Local classification: locally weighted–partial least squares-discriminant analysis (LW–PLS-DA)

Research output: Contribution to journalJournal articleResearchpeer-review

Standard

Local classification : locally weighted–partial least squares-discriminant analysis (LW–PLS-DA). / Bevilacqua, Marta; Marini, Federico.

In: Analytica Chimica Acta, Vol. 838, 2014, p. 20 - 30.

Research output: Contribution to journalJournal articleResearchpeer-review

Harvard

Bevilacqua, M & Marini, F 2014, 'Local classification: locally weighted–partial least squares-discriminant analysis (LW–PLS-DA)', Analytica Chimica Acta, vol. 838, pp. 20 - 30. https://doi.org/10.1016/j.aca.2014.05.057

APA

Bevilacqua, M., & Marini, F. (2014). Local classification: locally weighted–partial least squares-discriminant analysis (LW–PLS-DA). Analytica Chimica Acta, 838, 20 - 30. https://doi.org/10.1016/j.aca.2014.05.057

Vancouver

Bevilacqua M, Marini F. Local classification: locally weighted–partial least squares-discriminant analysis (LW–PLS-DA). Analytica Chimica Acta. 2014;838:20 - 30. https://doi.org/10.1016/j.aca.2014.05.057

Author

Bevilacqua, Marta ; Marini, Federico. / Local classification : locally weighted–partial least squares-discriminant analysis (LW–PLS-DA). In: Analytica Chimica Acta. 2014 ; Vol. 838. pp. 20 - 30.

Bibtex

@article{7ca11d35bd3845ea9e553dddcf5a1b33,
title = "Local classification: locally weighted–partial least squares-discriminant analysis (LW–PLS-DA)",
abstract = "The possibility of devising a simple, flexible and accurate non-linear classification method, by extending the locally weighted partial least squares (LW–PLS) approach to the cases where the algorithm is used in a discriminant way (partial least squares discriminant analysis, PLS-DA), is presented. In particular, to assess which category an unknown sample belongs to, the proposed algorithm operates by identifying which training objects are most similar to the one to be predicted and building a PLS-DA model using these calibration samples only. Moreover, the influence of the selected training samples on the local model can be further modulated by adopting a not uniform distance-based weighting scheme which allows the farthest calibration objects to have less impact than the closest ones. The performances of the proposed locally weighted–partial least squares-discriminant analysis (LW–PLS-DA) algorithm have been tested on three simulated data sets characterized by a varying degree of non-linearity: in all cases, a classification accuracy higher than 99{\%} on external validation samples was achieved. Moreover, when also applied to a real data set (classification of rice varieties), characterized by a high extent of non-linearity, the proposed method provided an average correct classification rate of about 93{\%} on the test set. By the preliminary results, showed in this paper, the performances of the proposed LW–PLS-DA approach have proved to be comparable and in some cases better than those obtained by other non-linear methods (k nearest neighbors, kernel-PLS-DA and, in the case of rice, counterpropagation neural networks).",
keywords = "Non-linear classification, Partial least squares-discriminant analysis (PLS-DA), Locally weighted classification, Nearest neighbors, Distance-based weighting scheme",
author = "Marta Bevilacqua and Federico Marini",
year = "2014",
doi = "10.1016/j.aca.2014.05.057",
language = "English",
volume = "838",
pages = "20 -- 30",
journal = "Analytica Chimica Acta",
issn = "0003-2670",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Local classification

T2 - locally weighted–partial least squares-discriminant analysis (LW–PLS-DA)

AU - Bevilacqua, Marta

AU - Marini, Federico

PY - 2014

Y1 - 2014

N2 - The possibility of devising a simple, flexible and accurate non-linear classification method, by extending the locally weighted partial least squares (LW–PLS) approach to the cases where the algorithm is used in a discriminant way (partial least squares discriminant analysis, PLS-DA), is presented. In particular, to assess which category an unknown sample belongs to, the proposed algorithm operates by identifying which training objects are most similar to the one to be predicted and building a PLS-DA model using these calibration samples only. Moreover, the influence of the selected training samples on the local model can be further modulated by adopting a not uniform distance-based weighting scheme which allows the farthest calibration objects to have less impact than the closest ones. The performances of the proposed locally weighted–partial least squares-discriminant analysis (LW–PLS-DA) algorithm have been tested on three simulated data sets characterized by a varying degree of non-linearity: in all cases, a classification accuracy higher than 99% on external validation samples was achieved. Moreover, when also applied to a real data set (classification of rice varieties), characterized by a high extent of non-linearity, the proposed method provided an average correct classification rate of about 93% on the test set. By the preliminary results, showed in this paper, the performances of the proposed LW–PLS-DA approach have proved to be comparable and in some cases better than those obtained by other non-linear methods (k nearest neighbors, kernel-PLS-DA and, in the case of rice, counterpropagation neural networks).

AB - The possibility of devising a simple, flexible and accurate non-linear classification method, by extending the locally weighted partial least squares (LW–PLS) approach to the cases where the algorithm is used in a discriminant way (partial least squares discriminant analysis, PLS-DA), is presented. In particular, to assess which category an unknown sample belongs to, the proposed algorithm operates by identifying which training objects are most similar to the one to be predicted and building a PLS-DA model using these calibration samples only. Moreover, the influence of the selected training samples on the local model can be further modulated by adopting a not uniform distance-based weighting scheme which allows the farthest calibration objects to have less impact than the closest ones. The performances of the proposed locally weighted–partial least squares-discriminant analysis (LW–PLS-DA) algorithm have been tested on three simulated data sets characterized by a varying degree of non-linearity: in all cases, a classification accuracy higher than 99% on external validation samples was achieved. Moreover, when also applied to a real data set (classification of rice varieties), characterized by a high extent of non-linearity, the proposed method provided an average correct classification rate of about 93% on the test set. By the preliminary results, showed in this paper, the performances of the proposed LW–PLS-DA approach have proved to be comparable and in some cases better than those obtained by other non-linear methods (k nearest neighbors, kernel-PLS-DA and, in the case of rice, counterpropagation neural networks).

KW - Non-linear classification

KW - Partial least squares-discriminant analysis (PLS-DA)

KW - Locally weighted classification

KW - Nearest neighbors

KW - Distance-based weighting scheme

U2 - 10.1016/j.aca.2014.05.057

DO - 10.1016/j.aca.2014.05.057

M3 - Journal article

VL - 838

SP - 20

EP - 30

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

SN - 0003-2670

ER -

ID: 228372683