A Knowledge-driven Multicriteria Decision Support System for Intelligent Building Assessment

The missions of research into Building Intelligence Assessment (BIA) are to maximize the quality of life, to maximize the value for money, and to minimize the demands for energy. In accordance with these missions, the BIA research will focus on develop novel decisionmaking approaches to real-time IB performance. Literature review reveals that current intelligent building (IB) rating systems such as the IB Index from the Asian Institute of Intelligent Buildings (AIIB) and the MATOOL from the Building Research Establishment Ltd. (BRE) can’t reflect interrelations between each two key performance indicators (KPIs) that lead to their weakness in IB assessment. To overcome limitations in current IB rating systems, this paper presents a knowledge-driven multicriteria decision-making method for IB assessment by integrating an artificial neural network (ANN) model with an analytic network process (ANP) model under supports from an IB database. As an innovative decision-making approach, the ANP has been used to salve problems for complex social and natural systems in the past near ten years; however, the complex system analysis and control require more efficient tools to accelerate decision-making process. In this regards, the ANP approach has limitations to popularize its decision-making models, especially when there are too many indicators involved in an ANP model for a complex system. The aim of this integration is to enhance traditional ANP approach with artificial intelligence for solving real-world decisionmaking problems relevant to complex IB systems. A case study is used to demonstrate the effectiveness of the proposed intelligent multicriteria decision support system. The case study will focus on the complex process of IBs through their lifecycle phases including design, construction and maintainance, in which the dynamic nature of participants, their activities, and relevant social, environmental, economic and engineering factors structures the complex system of IBs for the sustainable built environment.