TS-SEA：用于时间序列分类的时域-频域-季节性联合对比学习

打开文本图片集

中图分类号：TN911.7-34；TP301.6 文献标识码：A 文章编号：1004-373X（2025）16-0038-07

TS-SEA： temporal-frequency-seasonal joint contrastive learning for timeseriesclassification

LIKun’，TANJun²，GUINing²，ZHUZhaowei³ （1.School ofSoftware，XinjiangUniversity，Urumqi 83oo91，China; 2.SchoolofComputer Scienceand Engineering，Central South University，Changsha 41oo83，China; 3.School of Computer Scienceand Technology，Zhejiang Sci-Tech University，Hangzhou 311241，China）

Abstract：Timeseriesclasification （TSC）isthetaskofcategorizing sequentialdata intopredefined clasesaccording to their temporalpaterns.Real-world timeseriesusuallcontaincomplexcouplingoftrend terms，seasonalcomponents，outliers， andnoise，anditsacurateecompositioniscrucialtoimproveclasificationpeforance.Terefore，atimesriescassiication method，S-Ssoe，ichooiisnteioalydol FFTandSTL.Basedontheseviews，iterativelearningisrealizedbymeansofcontrastlearningbetweenencoders.Theresults indicate that incomparison with existing methods，theproposedTS-SEAmethodcanexhibitthebetterperformance whendealing with diverse time series applications.

Keywords：TS-SEA;timeseriesclasification;multi-viewjointlearning;contrastivelearnng;Fouriertransform;tieseries decomposition

0 引言

时间序列数据在现实世界中随处可见[1，对许多应用至关重要，特别是在诸如医疗保健[2-3]、金融[4、交通[5-6]和工业生产等领域。（剩余11295字）