Data-driven assessment competencies for AIoT-enhanced traffic management: A framework for educators

This paper, developed through a literature-informed conceptual synthesis, focused on how integrating Artificial Intelligence and the Internet of Things (AIoT) enables new approaches to urban traffic management through intelligent data collection, real-time analytics, and automated decision-making. Despite rapid technological advances, existing curricula and assessment frameworks provide little guidance for competency-based assessment, learning analytics, and institutional implementation in AIoT-enhanced traffic management education. Accordingly, the authors developed conceptual frameworks that support competency-based assessment and institutional implementation for AIoT-enhanced traffic management education. Drawing on contemporary literature in AIoT, competency-based education, learning analytics, authentic assessment, and digital education, two complementary conceptual frameworks were develop. The proposed Data-Driven Assessment Competency Framework (DACF) is associated competency domains, learning outcomes, authentic assessment tasks, evidence sources, AI-assisted analytics, educator judgement, analytic rubrics, feedback, and competency decisions. The accompanying AIoT Assessment Implementation Framework (AAIF) provides direction for strategic alignment, curriculum integration, infrastructure development, educator capacity building, and continuous evaluation to support sustainable institutional implementation. The authors further present competency progression levels, worked examples of assessments, analytic rubrics, assessment weighting, human-in-the-loop assessment practices, and quality assurance processes to support transparent and evidence-informed competency assessment. Unlike existing competency, digital education, or AI literacy frameworks, DACF and AAIF integrate competency mapping, authentic assessment, learning analytics, multi-source evidence, educator judgement, and institutional implementation within a unified model tailored to AIoT-enhanced traffic management education. Finally, the paper presents policy recommendations, a structured validation roadmap, and future research priorities to guide empirical validation and advance AIoT-enhanced traffic management education for smart city mobility.