2017
DOI: 10.1109/tsp.2017.2695445
|View full text |Cite
|
Sign up to set email alerts
|

Tensor Decompositions With Several Block-Hankel Factors and Application in Blind System Identification

Abstract: Several applications in biomedical data processing, telecommunications or chemometrics can be tackled by computing a structured tensor decomposition. In this paper, we focus on tensor decompositions with two or more block-Hankel factors, which arise in blind multiple-input-multipleoutput (MIMO) convolutive system identification. By assuming statistically independent inputs, the blind system identification problem can be reformulated as a Hankel structured tensor decomposition. By capitalizing on the available … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
25
0
2

Year Published

2017
2017
2019
2019

Publication Types

Select...
5
1

Relationship

2
4

Authors

Journals

citations
Cited by 8 publications
(27 citation statements)
references
References 41 publications
0
25
0
2
Order By: Relevance
“…Indeed, the application of such techniques has grown rapidly: micromagnetics [96][97][98], model order reduction [99,100], big data [101][102][103], signal processing [104][105][106][107], control design [108,109], and electronic design automation [93].…”
Section: Efficient Sampling Strategies For High-dimensional Problemsmentioning
confidence: 99%
“…Indeed, the application of such techniques has grown rapidly: micromagnetics [96][97][98], model order reduction [99,100], big data [101][102][103], signal processing [104][105][106][107], control design [108,109], and electronic design automation [93].…”
Section: Efficient Sampling Strategies For High-dimensional Problemsmentioning
confidence: 99%
“…The noisy tensor is obtained by adding Gaussian noise to the exact tensor. Method from [25] Opt. with our method as init.…”
Section: B Block-circulant Factorsmentioning
confidence: 99%
“…For better results, this a priori known structure can be taken into account when computing the decomposition. This explains why methods for various structured tensor decompositions are receiving increasing attention [9], [12], [22], [23], [25], [21]. In this paper, we focus on tensors admitting a canonical polyadic decomposition with (block-)circulant factors.…”
Section: Introductionmentioning
confidence: 99%
“…As técnicas de separação decorrentes dessa abordagem passaram a ser conhecidas, na literatura de BSS, como métodos baseados em propriedades algébricas de cumulantes, ou apenas métodos algébricos (CARDOSO, 1999). O interesse no estudo desses métodos cresceu ao longo dos anos (DE LATHAUWER, 1997; VAN EEGHEM;SØRENSEN;DE LATHAUWER, 2017; VAN EEGHEM et al, 2018), principalmente por 1.2. Objetivos 29 não necessitarem de escolhas arbitrárias de funções não lineares ou critérios heurísticos para realizar a separação.…”
Section: Motivação E Justificativaunclassified
“…Embora tensores sejam ferramentas matemáticas capazes de capturar a essência das transformações multilineares (LANDSBERG, 2012), como é o caso dos cumulantes, ainda há muitos problemas teóricos em aberto acerca de decomposições tensoriais, sua existência e unicidade (COMON et al, 2008;COMON, 2014). Sendo assim, a aplicação direta de tensores em processamento de sinais baseado em cumulantes, além de continuar sendo estudada MOTA, 2008;FAVIER, 2010), ainda inspira cuidados e possui limitações (VAN EEGHEM;SØRENSEN;DE LATHAUWER, 2017; VAN EEGHEM et al, 2018). Apesar disso, o uso da representação tensorial é extremamente útil à compreensão de propriedades algébricas de cumulantes, bem como à obtenção de representações simplificadas e convenientes do ponto de vista prático.…”
Section: Conclusões E Contribuiçõesunclassified