Learning occupancy in single person offices with mixtures of multi-lag markov chains

Carlo Manna; Damien Fay; Kenneth N. Brown; Nic Wilson

doi:10.1109/ICTAI.2013.32

Learning occupancy in single person offices with mixtures of multi-lag markov chains

Carlo Manna
, Damien Fay
, Kenneth N. Brown
, Nic Wilson

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

Abstract

The problem of real-time occupancy forecastingfor single person offices is critical for energy efficient buildings which use predictive control techniques. Due to the highly uncertain nature of occupancy dynamics, the modeling and prediction of occupancy is a challenging problem. This paper proposes an algorithm for learning and predicting single occupant presence in office buildings, by considering the occupant behaviour as an ensemble of multiple Markov models at different time lags. This model has been tested using real occupancy data collected from PIR sensors installed in three different buildings and compared with state of the art methods, reducing the error rate by on average 5% over the best comparator method.

Original language	English
Title of host publication	Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013
Pages	151-158
Number of pages	8
DOIs	https://doi.org/10.1109/ICTAI.2013.32
Publication status	Published - 2013
Event	25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013 - Washington, DC, United States Duration: 4 Nov 2013 → 6 Nov 2013

Publication series

Name	Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
ISSN (Print)	1082-3409

Conference

Conference	25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013
Country/Territory	United States
City	Washington, DC
Period	4/11/13 → 6/11/13

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

UCC Futures

Artificial Intelligence and Data Analytics

Keywords

Building control
Markov chains
Occupancy prediction

Access to Document

10.1109/ICTAI.2013.32

Cite this

Manna, C., Fay, D., Brown, K. N., & Wilson, N. (2013). Learning occupancy in single person offices with mixtures of multi-lag markov chains. In Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013 (pp. 151-158). Article 6735243 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI). https://doi.org/10.1109/ICTAI.2013.32

@inproceedings{a999c5873b6445d6b4b8fd650d0f5085,

title = "Learning occupancy in single person offices with mixtures of multi-lag markov chains",

abstract = "The problem of real-time occupancy forecastingfor single person offices is critical for energy efficient buildings which use predictive control techniques. Due to the highly uncertain nature of occupancy dynamics, the modeling and prediction of occupancy is a challenging problem. This paper proposes an algorithm for learning and predicting single occupant presence in office buildings, by considering the occupant behaviour as an ensemble of multiple Markov models at different time lags. This model has been tested using real occupancy data collected from PIR sensors installed in three different buildings and compared with state of the art methods, reducing the error rate by on average 5\% over the best comparator method.",

keywords = "Building control, Markov chains, Occupancy prediction",

author = "Carlo Manna and Damien Fay and Brown, \{Kenneth N.\} and Nic Wilson",

year = "2013",

doi = "10.1109/ICTAI.2013.32",

language = "English",

isbn = "9781479929719",

series = "Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI",

pages = "151--158",

booktitle = "Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013",

note = "25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013 ; Conference date: 04-11-2013 Through 06-11-2013",

}

Manna, C, Fay, D, Brown, KN & Wilson, N 2013, Learning occupancy in single person offices with mixtures of multi-lag markov chains. in Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013., 6735243, Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI, pp. 151-158, 25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013, Washington, DC, United States, 4/11/13. https://doi.org/10.1109/ICTAI.2013.32

Learning occupancy in single person offices with mixtures of multi-lag markov chains. / Manna, Carlo; Fay, Damien; Brown, Kenneth N. et al.
Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013. 2013. p. 151-158 6735243 (Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI).

Research output: Chapter in Book/Report/Conference proceedings › Conference proceeding › peer-review

TY - GEN

T1 - Learning occupancy in single person offices with mixtures of multi-lag markov chains

AU - Manna, Carlo

AU - Fay, Damien

AU - Brown, Kenneth N.

AU - Wilson, Nic

PY - 2013

Y1 - 2013

N2 - The problem of real-time occupancy forecastingfor single person offices is critical for energy efficient buildings which use predictive control techniques. Due to the highly uncertain nature of occupancy dynamics, the modeling and prediction of occupancy is a challenging problem. This paper proposes an algorithm for learning and predicting single occupant presence in office buildings, by considering the occupant behaviour as an ensemble of multiple Markov models at different time lags. This model has been tested using real occupancy data collected from PIR sensors installed in three different buildings and compared with state of the art methods, reducing the error rate by on average 5% over the best comparator method.

AB - The problem of real-time occupancy forecastingfor single person offices is critical for energy efficient buildings which use predictive control techniques. Due to the highly uncertain nature of occupancy dynamics, the modeling and prediction of occupancy is a challenging problem. This paper proposes an algorithm for learning and predicting single occupant presence in office buildings, by considering the occupant behaviour as an ensemble of multiple Markov models at different time lags. This model has been tested using real occupancy data collected from PIR sensors installed in three different buildings and compared with state of the art methods, reducing the error rate by on average 5% over the best comparator method.

KW - Building control

KW - Markov chains

KW - Occupancy prediction

UR - https://www.scopus.com/pages/publications/84897706359

U2 - 10.1109/ICTAI.2013.32

DO - 10.1109/ICTAI.2013.32

M3 - Conference proceeding

AN - SCOPUS:84897706359

SN - 9781479929719

T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI

SP - 151

EP - 158

BT - Proceedings - 25th International Conference on Tools with Artificial Intelligence, ICTAI 2013

T2 - 25th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2013

Y2 - 4 November 2013 through 6 November 2013

ER -

Learning occupancy in single person offices with mixtures of multi-lag markov chains

Abstract

Publication series

Conference

UN SDGs

UCC Futures

Keywords

Access to Document

Other files and links

Fingerprint

Cite this