TimeTector: A Twin-Branch Approach for Unsupervised Anomaly Detection in Livestock Sensor Noisy Data (TT-TBAD)
Sensors · 2024
DOI: 10.3390/s24082453 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Junaid Khan Kakar und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea. Hauptthemen laut MEDLINE: Livestock. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT Rural Development Administration (RDA), National Research Foundation, Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry (IPET).
Abstract (Originalsprache)
Unsupervised anomaly detection in multivariate time series sensor data is a complex task with diverse applications in different domains such as livestock farming and agriculture (LF&A), the Internet of Things (IoT), and human activity recognition (HAR). Advanced machine learning techniques are necessary to detect multi-sensor time series data anomalies. The primary focus of this research is to develop state-of-the-art machine learning methods for detecting anomalies in multi-sensor data. Time series sensors frequently produce multi-sensor data with anomalies, which makes it difficult to establish standard patterns that can capture spatial and temporal correlations. Our innovative approach enables the accurate identification of normal, abnormal, and noisy patterns, thus minimizing the risk of misinterpreting models when dealing with mixed noisy data during training. This can potentially result in the model deriving incorrect conclusions. To address these challenges, we propose a novel approach called “TimeTector-Twin-Branch Shared LSTM Autoencoder” which incorporates several Multi-Head Attention mechanisms. Additionally, our system now incorporates the Twin-Branch method which facilitates the simultaneous execution of multiple tasks, such as data reconstruction and prediction error, allowing for efficient multi-task learning. We also compare our proposed model to several benchmark anomaly detection models using our dataset, and the results show less error (MSE, MAE, and RMSE) in reconstruction and higher accuracy scores (precision, recall, and F1) against the baseline models, demonstrating that our approach outperforms these existing models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronics and Information Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea.
- Core Research Institute of Intelligent Robots, Jeonbuk National University, Jeonju 54896, Republic of Korea.
- Innovation Value Institute (IVI), School of Business, National University of Ireland Maynooth (NUIM), W23 F2H6 Maynooth, Ireland.
- Department of Electronics Engineering, Jeonbuk National University, Jeonju 54896, Republic of Korea.
ORCID-Profile: Junaid Khan Kakar, Shahid Hussain, Hyongsuk Kim
Förderung
- Ministry of Science and ICT Rural Development Administration (RDA)
- National Research Foundation
- Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry (IPET)
- Korea Smart Farm R&D Foundation
- Ministry of Agriculture, Food and Rural Affairs (MAFRA)
- Ministry of Education
Zitieren
APA
Kakar, J. K., Hussain, S., Kim, S. C., & Kim, H. (2024). TimeTector: A Twin-Branch Approach for Unsupervised Anomaly Detection in Livestock Sensor Noisy Data (TT-TBAD). Sensors. https://doi.org/10.3390/s24082453
Vancouver
Kakar JK, Hussain S, Kim SC, Kim H. TimeTector: A Twin-Branch Approach for Unsupervised Anomaly Detection in Livestock Sensor Noisy Data (TT-TBAD). Sensors. 2024. doi:10.3390/s24082453
BibTeX
@article{Kakar2024,
author = {Kakar, Junaid Khan and Hussain, Shahid and Kim, Sang Cheol and Kim, Hyongsuk},
title = {TimeTector: A Twin-Branch Approach for Unsupervised Anomaly Detection in Livestock Sensor Noisy Data (TT-TBAD)},
journal = {Sensors},
year = {2024},
doi = {10.3390/s24082453}
}
EUVIMED