典型文献
Self-Supervised Time Series Classification Based on LSTM and Contrastive Transformer
文献摘要：
Time series data has attached extensive attention as multi-domain data,but it is difficult to analyze due to its high di-mension and few labels.Self-supervised representation learning provides an effective way for processing such data.Considering the frequency domain features of the time series data itself and the contextual feature in the classification task,this paper proposes an unsupervised Long Short-Term Memory(LSTM)and contrastive transformer-based time series representation model using contras-tive learning.Firstly,transforming data with frequency domain-based augmentation increases the ability to represent features in the frequency domain.Secondly,the encoder module with three layers of LSTM and convolution maps the augmented data to the latent space and calculates the temporal loss with a contrastive transformer module and contextual loss.Finally,after self-supervised training,the representation vector of the original data can be got from the pre-trained encoder.Our model achieves satis-fied performances on Human Activity Recognition(HAR)and sleepEDF real-life datasets.
文献关键词：
中图分类号：
作者姓名：
ZOU Yuanhao;ZHANG Yufei;ZHAO Xiaodong
作者机构：
School of Electronic and Information Engineering,Tongji University,Shanghai 201804,China
文献出处：
引用格式：
[1]ZOU Yuanhao;ZHANG Yufei;ZHAO Xiaodong-.Self-Supervised Time Series Classification Based on LSTM and Contrastive Transformer)[J].武汉大学自然科学学报（英文版）,2022(06):521-530
A类：
contras,sleepEDF
B类：
Self,Supervised,Time,Series,Classification,Based,Contrastive,Transformer,series,has,attached,extensive,attention,multi,domain,but,difficult,analyze,due,high,mension,few,labels,representation,learning,provides,effective,way,processing,such,Considering,frequency,features,itself,contextual,classification,task,this,paper,proposes,unsupervised,Long,Short,Term,Memory,contrastive,transformer,model,using,Firstly,transforming,augmentation,increases,ability,Secondly,encoder,module,three,layers,convolution,maps,augmented,latent,space,calculates,temporal,loss,Finally,after,training,vector,original,can,got,from,trained,Our,achieves,satis,fied,performances,Human,Activity,Recognition,HAR,real,life,datasets
AB值：
0.590399
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
