Pub Date : 2024-11-12DOI: 10.1016/j.chemolab.2024.105269
Yi Liu , Angpeng Liu , Shuang Gao
High-precision oxygen content measurement is crucial for statistical analysis of combustion chemical reaction. Deep learning based soft sensor is a new class of intelligent tools for monitoring combustion oxygen content. But in the actual production, data for sensors are often insufficient. A new soft sensing model is proposed to display the excellent performance of denoising diffusion probabilistic model (DDPM) in data generation. Firstly, a UNet based soft sensor is designed by integrating self-attention mechanism into the convolution layers. Then, a denoising loss function is designed to link the feature extraction process of soft sensor model with the reverse denoising process of DDPM, and the noise prediction neural network of DDPM is used to improve the feature extractability of the soft sensor model. Finally, the proposed model is compared with common models. The effectiveness and superiority of the proposed soft sensing model for oxygen content prediction, especially in the case with a small sample size, are both confirmed by the results.
{"title":"A flame image soft sensor for oxygen content prediction based on denoising diffusion probabilistic model","authors":"Yi Liu , Angpeng Liu , Shuang Gao","doi":"10.1016/j.chemolab.2024.105269","DOIUrl":"10.1016/j.chemolab.2024.105269","url":null,"abstract":"<div><div>High-precision oxygen content measurement is crucial for statistical analysis of combustion chemical reaction. Deep learning based soft sensor is a new class of intelligent tools for monitoring combustion oxygen content. But in the actual production, data for sensors are often insufficient. A new soft sensing model is proposed to display the excellent performance of denoising diffusion probabilistic model (DDPM) in data generation. Firstly, a UNet based soft sensor is designed by integrating self-attention mechanism into the convolution layers. Then, a denoising loss function is designed to link the feature extraction process of soft sensor model with the reverse denoising process of DDPM, and the noise prediction neural network of DDPM is used to improve the feature extractability of the soft sensor model. Finally, the proposed model is compared with common models. The effectiveness and superiority of the proposed soft sensing model for oxygen content prediction, especially in the case with a small sample size, are both confirmed by the results.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105269"},"PeriodicalIF":3.7,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1016/j.chemolab.2024.105271
Qi Yang , Lihao Yao , Fang Jia , Guiyuan Pang , Meiyu Huang , Chengxiang Liu , Hua Luo , Lili Fan
The objective of this study is to develop a reliable predictive model for antitumour activity and to identify potential antitumour components in Ganoderma lucidum. Four machine learning models, including Random Forest, were employed to train predictive models for antitumour activity, utilising Morgan fingerprints as molecular descriptors. The most effective model was then employed to predict the chemical composition of Ganoderma lucidum, identifying the four most probable compounds for molecular docking with known TNF-α-related targets. The findings of the study indicate that a Support Vector Machine (SVM) model exhibits an accuracy, F1 score, AUC, and sensitivity of 0.7638, 0.7638, 0.8332, and 0.7621, respectively. The model demonstrated an 80 % accuracy rate in predicting the antitumour activity of 10 FDA-approved drugs. Besides, the model identified 11 components in Ganoderma lucidum, including 3-nitroanisole, with a probability of antitumour activity exceeding 0.5, indicating their potential as antitumour agents. The results of the molecular docking procedure indicated that the four most promising antitumour compounds derived from Ganoderma lucidum exhibited a favourable binding affinity with the TNF-α target. In conclusion, this study incorporated a machine learning prediction step prior to molecular docking, thereby enhancing the reliability of the latter. Furthermore, it identified previously unreported compounds in Ganoderma lucidum with potential antitumour activity, such as 3-nitroanisole.
