Approximation of simulation-derived visual comfort indicators in office spaces: a comparative study in machine learning
- 14 August 2015
- journal article
- research article
- Published by Informa UK Limited in Architectural Science Review
- Vol. 59 (4), 307-322
- https://doi.org/10.1080/00038628.2015.1072705
Abstract
In performance-oriented architectural design, the use of advanced computational simulation tools may provide valuable insight during design. However, the use of such tools is often a bottleneck in the design process, given that computational requirements are usually high. This is a fact that mostly affects the early conceptual stage of design, where crucial decisions mainly occur, and available time is limited. In order to deal with this, decision-makers frequently resort to drawing conclusions from experience, and, as such, valuable insight that advanced computational methods have to offer is lost. This paper explores an alternative approach, which builds on machine-learning algorithms that inductively learn from simulation-derived data, yielding models that approximate to a good degree and are orders of magnitude faster. We focus on visual comfort of office spaces. This is a type of space that specifically requires visual comfort more than others. Three machine-learning methods are compared with respect to applicability in approximating daylight autonomy and daylight glare probability. The comparison focuses on accuracy and time cost of training and estimation. Results demonstrate that machine-learning-based approaches achieve a favourable trade-off between accuracy and computational cost, and provide a worthwhile alternative for performance evaluations during architectural conceptual design.Keywords
This publication has 16 references indexed in Scilit:
- Real Time Head Pose Estimation from Consumer Depth CamerasLecture Notes in Computer Science, 2011
- Artificial neural networks to predict daylight illuminance in office buildingsJournal of Affective Disorders, 2009
- Prediction of building energy consumption by using artificial neural networksAdvances in Engineering Software, 2009
- Comparison between detailed model simulation and artificial neural network for forecasting building energy consumptionEnergy and Buildings, 2008
- Applying support vector machines to predict building energy consumption in tropical regionEnergy and Buildings, 2005
- kernlab- AnS4Package for Kernel Methods inRJournal of Statistical Software, 2004
- A comprehensive survey of fitness approximation in evolutionary computationSoft Computing, 2003
- Random ForestsMachine Learning, 2001
- Neural Networks as Decision Support System for Energy Efficient Building DesignArchitectural Science Review, 1997
- Integration of Simulation, Learning and Optimization to Support Engineering DesignCIRP Annals, 1991