Zhiyi Ji, Chunhua Yang, Jingxiu He, Yonggang Li, Dong Li
{"title":"Deep matrix factorization considering dynamic constraints to complete missing data of complex industrial processes","authors":"Zhiyi Ji, Chunhua Yang, Jingxiu He, Yonggang Li, Dong Li","doi":"10.1016/j.chemolab.2025.105433","DOIUrl":"10.1016/j.chemolab.2025.105433","url":null,"abstract":"<div><div>In the complex industrial processes, data loss is an unavoidable issue. Due to the lengthy process flow and complex reaction mechanisms, traditional data completion methods fail to deliver satisfactory results when data loss occurs. To address this challenge, this paper proposes deep matrix factorization considering dynamic constraints (DMFDC). This algorithm combines traditional matrix factorization with artificial neural networks, leveraging the strengths of neural networks to approximate nonlinear mappings in latent variable models and utilizing all available information to minimize discrepancies between raw and generated data. Additionally, DMFDC accounts for the dynamic characteristics of the complex industrial system, employing differential operations to transform irregularly changing industrial data into a more stable sequence, thereby enabling the model to better capture data evolution patterns. This approach allows DMFDC to intelligently address the issue of missing dynamic data in the complex industrial process and to predict missing values more accurately. To evaluate its effectiveness, we conducted case studies under various missing data conditions based on a digestion dataset collected from actual alumina production sites. The results indicate that DMFDC achieves higher data completion accuracy than other methods, confirming the applicability of our approach in diverse situations involving missing data.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105433"},"PeriodicalIF":3.7,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144131160","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}
Peng Shan , Ruige Yang , Teng Liang , Lin Zhang , Yuliang Zhao , Zhonghai He , Silong Peng
{"title":"An unsupervised domain adaptation regression method in kernel partial least squares subspace embedded with joint statistical and manifold alignment for Fourier-transform infrared spectroscopy in agri-food analysis","authors":"Peng Shan , Ruige Yang , Teng Liang , Lin Zhang , Yuliang Zhao , Zhonghai He , Silong Peng","doi":"10.1016/j.chemolab.2025.105442","DOIUrl":"10.1016/j.chemolab.2025.105442","url":null,"abstract":"<div><div>Within the agri-food sector, the precise measurement of essential ingredients in samples across different measurement contexts using Fourier Transform Infrared spectroscopy (FTIR) is crucial, underscoring the need for advanced calibration methods with extensive generalizability. Domain adaptation (DA) in machine learning is a pivotal area of research focused on training models to be adaptable to both source and target domains with differing data distributions. This paper delves into the application of unsupervised domain adaptation (UDA) for FTIR analysis in agri-food products, utilizing unlabeled data from the target domain to address the challenge of limited reference samples. To realize complex nonlinear adaptation, combining the advantages of statistical alignment and nonlinear ability from domain-invariant iterative partial least squares (DIPALS) and kernel domain adaptive partial least squares (da-PLS) respectively, a novel UDA regression method in kernel partial least squares subspace embedded with joint statistical and manifold alignment (JSMKPLS) is present by further integrating a manifold alignment strategy that could incorporate geometric nonlinear structure into the adaptation process. The framework simultaneously exploits the statistical and geometrical properties in reproducing kernel Hilbert space (RKHS) and extract the domain invariant features. Experimental results of corn, rice, γ-PGA fermentation and wheat datasets confirm the effectiveness of JSMKPLS for FTIR analysis.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105442"},"PeriodicalIF":3.7,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178170","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}
Alireza Aghili , Amir Hossein Haghighi , Amir Hossein Shabani
