Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.077521
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Prototype Memory and Contrastive Learning Based Unsupervised Anomaly Detection for Time Series

Xi Li1, Yingjie Chang1, Peng Chen1,*, Ang Bian1, Ning Lu1,2,*
1 School of Computer and Software Engineering, Xihua University, Chengdu, China
2 School of Art and Design, Xihua University, Chengdu, China
* Corresponding Author: Peng Chen. Email: email; Ning Lu. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.077521

Received 11 December 2025; Accepted 11 March 2026; Published online 01 April 2026

Abstract

Multivariate time series anomaly detection (MTSAD) is a critical task for real-time risk control and fault diagnosis in industrial monitoring, aerospace, and financial domains. Unsupervised MTSAD confronts three core challenges: label scarcity in practical scenarios, diverse anomaly patterns that demand adaptive modeling, and weak feature discriminability between normal and anomalous samples. To address these challenges, we propose a Prototype Memory and Contrastive Learning Based Unsupervised Anomaly Detection for Multivariate Time Series method named PC-UAD. PC-UAD comprises three core modules with hierarchical functionalities: (1) A Temporal PatchEmbedder, which adopts learnable positional encoding for dynamic temporal representation and incorporates channel projection to model adaptive cross-sensor dependencies in multivariate data; (2) A Prototype Memory Encoder, which embeds a prototype attention mechanism to explicitly memorize typical normal patterns, forming a “normal pattern dictionary” that enhances the model’s perception of normal behavioral boundaries; (3) A ContrastFusion module, which leverages contrastive learning to amplify feature distribution discrepancies between normal and anomalous data, strengthening the model’s ability to distinguish subtle anomalies. Experiments on five public multivariate time series datasets demonstrate that our method achieves superior detection accuracy compared to eight state-of-the-art approaches, with the average F1-score and ROC-AUC both ranking first.

Keywords

Multivariate time series; unsupervised anomaly detection; prototype memory; contrastive learning; transformer

  • 117

    View

  • 15

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link