An Anomaly Detection Study for the Smart Home Environment

Mehmet Erhan Bilgin; H. Hakan Kilinc; Abdul Halim Zaim

doi:10.1109/UBMK55850.2022.9919448

An Anomaly Detection Study for the Smart Home Environment

Mehmet Erhan Bilgin, H. Hakan Kilinc, Abdul Halim Zaim

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

2 Citations (Scopus)

Abstract

Unusual sensor data in smart homes may herald different problems based on sensor errors, security vulnera-bilities, activity and behavior changes. This study focuses on detecting anomalies and unusual situations in 7 different sensor data in a house. For this, a model created with a combination of unsupervised and supervised machine learning algorithms is used. The sensor data are labeled using Isolation Forest which is one of the unsupervised algorithms. Then, the data is trained with the supervised algorithms Decision Tree, Extra Trees, Random Forest and XGBoost classification algorithms. Anomaly decisions are made with an accuracy of over 99 percent.

Original language	English
Title of host publication	Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	31-36
Number of pages	6
ISBN (Electronic)	9781665470100
DOIs	https://doi.org/10.1109/UBMK55850.2022.9919448
Publication status	Published - 2022
Externally published	Yes
Event	7th International Conference on Computer Science and Engineering, UBMK 2022 - Diyarbakir, Turkey Duration: 14 Sept 2022 → 16 Sept 2022

Publication series

Name	Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022

Conference

Conference	7th International Conference on Computer Science and Engineering, UBMK 2022
Country/Territory	Turkey
City	Diyarbakir
Period	14/09/22 → 16/09/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Anomaly Detection
Edge Computing
IoT
Machine Learning
Smart Home

Access to Document

10.1109/UBMK55850.2022.9919448

Cite this

Bilgin, M. E., Kilinc, H. H., & Zaim, A. H. (2022). An Anomaly Detection Study for the Smart Home Environment. In Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022 (pp. 31-36). (Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/UBMK55850.2022.9919448

Bilgin, Mehmet Erhan ; Kilinc, H. Hakan ; Zaim, Abdul Halim. / An Anomaly Detection Study for the Smart Home Environment. Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 31-36 (Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022).

@inproceedings{6e8df06d4ce64509b67a43dcde0e6d39,

title = "An Anomaly Detection Study for the Smart Home Environment",

abstract = "Unusual sensor data in smart homes may herald different problems based on sensor errors, security vulnera-bilities, activity and behavior changes. This study focuses on detecting anomalies and unusual situations in 7 different sensor data in a house. For this, a model created with a combination of unsupervised and supervised machine learning algorithms is used. The sensor data are labeled using Isolation Forest which is one of the unsupervised algorithms. Then, the data is trained with the supervised algorithms Decision Tree, Extra Trees, Random Forest and XGBoost classification algorithms. Anomaly decisions are made with an accuracy of over 99 percent.",

keywords = "Anomaly Detection, Edge Computing, IoT, Machine Learning, Smart Home",

author = "Bilgin, {Mehmet Erhan} and Kilinc, {H. Hakan} and Zaim, {Abdul Halim}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 7th International Conference on Computer Science and Engineering, UBMK 2022 ; Conference date: 14-09-2022 Through 16-09-2022",

year = "2022",

doi = "10.1109/UBMK55850.2022.9919448",

language = "English",

series = "Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "31--36",

booktitle = "Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022",

address = "United States",

}

Bilgin, ME, Kilinc, HH & Zaim, AH 2022, An Anomaly Detection Study for the Smart Home Environment. in Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022. Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022, Institute of Electrical and Electronics Engineers Inc., pp. 31-36, 7th International Conference on Computer Science and Engineering, UBMK 2022, Diyarbakir, Turkey, 14/09/22. https://doi.org/10.1109/UBMK55850.2022.9919448

An Anomaly Detection Study for the Smart Home Environment. / Bilgin, Mehmet Erhan; Kilinc, H. Hakan; Zaim, Abdul Halim.
Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 31-36 (Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022).

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

TY - GEN

T1 - An Anomaly Detection Study for the Smart Home Environment

AU - Bilgin, Mehmet Erhan

AU - Kilinc, H. Hakan

AU - Zaim, Abdul Halim

PY - 2022

Y1 - 2022

N2 - Unusual sensor data in smart homes may herald different problems based on sensor errors, security vulnera-bilities, activity and behavior changes. This study focuses on detecting anomalies and unusual situations in 7 different sensor data in a house. For this, a model created with a combination of unsupervised and supervised machine learning algorithms is used. The sensor data are labeled using Isolation Forest which is one of the unsupervised algorithms. Then, the data is trained with the supervised algorithms Decision Tree, Extra Trees, Random Forest and XGBoost classification algorithms. Anomaly decisions are made with an accuracy of over 99 percent.

AB - Unusual sensor data in smart homes may herald different problems based on sensor errors, security vulnera-bilities, activity and behavior changes. This study focuses on detecting anomalies and unusual situations in 7 different sensor data in a house. For this, a model created with a combination of unsupervised and supervised machine learning algorithms is used. The sensor data are labeled using Isolation Forest which is one of the unsupervised algorithms. Then, the data is trained with the supervised algorithms Decision Tree, Extra Trees, Random Forest and XGBoost classification algorithms. Anomaly decisions are made with an accuracy of over 99 percent.

KW - Anomaly Detection

KW - Edge Computing

KW - IoT

KW - Machine Learning

KW - Smart Home

UR - http://www.scopus.com/inward/record.url?scp=85141836847&partnerID=8YFLogxK

U2 - 10.1109/UBMK55850.2022.9919448

DO - 10.1109/UBMK55850.2022.9919448

M3 - Conference contribution

AN - SCOPUS:85141836847

T3 - Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022

SP - 31

EP - 36

BT - Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on Computer Science and Engineering, UBMK 2022

Y2 - 14 September 2022 through 16 September 2022

ER -

Bilgin ME, Kilinc HH, Zaim AH. An Anomaly Detection Study for the Smart Home Environment. In Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 31-36. (Proceedings - 7th International Conference on Computer Science and Engineering, UBMK 2022). doi: 10.1109/UBMK55850.2022.9919448

An Anomaly Detection Study for the Smart Home Environment

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this