EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Contrastive Learning-Based Anomaly Detection for Actual Corporate Environments

Gi-Taek An iD, Jung-Min Park, Kyung-Soon Lee

Sensors · 15.05.2023 · 23 (10) · 4764

DOI: 10.3390/s23104764 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 15.05.2023. Verfasst von Gi-Taek An und 2 weiteren Autor:innen. Beteiligte Einrichtung: Korea Food Research Institute, Wanju-gun 55365, Republic of Korea. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Food Research Institute, Ministry of Science and ICT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Information systems play an important role in business management, especially in personnel, budget, and financial management. If an anomaly ensues in an information system, all operations are paralyzed until their recovery. In this study, we propose a method for collecting and labeling datasets from actual operating systems in corporate environments for deep learning. The construction of a dataset from actual operating systems in a company’s information system involves constraints. Collecting anomalous data from these systems is challenging because of the need to maintain system stability. Even with data collected over a long period, the training dataset may have an imbalance of normal and anomalous data. We propose a method that utilizes contrastive learning with data augmentation through negative sampling for anomaly detection, which is particularly suitable for small datasets. To evaluate the effectiveness of the proposed method, we compared it with traditional deep learning models, such as the convolutional neural network (CNN) and long short-term memory (LSTM). The proposed method achieved a true positive rate (TPR) of 99.47%, whereas CNN and LSTM achieved TPRs of 98.8% and 98.67%, respectively. The experimental results demonstrate the method’s effectiveness in utilizing contrastive learning and detecting anomalies in small datasets from a company’s information system.

Schlagwörter

Stichwörter der Autor:innen

anomaly detectionconstructing datasetcontrastive learningenterprise information system dataset

Autor:innen und Institutionen

  • Korea Food Research Institute, Wanju-gun 55365, Republic of Korea.
  • Division of Computer Science and Artificial Intelligence, CAIIT, Jeonbuk National University, Jeonju 54896, Republic of Korea.

ORCID-Profile: Gi-Taek An

Förderung

  • Korea Food Research Institute
  • Ministry of Science and ICT

Zitieren

APA

An, G. T., Park, J. M., & Lee, K. S. (2023). Contrastive Learning-Based Anomaly Detection for Actual Corporate Environments. Sensors, 23(10), 4764. https://doi.org/10.3390/s23104764

Vancouver

An GT, Park JM, Lee KS. Contrastive Learning-Based Anomaly Detection for Actual Corporate Environments. Sensors. 2023;23(10):4764. doi:10.3390/s23104764

BibTeX
@article{An2023,
  author = {An, Gi-Taek and Park, Jung-Min and Lee, Kyung-Soon},
  title = {Contrastive Learning-Based Anomaly Detection for Actual Corporate Environments},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {10},
  pages = {4764},
  doi = {10.3390/s23104764}
}
Kostenlos starten →