摘要
针对深度聚类算法对多变量时间序列数据(MTS)的特征提取能力不足等问题,提出一种新的深度聚类结构模型(MDTC)。为了提取MTS的关键特征并实现降维,提出一维卷积学习MTS的属性和时序维度的特征表示与循环神经网络等网络层组成的自编码器结构;为了提高模型对时序特征的表示能力,提出了MCBAM时序注意力模块,用于增强MTS序列中不同时间段的表示特征。在九个公开UEA多元时序数据集进行了实验,模型的自编码器结构相较其他自编码器在七个数据集上提升了2%~9%;模型的MCBAM模块相较其他注意力模块在六个数据集上提升了0.3%~2%。实验表明MDTC模型结构和MCBAM模块的有效性,同时模型对比其他聚类算法具有优异的表现。
Aiming at the problem of insufficient feature extraction ability of deep clustering algorithm on multivariate time series data(MTS),this paper proposed a new deep clustering structure model(MDTC).In order to extract the key features of MTS and realize dimensionality reduction,one-dimensional convolution learned the attribute and temporal dimension feature representation of MTS and the AutoEncoder structure composed of network layers such as recurrent neural network.To improve the model’s ability to represent temporal features,this paper proposed MCBAM temporal attention module,which was used to enhance the representation features of different time periods in the MTS sequence.This paper conducted experiments on nine publicly available UEA multivariate time series datasets,compared with other autoencoders,the AutoEncoder structure of the model improved by 2%~9%on seven datasets.Compared with other attention modules,the MCBAM module of the model improved by 0.3%~2%on six datasets.Experiments show the effectiveness of the MDTC model structure and MCBAM module,and the model has excellent performance compared with other clustering algorithms.
作者
张梓靖
张建勋
全文君
南海
Zhang Zijing;Zhang Jianxun;Quan Wenjun;Nan Hai(School of Computer Science&Engineering,Chongqing University of Technology,Chongqing 400054,China)
出处
《计算机应用研究》
CSCD
北大核心
2023年第8期2387-2392,共6页
Application Research of Computers
基金
重庆市教育委员会科学技术研究计划项目(KJQN201901133)
重庆理工大学研究生教育高质量发展行动计划资助项目(gzlcx20223213)。
关键词
深度学习
深度聚类
注意力机制
自编码器
一维卷积
deep learning
deep clustering
mechanism of attention
self encoder
one dimensional convolution
