3DACN: 3D Augmented convolutional network for time series data

doi:10.1016/j.ins.2019.11.040

	3DACN: 3D Augmented convolutional network for time series data
	Pei, Songwen 1,2,3; Shen, Tianma 1; Wang, Xianrong 1; Gu, Chunhua 1; Ning, Zhong 2; Ye, Xiaochun 3; Xiong, Naixue 4
	2020-03-01
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
卷号	513 页码:17-29
摘要	Time series data and non-time series data are increasing in the credit system of financial market, so that an effective and intelligent data mining model plays a critical role to analyze hybrid time series data. In addition, traditional mining models sometimes fail to converge because of imbalanced data problem. Therefore, we propose a 3D Augmented Convolutional Network (3DACN) to extract time series information and solve the serious imbalanced data problem. By using the augmented algorithm on time series data, hybrid time series data are enlarged to generate more examples on the minority classes. 3DACN ensures the latent variables with an Expectation-Maximization(EM) algorithm to improve F1 score (F1) and Area Under Curve (AUC). Experimental results show that in the benchmark of Bank database, it can gain F1 score by 81.1% and the AUC by 88.2% respectively; while in the benchmark of Credit Risk database, the 3DACN can reach high performance on F1 score by 88.1% and the AUC by 88.4%. (C) 2019 Elsevier Inc. All rights reserved.
关键词	Time series data Gated recurrent units Convolutional neural network Expectation-maximization algorithm Augmented algorithm
DOI	10.1016/j.ins.2019.11.040
收录类别	SCI
语种	英语
资助项目	National Science Foundation of China[61975124] ; National Science Foundation of China[61775139] ; National Science Foundation of China[61332009] ; China Postdoctoral Science Foundation[2017M610230] ; Opening Project Foundation of the State Key Lab of Computer Architecture[CARCH 201807]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000512221800002
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：36[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/14668
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Pei, Songwen
作者单位	1.Univ Shanghai Sci & Technol, Sch Opt Elect & Comp Engn, Shanghai 200093, Peoples R China 2.Fudan Univ, Sch Management, Shanghai 200433, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 4.Northeastern State Univ, Dept Comp Sci, Tahlequah, OK 74464 USA
推荐引用方式 GB/T 7714	Pei, Songwen,Shen, Tianma,Wang, Xianrong,et al. 3DACN: 3D Augmented convolutional network for time series data[J]. INFORMATION SCIENCES,2020,513:17-29.
APA	Pei, Songwen.,Shen, Tianma.,Wang, Xianrong.,Gu, Chunhua.,Ning, Zhong.,...&Xiong, Naixue.(2020).3DACN: 3D Augmented convolutional network for time series data.INFORMATION SCIENCES,513,17-29.
MLA	Pei, Songwen,et al."3DACN: 3D Augmented convolutional network for time series data".INFORMATION SCIENCES 513(2020):17-29.