Nonlinear feature extraction through manifold learning in an electronic tongue classification task

View/Open
Document typeArticle
Defense date2020-08-27
PublisherMultidisciplinary Digital Publishing Institute (MDPI)
Rights accessOpen Access
Abstract
A nonlinear feature extraction-based approach using manifold learning algorithms is developed in order to improve the classification accuracy in an electronic tongue sensor array. The developed signal processing methodology is composed of four stages: data unfolding, scaling, feature extraction, and classification. This study aims to compare seven manifold learning algorithms: Isomap, Laplacian Eigenmaps, Locally Linear Embedding (LLE), modified LLE, Hessian LLE, Local Tangent Space Alignment (LTSA), and t-Distributed Stochastic Neighbor Embedding (t-SNE) to find the best classification accuracy in a multifrequency large-amplitude pulse voltammetry electronic tongue. A sensitivity study of the parameters of each manifold learning algorithm is also included. A data set of seven different aqueous matrices is used to validate the proposed data processing methodology. A leave-one-out cross validation was employed in 63 samples. The best accuracy (96.83%) was obtained when the methodology uses Mean-Centered Group Scaling (MCGS) for data normalization, the t-SNE algorithm for feature extraction, and k-nearest neighbors (kNN) as classifier.
CitationLeon-Medina, J.X. [et al.]. Nonlinear feature extraction through manifold learning in an electronic tongue classification task. "Sensors", 27 Agost 2020, vol. 2020, núm. 20, p. 1-20.
ISSN1424-8220
Publisher versionhttps://www.mdpi.com/1424-8220/20/17/4834/htm
Files | Description | Size | Format | View |
---|---|---|---|---|
2020_54_SENSORS_leo_ana_poz_tib_ETONGUE.pdf | Article principal | 3,858Mb | View/Open |
Except where otherwise noted, content on this work
is licensed under a Creative Commons license
:
Attribution-NonCommercial-NoDerivs 3.0 Spain