Search

AI for AEC The article surveys current methods of data integration, artificial intelligence (AI), optimization, and control and their (potential) applications in architecture, engineering and construction. The survey includes symbolic AI‐methods as well as subsymbolic AI methods, i. e., machine learning. The article presents these methods in the context of applications that provide insight into current research projects at the Cluster of Excellence "Integrative Computational Design and Construction for Architecture" (IntCDC) at the University of Stuttgart: (1) Data integration to link data silos in design and construction processes, (2) knowledge graphs to represent knowledge in multidisciplinary design processes, (3) automated planning for scheduling and distribution of construction tasks, (4) supervised learning to estimate the results of expensive building simulations such as operational energy or of the behavior of natural materials such as wood, (5) unsupervised learning to visualize optimization results, (6) reinforcement learning for building with fibers and bamboo, and (8) control for construction robotics. The article concludes that integrative computational design and construction requires the cooperation of humans, material, and machines, and that AI – instead of merely automating design and construction processes – can moderate this cooperation. [ABSTRACT FROM AUTHOR]

Duplicate detection determines different representations of real-world objects in a database. Recent research has considered the use of relationships among object representations to improve duplicate detection. In the general case where relationships form a graph, research has mainly focused on duplicate detection quality/effectiveness. Scalability has been neglected so far, even though it is crucial for large real-world duplicate detection tasks. We scale-up duplicate detection in graph data (ddg) to large amounts of data and pairwise comparisons, using the support of a relational database management system. To this end, we first present a framework that generalizes the ddg process. We then present algorithms to scale ddg in space (amount of data processed with bounded main memory) and in time. Finally, we extend our framework to allow batched and parallel ddg, thus further improving efficiency. Experiments on data of up to two orders of magnitude larger than data considered so far in ddg show that our methods achieve the goal of scaling ddg to large volumes of data. [ABSTRACT FROM AUTHOR]