{"title":"Prediction of potential antitumor components in Ganoderma lucidum: A combined approach using machine learning and molecular docking","authors":"Qi Yang , Lihao Yao , Fang Jia , Guiyuan Pang , Meiyu Huang , Chengxiang Liu , Hua Luo , Lili Fan","doi":"10.1016/j.chemolab.2024.105271","DOIUrl":"10.1016/j.chemolab.2024.105271","url":null,"abstract":"<div><div>The objective of this study is to develop a reliable predictive model for antitumour activity and to identify potential antitumour components in <em>Ganoderma lucidum</em>. Four machine learning models, including Random Forest, were employed to train predictive models for antitumour activity, utilising Morgan fingerprints as molecular descriptors. The most effective model was then employed to predict the chemical composition of <em>Ganoderma lucidum</em>, identifying the four most probable compounds for molecular docking with known TNF-α-related targets. The findings of the study indicate that a Support Vector Machine (SVM) model exhibits an accuracy, F1 score, AUC, and sensitivity of 0.7638, 0.7638, 0.8332, and 0.7621, respectively. The model demonstrated an 80 % accuracy rate in predicting the antitumour activity of 10 FDA-approved drugs. Besides, the model identified 11 components in <em>Ganoderma lucidum</em>, including 3-nitroanisole, with a probability of antitumour activity exceeding 0.5, indicating their potential as antitumour agents. The results of the molecular docking procedure indicated that the four most promising antitumour compounds derived from <em>Ganoderma lucidum</em> exhibited a favourable binding affinity with the TNF-α target. In conclusion, this study incorporated a machine learning prediction step prior to molecular docking, thereby enhancing the reliability of the latter. Furthermore, it identified previously unreported compounds in <em>Ganoderma lucidum</em> with potential antitumour activity, such as 3-nitroanisole.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105271"},"PeriodicalIF":3.7,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-05DOI: 10.1016/j.chemolab.2024.105270
Junhua Zheng , Zeyu Yang , Zhiqiang Ge
Independent component regression (ICR) has recently become quite popular in spectra data calibration, due to its advantages in non-Gaussian data modeling and high-order statistics feature extraction. Inspired by the idea of deep learning, this paper extends the basic ICR model to the deep form by introducing a layer-wise residual learning strategy. Based on the residual information generated from last layer of the deep learning model, more and more different patterns of independent components can be extracted layer-by-layer. Then, a further information compression step is taken to combine and also to condense those independent components obtained from different layers of the deep model. Two detailed benchmark case studies are implemented to evaluate the calibration performance of the develop model, based on which the effectiveness of both layer-by-layer component extraction and further information compression are well confirmed.
{"title":"Spectra data calibration based on deep residual modeling of independent component regression","authors":"Junhua Zheng , Zeyu Yang , Zhiqiang Ge","doi":"10.1016/j.chemolab.2024.105270","DOIUrl":"10.1016/j.chemolab.2024.105270","url":null,"abstract":"<div><div>Independent component regression (ICR) has recently become quite popular in spectra data calibration, due to its advantages in non-Gaussian data modeling and high-order statistics feature extraction. Inspired by the idea of deep learning, this paper extends the basic ICR model to the deep form by introducing a layer-wise residual learning strategy. Based on the residual information generated from last layer of the deep learning model, more and more different patterns of independent components can be extracted layer-by-layer. Then, a further information compression step is taken to combine and also to condense those independent components obtained from different layers of the deep model. Two detailed benchmark case studies are implemented to evaluate the calibration performance of the develop model, based on which the effectiveness of both layer-by-layer component extraction and further information compression are well confirmed.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105270"},"PeriodicalIF":3.7,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.chemolab.2024.105268
Chairul Ichsan , Navinda Ramadhan , Komang Gede Yudi Arsana , M. Mahfudz Fauzi Syamsuri , Rohmatullaili
The importance of effective carbon capture and storage (CCS) in addressing climate change issues highlights the need for robust CO2 leak monitoring systems. Limitations of conventional methods have prompted interest in alternative approaches, such as optical CO2 sensors, which offer non-invasive and continuous monitoring. Here, we present a novel methodology for high-fidelity digital colorimetry to enhance CO2 leak detection in soil, integrating machine learning algorithms with the ACES AP0 color space. Optical CO2 sensors, utilizing a cresol red-based detection solution, were calibrated and validated in a controlled environment chamber designed to simulate CO2 leakage. Digital images of the sensor's colorimetric response to varying CO2 levels were analyzed in five color spaces. The ACES AP0 color space, renowned for its expansive color gamut and perceptual uniformity, exhibited optimal performance in discerning subtle color variations induced by changes in CO2 concentration. Ten machine learning regression models were evaluated, and Multivariate Polynomial Regression (MPR) emerged as the most effective in converting ACES AP0 color data into precise CO2 concentration estimates, achieving a Mean Absolute Percentage Error (MAPE) of 2.9 % and a Root Mean Square Error (RMSE) of 0.0731. Field validation at a carbon capture and storage (CCS) facility corroborated the robustness and accuracy of this method, showcasing its potential for real-world applications in CCS and environmental monitoring.
