Predicting energy cost of public buildings by artificial neural networks, CART, and random forest
Authors:
- Marijana Zekić-SušacMZMarijana Zekić-Sušac
- Adela HasAHAdela Has
- Marinela KneževićMKMarinela Knežević
- 1 June 2021
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 439, 223-233
Abstract
No abstract availableKeywords
Funding Information
- Asia-Pacific Network for Global Change Research
- Hrvatska Zaklada za Znanost (IP-2016-06-8350)
This publication has 31 references indexed in Scilit:
- An occupant-based energy consumption prediction model for office equipmentEnergy and Buildings, 2015
- Handling data uncertainties when using Swedish energy performance certificate data to describe energy usage in the building stockEnergy and Buildings, 2015
- A better measure of relative prediction accuracy for model selection and model estimationJournal of the Operational Research Society, 2015
- RETRACTED ARTICLE: Soft computing methodologies for estimation of energy consumption in buildings with different envelope parametersEnergy Efficiency, 2015
- Deep learningNature, 2015
- Random Forests2012
- Variable Importance Assessment in Regression: Linear Regression versus Random ForestThe American Statistician, 2009
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009
- Unbiased Recursive Partitioning: A Conditional Inference FrameworkJournal of Computational and Graphical Statistics, 2006
- Data mining with decision trees and decision rulesFuture Generation Computer Systems, 1997