretability, making them less reliable for real-time applications in complex operational settings. To address these challenges, this study introduces a Principal Component Analysis-based Cognitive Load Indexing (PCA-CLI) framework. By integrating physiological and behavioral signals, PCA is applied to reduce dimensionality, extract the most relevant features, and construct a composite index that accurately represents cognitive load dynamics with reduced noise. The proposed PCA-CLI method is applied to control room environments, enabling real-time monitoring of operator workload during critical scenarios such as alarm management and fault diagnosis. This allows supervisors and adaptive systems to intervene when workload thresholds are exceeded, ensuring safety and operational resilience. Findings demonstrate that PCA-CLI enhances accuracy, reduces redundancy, and provides a reliable cognitive load measure, supporting improved decision-making and safer control room operations.