{"title":"Enhanced CO2 leak detection in soil: High-fidelity digital colorimetry with machine learning and ACES AP0","authors":"Chairul Ichsan , Navinda Ramadhan , Komang Gede Yudi Arsana , M. Mahfudz Fauzi Syamsuri , Rohmatullaili","doi":"10.1016/j.chemolab.2024.105268","DOIUrl":"10.1016/j.chemolab.2024.105268","url":null,"abstract":"<div><div>The importance of effective carbon capture and storage (CCS) in addressing climate change issues highlights the need for robust CO<sub>2</sub> leak monitoring systems. Limitations of conventional methods have prompted interest in alternative approaches, such as optical CO<sub>2</sub> sensors, which offer non-invasive and continuous monitoring. Here, we present a novel methodology for high-fidelity digital colorimetry to enhance CO<sub>2</sub> leak detection in soil, integrating machine learning algorithms with the ACES AP0 color space. Optical CO<sub>2</sub> sensors, utilizing a cresol red-based detection solution, were calibrated and validated in a controlled environment chamber designed to simulate CO<sub>2</sub> leakage. Digital images of the sensor's colorimetric response to varying CO<sub>2</sub> levels were analyzed in five color spaces. The ACES AP0 color space, renowned for its expansive color gamut and perceptual uniformity, exhibited optimal performance in discerning subtle color variations induced by changes in CO<sub>2</sub> concentration. Ten machine learning regression models were evaluated, and Multivariate Polynomial Regression (MPR) emerged as the most effective in converting ACES AP0 color data into precise CO<sub>2</sub> concentration estimates, achieving a Mean Absolute Percentage Error (MAPE) of 2.9 % and a Root Mean Square Error (RMSE) of 0.0731. Field validation at a carbon capture and storage (CCS) facility corroborated the robustness and accuracy of this method, showcasing its potential for real-world applications in CCS and environmental monitoring.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105268"},"PeriodicalIF":3.7,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-02DOI: 10.1016/j.chemolab.2024.105266
Rong Fan , Abdul Rauf , Manal Elzain Mohamed Abdalla , Arif Nazir , Muhammad Faisal , Adnan Aslam
Nonsteroidal Anti-Inflammatory Drugs (NSAIDs) are a class of medications that are used for different therapeutic uses. They effectively alleviate pain, reduce inflammation, and manage fever. These drugs are available in various forms. NSAIDs are prescribed by healthcare professionals to address a wide range of symptoms, from headaches and dental pain to conditions like arthritis and muscle stiffness. In this work, we use ve-degree-based reducible topological descriptors in quantitative structure-property relationship (QSPR) analysis to estimate the physicochemical properties of NSAIDs. In the first step, we have developed a MAPLE-based code to compute the reducible ve-degree-based topological descriptors of NSAIDs. Then, a linear regression model was used to estimate four physicochemical properties of seventy NSAIDs. It has been observed that two physicochemical properties, namely Molecular Weight and Complexity show a very strong correlation with the reducible ve-degree-based topological descriptors. For both cases, the value of correlation coefficient is greater than 0.9. Finally, quadratic and cubic regression models were constructed, and a comparative analysis with these models is presented. These results may help enhance the understanding of NSAIDs medication structures and aid in predicting their pharmacological activity.
