AI-Based Classification Model for Low-Energy Buildings: Promoting Sustainable Economic Development of Smart Cities With Spherical Fuzzy Decision Algorithm

Abstract

AI-based classification models for low-energy buildings are essential in promoting the economic development of smart cities by optimizing energy use, reducing operational costs, and enhancing overall efficiency. These models classify buildings based on energy consumption patterns, predicting energy needs and identifying areas for improvement. The spherical fuzzy set (SFS) is a potent approach used to handle ambiguous information during decision analysis and integrate big expert’s opinions. This article evaluates intelligent AI-based models for low-energy buildings and economic development under some specific characteristics or key features. For this purpose, we modified the theory of criteria importance through intercriteria correlation (CRITIC) and combined compromise solution (COCOSO) methods to assess suitable optimal options for the multi-attribute group decision-making (MAGDM) problem. Moreover, we also propose a novel decision algorithm of the CRITIC-COCOSO method under consideration of spherical fuzzy situations. The CRITIC-COCOSO method has great capabilities to investigate weights of criterion and accurate ranking of preferences under specific linguistic scales. An experimental case study is established to investigate a reliable AI-based advanced technology and prove the superiority of diagnosed theories. Additionally, a robust comparison method is used to prove the supremacy of derived theories and pioneered mathematical terminologies. In the end, some key features and remarkable comments are also discussed.

Keywords

• Spherical fuzzy information
• Schweizer-Sklar operators
• CRITIC-COCOSO method and decision-making process