File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1002/nla.1993
- Scopus: eid_2-s2.0-84955200728
- WOS: WOS:000368371500007
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Total variation based tensor decomposition for multi-dimensional data with time dimension
Title | Total variation based tensor decomposition for multi-dimensional data with time dimension |
---|---|
Authors | |
Keywords | Alternating direction method of multipliers Regularization Tensor decomposition Time dimension Total variation Multidimensional data |
Issue Date | 2015 |
Citation | Numerical Linear Algebra with Applications, 2015, v. 22, n. 6, p. 999-1019 How to Cite? |
Abstract | © 2015 John Wiley & Sons, Ltd. In this paper, we study tensors with time dimension which arises in many scientific and engineering applications such as time series gene expression analysis and video analysis. In these applications, we are interested in determining a set of components interacting closely and consistently together over a period of time. The main aim of this paper is to develop a numerical method to compute such constrained CANDECOMP/PARAFAC (CP) decompositions. We make use of the total variation regularization to constrain the time dimension factor in the decomposition in order to obtain a piecewise constant function with respect to time points. The components of the other dimensions corresponding to these time points are closely related. For example, in time series gene expression analysis, a set of genes may regulate a biological process together during a specific time period; in video analysis, a set of image pixels may refer to a foreground object in the video frames. We employ ADMM to solve the resulting optimization problem, and study its convergence. Numerical examples on synthetic and real data sets are used to demonstrate that the proposed total variation based CP decomposition model can provide more accurate and interesting results. |
Persistent Identifier | http://hdl.handle.net/10722/251136 |
ISSN | 2021 Impact Factor: 2.138 2020 SCImago Journal Rankings: 1.020 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chen, Chuan | - |
dc.contributor.author | Li, Xutao | - |
dc.contributor.author | Ng, Michael K. | - |
dc.contributor.author | Yuan, Xiaoming | - |
dc.date.accessioned | 2018-02-01T01:54:42Z | - |
dc.date.available | 2018-02-01T01:54:42Z | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Numerical Linear Algebra with Applications, 2015, v. 22, n. 6, p. 999-1019 | - |
dc.identifier.issn | 1070-5325 | - |
dc.identifier.uri | http://hdl.handle.net/10722/251136 | - |
dc.description.abstract | © 2015 John Wiley & Sons, Ltd. In this paper, we study tensors with time dimension which arises in many scientific and engineering applications such as time series gene expression analysis and video analysis. In these applications, we are interested in determining a set of components interacting closely and consistently together over a period of time. The main aim of this paper is to develop a numerical method to compute such constrained CANDECOMP/PARAFAC (CP) decompositions. We make use of the total variation regularization to constrain the time dimension factor in the decomposition in order to obtain a piecewise constant function with respect to time points. The components of the other dimensions corresponding to these time points are closely related. For example, in time series gene expression analysis, a set of genes may regulate a biological process together during a specific time period; in video analysis, a set of image pixels may refer to a foreground object in the video frames. We employ ADMM to solve the resulting optimization problem, and study its convergence. Numerical examples on synthetic and real data sets are used to demonstrate that the proposed total variation based CP decomposition model can provide more accurate and interesting results. | - |
dc.language | eng | - |
dc.relation.ispartof | Numerical Linear Algebra with Applications | - |
dc.subject | Alternating direction method of multipliers | - |
dc.subject | Regularization | - |
dc.subject | Tensor decomposition | - |
dc.subject | Time dimension | - |
dc.subject | Total variation | - |
dc.subject | Multidimensional data | - |
dc.title | Total variation based tensor decomposition for multi-dimensional data with time dimension | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1002/nla.1993 | - |
dc.identifier.scopus | eid_2-s2.0-84955200728 | - |
dc.identifier.volume | 22 | - |
dc.identifier.issue | 6 | - |
dc.identifier.spage | 999 | - |
dc.identifier.epage | 1019 | - |
dc.identifier.eissn | 1099-1506 | - |
dc.identifier.isi | WOS:000368371500007 | - |
dc.identifier.issnl | 1070-5325 | - |