Gaussian Process models for ubiquitous user comfort preference sampling; global priors, active sampling and outlier rejection

Authors: Fay, D., O'Toole, L. and Brown, K.

http://eprints.bournemouth.ac.uk/24915/

Journal: Pervasive and Mobile Computing

ISSN: 1873-1589

This paper presents a ubiquitous thermal comfort preference learning study in a noisy environment. We introduce Gaussian Process models into this field and show they are ideal, allowing rejection of outliers, deadband samples, and produce excellent estimates of a users preference function. In addition, informative combinations of users preferences becomes possible, some of which demonstrate well defined maxima ideal for control signals. Interestingly, while those users studied have differing preferences, their hyperparameters are concentrated allowing priors for new users.

In addition, we present an active learning algorithm which estimates when to poll users to maximise the information returned.

This data was imported from Scopus:

Authors: Fay, D., O'Toole, L. and Brown, K.N.

http://eprints.bournemouth.ac.uk/24915/

Journal: Pervasive and Mobile Computing

Volume: 39

Pages: 135-158

ISSN: 1574-1192

DOI: 10.1016/j.pmcj.2016.08.012

© 2016 This paper presents a ubiquitous thermal comfort preference learning study in a noisy environment. We introduce Gaussian Process models into this field and show they are ideal, allowing rejection of outliers, deadband samples, and produce excellent estimates of a users preference function. In addition, informative combinations of users preferences becomes possible, some of which demonstrate well defined maxima ideal for control signals. Interestingly, while those users studied have differing preferences, their hyperparameters are concentrated allowing priors for new users. In addition, we present an active learning algorithm which estimates when to poll users to maximise the information returned.

This source preferred by Damien Fay

This data was imported from Web of Science (Lite):

Authors: Fay, D., O'Toole, L. and Brown, K.N.

http://eprints.bournemouth.ac.uk/24915/

Journal: PERVASIVE AND MOBILE COMPUTING

Volume: 39

Pages: 135-158

eISSN: 1873-1589

ISSN: 1574-1192

DOI: 10.1016/j.pmcj.2016.08.012

The data on this page was last updated at 04:47 on December 17, 2017.