{"title":"Confidence interval on the kinetic parameters of simple condensed phase reactions","authors":"Alireza Aghili , Amir Hossein Haghighi , Amir Hossein Shabani","doi":"10.1016/j.chemolab.2025.105434","DOIUrl":"10.1016/j.chemolab.2025.105434","url":null,"abstract":"<div><div>Confidence intervals play a crucial role in statistical inference, as they provide a range of values within which a population parameter is likely to fall, thereby enabling researchers to quantify the uncertainty associated with their estimates. This study proposes a new approach for estimating the confidence intervals on kinetic parameters of simple condensed phase reactions using a combined kinetic analysis and multiple linear regression. The conversion function may be represented in the form of truncated Šesták-Berggren (TSB), Šesták-Berggren (SB), or discrete cosine transform (DCT) models. The confidence intervals are calculated for pre-exponential factor, activation energy, and reaction exponents directly from multiple linear regression. However, for rate constant and conversion function, we need to estimate the variance of these parameters using the delta method. The proposed method was applied to the kinetic data from a simulated reaction as well as those of thermal decomposition of a commercial poly(methyl methacrylate). The results revealed that the DCT model provides highly accurate estimates with extremely narrow confidence intervals for kinetic parameters of the simulated reaction, whereas the TSB and SB models may exhibit systematic errors. The research also includes GNU Octave/MATLAB codes enabling readers to generate smooth reaction rate curves from noisy experimental data using the Fourier cosine series expansion and discrete cosine transform, approximate conversion functions with TSB, SB, and DCT models, and determine kinetic parameters and their confidence intervals for simple reactions through the new combined kinetic analysis methods.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105434"},"PeriodicalIF":3.7,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144134452","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}
{"title":"Pattern modeling and fault detection based on dynamic controlled autoencoder","authors":"Wei Guo, Xiaoli Luan, Fei Liu","doi":"10.1016/j.chemolab.2025.105422","DOIUrl":"10.1016/j.chemolab.2025.105422","url":null,"abstract":"<div><div>Industrial processes often exhibit significant nonlinear and dynamic characteristics. To effectively monitor these processes, this paper proposes a dynamic controlled autoencoder (DCAE) model for pattern extraction, which primarily consists of an autoencoder and dynamic mapping components. It is capable of simultaneously extracting the nonlinear structural relationships of process variables in static space and their nonlinear dynamics in the time domain, and in particular, establishing the dynamic causality between control input and pattern. The dynamic controlled pattern extracted using DCAE can sufficiently represent the operation information of the nonlinear process. Then, the relationships between DCAE modeling errors and model variables are explored, leading to the construction of error statistics for monitoring industrial processes and the development of a DCAE-based fault detection scheme. Finally, the case study of an industrial boiler combustion system illustrates the effectiveness and superiority of the DCAE model in extracting the pattern of industrial processes and performing fault detection.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105422"},"PeriodicalIF":3.7,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144194544","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}
Tomasz Urbańczyk , Jakub Bożek , Szymon Mirczak , Jarosław Koperski , Marek Krośnicki
{"title":"Kolmogorov–Arnold neural network for identification of functional groups from FTIR spectra","authors":"Tomasz Urbańczyk , Jakub Bożek , Szymon Mirczak , Jarosław Koperski , Marek Krośnicki","doi":"10.1016/j.chemolab.2025.105421","DOIUrl":"10.1016/j.chemolab.2025.105421","url":null,"abstract":"<div><div>New architecture of a deep neural network for identification of functional groups of molecules based on FTIR spectra is presented. The architecture employs the innovative Kolmogorov–Arnold layers. Instead of a single weight, each input in neurons belonging to these layers, possesses an independent learnable activation function. The article analyzes the quality of the neural network prediction for convolutional network containing Kolmogorov–Arnold layers in comparison with a classic convolutional neural network for 22 functional groups. The obtained results are compared with the results available from other studies.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105421"},"PeriodicalIF":3.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106504","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}