非甾体抗炎药（NSAIDs）是一类用于不同治疗用途的药物。它们能有效缓解疼痛、减轻炎症和控制发烧。这类药物有多种剂型。医护人员会开非甾体抗炎药来治疗各种症状，从头痛和牙痛到关节炎和肌肉僵硬等疾病。在这项工作中，我们在定量结构-性质关系（QSPR）分析中使用了基于ve-degree的可还原拓扑描述符来估计非甾体抗炎药的理化性质。首先，我们开发了基于 MAPLE 的代码来计算非甾体抗炎药的可还原ve度拓扑描述符。然后，使用线性回归模型估计了 70 种非甾体抗炎药的四种理化性质。结果表明，分子量和复杂性这两种理化性质与基于还原ve-degree的拓扑描述符有很强的相关性。在这两种情况下，相关系数都大于 0.9。最后，构建了二次回归模型和三次回归模型，并对这些模型进行了比较分析。这些结果可能有助于加深对非甾体抗炎药药物结构的理解，并有助于预测其药理活性。
{"title":"Quantitative structure properties relationship (QSPR) analysis for physicochemical properties of nonsteroidal anti-inflammatory drugs (NSAIDs) usingVe degree-based reducible topological indices","authors":"Rong Fan , Abdul Rauf , Manal Elzain Mohamed Abdalla , Arif Nazir , Muhammad Faisal , Adnan Aslam","doi":"10.1016/j.chemolab.2024.105266","DOIUrl":"10.1016/j.chemolab.2024.105266","url":null,"abstract":"<div><div>Nonsteroidal Anti-Inflammatory Drugs (NSAIDs) are a class of medications that are used for different therapeutic uses. They effectively alleviate pain, reduce inflammation, and manage fever. These drugs are available in various forms. NSAIDs are prescribed by healthcare professionals to address a wide range of symptoms, from headaches and dental pain to conditions like arthritis and muscle stiffness. In this work, we use ve-degree-based reducible topological descriptors in quantitative structure-property relationship (QSPR) analysis to estimate the physicochemical properties of NSAIDs. In the first step, we have developed a MAPLE-based code to compute the reducible ve-degree-based topological descriptors of NSAIDs. Then, a linear regression model was used to estimate four physicochemical properties of seventy NSAIDs. It has been observed that two physicochemical properties, namely Molecular Weight and Complexity show a very strong correlation with the reducible ve-degree-based topological descriptors. For both cases, the value of correlation coefficient is greater than 0.9. Finally, quadratic and cubic regression models were constructed, and a comparative analysis with these models is presented. These results may help enhance the understanding of NSAIDs medication structures and aid in predicting their pharmacological activity.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105266"},"PeriodicalIF":3.7,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-30DOI: 10.1016/j.chemolab.2024.105252
Hugues Kouakou , José Henrique de Morais Goulart , Raffaele Vitale , Thomas Oberlin , David Rousseau , Cyril Ruckebusch , Nicolas Dobigeon
This work introduces an on-the-fly (i.e., online) linear spectral unmixing method which is able to sequentially analyze spectral data acquired on a spectrum-by-spectrum basis. After deriving a sequential counterpart of the conventional linear mixing model, the proposed approach recasts the linear unmixing problem into a linear state-space estimation framework. Under Gaussian noise and state models, the estimation of the pure spectra can be efficiently conducted by resorting to Kalman filtering. Interestingly, it is shown that this Kalman filter can operate in a lower-dimensional subspace to lighten the computational burden of the overall unmixing procedure. Experimental results obtained on synthetic and real Raman data sets show that this Kalman filter-based method offers a convenient trade-off between unmixing accuracy and computational efficiency, which is crucial for operating in an on-the-fly setting. The proposed method constitutes a valuable building block for benefiting from acquisition and processing frameworks recently proposed in the microscopy literature, which are motivated by practical issues such as reducing acquisition time and avoiding potential damages being inflicted to photosensitive samples. The code associated with the numerical illustrations reported in this paper is freely available online at https://github.com/HKouakou/KF-OSU.
