Article
Computer Science, Information Systems
M. Tanveer, S. Sharma, K. Muhammad
Summary: The proposed LS-LSTSVM addresses the shortcomings of TWSVM and LSTSVM by introducing a different Lagrangian function to eliminate the need for calculating inverse matrices, using the kernel trick directly for non-linear cases, and minimizing structural risk. These improvements aim to enhance classification accuracy on datasets, especially for large-scale problems.
ACM TRANSACTIONS ON INTERNET TECHNOLOGY
(2021)
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
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
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
Matteo Stocchero, Martino De Nardi, Bruno Scarpa
Summary: In this study, an alternative formulation of PLS2 based on gradient descent method is proposed and a new algorithm called gradient descent PLS2 is introduced to solve the least squares problem. The algorithm uses well-defined elements of linear algebra and is developed within the field of non-linear programming, showing equivalent performance to the standard eigenvalue PLS2 algorithm.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Chemistry, Multidisciplinary
Jinhwan Ryu, Seunghwan Wi, Hoonsoo Lee
Summary: This study aimed to develop a model for detecting heat stress in southern-type garlic using a multispectral snapshot camera. Raw snapshot images from garlic cloves were captured during the garlic bulb enlargement period, covering the visible and near-infrared regions. Preprocessing of images led to a 38-wavelength spectrum, which was used to develop models including PLS-DA, LS-SVM, DNN, and RP-CNN. The LS-SVM model showed the best performance in detecting heat stress, attributed to the nonlinear nature of spectral differences caused by abiotic stress in garlic. LS-SVM outperformed RP-CNN, DNN, and PLS-DA in terms of model performance. This study confirms the potential of snapshot-based multispectral imaging for measuring high-temperature stress-induced changes in garlic crops.
APPLIED SCIENCES-BASEL
(2023)
Article
Multidisciplinary Sciences
Xiangyu Guo, Ahmed Jahoor, Just Jensen, Pernille Sarup
Summary: In this study, metabolomic spectra were used to predict malting quality phenotypes in different locations, and the prediction ability of different models and training population sizes were compared. The results showed that more than 90% of the total variance in malting quality traits could be explained by metabolomic features. The prediction accuracy increased with increasing training population size and stabilized when the size reached 1000. The optimal number of components considered in the prediction models was 20. The accuracy using cross-validation ranged from 0.722 to 0.865 for leave-one-line-out and from 0.517 to 0.817 for leave-one-location-out. Therefore, metabolomic prediction of malting quality traits using metabolomic features has high accuracy, and MBLUP is better than PLSR when the training population size is larger than 100.
SCIENTIFIC REPORTS
(2022)
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
Chemistry, Analytical
Etil Guzelmeric, Durmus Ozdemir, Nisa Beril Sen, Cansel Celik, Erdem Yesilada
Summary: The plant source of propolis determines its chemical composition, which can be identified and quantified using HPTLC and HPLC techniques. This study compared the amounts of marker components in propolis samples using HPTLC images and validated HPLC methods, and successfully demonstrated the feasibility of quantifying propolis using HPTLC images.
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS
(2023)
Article
Engineering, Environmental
Mainak Chatterjee, Kunal Roy
Summary: This paper developed QSAR models for predicting aquatic toxicity, using Partial Least Squares regression as a statistical tool. The models were based on structural features of individual chemicals and mixture components, with quality assessed by strict validation parameters. The final models are robust, highly predictive, and mechanistically interpretable for predicting toxicity of untested chemical mixtures within the domain of applicability.
JOURNAL OF HAZARDOUS MATERIALS
(2021)
Article
Optics
Hu Jun, Yang Liang, Tongzheng Lin, Hongyang Shi, Qiao Peng, He Yong, Liu Yande
Summary: The study utilizes LIBS technology to conduct discriminant analysis of the metallographic structure of train wheel steel, and performs initial analysis of the spectral data through principal component analysis. The results show that the SVM model established using pre-processed MSC data has the best performance.
Article
Food Science & Technology
Ying Bu, Menglin Han, Guizhi Tan, Wenhui Zhu, Xuepeng Li, Jianrong Li
Summary: This study investigated the quality characteristics of southern bluefin tuna during refrigerated storage at 4 degrees C, finding that lipid and protein oxidation aggravated with storage time, leading to browning. The model constructed using partial least squares showed that thiobarbituric acid reactive substance content was significantly correlated with color stability.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2022)
Article
Chemistry, Multidisciplinary
Jiaqi Zheng, Lianwei Ma, Yi Wu, Lingjian Ye, Feifan Shen
Summary: This paper proposes a supervised hybrid network based on dynamic CNN and LSTM networks to address the issue of incomplete quality-relevant features in conventional deep learning methods. The effectiveness of the proposed soft sensor development is validated through two industrial applications.