{"title":"Leveraging PLS and Lasso in MARS for high-dimensional FTIR data: A hybrid proposed model for antidiabetic activity of schiff base compounds","authors":"Sughra Sarwar, Tahir Mehmood, Muhammad Arfan","doi":"10.1016/j.chemolab.2025.105418","DOIUrl":"10.1016/j.chemolab.2025.105418","url":null,"abstract":"<div><div>In this study, we utilized Fourier Transform Infrared (FTIR) spectral data to create and analyze multiple regression models to predict the anti-diabetic potential of synthesized Schiff bases. Schiff bases are a wide range of compounds characterized by a double bond between the nitrogen and carbon atoms. Their versatility stems from various strategies by which these can be coupled with multiple alkyl or aryl substitutes. The models that were examined consisted of MARS, PLS, SPLS, KPLS, MARS-SPLS, MARS-Kernel-PLS, and an innovative method called MARS-PLS-Lasso, which combines the traditional MARS algorithm with partial least squares and Lasso regularization. To assess the efficacy of the proposed method, we used a high-dimensional spectral data set comprising 19 samples and 1627 predictors. To capture nonlinear interactions in the data, MARS-PLS-Lasso improves the conventional MARS approach by creating adaptive basis functions for each predictor. Lasso regularization was used to choose the most pertinent basis functions and make sure that only the most important predictors were kept. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were used on train and test datasets to evaluate the prediction performance. The MARS-PLS-Lasso model outperformed the typical MARS (RMSE = 30.48, MAE = 23.46) and PLS (RMSE = 14.00, MAE = 11.90) models by achieving the lowest test RMSE of 13.00 and MAE of 10.55. When we performed simulation study, MARS-PLS-LASSO again performed the best among basis-integrated models in terms of both low and high correlated data, with the lowest RMSE (0.4708) and MAE (0.2812) in case of data with dimensions 20, 50 and RMSE (0.685, 0.4806) and MAE (0.1325, 0.3819) using data with dimensions 20, 5000 respectively. These results show that the best way to model complicated relationships in high-dimensional data is to use MARS-PLS-Lasso to improve predictive accuracy.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105418"},"PeriodicalIF":3.7,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071931","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}
{"title":"A novel three-dimensional strategy to elucidate the interactions of two fluoroquinolones with DNA using two-dimensional fluorescence maps","authors":"Erdal Dinç , Asiye Üçer","doi":"10.1016/j.chemolab.2025.105437","DOIUrl":"10.1016/j.chemolab.2025.105437","url":null,"abstract":"<div><div>A novel three-dimensional strategy was introduced to elucidate the interactions of two fluoroquinolones, ciprofloxacin (CIP) and norfloxacin (NOR), with DNA using two-dimensional fluorescence maps (fluorescence excitation and emission measurements). This chemometric strategy is based on decomposing fluorescence excitation-emission matrices to extract detailed excitation, emission, and concentration profiles. By recording the fluorescence spectra after the reactions of CIP and NOR with calf thymus DNA and applying parallel factor analysis (PARAFAC) to the resulting data array, the quantitative estimations of the excitation and emission curves and the relative concentrations of the drugs and their DNA complexes were achieved. This investigation revealed the intricate interactions between CIP and DNA and NOR and DNA, characterized by Stern-Volmer constants (K<sub>sv</sub>) and quenching rate constants (K<sub>q</sub>). These constants related to the drug-DNA reaction equilibrium were derived from the correlation between actual DNA concentrations and the estimated relative amounts of CIP and NOR. The binding constants obtained through our innovative three-dimensional strategy were rigorously compared with those determined by classic spectrophotometric and spectrofluorometric methods, highlighting the efficacy and accuracy of our proposed approach.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105437"},"PeriodicalIF":3.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144083993","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}
Jingyun Huang , Geng Leng , Siyu Liu , Zeyuan Zhang , Hongbo Zhang , Xiangchao Fu , Yuewu Wang , Zhenwei Xie , Junwei Wang
{"title":"Multiscale transfer learning improves soil calcium carbonate equivalent measurement in data-limited regions using Vis-NIR spectroscopy","authors":"Jingyun Huang , Geng Leng , Siyu Liu , Zeyuan Zhang , Hongbo Zhang , Xiangchao Fu , Yuewu Wang , Zhenwei Xie , Junwei Wang","doi":"10.1016/j.chemolab.2025.105436","DOIUrl":"10.1016/j.chemolab.2025.105436","url":null,"abstract":"<div><div>Accurate measurement of soil calcium carbonate equivalent (CCE) is essential for agricultural management and carbon cycle assessments. While Vis-NIR offers a rapid and non-invasive alternative to traditional labor-intensive chemical method, its effectiveness is often constrained by regional variability and the scarcity of local datasets, limiting its applicability in data-scarce regions. Here, we introduce an innovative methodology that leverages large-scale soil spectral datasets and applies transfer learning via transfer component analysis (TCA) to enhance Vis-NIR model performance for measuring cropland soil CCE in data-scarce regions. Our TCA-based transfer models significantly outperformed locally constructed models, achieving an R<sup>2</sup> of 0.893, RMSE of 19.569, and RPD of 3.17, representing a 64.52 % improvement in accuracy. Remarkably, the proposed transfer learning strategies showcased consistent improvements even with minimal local data (R<sup>2</sup> = 0.852 and RMSE = 23.077 when only 30 local samples were available), highlighting their robustness and scalability. These findings demonstrate that the integration of transfer learning with Vis-NIR offers a reliable solution for soil CCE measurement in regions lacking sufficient local data, advancing the broader application of spectral analysis in soil science and contributing to more effective agricultural practices.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105436"},"PeriodicalIF":3.7,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932014","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}
