Repositori institucional URV
| URV's Author/s: | Ferré Baldrich, Joan / Larrechi García, Maria Soledad |
| Author, as appears in the article.: | Rodriguez-Barrios, M Suliany; Ferre, Joan; Larrechi, M Soledad; Ruiz, Enric |
| Author's mail: | joan.ferre@urv.cat |
| Author identifier: | 0000-0001-6240-413X |
| Journal publication year: | 2024 |
| Publication Type: | Journal Publications |
| APA: | Rodriguez-Barrios, M Suliany; Ferre, Joan; Larrechi, M Soledad; Ruiz, Enric (2024). Applicability domain of a calibration model based on neural networks and infrared spectroscopy. Chemometrics And Intelligent Laboratory Systems, 254(), 105242-. DOI: 10.1016/j.chemolab.2024.105242 |
| Papper original source: | Chemometrics And Intelligent Laboratory Systems. 254 105242- |
| Abstract: | Artificial neural networks are used as calibration models in routine analytical determinations that involve spectroscopic data. To ensure that the model will generate reliable predictions for new samples, the applicability domain must be well defined. This article describes a strategy for establishing the limits of the applicability domain when the calibration model is a feed-forward neural network. The applicability domain was defined by two limits: 1) the 0.99 quantile of the squared Mahalanobis distance calculated from the network activations of the training set and 2) the 0.99 quantile of the reconstruction error of the training spectra using either an autoencoder network or a decoder network. A new sample with a squared Mahalanobis distance and/or spectral residuals beyond these limits is said to be outside the applicability domain, and the prediction is questionable. The approach was illustrated by predicting the density of diesel fuel samples from mid-infrared spectra and the fat content in meat from near-infrared spectra. The methodology could correctly detect anomalous spectra in prediction using either the autoencoder or the decoder. |
| Article's DOI: | 10.1016/j.chemolab.2024.105242 |
| Link to the original source: | https://www.sciencedirect.com/science/article/pii/S0169743924001825?via%3Dihub |
| Papper version: | info:eu-repo/semantics/publishedVersion |
| licence for use: | https://creativecommons.org/licenses/by/3.0/es/ |
| Department: | Química Analítica i Química Orgànica |
| Licence document URL: | https://repositori.urv.cat/ca/proteccio-de-dades/ |
| Thematic Areas: | Analytical chemistry Automation & control systems Biotecnología Chemistry, analytical Ciência da computação Ciência de alimentos Ciências agrárias i Ciências ambientais Computer science applications Computer science, artificial intelligence Engenharias ii Engenharias iii Engenharias iv Farmacia Instruments & instrumentation Interdisciplinar Matemática / probabilidade e estatística Mathematics, interdisciplinary applications Process chemistry and technology Química Robotics & automatic control Software Spectroscopy Statistics & probability |
| Keywords: | Applicability domain Artificial neural networks Autoencoder Decoder Diese Diesel Distance Infrared spectroscopy Novelty detection Prediction Regression Spac |
| Entity: | Universitat Rovira i Virgili |
| Record's date: | 2024-11-09 |
| Search your record at: |   |
| File | Description | Format | |
|---|---|---|---|
| DocumentPrincipal | DocumentPrincipal | application/pdf |
© 2011 Universitat Rovira i Virgili