Artificial Intelligence for Building Defect Detection: A Systematic Review of Techniques and Benefits

The adoption of artificial intelligence (AI) techniques for detecting building defects has significantly transformed traditional inspection methods in recent years. However, the application of AI techniques for detecting building defects and their benefits is limited. This study aimed to examine applications of AI in defect detection and their benefits through a systematic literature review (SLR). Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework guidelines, 39 journal documents were retrieved from the Scopus and Web of Science (WoS) databases. The study found that six AI techniques were employed: machine learning (ML), computer vision, natural language processing (NLP), knowledge-based systems (KBS), automated planning and Scheduling (APS), and optimization. The findings indicated that ML, computer vision, and NLP are emerging techniques that have been most widely used in recent years because of their increased accuracy, efficiency, and real-time monitoring capabilities. The study findings address the knowledge gap in the current literature and could assist practitioners and stakeholders in implementing AI techniques for detecting building defects.