Lei Li , Xulong Fu , Juan Qin, Lianrong Lv, Mengdan Cheng, Biao Wang, Junjie He, Dan Xia, Meng Wang, Haiping Ren, Shike Wang
{"title":"MIAUnet++: Multi-inception attention network for MR spine image segmentation","authors":"Lei Li , Xulong Fu , Juan Qin, Lianrong Lv, Mengdan Cheng, Biao Wang, Junjie He, Dan Xia, Meng Wang, Haiping Ren, Shike Wang","doi":"10.1016/j.chemolab.2025.105425","DOIUrl":"10.1016/j.chemolab.2025.105425","url":null,"abstract":"<div><div>Accurate segmentation of MR spine images is of great important for the evaluation of spinal diseases. With its unique encoder-decoder symmetric architecture and jump connection design, Unet has become a benchmark model in medical image segmentation since its proposal in 2015. However, the traditional Unet encoder-decoder structure suffers from the problem of semantic information loss during deep feature extraction, and the single-hop connection method is difficult to effectively fuse multi-scale features, resulting in limited segmentation accuracy for complex structures. Responding to these challenges, this study proposes a multi-Inception attention Unet++ (MIAUnet++) model. The model uses different Inception modules to replace the standard convolutional layers of the Unet++, which significantly enhances the multi-scale feature extraction capability by extending the network width and depth. At the same time, multiple attention mechanisms are introduced to further enhance the sensitivity of the network to the boundary information, so that the model can more accurately capture the subtle anatomical structural differences between spine-soft tissues, thus improving the segmentation performance of the network. The experimental results show that the proposed model performs well in the spine image segmentation task with IoU, DSC, TPR and PPV reaching 0.8327, 0.9041, 0.9060 and 0.9068 respectively, outperforming the benchmark method in all metrics. It shows that the proposed method has good performance in MR Spine image segmentation.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105425"},"PeriodicalIF":3.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943438","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}
{"title":"Kernel-based reliability potential to assist QSPR prediction and system transfer of SFC−MS retention time","authors":"Viviana Consonni , Cristian Rojas , Jessica Guerrero , Mateo Mendoza , Veronica Termopoli , Davide Ballabio","doi":"10.1016/j.chemolab.2025.105435","DOIUrl":"10.1016/j.chemolab.2025.105435","url":null,"abstract":"<div><div>Quantitative Structure-Property Relationship (QSPR) allows <em>in silico</em> prediction of chromatographic retention time of chemicals from their molecular structure. The QSPR approach relies on the principle that retention time is influenced by molecular properties, which can be encoded into chemical-structural descriptors and modelled with chemometric techniques. This study focuses on <em>in silico</em> prediction of supercritical fluid chromatography (SFC) retention time. First, we developed a novel QSPR model for predicting retention times measured with high-resolution mass spectrometry (SFC-HRMS); then, the same model was adapted to predict retention times of a different chromatographic system based on low-resolution mass spectrometry (SFC-LRMS). We used a kernel-based approach to account for prediction uncertainties and to leverage the model reliability by defining a structural domain in the chemical space where lower uncertainty is expected. Results demonstrated that the proposed approach can predict retention time across two chromatographic systems when considering the reliability domain established with the kernel approach. The use of the proposed method for estimating the reliability domain can enhance the application of QSPR models to predict and transfer retention times in chromatographic systems similar to those used for the calibration and, consequently, simplify the identification of compounds in untargeted analyses and boost the design, development and optimization of novel chromatographic methods.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"263 ","pages":"Article 105435"},"PeriodicalIF":3.7,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143936288","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}