Lea Vojković

Cognitive workload and stress are key factors affecting human performance and safety in maritime navigation operations. This research proposes a composite gaze-tracking index, the Stress-Induced Gaze Pattern Score (SGPS), which integrates three complementary oculomotor metrics: pupil entropy, gaze dispersion, and gaze shift frequency. Single-blind research was conducted on a maritime navigation simulator with 65 participants of different ages, educational backgrounds, and maritime experience, who were exposed to an unexpected crisis scenario while eye movements and heart rate (HR) were simultaneously recorded. A two-layer interpretative model was introduced, in which SGPS serves as a quantitative measure of workload intensity, while FSR (Fixation-to-Saccade Ratio) acts as a qualitative moderator. Results showed that SGPS significantly correlated with HR in students (r = 0.77 in the acute phase, r = 0.74 in the sustained phase), thereby confirming its validity. At the whole-sample level, a significant correlation was observed in the sustained phase (r = 0.26, p = 0.05), suggesting broader applicability of the index. SGPS represents a promising objective tool for assessing cognitive workload in maritime simulation training and education, enabling early recognition of maladaptive stress responses, such as panic searching and cognitive tunnelling.

The obligated implementation of the Electronic Chart Display and Information System (ECDIS) began ten years ago, and during this time, we could observe different types of familiarization with the system through its users. The incorrect use of the ECDIS is a problem recognized by the International Hydrographic Organization (IHO), and it is caused by disparate levels of education and the quality of courses. Another aspect of the recognized problem is the unequal length of the ECDIS specific course training period through which users acquire type-specific familiarization with the system. Switching between different types of ECDISs makes users more prone to errors until they become fully familiar with the new product system. This paper analyzes seafarers’ knowledge and ECDIS usage over a 6-year period. Based on obtained data, models that enable risk analysis based on conditional probability were created. This paper presents the use of Bayesian modeling to reduce errors in maritime accidents caused by inadequate use of the ECDIS.

Human error caused by the interaction and effect of fatigue, stress and anxiety in seafarers is the subject of this research. The human element is a major part of the maritime system. We used Bayesian networks to predict human error in maritime affairs by analysing interactions between people, technology, organisational and environmental factors which make up the specificity of the maritime system. Bayesian networks are graphical structures developed to represent the conditional dependencies among a number of variables and to make conditional conclusions related to the selected variables. Through the analysis of psychic causes such as stress, fatigue, anxiety and so on, the model can produce graphic diagrams indicating which rank on which type of vessel at which seafarers age contributes to an increase in conditional probability of human error. The contribution of the paper is to find the worst combinations of influencing variables that can lead to an increase in the risk of human error. The results show a significant level of fatigue and stress in all officers (engine and nautical), regardless of the type of vessel they serve. A strong presence of anxiety is also reported in all surveyed officers, with a higher degree between engine officers.

An integrative approach to maritime accident risk factor assessment in accordance with formal safety assessment is proposed, which exploits the multifaceted capabilities of Bayesian networks (BNs) by consolidation of modelling, verification, and validation. The methodology for probabilistic modelling with BNs is well known and its application to risk assessment is based on the model verified though sensitivity analysis only, while validation of the model is often omitted due to a lack of established evaluation measures applicable to scarce real-world data. For this reason, in this work, the modified Lyapunov divergence measure is proposed as a novel quantitative assessor that can be efficiently exploited on an individual accident scenario for contributing causal factor identification, and thus can serve as the measure for validation of the developed expert elicited BN. The proposed framework and its approach are showcased for maritime grounding of small passenger ships in the Adriatic, with the complete grounding model disclosed, quantitative validation performed, and its utilization for causal factor identification and risk factor ranking presented. The data from two real-world grounding cases demonstrate the explanatory capabilities of the developed approach.