Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN

Muhammad Imad; Ian Cleland; Patrick McAllister; Christopher Nugent

doi:10.1145/3652037.3652052

Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN

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

Abstract

Unusual sensor data within intelligent built-up environments can indicate a range of concerns, including sensor inaccuracies, susceptibility to security breaches, and alterations in activity and behavioural patterns. This study aims to assess the effectiveness of 1D-CNN in detecting and improving the accuracy of anomalies in multimodal sensor data. This method effectively captures temporal patterns in lengthy data sequences collected over extended periods of time. Through comprehensive experiments utilising a public dataset for smart homes, we have empirically verified, after balancing the dataset, the proposed technique's efficacy, and a high accuracy of 0.96 in predicting anomalies.

Original language	English
Title of host publication	Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024
Editors	Enamul Karim, Sama Nikanfar, Hamza Reza Pavel
Pages	212-221
Number of pages	10
ISBN (Electronic)	9798400717604
DOIs	https://doi.org/10.1145/3652037.3652052
Publication status	Published (in print/issue) - 26 Jun 2024
Event	17th ACM International Conference on PErvasive Technologies Related to Assistive Environments - Crete Duration: 26 Jun 2024 → 28 Jul 2024

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	17th ACM International Conference on PErvasive Technologies Related to Assistive Environments
Period	26/06/24 → 28/07/24

Bibliographical note

Publisher Copyright:
© 2024 Owner/Author.

Funding

This research is supported by the ARC (Advanced Research Engineering Centre) project, funded by PwC1 and Invest Northern Ireland.

Funders
Advanced Research Engineering Centre
Invest Northern Ireland

UN SDGs

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

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Keywords

Anomaly Detection
Deep Learning
HAR
Multimodal Sensor Data

Access to Document

10.1145/3652037.3652052

Cite this

Imad, M., Cleland, I., McAllister, P., & Nugent, C. (2024). Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN. In E. Karim, S. Nikanfar, & H. R. Pavel (Eds.), Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024 (pp. 212-221). (ACM International Conference Proceeding Series). https://doi.org/10.1145/3652037.3652052

Imad, Muhammad ; Cleland, Ian ; McAllister, Patrick et al. / Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN. Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024. editor / Enamul Karim ; Sama Nikanfar ; Hamza Reza Pavel. 2024. pp. 212-221 (ACM International Conference Proceeding Series).

@inproceedings{a2e305f5ba8c478bb4937dd142b36880,

title = "Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN",

abstract = "Unusual sensor data within intelligent built-up environments can indicate a range of concerns, including sensor inaccuracies, susceptibility to security breaches, and alterations in activity and behavioural patterns. This study aims to assess the effectiveness of 1D-CNN in detecting and improving the accuracy of anomalies in multimodal sensor data. This method effectively captures temporal patterns in lengthy data sequences collected over extended periods of time. Through comprehensive experiments utilising a public dataset for smart homes, we have empirically verified, after balancing the dataset, the proposed technique's efficacy, and a high accuracy of 0.96 in predicting anomalies.",

keywords = "Anomaly Detection, Deep Learning, HAR, Multimodal Sensor Data",

author = "Muhammad Imad and Ian Cleland and Patrick McAllister and Christopher Nugent",

note = "Publisher Copyright: {\textcopyright} 2024 Owner/Author.; 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments ; Conference date: 26-06-2024 Through 28-07-2024",

year = "2024",

month = jun,

day = "26",

doi = "10.1145/3652037.3652052",

language = "English",

isbn = "979-8-4007-1760-4",

series = "ACM International Conference Proceeding Series",

pages = "212--221",

editor = "Enamul Karim and Sama Nikanfar and Pavel, \{Hamza Reza\}",

booktitle = "Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024",

}

Imad, M , Cleland, I , McAllister, P & Nugent, C 2024, Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN. in E Karim, S Nikanfar & HR Pavel (eds), Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024. ACM International Conference Proceeding Series, pp. 212-221, 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, 26/06/24. https://doi.org/10.1145/3652037.3652052

Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN. / Imad, Muhammad ; Cleland, Ian ; McAllister, Patrick et al.
Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024. ed. / Enamul Karim; Sama Nikanfar; Hamza Reza Pavel. 2024. p. 212-221 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN

AU - Imad, Muhammad

AU - Cleland, Ian

AU - McAllister, Patrick

AU - Nugent, Christopher

PY - 2024/6/26

Y1 - 2024/6/26

N2 - Unusual sensor data within intelligent built-up environments can indicate a range of concerns, including sensor inaccuracies, susceptibility to security breaches, and alterations in activity and behavioural patterns. This study aims to assess the effectiveness of 1D-CNN in detecting and improving the accuracy of anomalies in multimodal sensor data. This method effectively captures temporal patterns in lengthy data sequences collected over extended periods of time. Through comprehensive experiments utilising a public dataset for smart homes, we have empirically verified, after balancing the dataset, the proposed technique's efficacy, and a high accuracy of 0.96 in predicting anomalies.

AB - Unusual sensor data within intelligent built-up environments can indicate a range of concerns, including sensor inaccuracies, susceptibility to security breaches, and alterations in activity and behavioural patterns. This study aims to assess the effectiveness of 1D-CNN in detecting and improving the accuracy of anomalies in multimodal sensor data. This method effectively captures temporal patterns in lengthy data sequences collected over extended periods of time. Through comprehensive experiments utilising a public dataset for smart homes, we have empirically verified, after balancing the dataset, the proposed technique's efficacy, and a high accuracy of 0.96 in predicting anomalies.

KW - Anomaly Detection

KW - Deep Learning

KW - HAR

KW - Multimodal Sensor Data

UR - https://www.scopus.com/pages/publications/85198116187

U2 - 10.1145/3652037.3652052

DO - 10.1145/3652037.3652052

M3 - Conference contribution

SN - 979-8-4007-1760-4

T3 - ACM International Conference Proceeding Series

SP - 212

EP - 221

BT - Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024

A2 - Karim, Enamul

A2 - Nikanfar, Sama

A2 - Pavel, Hamza Reza

T2 - 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments

Y2 - 26 June 2024 through 28 July 2024

ER -

Imad M , Cleland I , McAllister P , Nugent C. Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN. In Karim E, Nikanfar S, Pavel HR, editors, Proceedings of the 17th ACM International Conference on PErvasive Technologies Related to Assistive Environments, PETRA 2024. 2024. p. 212-221. (ACM International Conference Proceeding Series). Epub 2024 Jun 26. doi: 10.1145/3652037.3652052

Improving the accuracy of Anomaly Detection in Multimodal Sensors using 1D-CNN

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this