An anomaly detection scheme for data stream in cold chain logistics
PLOS ONE · 10.03.2025 · 20 (3) · e0315322
DOI: 10.1371/journal.pone.0315322 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 10.03.2025. Verfasst von Zhibo Xie und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of information and intelligent engineering, Zhejiang wanli University, Ningbo, China. Hauptthemen laut MEDLINE: Refrigeration. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Commonweal Projects of Zhejiang Province, Innovation and Entrepreneurship Project for College Students.
Abstract (Originalsprache)
Anomaly detection is widely used in cold chain logistics (CCL). But, because of the high cost and technical problem, the anomaly detection performance is poor, and the anomaly can not be detected in time, which affects the quality of goods. To solve these problems, the paper presents a new anomaly detection scheme for CCL. At first, the characteristics of the collected data of CCL are analyzed, the mathematical model of data flow is established, and the sliding window and correlation coefficient are defined. Then the abnormal events in CCL are summarized, and three types of abnormal judgment conditions based on cor-relation coefficient ρjk are deduced. A measurement anomaly detection algorithm based on the improved isolated forest algorithm is proposed. Subsampling and cross factor are designed and used to overcome the shortcomings of the isolated forest algorithm (iForest). Experiments have shown that as the dimensionality of the data increases, the performance indicators of the new scheme, such as P (precision), R (recall), F1 score, and AUC (area under the curve), become increasingly superior to commonly used support vector machines (SVM), local outlier factors (LOF), and iForests. Its average P is 0.8784, average R is 0.8731, average F1 score is 0.8639, and average AUC is 0.9064. However, the execution time of the improved algorithm is slightly longer than that of the iForest.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of information and intelligent engineering, Zhejiang wanli University, Ningbo, China.
- Ningbo Municipal Bereau of Ecology and Enviroment, Ningbo, China.
ORCID-Profile: Zhibo Xie
Förderung
- Commonweal Projects of Zhejiang Province
- Innovation and Entrepreneurship Project for College Students
Zitieren
APA
Xie, Z., Long, H., Ling, C., Zhou, Y., & Luo, Y. (2025). An anomaly detection scheme for data stream in cold chain logistics. PLOS ONE, 20(3), e0315322. https://doi.org/10.1371/journal.pone.0315322
Vancouver
Xie Z, Long H, Ling C, Zhou Y, Luo Y. An anomaly detection scheme for data stream in cold chain logistics. PLOS ONE. 2025;20(3):e0315322. doi:10.1371/journal.pone.0315322
BibTeX
@article{Xie2025,
author = {Xie, Zhibo and Long, Heng and Ling, Chengyi and Zhou, Yingjun and Luo, Yan},
title = {An anomaly detection scheme for data stream in cold chain logistics},
journal = {PLOS ONE},
year = {2025},
volume = {20},
number = {3},
pages = {e0315322},
doi = {10.1371/journal.pone.0315322}
}
EUVIMED