A new efficient method for determining the number of components in PARAFAC models

By Rasmus Bro, Henk A. L. Kiers. 2003

1,217 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Food Science, Plant Science

View Paper: https://www.semanticscholar.org/paper/8050743bdccda5070f7c96f87a9d451da40f988b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Evrim Acar
2. Tamara G. Kolda
3. Bülent Yener
4. C. Cordella
5. Daniel M. Dunlavy
6. N. Sidiropoulos
7. Christos Faloutsos
8. Evangelos E. Papalexakis

In Food Science

1. C. Cordella
2. N. Sidiropoulos
3. Evrim Acar
4. Bülent Yener
5. Tamara G. Kolda
6. Dimitri Nion
7. Christos Faloutsos
8. Ali Anaissi

In Plant Science

1. C. Cordella
2. N. Sidiropoulos
3. Evrim Acar
4. Dimitri Nion
5. Bülent Yener
6. Tamara G. Kolda
7. Christos Faloutsos
8. Ali Anaissi

Citations in the corpus

• Multilinear operators for higher-order decompositions (2006, background): “, [11] for more discussion of this issue.”
• Unsupervised Multiway Data Analysis: A Literature Survey (2009, methodology): “Nevertheless, there is no bulletproof way to determine the optimal number of factors (optimal in terms of interpretation) for real data, and it is often suggested that several diagnostic tools are used together rather than a single method [20], [25].”
• Smart Infrastructure Maintenance Using Incremental Tensor Analysis: Extended Abstract (2017, methodology): “In order to decide the number of rank-one tensors R in the CP method, core consistency diagnostic technique (CORCONDIA) described in [7] was applied, in which a Tucker core is used for assessing the appropriateness of a CP model.”
• A comparison of algorithms for fitting the PARAFAC model (2006, background): “The SWATLD solutions typically have a higher core consistency (Bro and Kiers, 2003) than the corresponding least squares solution (not shown), i.e. they seem to be biased towards describing only the strictly trilinear contributions and are likely less affected by possible interactions between…”
• Tensors for Data Mining and Data Fusion (2016, methodology): “The most intuitive and popular heuristic for model order selection is the so-called Core Consistency Diagnostic or CORCONDIA [Bro 1998; Bro and Kiers 2003].”
• PCA: The Basic Building Block of Chemometrics (2012, methodology): “The corcondia criterion was created and used [94] to facilitate the choice of the optimal number of components in the calculated model.”
• Hyperspectral image noise reduction based on rank-1 tensor decomposition (2013, background): “(6) implies that the HSI data is a linear combination of a sequence of rank-1 tensors (Bro and Kiers, 2003).”
• A scalable optimization approach for fitting canonical tensor decompositions (2011, background): “, model fit and the core consistency (CORCONDIA) diagnostic [9].”