Fault detection for binary sensors in smart home environments

Juan Ye; Graeme Stevenson; Simon Dobson

doi:10.1109/PERCOM.2015.7146505

Fault detection for binary sensors in smart home environments

Juan Ye, Graeme Stevenson, Simon Dobson

School of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Experiments in assisted living confirm that such systems can provide context-aware services that enable occupants to remain active and independent. They also demonstrate that abnormal sensor events hamper the correct identification of critical (and potentially life-threatening) situations, and that existing learning, estimation, and time-based approaches are inaccurate and inflexible when applied to multiple people sharing a living space. We propose a technique that integrates the semantics of sensor readings with statistical outlier detection. We evaluate the technique against four real-world datasets that include multiple individuals, and show consistent rates of anomaly detection across different environments.

Original language	English
Title of host publication	2015 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Publisher	IEEE Computer Society
Pages	20-28
Number of pages	9
DOIs	https://doi.org/10.1109/PERCOM.2015.7146505
Publication status	Published - 23 Mar 2015
Event	IEEE International Conference on Pervasive Computing and Communications (PerCom 2015) - Renaissance St. Louis Grand Hotel, St Louis, Missouri, United States Duration: 23 Mar 2015 → 27 Mar 2015

Conference

Conference	IEEE International Conference on Pervasive Computing and Communications (PerCom 2015)
Country/Territory	United States
City	St Louis, Missouri
Period	23/03/15 → 27/03/15

Keywords

Wireless sensor network
Fault detection
Activity recognition
Ontologies

Access to Document

10.1109/PERCOM.2015.7146505

binarysensorfaults-15
© 2015. IEEE. This is the accepted mansucript of a conference paper originally submitted to the IEEE International Conference on Pervasive Computing and Communications, Fault detection for binary sensors in smart home environments Ye, J., Stevenson, G. & Dobson, S. 23 Mar 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom 2015). IEEE Computer Society, available from http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000551
Accepted author manuscript, 2.92 MB

Cite this

@inproceedings{f6ce957134454759abfac073ffbed292,

title = "Fault detection for binary sensors in smart home environments",

abstract = "Experiments in assisted living confirm that such systems can provide context-aware services that enable occupants to remain active and independent. They also demonstrate that abnormal sensor events hamper the correct identification of critical (and potentially life-threatening) situations, and that existing learning, estimation, and time-based approaches are inaccurate and inflexible when applied to multiple people sharing a living space. We propose a technique that integrates the semantics of sensor readings with statistical outlier detection. We evaluate the technique against four real-world datasets that include multiple individuals, and show consistent rates of anomaly detection across different environments.",

keywords = "Wireless sensor network, Fault detection, Activity recognition, Ontologies",

author = "Juan Ye and Graeme Stevenson and Simon Dobson",

year = "2015",

month = mar,

day = "23",

doi = "10.1109/PERCOM.2015.7146505",

language = "English",

pages = "20--28",

booktitle = "2015 IEEE International Conference on Pervasive Computing and Communications (PerCom)",

publisher = "IEEE Computer Society",

address = "United States",

note = "IEEE International Conference on Pervasive Computing and Communications (PerCom 2015) ; Conference date: 23-03-2015 Through 27-03-2015",

}

Ye, J, Stevenson, G & Dobson, S 2015, Fault detection for binary sensors in smart home environments. in 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE Computer Society, pp. 20-28, IEEE International Conference on Pervasive Computing and Communications (PerCom 2015), St Louis, Missouri, United States, 23/03/15. https://doi.org/10.1109/PERCOM.2015.7146505

TY - GEN

T1 - Fault detection for binary sensors in smart home environments

AU - Ye, Juan

AU - Stevenson, Graeme

AU - Dobson, Simon

PY - 2015/3/23

Y1 - 2015/3/23

N2 - Experiments in assisted living confirm that such systems can provide context-aware services that enable occupants to remain active and independent. They also demonstrate that abnormal sensor events hamper the correct identification of critical (and potentially life-threatening) situations, and that existing learning, estimation, and time-based approaches are inaccurate and inflexible when applied to multiple people sharing a living space. We propose a technique that integrates the semantics of sensor readings with statistical outlier detection. We evaluate the technique against four real-world datasets that include multiple individuals, and show consistent rates of anomaly detection across different environments.

AB - Experiments in assisted living confirm that such systems can provide context-aware services that enable occupants to remain active and independent. They also demonstrate that abnormal sensor events hamper the correct identification of critical (and potentially life-threatening) situations, and that existing learning, estimation, and time-based approaches are inaccurate and inflexible when applied to multiple people sharing a living space. We propose a technique that integrates the semantics of sensor readings with statistical outlier detection. We evaluate the technique against four real-world datasets that include multiple individuals, and show consistent rates of anomaly detection across different environments.

KW - Wireless sensor network

KW - Fault detection

KW - Activity recognition

KW - Ontologies

UR - http://www.percom.org/

U2 - 10.1109/PERCOM.2015.7146505

DO - 10.1109/PERCOM.2015.7146505

M3 - Conference contribution

SP - 20

EP - 28

BT - 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom)

PB - IEEE Computer Society

T2 - IEEE International Conference on Pervasive Computing and Communications (PerCom 2015)

Y2 - 23 March 2015 through 27 March 2015

ER -

Fault detection for binary sensors in smart home environments

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this