Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network

Tyler Cultice; Dan Ionel; Himanshu Thapliyal

doi:10.1109/iSES50453.2020.00026

Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network

Tyler Cultice
, Dan Ionel
, Himanshu Thapliyal

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

23 Scopus citations

Abstract

We propose an autoencoder based approach to anomaly detection in smart grid systems. Data collecting sensors within smart home systems are susceptible to many data corruption issues, such as malicious attacks or physical malfunctions. By applying machine learning to a smart home or grid, sensor anomalies can be detected automatically for secure data collection and sensor-based system functionality. In addition, we tested the effectiveness of this approach on real smart home sensor data collected for multiple years. An early detection of such data corruption issues is essential to the security and functionality of the various sensors and devices within a smart home.

Original language	English
Title of host publication	Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020
Pages	67-70
Number of pages	4
ISBN (Electronic)	9780738142647
DOIs	https://doi.org/10.1109/iSES50453.2020.00026
State	Published - Dec 2020
Event	6th IEEE International Symposium on Smart Electronic Systems, iSES 2020 - Virtual, Chennai, India Duration: Dec 14 2020 → Dec 16 2020

Publication series

Name	Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020

Conference

Conference	6th IEEE International Symposium on Smart Electronic Systems, iSES 2020
Country/Territory	India
City	Virtual, Chennai
Period	12/14/20 → 12/16/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

This research was supported by University of Kentucky ECE Undergraduate Fellowship Award by Schneider Electric.

Funders
University of Kentucky

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

Anomaly Detection
Cybersecurity
Machine Learning
Sensors
Smart Home

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Information Systems and Management
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality
Control and Optimization

Access to Document

10.1109/iSES50453.2020.00026

Cite this

Cultice, T., Ionel, D., & Thapliyal, H. (2020). Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network. In Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020 (pp. 67-70). Article 9426175 (Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020). https://doi.org/10.1109/iSES50453.2020.00026

@inproceedings{ce8ecc2660bf4d6a8ab4de7937e54490,

title = "Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network",

abstract = "We propose an autoencoder based approach to anomaly detection in smart grid systems. Data collecting sensors within smart home systems are susceptible to many data corruption issues, such as malicious attacks or physical malfunctions. By applying machine learning to a smart home or grid, sensor anomalies can be detected automatically for secure data collection and sensor-based system functionality. In addition, we tested the effectiveness of this approach on real smart home sensor data collected for multiple years. An early detection of such data corruption issues is essential to the security and functionality of the various sensors and devices within a smart home.",

keywords = "Anomaly Detection, Cybersecurity, Machine Learning, Sensors, Smart Home",

author = "Tyler Cultice and Dan Ionel and Himanshu Thapliyal",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020 ; Conference date: 14-12-2020 Through 16-12-2020",

year = "2020",

month = dec,

doi = "10.1109/iSES50453.2020.00026",

language = "English",

series = "Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020",

pages = "67--70",

booktitle = "Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020",

}

Cultice, T, Ionel, D & Thapliyal, H 2020, Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network. in Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020., 9426175, Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020, pp. 67-70, 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020, Virtual, Chennai, India, 12/14/20. https://doi.org/10.1109/iSES50453.2020.00026

Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network. / Cultice, Tyler; Ionel, Dan; Thapliyal, Himanshu.
Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020. 2020. p. 67-70 9426175 (Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020).

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

TY - GEN

T1 - Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network

AU - Cultice, Tyler

AU - Ionel, Dan

AU - Thapliyal, Himanshu

PY - 2020/12

Y1 - 2020/12

N2 - We propose an autoencoder based approach to anomaly detection in smart grid systems. Data collecting sensors within smart home systems are susceptible to many data corruption issues, such as malicious attacks or physical malfunctions. By applying machine learning to a smart home or grid, sensor anomalies can be detected automatically for secure data collection and sensor-based system functionality. In addition, we tested the effectiveness of this approach on real smart home sensor data collected for multiple years. An early detection of such data corruption issues is essential to the security and functionality of the various sensors and devices within a smart home.

AB - We propose an autoencoder based approach to anomaly detection in smart grid systems. Data collecting sensors within smart home systems are susceptible to many data corruption issues, such as malicious attacks or physical malfunctions. By applying machine learning to a smart home or grid, sensor anomalies can be detected automatically for secure data collection and sensor-based system functionality. In addition, we tested the effectiveness of this approach on real smart home sensor data collected for multiple years. An early detection of such data corruption issues is essential to the security and functionality of the various sensors and devices within a smart home.

KW - Anomaly Detection

KW - Cybersecurity

KW - Machine Learning

KW - Sensors

KW - Smart Home

UR - https://www.scopus.com/pages/publications/85106627342

UR - https://www.scopus.com/pages/publications/85106627342#tab=citedBy

U2 - 10.1109/iSES50453.2020.00026

DO - 10.1109/iSES50453.2020.00026

M3 - Conference contribution

AN - SCOPUS:85106627342

T3 - Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020

SP - 67

EP - 70

BT - Proceedings - 2020 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020

T2 - 6th IEEE International Symposium on Smart Electronic Systems, iSES 2020

Y2 - 14 December 2020 through 16 December 2020

ER -

Smart Home Sensor Anomaly Detection Using Convolutional Autoencoder Neural Network

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this