Hidden Markov model for improved ultrasound-based presence detection

P.A. Jaramillo Garcia; J.P.M.G. Linnartz

doi:10.1109/CIT/IUCC/DASC/PICOM.2015.14

Hidden Markov model for improved ultrasound-based presence detection

P.A. Jaramillo Garcia, J.P.M.G. Linnartz

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

10 Citations (Scopus)

Abstract

Adaptive lighting systems typically use a presence detector to save energy by switching off lights in unoccupied rooms. However, it is highly annoying when lights are erroneously turned off while a user is present (false negative, FN). This paper focuses on the estimation of presence, using a Hidden Markov Model (HMM) in a ultrasound-based presence detection system. Our results show that estimating the Log Likelihood Ratio (LLR) of presence / no-presence in real-time can achieve improvements in the accuracy of presence detection. We compare the performance of the LLR algorithm with previous presence detection algorithms. Moreover we use the concepts of receiver operating curves and a genius (perfect) detector to benchmark the trade-off between energy consumption and user comfort.

Original language	English
Title of host publication	2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom
Place of Publication	Brussels
Publisher	IEEE Computer Society
Pages	68-74
ISBN (Print)	978-1-5090-0153-8
DOIs	https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.14
Publication status	Published - 28 Oct 2015
Event	15th IEEE International Conference on Computer and Information Technology (CIT-2015) - Jurys Inn Liverpool Hotel, Liverpool, United Kingdom Duration: 26 Oct 2015 → 28 Oct 2015 Conference number: 15 http://cse.stfx.ca/~cit2015/

Conference

Conference	15th IEEE International Conference on Computer and Information Technology (CIT-2015)
Abbreviated title	CIT-2015
Country/Territory	United Kingdom
City	Liverpool
Period	26/10/15 → 28/10/15
Internet address	http://cse.stfx.ca/~cit2015/

UN SDGs

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

Access to Document

10.1109/CIT/IUCC/DASC/PICOM.2015.14

Cite this

Jaramillo Garcia, P. A., & Linnartz, J. P. M. G. (2015). Hidden Markov model for improved ultrasound-based presence detection. In 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom (pp. 68-74). IEEE Computer Society. https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.14

Jaramillo Garcia, P.A. ; Linnartz, J.P.M.G. / Hidden Markov model for improved ultrasound-based presence detection. 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom. Brussels : IEEE Computer Society, 2015. pp. 68-74

@inproceedings{3bda9e611b85453699d00963224e071f,

title = "Hidden Markov model for improved ultrasound-based presence detection",

abstract = "Adaptive lighting systems typically use a presence detector to save energy by switching off lights in unoccupied rooms. However, it is highly annoying when lights are erroneously turned off while a user is present (false negative, FN). This paper focuses on the estimation of presence, using a Hidden Markov Model (HMM) in a ultrasound-based presence detection system. Our results show that estimating the Log Likelihood Ratio (LLR) of presence / no-presence in real-time can achieve improvements in the accuracy of presence detection. We compare the performance of the LLR algorithm with previous presence detection algorithms. Moreover we use the concepts of receiver operating curves and a genius (perfect) detector to benchmark the trade-off between energy consumption and user comfort.",

author = "{Jaramillo Garcia}, P.A. and J.P.M.G. Linnartz",

year = "2015",

month = oct,

day = "28",

doi = "10.1109/CIT/IUCC/DASC/PICOM.2015.14",

language = "English",

isbn = "978-1-5090-0153-8 ",

pages = "68--74",

booktitle = "2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom",

publisher = "IEEE Computer Society",

address = "United States",

note = "15th IEEE International Conference on Computer and Information Technology (CIT-2015), CIT-2015 ; Conference date: 26-10-2015 Through 28-10-2015",

url = "http://cse.stfx.ca/~cit2015/",

}

Jaramillo Garcia, PA & Linnartz, JPMG 2015, Hidden Markov model for improved ultrasound-based presence detection. in 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom. IEEE Computer Society, Brussels, pp. 68-74, 15th IEEE International Conference on Computer and Information Technology (CIT-2015), Liverpool, United Kingdom, 26/10/15. https://doi.org/10.1109/CIT/IUCC/DASC/PICOM.2015.14

Hidden Markov model for improved ultrasound-based presence detection. / Jaramillo Garcia, P.A.; Linnartz, J.P.M.G.
2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom. Brussels: IEEE Computer Society, 2015. p. 68-74.

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

TY - GEN

T1 - Hidden Markov model for improved ultrasound-based presence detection

AU - Jaramillo Garcia, P.A.

AU - Linnartz, J.P.M.G.

N1 - Conference code: 15

PY - 2015/10/28

Y1 - 2015/10/28

N2 - Adaptive lighting systems typically use a presence detector to save energy by switching off lights in unoccupied rooms. However, it is highly annoying when lights are erroneously turned off while a user is present (false negative, FN). This paper focuses on the estimation of presence, using a Hidden Markov Model (HMM) in a ultrasound-based presence detection system. Our results show that estimating the Log Likelihood Ratio (LLR) of presence / no-presence in real-time can achieve improvements in the accuracy of presence detection. We compare the performance of the LLR algorithm with previous presence detection algorithms. Moreover we use the concepts of receiver operating curves and a genius (perfect) detector to benchmark the trade-off between energy consumption and user comfort.

AB - Adaptive lighting systems typically use a presence detector to save energy by switching off lights in unoccupied rooms. However, it is highly annoying when lights are erroneously turned off while a user is present (false negative, FN). This paper focuses on the estimation of presence, using a Hidden Markov Model (HMM) in a ultrasound-based presence detection system. Our results show that estimating the Log Likelihood Ratio (LLR) of presence / no-presence in real-time can achieve improvements in the accuracy of presence detection. We compare the performance of the LLR algorithm with previous presence detection algorithms. Moreover we use the concepts of receiver operating curves and a genius (perfect) detector to benchmark the trade-off between energy consumption and user comfort.

U2 - 10.1109/CIT/IUCC/DASC/PICOM.2015.14

DO - 10.1109/CIT/IUCC/DASC/PICOM.2015.14

M3 - Conference contribution

SN - 978-1-5090-0153-8

SP - 68

EP - 74

BT - 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom

PB - IEEE Computer Society

CY - Brussels

T2 - 15th IEEE International Conference on Computer and Information Technology (CIT-2015)

Y2 - 26 October 2015 through 28 October 2015

ER -

Jaramillo Garcia PA, Linnartz JPMG. Hidden Markov model for improved ultrasound-based presence detection. In 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing (CIT/IUCC/DASC/PICOM), 26-28 October 2015, Liverpool, United Kingdom. Brussels: IEEE Computer Society. 2015. p. 68-74 doi: 10.1109/CIT/IUCC/DASC/PICOM.2015.14

Hidden Markov model for improved ultrasound-based presence detection

Abstract

Conference

UN SDGs

Access to Document

Fingerprint

Cite this