AI-Enhanced Semantic IoT Framework for Smart City Management Information Systems

Abstract

Rapid advances in the Internet of Things (IoT) and artificial intelligence (AI) have transformed smart city management, but the resulting data deluge challenges traditional Management Information Systems (MIS). Conventional data-centric networks struggle with bandwidth and latency constraints, while smart city MIS requires real-time, context-aware insights. This paper proposes an integrated conceptual framework that combines semantic communications and AI-driven data analytics to enhance MIS in IoT-enabled smart cities. The framework uses semantic encoding at the IoT edge to transmit meaningful context rather than raw data, and employs AI models for decision support. We simulate a representative smart-city use case (traffic monitoring), implementing the proposed framework in an edge-cloud environment. Key contributions include the design of the semantic-AI MIS architecture and a replicable simulation scenario. In experiments, our approach improved decision accuracy by ~15% and reduced data transmission by ~20% compared to a baseline MIS using raw data. These results demonstrate that semantic-aware AI processing can significantly alleviate network load while enhancing analytical performance. The findings have practical implications for scalable smart city MIS, suggesting new directions for AI and communication co-design. Our study bridges gaps in current research by integrating semantic communication concepts with AI in organizational decision systems.