Presentation
Human Factors in AI-Enabled Decision Support for Industry 4.0/5.0: A Scoping Review of Technical and Empirical Validation
DescriptionArtificial intelligence (AI) is increasingly integrated into industrial decision-support systems across manufacturing, aviation maintenance, and other safety-critical domains. In Industry 4.0 and emerging Industry 5.0 environments, workers are required to interpret and act on AI-generated recommendations, shifting cognitive demands toward human–AI collaboration. This study presents a scoping review examining how AI-enabled decision-support systems are designed and evaluated from a human factors perspective. A structured review of 15 studies revealed that while AI systems commonly incorporate technical explainability methods such as SHAP, LIME, and retrieval-augmented generation, there is limited empirical validation of their impact on human performance. Although trust and situation awareness are frequently discussed, they are rarely measured using validated human factors instruments. Notably, no studies reported standardized cognitive workload assessments, and usability evaluations were limited. These findings highlight a critical gap between technical system design and human-centered validation. The results suggest that current AI systems may not adequately support operator cognitive performance or calibrated reliance in high-risk environments. This work emphasizes the need to integrate validated human factors measures into the design and evaluation of AI-enabled decision-support systems to ensure safe and effective human–AI collaboration.
Event Type
Lecture
TimeTuesday, October 20th4:30pm - 4:50pm PDT
Location