Proposed MMLA design for maritime simulation combining body sensors, eye-tracking, and speech recognition¶

Element · All elements
Evidence · no claims cited

Description¶

The proposed multimodal learning analytics design for full-mission bridge simulators proposes sensors and technologies to capture collaborative navigation training: "Body sensors: Capturing the amount of movement, student position in the spatial workspace, distance between students, active posture, and head, hand, and wrist movements"; eye-tracking capturing areas of interest and joint visual attention; and speech recognition capturing linguistic coordination, verbal coherence, and contribution to decision-making. Simulator log data may also be encompassed.

Design Implications¶

Context¶

Requirements¶

• Effective implementation requires the correct technology and a focus on appropriate pedagogy

Constraints¶

• The authors encountered problems attempting to assess these data sources' impact on actual learning during simulation

Target Learners¶

• maritime students in high-fidelity navigation simulator training

Target Learning Goals¶

• teamwork, attention coordination, communication, and professional decision-making on the bridge

Related Elements¶

Examples¶

• Combine system logs, eye-tracking, and speech recognition to capture professional performance, communication, and collaboration for automated feedback in full-mission simulator training

Key Sources¶

• Susan Harrington and Charlott Sellberg. (2026). 12 Heuristics for Learning Analytics in Simulation-Based Professional Learning. Journal of Learning Analytics, 13(1), 130-142. https://doi.org/10.18608/jla.2026.9141