{"title":"On-the-fly spectral unmixing based on Kalman filtering","authors":"Hugues Kouakou , José Henrique de Morais Goulart , Raffaele Vitale , Thomas Oberlin , David Rousseau , Cyril Ruckebusch , Nicolas Dobigeon","doi":"10.1016/j.chemolab.2024.105252","DOIUrl":"10.1016/j.chemolab.2024.105252","url":null,"abstract":"<div><div>This work introduces an on-the-fly (i.e., online) linear spectral unmixing method which is able to sequentially analyze spectral data acquired on a spectrum-by-spectrum basis. After deriving a sequential counterpart of the conventional linear mixing model, the proposed approach recasts the linear unmixing problem into a linear state-space estimation framework. Under Gaussian noise and state models, the estimation of the pure spectra can be efficiently conducted by resorting to Kalman filtering. Interestingly, it is shown that this Kalman filter can operate in a lower-dimensional subspace to lighten the computational burden of the overall unmixing procedure. Experimental results obtained on synthetic and real Raman data sets show that this Kalman filter-based method offers a convenient trade-off between unmixing accuracy and computational efficiency, which is crucial for operating in an on-the-fly setting. The proposed method constitutes a valuable building block for benefiting from acquisition and processing frameworks recently proposed in the microscopy literature, which are motivated by practical issues such as reducing acquisition time and avoiding potential damages being inflicted to photosensitive samples. The code associated with the numerical illustrations reported in this paper is freely available online at <span><span>https://github.com/HKouakou/KF-OSU</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105252"},"PeriodicalIF":3.7,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.chemolab.2024.105254
Francisco de Asis López , Javier Roca-Pardiñas , Celestino Ordóñez
Regression models for spatial data have attracted the attention of researchers from different fields given their widespread application. In this work we analyze the utility of generalized additive models (GAMs) as regression methods with spatially-dependent coefficients. Particularly, three different aspects of the regression analysis were addressed: model definition and estimation, testing spatial heterogeneity, and variable selection. Spatial heterogeneity was addressed through bootstrapping, while and algorithm using the Bayesian Information Criterion (BIC) was implemented for variable selection to reduce computation time. In addition, this study makes a comparison of GAMs with two of the most common methods for regression with spatially-varying coefficients: Geographically Weighted Regression (GWR) and Multiscale Geographically Weighted Regression (MGWR), using both synthetic and real data.
{"title":"Regression analysis with spatially-varying coefficients using generalized additive models (GAMs)","authors":"Francisco de Asis López , Javier Roca-Pardiñas , Celestino Ordóñez","doi":"10.1016/j.chemolab.2024.105254","DOIUrl":"10.1016/j.chemolab.2024.105254","url":null,"abstract":"<div><div>Regression models for spatial data have attracted the attention of researchers from different fields given their widespread application. In this work we analyze the utility of generalized additive models (GAMs) as regression methods with spatially-dependent coefficients. Particularly, three different aspects of the regression analysis were addressed: model definition and estimation, testing spatial heterogeneity, and variable selection. Spatial heterogeneity was addressed through bootstrapping, while and algorithm using the Bayesian Information Criterion (BIC) was implemented for variable selection to reduce computation time. In addition, this study makes a comparison of GAMs with two of the most common methods for regression with spatially-varying coefficients: Geographically Weighted Regression (GWR) and Multiscale Geographically Weighted Regression (MGWR), using both synthetic and real data.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105254"},"PeriodicalIF":3.7,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.chemolab.2024.105267
Maria Luiza de Godoy Bertanha, Felipe Rebello Lourenço
Pharmaceutical equivalence evaluation requires a multiparametric conformity assessment for both generic and reference medicines. This paper investigates the impact of metrological correlations on the total combined risk in pharmaceutical equivalence evaluations. The study focused on the equivalence between ranitidine hydrochloride tablets, assessed by determining the average weight, the assay of the active pharmaceutical ingredient, and the uniformity of dosage units. The risks of false conformity decisions were evaluated using Monte Carlo method simulations across four scenarios, each reflecting different correlation conditions. The results of the study focus on evaluating pharmaceutical equivalence between ranitidine hydrochloride tablets from two manufacturers. The tablets were tested for three parameters: average weight, active pharmaceutical ingredient (API) assay, and uniformity of dosage units. The measured values were within the regulatory specifications for both medicines A and B. Four scenarios of metrological correlation were assessed: #1 – actual correlation from shared analytical steps, #2 – correlation between parameters within the same medicine, #3 – correlation between generic and reference medicines, and #4 – uncorrelated parameters. The study revealed that correlations significantly affect total and combined risk values. The correlations between different parameters of the same medicine affect the total risk values, while the correlations between generic and reference medicines for a given parameter influence the combined particular risk values. Correlations between parameters of the same medicine affect total risk values, while correlations between generic and reference medicines impact combined particular risk values. Both types of correlations significantly influence combined total risk values, making metrological correlations crucial in pharmaceutical equivalence evaluations. Proper consideration of these correlations ensures the quality, efficacy, and safety of generic and reference medicines.
