《计算机应用》唯一官方网站 ›› 2026, Vol. 46 ›› Issue (10): 3206-3214.DOI: 10.11772/j.issn.1001-9081.2025080971

• 数据科学与技术 • 上一篇    

基于转置自注意力机制与卷积自编码器的多元时序数据分析方法

刘晟1, 童英华1,2()   

  1. 1.青海师范大学 计算机学院,西宁 810000
    2.藏语智能全国重点实验室(青海师范大学),西宁 810008
  • 收稿日期:2025-08-25 修回日期:2025-09-11 接受日期:2025-09-29 发布日期:2025-11-07 出版日期:2026-10-10
  • 通讯作者: 童英华
  • 作者简介:刘晟(1998—),男,江西吉安人,硕士研究生,CCF会员,主要研究方向:物联网系统的可靠性、深度学习
  • 基金资助:
    青海省应用基础研究项目(2023-ZJ-713)

Multivariate time series data analysis method based on transposed self-attention mechanism and convolutional autoencoder

Sheng LIU1, Yinghua TONG1,2()   

  1. 1.School of Computer,Qinghai Normal University,Xining Qinghai 810000,China
    2.The State Key Laboratory of Tibetan Intelligence (Qinghai Normal University),Xining Qinghai 810008,China
  • Received:2025-08-25 Revised:2025-09-11 Accepted:2025-09-29 Online:2025-11-07 Published:2026-10-10
  • Contact: Yinghua TONG
  • About author:LIU Sheng, born in 1998, M. S. candidate. His research interests include IoT system reliability, deep learning.
  • Supported by:
    Qinghai Province Application Basic Research Project(2023-ZJ-713)

摘要:

针对现有Transformer类模型在趋势性信息提取方面存在的不足,以及传感器异构性导致的变量相关性建模失真等问题,提出一种基于转置自注意力机制(TSA)与卷积自编码器(CAE)的多元时序数据分析方法。该方法通过构建转置一维CAE结构,从时间维度实现时序数据的特征重建,有效捕获多元时序数据中的长期趋势信息;同时,将TSA机制引入多变量相关性分析过程,显著提升变量间关联关系的建模精度。与近年主流方法的预测性能对比实验结果表明,所提方法的平均均方误差(MSE)为0.545,相较于iTransformer和DLinear分别降低了11.4%和7.4%。此外,在5个公共数据集上的异常检测实验结果表明,该方法的平均F1分数为84.92%,优于所有基线方法。在真实水质监测数据集上的预测实验结果表明,所提方法的平均绝对误差(MAE)和MSE相较于Autoformer分别降低了46.2%和42.9%,验证了该方法在实际应用场景中的有效性。

关键词: 异常检测, 时序预测, 自注意力机制, 卷积自编码器, 环境监测

Abstract:

To address the limitations of the existing Transformer models in trend information extraction and the distortion in modeling variable correlations caused by sensor heterogeneity, a multivariate time series data analysis method based on Transposed Self-Attention (TSA) mechanism and Convolutional AutoEncoder (CAE) was proposed. In the method, a transposed one-dimensional CAE structure was constructed to reconstruct time series data features in the time dimension, which captured long-term trend information in multivariate time series data effectively. Meanwhile, the TSA mechanism was introduced into the multivariate correlation analysis process, which improved the modeling accuracy of inter-variable relationships significantly. Comparative experimental results on prediction performance of the proposed method and recent mainstream methods showed that the proposed method achieved an average Mean Squared Error (MSE) of 0.545, which was 11.4% lower than that of iTransformer and 7.4% lower than that of DLinear. Furthermore, anomaly detection experimental results on five public datasets showed that the proposed method achieved an average F1 score of 84.92%, outperforming all the baseline methods. Prediction experimental results on a real-world water quality monitoring dataset showed that the proposed method reduced the average Mean Absolute Error (MAE) and MSE by 46.2% and 42.9%, respectively, compared to Autoformer, demonstrating its effectiveness in practical applications.

Key words: anomaly detection, time series forecasting, self-attention mechanism, Convolutional AutoEncoder (CAE), environmental monitoring

中图分类号: