Project code: PID2019-104269RR-C33 / AEI / 10.13039/501100011033
Keywords: Vibrational spectroscopy Validation Root mean square error Preprocessing Partial least squares regression Latent variables Cross-validation vibrational spectroscopy validation root mean square error preprocessing latent variables calibration
Record's date: 2024-11-16
Papper version: info:eu-repo/semantics/publishedVersion
Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
Papper original source: Chemometrics And Intelligent Laboratory Systems. 240
APA: Ezenarro, J; Schorn-García, D; Aceña, L; Mestres, M; Busto, O; Boqué, R (2023). J-Score: A new joint parameter for PLSR model performance evaluation of spectroscopic data. Chemometrics And Intelligent Laboratory Systems, 240(), -. DOI: 10.1016/j.chemolab.2023.104883
Acronym: ALLFRUIT4ALL
Publication Type: Journal Publications
Project code 3: 2021PMF-BS-12
Author, as appears in the article.: Ezenarro, J; Schorn-García, D; Aceña, L; Mestres, M; Busto, O; Boqué, R
Department: Química Analítica i Química Orgànica
URV's Author/s: Aceña Muñoz, Laura / Boqué Martí, Ricard / Busto Busto, Olga / EZENARRO GARATE, JOKIN / Mestres Solé, Maria Montserrat / Schorn García, Daniel
Abstract: Since its beginnings, many parameters have been proposed to evaluate the goodness of Partial Least Squares Regression (PLSR) models and thus help chemometricians to choose the most appropriate one. This article proposes a new performance evaluation parameter for regression models based on spectroscopic data, the J-Score, which combines some of the most commonly used model evaluation parameters (Ratio of Performance to Deviation, Calibration and Validation Root Mean Square Errors and Regression Vector) into a single indicator. The J-Score can help non-experienced analysts select both the adequate number of Latent Variables (LVs) and the best preprocessing technique for their dataset in an automated way. The performance of the J-Score has been compared to other evaluation methods with different datasets, demonstrating that it can be used for different types of samples and spectroscopic data; that it is stable and objective, and offers an easy way to select the optimal number of LVs.
Program founding action 2: Agencia de Gestión de Ayudas Universitarias y de Investigación (AGAUR)
Thematic Areas: Statistics & probability Spectroscopy Software Robotics & automatic control Química Process chemistry and technology Mathematics, interdisciplinary applications Matemática / probabilidade e estatística Interdisciplinar Instruments & instrumentation Farmacia Engenharias iv Engenharias iii Engenharias ii Computer science, artificial intelligence Computer science applications Ciências ambientais Ciências agrárias i Ciência de alimentos Ciência da computação Chemistry, analytical Biotecnología Automation & control systems Analytical chemistry
licence for use: https://creativecommons.org/licenses/by/3.0/es/
Author's mail: jokin.ezenarro@urv.cat jokin.ezenarro@urv.cat daniel.schorn@alumni.urv.cat daniel.schorn@alumni.urv.cat montserrat.mestres@urv.cat ricard.boque@urv.cat olga.busto@urv.cat laura.acena@urv.cat
Author identifier: 0000-0001-9234-7877 0000-0001-9234-7877 0000-0003-0997-2191 0000-0003-0997-2191 0000-0001-9805-3482 0000-0001-7311-4824 0000-0002-2318-6800 0000-0001-5942-9424
Founding program action 3: Universitat Rovira i Virgili - Banco Santander
Project code 2: 2020 FISDU 00221
Founding program 2: Ayudas de apoyo a departamentos y unidades de investigación universitarios para la contratación de personal investigador predoctoral en formación (FI SDUR 2020)
Funding program: Programa Estatal de Generación de Conocimiento y Fortalecimiento Científico y Tecnológico del Sistema de I+D+i y de I+D+i Orientada a los Retos de la Sociedad. Proyectos de I+D+i Retos Investigación 2017-2020
Founding program 3: Contratos de personal investigador predoctoral en formación
Entity: Universitat Rovira i Virgili
Journal publication year: 2023
Funding program action: Ciencias y tecnologías de alimentos
Repositori URV