{"title":"Impact of metrological correlation on the total combined risk in pharmaceutical equivalence evaluations","authors":"Maria Luiza de Godoy Bertanha, Felipe Rebello Lourenço","doi":"10.1016/j.chemolab.2024.105267","DOIUrl":"10.1016/j.chemolab.2024.105267","url":null,"abstract":"<div><div>Pharmaceutical equivalence evaluation requires a multiparametric conformity assessment for both generic and reference medicines. This paper investigates the impact of metrological correlations on the total combined risk in pharmaceutical equivalence evaluations. The study focused on the equivalence between ranitidine hydrochloride tablets, assessed by determining the average weight, the assay of the active pharmaceutical ingredient, and the uniformity of dosage units. The risks of false conformity decisions were evaluated using Monte Carlo method simulations across four scenarios, each reflecting different correlation conditions. The results of the study focus on evaluating pharmaceutical equivalence between ranitidine hydrochloride tablets from two manufacturers. The tablets were tested for three parameters: average weight, active pharmaceutical ingredient (API) assay, and uniformity of dosage units. The measured values were within the regulatory specifications for both medicines A and B. Four scenarios of metrological correlation were assessed: #1 – actual correlation from shared analytical steps, #2 – correlation between parameters within the same medicine, #3 – correlation between generic and reference medicines, and #4 – uncorrelated parameters. The study revealed that correlations significantly affect total and combined risk values. The correlations between different parameters of the same medicine affect the total risk values, while the correlations between generic and reference medicines for a given parameter influence the combined particular risk values. Correlations between parameters of the same medicine affect total risk values, while correlations between generic and reference medicines impact combined particular risk values. Both types of correlations significantly influence combined total risk values, making metrological correlations crucial in pharmaceutical equivalence evaluations. Proper consideration of these correlations ensures the quality, efficacy, and safety of generic and reference medicines.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105267"},"PeriodicalIF":3.7,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soft-sensors are widely used in manufacturing processes to estimate key process variables; however, their performance may deteriorate when process characteristics change. Although Just-In-Time (JIT) modeling techniques have been proposed for adaptive soft-sensor design, they do not always adapt to abrupt changes. Transfer learning (TL) has been suggested as a means to address this issue, with Frustratingly Easy Domain Adaptation (FEDA) being used for soft-sensor design. This study proposes a new TL method called Latest Sample Targeting-FEDA (LST-FEDA) for JIT-based soft-sensor, which can handle both sudden and gradual changes in process characteristics. LST-FEDA updates soft-sensors using a fixed number of latest samples whenever a new sample is obtained. The effectiveness of the proposed method was demonstrated using simulation data from a vinyl acetate monomer (VAM) process and actual operation data from a fluorine-based monomer (FM) process. LST-FEDA accurately estimated objective variables during sudden malfunctions and scheduled maintenance, contributing to efficient and safe process operation.
