EUVIMEDEUVIMED entdecken
Open Access

A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding

Zhongjing Ma, Zhan Chen, Xiaochen Zheng, Tianyu Wang, Yuyang You, Suli Zou, Yu Wang

Cyborg and Bionic Systems · 2024-01 · 5

DOI: 10.34133/cbsystems.0086 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Cyborg and Bionic Systems, online erschienen am 16.01.2024. Verfasst von Zhongjing Ma und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly detection has wide applications to help people recognize false, intrusion, flaw, equipment failure, etc. In most practical scenarios, the amount of the annotated data and the trusted labels is low, resulting in poor performance of the detection. In this paper, we focus on the anomaly detection for the text type data and propose a detection network based on biological immunity for few-shot detection, by imitating the working mechanism of the immune system of biological organisms. This network enabling the protected system to distinguish the aggressive behavior of “nonself” from the legitimate behavior of “self” by embedding characters. First, it constructs episodic task sets and extracts data representations at the character level. Then, in the pretraining phase, Word2Vec is used to embed the representations. In the meta-learning phase, a dynamic prototype containing encoder, routing, and relation is designed to identify the data traffic. Compare to the mean-based prototype, the proposed prototype applies a dynamic routing algorithm that assigns different weights to samples in the support set through multiple iterations to obtain a prototype that combines the distribution of samples. The proposed method is validated on 2 real traffic datasets. The experimental results indicate that (a) the proposed anomaly detection prototype outperforms state-of-the-art few-shot techniques with 1.3% to 4.48% accuracy and 0.18% to 4.55% recall; (b) under the premise of ensuring the accuracy and recall, the number of training samples is reduced to 5 or 10; (c) ablation experiments are designed for each module, and the results show that more accurate prototypes can be obtained by using the dynamic routing algorithm.

Autor:innen und Institutionen

  • School of Automation, Beijing Institute of Technology, Beijing 100081, China.
  • ETH AI Center, Andreasstrasse 5, 8092 Zürich, Switzerland.
  • State Key Lab of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100095, China.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation

Zitieren

APA

Ma, Z., Chen, Z., Zheng, X., Wang, T., You, Y., Zou, S., & Wang, Y. (2024). A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding. Cyborg and Bionic Systems, 5. https://doi.org/10.34133/cbsystems.0086

Vancouver

Ma Z, Chen Z, Zheng X, Wang T, You Y, Zou S, et al. A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding. Cyborg and Bionic Systems. 2024;5. doi:10.34133/cbsystems.0086

BibTeX
@article{Ma2024,
  author = {Ma, Zhongjing and Chen, Zhan and Zheng, Xiaochen and Wang, Tianyu and You, Yuyang and Zou, Suli and Wang, Yu},
  title = {A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding},
  journal = {Cyborg and Bionic Systems},
  year = {2024},
  volume = {5},
  doi = {10.34133/cbsystems.0086}
}
Kostenlos starten →