Search

The energy performance of buildings has become a main concern globally in response to increased energy demand, the environmental impacts of energy production, and the reality of energy poverty. To improve energy efficiency, proper building design should be secured at the early design phase. Digital tools are currently available for performing energy assessment analyses and can efficiently handle complex and technically demanding buildings. However, alternative designs should be checked individually, and this makes the process time-consuming and prone to errors. Machine learning techniques can provide valuable assistance in developing decision support tools. In this paper, typical residential buildings are considered along with eleven factors that highly affect energy performance. A dataset of 337 instances of such parameters is developed. For each dataset, the building energy performance is estimated based on BIM analysis. Next, statistical and machine learning techniques are implemented to provide artificial models of energy performance. They include statistical regression modeling (SRM), decision trees (DTs), random forests (RFs), and artificial neural networks (ANNs). The analysis reveals the contribution of each factor and highlights the ANN as the best performing model. An easy-to-use interface tool has been developed for the instantaneous calculation of the energy performance based on the independent parameter values. [ABSTRACT FROM AUTHOR]

Seismic risk assessment in bridge networks is of great interest in reducing earthquake adverse effects in structures and the society. Among existing methods for risk and loss assessment, Hazus methodology is widely accepted and used. The method includes several steps and calculations, being thus rather complex and time-consuming, especially if several bridges with diverse characteristics are to be examined. The present study investigates the potential of using soft computing techniques for determining the seismic hazard and expected losses as an alternative to the Hazus methodology. In particular, a number of representative datasets have been developed on the basis of Hazus and a number of methods have been formulated and tested regarding their capacity to effectively simulate the process. The methods that are examined range from regression curve-fitting to artificial neural networks of different size and characteristics. Alternative statistical tests have been used to evaluate the developed model capabilities. Evaluation results indicate that appropriately designed ANN methods can attain high accuracy and stable results among different datasets (training, testing, and validation). The analysis indicates the potential of using similar techniques to simulate seismic risk assessment based on actual data from earthquake events that have taken place in the past. [ABSTRACT FROM AUTHOR]