{"title":"Adaptive soft-sensor update by Latest Sample Targeting Frustratingly Easy Domain Adaptation","authors":"Kaito Katayama , Kazuki Yamamoto , Koichi Fujiwara","doi":"10.1016/j.chemolab.2024.105246","DOIUrl":"10.1016/j.chemolab.2024.105246","url":null,"abstract":"<div><div>Soft-sensors are widely used in manufacturing processes to estimate key process variables; however, their performance may deteriorate when process characteristics change. Although Just-In-Time (JIT) modeling techniques have been proposed for adaptive soft-sensor design, they do not always adapt to abrupt changes. Transfer learning (TL) has been suggested as a means to address this issue, with Frustratingly Easy Domain Adaptation (FEDA) being used for soft-sensor design. This study proposes a new TL method called Latest Sample Targeting-FEDA (LST-FEDA) for JIT-based soft-sensor, which can handle both sudden and gradual changes in process characteristics. LST-FEDA updates soft-sensors using a fixed number of latest samples whenever a new sample is obtained. The effectiveness of the proposed method was demonstrated using simulation data from a vinyl acetate monomer (VAM) process and actual operation data from a fluorine-based monomer (FM) process. LST-FEDA accurately estimated objective variables during sudden malfunctions and scheduled maintenance, contributing to efficient and safe process operation.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105246"},"PeriodicalIF":3.7,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1016/j.chemolab.2024.105253
Nguyen-Xuan Hau , Nguyen-Thanh Tuan , Lai-Quang Trung, Tran-Thuy Chi
Accurate estimation of Soil Organic Carbon (SOC) is vital for assessing soil fertility, health, and carbon sequestration. Visible and Near-Infrared (Vis-NIR) spectroscopy has gained popularity worldwide for SOC estimation due to its cost-effectiveness and environmental benefits. However, inconsistencies arise from varying preprocessing techniques and regression models applied across different datasets and regions. Few studies explore combinations of spectral preprocessing, modeling algorithms, and resampling techniques. This study presents the first SOC estimation using Vis-NIR spectroscopy in the Red River Delta, Vietnam. We assessed estimation performances incorporating fifteen preprocessing techniques, four regression models, and three resampling methods to identify the most effective strategies. Standard Normal Variate (SNV) emerged as the top preprocessing technique, while Partial Least Squares Regression (PLSR) demonstrated the highest accuracy with minimal discrepancies between calibration and validation. Regarding resampling methods, repeated cross-validation (repeatedcv) proved most robust, with simple cross-validation as an alternative. By utilizing SNV, PLSR, and repeatedcv, we achieved the first successful Vis-NIR spectroscopy-based SOC estimation in the Red River Delta and Vietnam. This approach satisfied stringent statistical criteria for predictive models, yielding validation performance metrics of R2 = 0.740, RMSE = 0.166, RPD = 2.337, and RPIQ = 2.321. Our findings highlight the importance of optimizing preprocessing, regression, and resampling techniques for accurate Vis-NIR spectroscopy-based SOC prediction.
{"title":"Estimation of soil organic carbon content using visible and near-infrared spectroscopy in the Red River Delta, Vietnam","authors":"Nguyen-Xuan Hau , Nguyen-Thanh Tuan , Lai-Quang Trung, Tran-Thuy Chi","doi":"10.1016/j.chemolab.2024.105253","DOIUrl":"10.1016/j.chemolab.2024.105253","url":null,"abstract":"<div><div>Accurate estimation of Soil Organic Carbon (SOC) is vital for assessing soil fertility, health, and carbon sequestration. Visible and Near-Infrared (Vis-NIR) spectroscopy has gained popularity worldwide for SOC estimation due to its cost-effectiveness and environmental benefits. However, inconsistencies arise from varying preprocessing techniques and regression models applied across different datasets and regions. Few studies explore combinations of spectral preprocessing, modeling algorithms, and resampling techniques. This study presents the first SOC estimation using Vis-NIR spectroscopy in the Red River Delta, Vietnam. We assessed estimation performances incorporating fifteen preprocessing techniques, four regression models, and three resampling methods to identify the most effective strategies. Standard Normal Variate (SNV) emerged as the top preprocessing technique, while Partial Least Squares Regression (PLSR) demonstrated the highest accuracy with minimal discrepancies between calibration and validation. Regarding resampling methods, repeated cross-validation (repeatedcv) proved most robust, with simple cross-validation as an alternative. By utilizing SNV, PLSR, and repeatedcv, we achieved the first successful Vis-NIR spectroscopy-based SOC estimation in the Red River Delta and Vietnam. This approach satisfied stringent statistical criteria for predictive models, yielding validation performance metrics of R<sup>2</sup> = 0.740, RMSE = 0.166, RPD = 2.337, and RPIQ = 2.321. Our findings highlight the importance of optimizing preprocessing, regression, and resampling techniques for accurate Vis-NIR spectroscopy-based SOC prediction.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"255 ","pages":"Article 105253"},"PeriodicalIF":3.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142652926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号