This study presents an artificial intelligence technique based on ensemble of artificial neural networks for the purposes of analysis and prediction of labour productivity. The study focuses on the development of model that combines several artificial neural networks on the basis of real-life data collected on a construction site for steel reinforcement works. The data includes conditions, characteristics, features of steel reinforcement works and related efficiencies of workers assigned to particular tasks recorded on site. The proposed ensemble based model combines five supervised learning models — five different multilayer perceptron networks, which contribution in the prediction is weighted due to the application of generalised averaging approach. Testing results show that the proposed ensemble based model achieves the satisfactory evaluation criteria for coefficient of correlation (0.989), root-mean-squared error (2.548), mean absolute percentage error (4.65%) and maximum absolute percentage error (8.98%).

Due to the organization of construction works, one of the most difficult situations is when a building is planned in a heritage or a densely built-up location. Fixing an existing situation manually takes a lot of time and effort and is usually not accurate. For example, it is not always possible to measure the exact spacing between buildings at different levels and to consider all outside elements of an existing building. Improper fixation of the existing situation causes mistakes and collisions in design and the use of inappropriate construction solutions. The development and progress in technologies such as BIM, laser scanning, and photogrammetry broaden the options for supporting the management of construction projects. It is important to have an effective fast collection and processing of useful information for management processes. The purpose of this paper is to analyze and present some aspects of photogrammetry to collect and process information about existing buildings. The methodology of the study is based on the comparison of two alternative approaches, namely photogrammetry and BIM modelling. Case studies present an analysis of the quantity take-offs for selected elements and parts of the buildings based on the two approaches. In this article, the specific use of photogrammetry shows that the error between the detailed BIM model and the photogrammetry model is only 1.02% and the accuracy is 98.98%. Moreover, physical capabilities do not always allow us to measure every desired element in reality. This is followed by a discussion on the usability of photogrammetry.