Exploring the Application of Deep Learning in Enhancing The QLASSIC: A Review

Abstract

As society evolves, there is an increasing demand for quality living spaces. However, defects in new housing have become a growing concern for homeowners. To address this, the Construction Industry Development Board Malaysia (CIDB) introduced the Quality Assessment System in Construction (QLASSIC), quantifying construction quality. Meanwhile, deep learning has emerged as a highly accurate method for defect detection, surpassing traditional techniques and gaining widespread use in various industrial applications. This paper searches and analyzes 181 articles' keywords by the google scholar database. It first explores housing quality assessment practices from various countries as the research background. Then it centers on reviewing the current QLASSIC practices. Since QLASSIC evaluates construction quality largely through visual defects (comprising approximately 70% of its criteria), the potential application of deep learning, which has attracted significant interest, is also being discussed. Towards the end of this review paper, future research directions are also suggested.