Analysis of Nonstationary Time Series Using Support Vector Machines | Publication

Title	Analysis of Nonstationary Time Series Using Support Vector Machines
Creator	Weng, Ruby C.;Lin, Chih-jen;Chang, Ming-wei 翁久幸
Contributor	統計系
Date	2002
Date Issued	7-Apr-2015 17:02:07 (UTC+8)
Summary	Time series from alternating dynamics have many important applications. In [5], the authors propose an approach to solve the drifting dynamics. Their method directly solves a non-convex optimization problem. In this paper, we propose a strategy which solves a sequence of convex optimization problems by using modified support vector regression. Experimental results showing its practical viability are presented and we also discuss the advantages and disadvantages of the proposed approach.
Relation	Pattern Recognition with Support Vector Machines Lecture Notes in Computer Science Volume 2388, 2002, pp 160-170
Type	article
DOI	http://dx.doi.org/10.1007/3-540-45665-1_13

dc.contributor	統計系	-
dc.creator (作者)	Weng, Ruby C.;Lin, Chih-jen;Chang, Ming-wei	-
dc.creator (作者)	翁久幸	-
dc.date (日期)	2002	-
dc.date.accessioned	7-Apr-2015 17:02:07 (UTC+8)	-
dc.date.available	7-Apr-2015 17:02:07 (UTC+8)	-
dc.date.issued (上傳時間)	7-Apr-2015 17:02:07 (UTC+8)	-
dc.identifier.uri (URI)	http://nccur.lib.nccu.edu.tw/handle/140.119/74370	-
dc.description.abstract (摘要)	Time series from alternating dynamics have many important applications. In [5], the authors propose an approach to solve the drifting dynamics. Their method directly solves a non-convex optimization problem. In this paper, we propose a strategy which solves a sequence of convex optimization problems by using modified support vector regression. Experimental results showing its practical viability are presented and we also discuss the advantages and disadvantages of the proposed approach.	-
dc.relation (關聯)	Pattern Recognition with Support Vector Machines Lecture Notes in Computer Science Volume 2388, 2002, pp 160-170	-
dc.title (題名)	Analysis of Nonstationary Time Series Using Support Vector Machines	-
dc.type (資料類型)	article	en
dc.identifier.doi (DOI)	10.1007/3-540-45665-1_13	en_US
dc.doi.uri (DOI)	http://dx.doi.org/10.1007/3-540-45665-1_13	en_US