Article
Multidisciplinary Sciences
Emilio Gomez-Gonzalez, Alejandro Barriga-Rivera, Beatriz Fernandez-Munoz, Jose Manuel Navas-Garcia, Isabel Fernandez-Lizaranzu, Francisco Javier Munoz-Gonzalez, Ruben Parrilla-Giraldez, Desiree Requena-Lancharro, Pedro Gil-Gamboa, Cristina Rosell-Valle, Carmen Gomez-Gonzalez, Maria Jose Mayorga-Buiza, Maria Martin-Lopez, Olga Munoz, Juan Carlos Gomez-Martin, Maria Isabel Relimpio-Lopez, Jesus Aceituno-Castro, Manuel A. Perales-Esteve, Antonio Puppo-Moreno, Francisco Jose Garcia-Cozar, Lucia Olvera-Collantes, Raquel Gomez-Diaz, Silvia de los Santos-Trigo, Monserrat Huguet-Carrasco, Manuel Rey, Emilia Gomez, Rosario Sanchez-Pernaute, Javier Padillo-Ruiz, Javier Marquez-Rivas
Summary: This study demonstrates the feasibility of using hyperspectral image analysis in the visible and near-infrared range for primary screening of SARS-CoV-2. By applying spectral feature descriptors, partial least square-discriminant analysis, and artificial intelligence, information can be extracted from fluid samples and analyzed quantitatively and descriptively. The proposed technology is reagent-free, fast, scalable, and could significantly reduce the number of molecular tests required for COVID-19 mass screening, even in resource-limited settings.
SCIENTIFIC REPORTS
(2022)
Article
Automation & Control Systems
Zhonghao Xie, Xi'an Feng, Xiaojing Chen
Summary: This paper proposes a robust method for PLS based on the idea of least trimmed squares (LTS), which effectively deals with high-dimensional regressors. By formulating the LTS problem as a concave maximization problem, the complexity of solving LTS is simplified. The results from simulation and real data sets demonstrate the effectiveness and robustness of the proposed approach.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Chemistry, Applied
Limin Li, Wee Shong Chin
Summary: This study developed a facile Ag nanocube (NC) array substrate for rapid SERS detection of melamine in milk with high Raman enhancement and good reproducibility. The proposed method can detect melamine at low concentrations and SVM regression models showed better predictive performance, especially in liquid milk samples.
Article
Multidisciplinary Sciences
Jing Zhu, Siyu Zhang, Ruting Wang, Ruhua Fang, Lan Lei, Ji Zheng, Zhongjian Chen
Summary: This study explores an effective, noninvasive, and convenient diagnostic tool for cancer using urine based near-infrared spectroscopy (NIRS) analysis combined with machine learning algorithm. The results show that the combination of urine based NIRS analysis and machine learning can achieve high prediction accuracy, providing encouragement for further evaluation in large-scale multi-center studies.
Article
Agriculture, Multidisciplinary
Yongni Shao, Jialing Liu, Zhi Zhu, Yutian Wang, Yiming Zhu, Yan Peng
Summary: This study investigates the feasibility of using terahertz spectroscopy for synchronous detection on metabolites concentration in microalgae production process. By capturing terahertz spectrum of stressed Haematococcus Pluvialis under nitrogen starvation, a correlation between metabolite contents and characteristic peak intensities was established, showing relatively accurate prediction of metabolite concentrations. A precise model combining partial least squares with intensities of interval characteristic peaks demonstrated high prediction correlation coefficients, low root-mean-square error of prediction, and validation of terahertz spectroscopy for monitoring metabolites concentration.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Critical Care Medicine
Hanglin Ye, Rahul, Uwe Kruger, Tianmeng Wang, Sufei Shi, Jack Norfleet, Suvranu De
Summary: The feasibility of classifying burn severities using Raman spectroscopy alone has been demonstrated, with an average accuracy of 92% achieved by kernel support vector machine and partial least-square regression.
Article
Biochemical Research Methods
Ruoyu Tang, Xinyu He, Ruiqi Wang
Summary: The study presents a general computational method for constructing maps between different cell fates and parametric conditions by systematic perturbations. The method does not require accurate parameter measurements or bifurcations. The maps obtained can help in understanding how systematic perturbations drive cell fate decisions and transitions, providing valuable information for predicting and controlling cell states.
Article
Engineering, Chemical
Hye Ji Lee, Shinje Lee, Jong Min Lee
Summary: The proposed method improves trajectory tracking performance and reduces tracking error by applying online alignment, selecting multiple models, and adaptively applying future reference based on current batch measurements. Additionally, the method adaptively decides batch duration, leading to improved overall performance in industrial penicillin production.
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
(2022)
Article
Chemistry, Analytical
Alessandra Biancolillo, Jean-Michel Roger, Federico Marini
Summary: In this paper, a feature selection strategy for N-way data based on the Covariance Selection (CovSel) approach, referred to as N-CovSel, is discussed. The method allows the selection of meaningful features of different dimensionality and proposes different strategies for further analysis of the selected features.
ANALYTICA CHIMICA ACTA
(2022)
Article
Green & Sustainable Science & Technology
Jose Ramon Segarra-Moliner, Inmaculada Bel-Oms
Summary: The aim of this study is to analyze the relationship between environmental, social and governance dimensions of corporate sustainability initiatives and customer lifetime value. A data sample of 547 US listed firms was divided into three segments and a prediction-oriented modeling segmentation was used to test hypotheses and evaluate the predictive validity of a partial least squares model. The results showed that ESG dimensions encompass ten sustainability initiatives that are precursors of future financial firm performance represented by CLV.
Article
Automation & Control Systems
Matteo Stocchero, Martino De Nardi, Bruno Scarpa
Summary: PLS regression is a technique for multivariate responses in the presence of multicollinearity, and efforts have been made to extend it to classification problems. A new technique called PLS for classification has been introduced to address the general G-class problem, estimating conditional probabilities and using score vectors for model interpretation.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2021)
Article
Multidisciplinary Sciences
M. Mamouei, K. Budidha, N. Baishya, M. Qassem, P. A. Kyriacou
Summary: The use of linear models in spectroscopy applications is valid, however, nonlinear effects may exist in high concentrations and scattering media, justifying the use of complex nonlinear models.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Chemical
James Odgers, Chrysoula Kappatou, Ruth Misener, Salvador Garcia Munoz, Sarah Filippi
Summary: This article presents an approach based on bootstrapping to model the uncertainty in partial least squares (PLS), which is difficult due to the nonlinear effect of the observed data on the latent space. The approach allows for equally representing confidence intervals for points close to or far away from the latent space. Applications in determining the Design Space for industrial processes and modeling the uncertainty of spectroscopy data demonstrate the benefits and performance of the method.
Article
Engineering, Mechanical
Yushan Liu, Luyi Li, Sihan Zhao
Summary: This paper combines Kriging and PLS to develop a global surrogate model for high-dimensional structural systems, named as PLS-K. In the proposed method, PLS is employed to identify the input-output principal components, wherein Kriging model is used to establish the relationship between each pair of principal components.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Business
Maria-Teresa Mendez-Picazo, Miguel-Angel Galindo-Martin, Maria-Soledad Castano-Martinez
Summary: Concern about environmental problems has led to greater attention to the sustainable development objective. Social entrepreneurship and entrepreneurship in general are closely related to this objective due to their activities in developing new products, seeking new markets, and introducing innovations. Identifying variables that influence these entrepreneurship types is important in designing measures to stimulate sustainable development.
JOURNAL OF INNOVATION & KNOWLEDGE
(2021)