A Study on Several Machine Learning Methods for Estimating Cabin Occupant Equivalent Temperature

Diana Hintea, James Brusey, Elena Gaura

2015

Abstract

Occupant comfort oriented Heating, Ventilation and Air Conditioning (HVAC) control rises to the challenge of delivering comfort and reducing the energy budget. Equivalent temperature represents a more accurate predictor for thermal comfort than air temperature in the car cabin environment, as it integrates radiant heat and airflow. Several machine learning methods were investigated with the purpose of creating an estimator of cabin occupant equivalent temperature from sensors throughout the cabin, namely Multiple Linear Regression, MultiLayer Perceptron, Multivariate Adaptive Regression Splines, Radial Basis Function Network, REPTree, K-Nearest Neighbour and Random Forest. Experimental equivalent temperature and cabin data at 25 points was gathered in a variety of environmental conditions. A total of 30 experimental hours were used for training and evaluation of the estimator's performance. Most machine learning tehniques provided a Root Mean Square Error (RMSE) between 1.51 °C and 1.85 °C , while the Radial Basis Function Network performed the worst, with an average RMSE of 3.37 °C . The Multiple Linear Regression had an average RMSE of 1.60 °C over the eight body part equivalent temperatures and also had the fastest processing time, enabling a straightforward real-time implementation in a car's engine control unit.

Paper Citation

in Harvard Style

Hintea D., Brusey J. and Gaura E. (2015). A Study on Several Machine Learning Methods for Estimating Cabin Occupant Equivalent Temperature . In Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-122-9, pages 629-634. DOI: 10.5220/0005573606290634

in Bibtex Style

@conference{icinco15,
author={Diana Hintea and James Brusey and Elena Gaura},
title={A Study on Several Machine Learning Methods for Estimating Cabin Occupant Equivalent Temperature},
booktitle={Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2015},
pages={629-634},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005573606290634},
isbn={978-989-758-122-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - A Study on Several Machine Learning Methods for Estimating Cabin Occupant Equivalent Temperature
SN - 978-989-758-122-9
AU - Hintea D.
AU - Brusey J.
AU - Gaura E.
PY - 2015
SP - 629
EP - 634
DO - 10.5220/0005573606290634