中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
Small Sample Time Series Classification Based on Data Augmentation and Semi-supervised

文献类型：期刊论文

作者Liu, Jing-Jing1,2; Yao, Jie-Peng3; Wang, Zhuo1,4; Wang, Zhong-Yi1,2,4; Huang, Lan1,2
刊名INFORMATION TECHNOLOGY AND CONTROL
出版日期2024
卷号53期号:2页码:336
关键词Small sample time series Data augmentation Fast Shapelets Self-supervised learning Semi-su- pervised classification
ISSN号1392-124X
DOI10.5755/j01.itc.53.2.35797
通讯作者Huang, Lan(hlan@cau.edu.cn)
英文摘要Realistic scenarios produce labeled data and unlabeled data, however, there are significant challenges in labeling time series data. It is imperative to effectively integrate the relationship between labeled and unlabeled data within semi-supervised classification model. This paper presents a novel semi-supervised classification method, namely Data Augmentation -Fast Shapelet Semi-Supervised Classification, which employs a data augmentation module to enhance the diversity of data and improve the generalization ability of the model, as well as a feature fusion module to enhance the semi-supervised network. A conditional generative adversarial network is used to synthesize excellent labeled time series samples to enhance the homogeneous data in the sample space, the fast shapelets method is used to quickly extract the important shape feature vectors in the time series, self-supervised and supervised learning are combined to fully learn the unlabeled and labeled data of the time series dataset. The joint loss function combines the loss functions of the two networks to optimize multiple objectives. Reinforcement learning is used to determine the weight coefficients of the joint loss function, at the same time, the reward function is modified to bias the supervisory loss, which improves the classification performance of the model under limited labeled data, and the model can also better achieve the semi-supervised classification task. The proposed method is validated on the UCR benchmark dataset, Electrocardiogram dataset, and Electroencephalogram dataset, the results show that the semi-supervised classification method can perform a more accurate semi-supervised classification of the time series, with an accuracy better than the comparison methods. Meanwhile, we use the plant electrical signal dataset obtained from actual measurements for testing, the visualization analysis can clearly show the model role in the semi-supervised classification task, and the experimental results fully demonstrate the effectiveness and applicability of the proposed method.
资助项目National Natural Sci-ence Foundation of China[62271488] ; National Natural Sci-ence Foundation of China[61571443]
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
WOS记录号WOS:001266770800011
出版者KAUNAS UNIV TECHNOLOGY
资助机构National Natural Sci-ence Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59251]  
专题类脑芯片与系统研究
通讯作者Huang, Lan
作者单位1.China Agr Univ, Coll Informat & Elect Engn, Beijing 100083, Peoples R China
2.Minist Agr, Key Lab Agr Informat Acquisit Technol Beijing, Beijing 100083, Peoples R China
3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
4.Minist Educ, Key Lab Modern Precis Agr Syst Integrat Beijing, Beijing 100083, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Jing-Jing,Yao, Jie-Peng,Wang, Zhuo,et al. Small Sample Time Series Classification Based on Data Augmentation and Semi-supervised[J]. INFORMATION TECHNOLOGY AND CONTROL,2024,53(2):336.
APA Liu, Jing-Jing,Yao, Jie-Peng,Wang, Zhuo,Wang, Zhong-Yi,&Huang, Lan.(2024).Small Sample Time Series Classification Based on Data Augmentation and Semi-supervised.INFORMATION TECHNOLOGY AND CONTROL,53(2),336.
MLA Liu, Jing-Jing,et al."Small Sample Time Series Classification Based on Data Augmentation and Semi-supervised".INFORMATION TECHNOLOGY AND CONTROL 53.2(2024):336.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。