时频域多尺度交叉注意力融合的时间序列分类方法  

Time series classification method based on multi-scale cross-attention fusion in time-frequency domain

作　　者：王美[1,2] 苏雪松[1] 刘佳 殷若南[2] 黄珊 WANG Mei;SU Xuesong;LIU Jia;YIN Ruonan;HUANG Shan(Shengli Oilfield Technical Testing Center,China Petroleum and Chemical Corporation,Dongying Shandong 257000,China;School of Computer Science and Technology,China University of Petroleum(East China),Qingdao Shandong 266000,China;College of Pipeline and Civil Engineering,China University of Petroleum(East China),Qingdao Shandong 266000,China)

机构地区：[1]中国石油化工股份有限公司胜利油田技术检测中心,山东东营257000 [2]中国石油大学(华东)计算机科学与技术学院,山东青岛266000 [3]中国石油大学(华东)储运与建筑工程学院,山东青岛266000

出　　处：《计算机应用》2024年第6期1842-1847,共6页journal of Computer Applications

基　　金：中国石化股份公司科研项目(323016);胜利油田分公司科研项目(YG2208)。

摘　　要：针对时间序列子序列间的潜在信息交互不足导致分类准确率低的问题,提出时频域多尺度交叉注意力融合的时间序列分类方法TFFormer(Time-Frequency Transformer)。首先,将原始时间序列的时频域谱分别划分为等长子序列,经线性投影后加入位置信息解决时间序列的点值耦合问题;其次,通过改进的多头自注意力(IMHA)模块使模型关注更重要的序列特征,解决长时间序列的前后依赖问题;最后,构造多尺度时频域交叉注意力(CMA)模块增强时间序列在时域和频域之间的信息交互,使模型进一步挖掘序列的频域信息。实验结果表明,在Trace、StarLightCurves和UWaveGestureLibraryAll数据集上,相较于全卷积网络(FCN),所提方法的分类准确率分别提高了0.3、0.9和1.4个百分点,验证了通过增强时间序列时域和频域间的信息交互,可以提高模型收敛速度和分类精度。To address the problem of low classification accuracy caused by insufficient potential information interaction between time series subsequences,a time series classification method based on multi-scale cross-attention fusion in timefrequency domain called TFFormer(Time-Frequency Transformer)was proposed.First,time and frequency spectrums of the original time series were divided into subsequences with the same length respectively,and the point-value coupling problem was solved by adding positional embedding after linear projection.Then,the long-term time series dependency problem was solved because the model was made to focus on more important time series features by Improved Multi-Head self-Attention(IMHA)mechanism.Finally,a multi-scale Cross-Modality Attention(CMA)module was proposed to enhance the interaction between the time domain and frequency domain,so that the model could further mine the frequency information of the time series.The experimental results show that compared with Fully Convolutional Network(FCN),the classification accuracy of the proposed method on Trace,StarLightCurves and UWaveGestureLibraryAll datasets increased by 0.3,0.9 and 1.4 percentage points.It is proved that by enhancing the information interaction between time domain and frequency domain of the time series,the model convergence speed and classification accuracy can be improved.

关 键 词：时间序列 注意力机制 位置编码 深度神经网络 多尺度融合 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]