AI-Driven Optimization of Smart Spaces: A WASPAS Decision Model to Intelligent Environment Design

Smart spaces are continually developing, needing cutting-edge ideas for better intelligent environment design to increase user experience, energy efficiency, and operational performance. This research presents a unique computational strategy that addresses the challenges of smart space design by leveraging AI-driven optimization principles. To handle uncertainty and imprecision in data, we propose merging Dempster-Shafer Fuzzy Sets (DSFS) with the Weighted Aggregated Sum Product Assessment (WASPAS) method for multi-criteria decisions. The DSFS framework enables robust modeling of ambiguous and conflicting information, while the WASPAS technique ensures a balanced assessment of competing design objectives. Through case studies in office and residential smart environments, our approach demonstrated a 15Ű22% improvement in energy efficiency, a 12Ű18% enhancement in user comfort scores, and a 20% reduction in system response latency compared to conventional methods. Additionally, the hybrid DSFS-WASPAS model showed 92.3% accuracy in resolving conflicting design constraints under uncertainty. These results highlight the efficacy of AI-driven optimization in smart space layouts, offering scalable and adaptable solutions for future intelligent environments. This study contributes to intelligent environment design by presenting a comprehensive, computationally efficient, and uncertainty-aware strategy.