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, Applied
Simona Funar-Timofei, Ludovic Kurunczi
Article
Polymer Science
Luminita Crisan, Smaranda Iliescu, Simona Funar-Timofei
POLIMEROS-CIENCIA E TECNOLOGIA
(2016)
Article
Biochemistry & Molecular Biology
Simona Funar-Timofei, Ana Borota, Luminita Crisan
MOLECULAR DIVERSITY
(2017)
Article
Materials Science, Multidisciplinary
Luminita Crisan, Smaranda Iliescu, Gheorghe Ilia, Simona Funar-Timofei
FIRE AND MATERIALS
(2019)
Article
Biochemistry & Molecular Biology
Sergiu Adrian Chicu, Melania Munteanu, Ioana Citu, Codruta Soica, Cristina Dehelean, Cristina Trandafirescu, Simona Funar-Timofei, Daniela Ionescu, Georgeta Maria Simu
Article
Chemistry, Multidisciplinary
Simona Funar-Timofei, Smaranda Iliescu, Takahiro Suzuki
STRUCTURAL CHEMISTRY
(2014)
Article
Chemistry, Medicinal
Luminita Crisan, Ana Borota, Takahiro Suzuki, Simona Funar-Timofei
MOLECULAR INFORMATICS
(2019)
Article
Environmental Sciences
Alina Bora, Takahiro Suzuki, Simona Funar-Timofei
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2019)
Article
Chemistry, Medicinal
Luminita Crisan, Ana Borota, Alina Bora, Takahiro Suzuki, Simona Funar-Timofei
Summary: This study explored the insecticidal activity of neonicotinoids with diverse scaffolds against Aphis craccivora using combined methods, and identified new insecticide candidates with less potential toxic effects for honeybees through molecular docking and regression analysis.
MOLECULAR INFORMATICS
(2022)
Article
Biochemistry & Molecular Biology
Luminita Crisan, Simona Funar-Timofei, Ana Borota
Summary: This article investigates new insecticides targeting vector-borne infectious diseases, particularly malaria transmitted by mosquitoes. By constructing a 3D model of the receptor and conducting docking experiments, researchers identified possible binding sites and discovered a potential new insecticide.
Article
Chemistry, Physical
Sabina Nitu, Marius Silviu Milea, Sorina Boran, Giannin Mosoarca, Alina D. Zamfir, Simona Popa, Simona Funar-Timofei
Summary: This paper describes the synthesis and characterization of eight new pyrazole azo dyes using ethyl 5-amino-3-methyl-1H-pyrazole-4-carboxylate as the diazotization component and various active methylene derivatives as coupling components. The results suggest that these newly synthesized dyes have good color properties and can be used for light color paints in the varnishes industry.
Article
Chemistry, Multidisciplinary
Alina Bora, Sorin Avram, Simona Funar-Timofei, Liliana Halip
REVUE ROUMAINE DE CHIMIE
(2018)
Article
Chemistry, Multidisciplinary
Luminita Crisan, Simona Funar-Timofei, Ana Borota
REVUE ROUMAINE DE CHIMIE
(2017)
Article
Chemistry, Multidisciplinary
Luminita Crisan, Smaranda Iliescu, Simona Funar-Timofei
REVUE ROUMAINE DE CHIMIE
(2015)
Article
Chemistry, Multidisciplinary
Ana Borota, Simona Funar-Timofei, Alina Bora, Ramona Curpan
REVUE ROUMAINE DE CHIMIE
(2018)
Article
Toxicology
Kathryn Page, Walter Westerink, Kristie Sullivan, Thomas McDonald, Clive Roper
Summary: This study developed a new method to assess the skin irritation of antimicrobial cleaning products. The method utilized a more human-like model and demonstrated its effectiveness through comparison with in vivo rabbit skin irritation data.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Arupam Patra, Thirukumaran Kandasamy, Siddhartha Sankar Ghosh, Gurvinder Kaur Saini
Summary: This study successfully produced recombinant anisoplin and demonstrated its significant anti-cancer effect and ability to induce apoptosis in breast cancer cells. The activation of related signaling pathways may be the key to cell death.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Thomas Haller, Alexander Jesacher, Alberto Hidalgo, Christina Schmidt
Summary: This study used live cell imaging to observe the accumulation of amiodarone in primary rat alveolar type II cells, and found that it specifically accumulates in lamellar bodies. The uptake is rapid, while storage is persistent. The main mechanisms for intracellular bioaccumulation of amiodarone are proposed to be passive diffusion, ion-trapping, and lipophilic interactions.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Filiz Bakar-Ates, Erva Ozkan
Summary: This study investigated the ferroptotic effect of CuB in breast cancer cells and evaluated its combination with erastin, a ferroptosis inducer. The results showed that the combination treatment significantly activated the ferroptotic pathways and altered the expression of iron-related proteins in breast cancer cells.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Rachel Z. Bennie, Ian C. Shaw
Summary: Estrogen mimics are synthetic and naturally occurring compounds that can interact with estrogen receptors in animals. In vitro transactivation reporter gene assay and in silico molecular modelling can be used to predict the mimicry of these compounds, reducing reliance on animal studies.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Sevda Isik, Semra Cicek
Summary: This study found that high doses of riboflavin can cause cytotoxicity in rainbow trout gonad cells and affect the transcriptional expressions of antioxidant enzymes and growth and reproductive genes, potentially leading to DNA damage and cell death.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Ying Wang, Jie Wu, Mengqi Wan, Dou Yang, Fasheng Liu, Kehao Li, Manxin Hu, Yuanyuan Tang, Huiqiang Lu, Shouhua Zhang, Yuanzhen Xiong
Summary: m-Cresol is commonly used as an intermediate for pesticides and other industrial applications. This study investigated the hepatotoxicity of m-cresol using zebrafish larvae and explored its molecular mechanisms. The results suggest that m-cresol may induce liver damage in zebrafish larvae through oxidative stress and cell apoptosis pathways.
TOXICOLOGY IN VITRO
(2024)
Article
Toxicology
Vincent J. Manna, Shannon Dwyer, Vanessa Pizutelli, Salvatore J. Caradonna
Summary: The widespread use of electronic cigarettes and the emergence of a new illness have raised concerns about the effects of e-cigarette vapor on respiratory tissues. Researchers have developed a simple device to mimic the response of human airway tissue after long-term exposure to e-cigarette vapor, and have identified differences in the effects of different vapor compositions on airway tissue.
TOXICOLOGY IN VITRO
(2024)