Journal of Chemometrics最新文献_第4页

TCN–GRU With Multihead Attention (TCN–GRU–MATT) for Quantitative Regression of NO2 From SERS Spectra 基于多头关注的TCN-GRU （TCN-GRU - matt）对SERS光谱中NO2的定量回归

IF 2 4区化学

Journal of Chemometrics Pub Date : 2026-06-16 DOI: 10.1002/cem.70154

Nan Zou, Yaping Tian, Yuxuan Bai, Hanyue Zhong, Xintong Zhang, Yujia Chen, Shuang Zhao, Xinming Nie

{"title":"TCN–GRU With Multihead Attention (TCN–GRU–MATT) for Quantitative Regression of NO2 From SERS Spectra","authors":"Nan Zou, Yaping Tian, Yuxuan Bai, Hanyue Zhong, Xintong Zhang, Yujia Chen, Shuang Zhao, Xinming Nie","doi":"10.1002/cem.70154","DOIUrl":"https://doi.org/10.1002/cem.70154","url":null,"abstract":"<div>\u0000 \u0000 Accurate quantification of NO2 in construction machinery exhaust remains challenging because surface-enhanced Raman scattering (SERS) spectra are susceptible to fluorescence background, baseline drift, and random noise. In this study, an end-to-end hybrid deep learning model integrating a temporal convolutional network (TCN), a gated recurrent unit (GRU), and multihead attention mechanism (MATT) was developed for NO2 concentration prediction from SERS spectra. A dataset containing 7500 spectra at six concentration levels was established using the FL_ArraySERS sensing platform. The TCN module was used to extract local multiscale spectral features, the GRU module to capture sequential dependencies across spectral bands, and the attention module to enhance informative regions while suppressing irrelevant interference. Compared with TCN, GRU, and TCN–GRU models, the proposed TCN–GRU–MATT model achieved the best predictive performance, with MAE, RMSE, and R2 values of 0.5199, 0.8073, and 0.9996, respectively. Residual and spectral-band importance analyses further confirmed the robustness and interpretability of the proposed model. The results demonstrate that the proposed framework provides an effective strategy for quantitative analysis of NO2 in complex exhaust environments.\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148282185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of Dough Yield, Flour Type and Fermentation Time on Sourdough Near-Infrared Spectral Data With ANOVA–Simultaneous Component Analysis 面团产率、面粉种类和发酵时间对酵母近红外光谱数据的影响

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-06-12 DOI: 10.1002/cem.70153

Mari van Wyk, Federico Marini, Marena Manley

{"title":"Effect of Dough Yield, Flour Type and Fermentation Time on Sourdough Near-Infrared Spectral Data With ANOVA–Simultaneous Component Analysis","authors":"Mari van Wyk, Federico Marini, Marena Manley","doi":"10.1002/cem.70153","DOIUrl":"https://doi.org/10.1002/cem.70153","url":null,"abstract":"Near-infrared (NIR) spectroscopy combined with ANOVA–simultaneous component analysis (ASCA) provides a powerful approach for investigating sourdough fermentation. Two complementary longitudinal experiments (repeated four times) were conducted to evaluate the influence of key design factors on sourdough development over a 28-day refreshment period. Experiment 1 examined the effects of dough yield (DY, firm DY 150 and liquid DY 200) and fermentation time, whereas Experiment 2 evaluated the effects of flour type (coarse stone-milled, two sifted stone-milled or roller-milled) and fermentation time in firm and liquid sourdoughs. Prior to each refreshment (every fourth day), pH and total titratable acidity (TTA) were measured, and NIR spectra acquired. In Experiment 1 (64 samples), DY significantly (p ≤ 0.05) influenced pH but not TTA (p > 0.05). DY, fermentation time and their interaction significantly (p ≤ 0.05) influenced the spectral profiles. Liquid sourdoughs are associated with moisture, organic acids and starch-related spectral bands, whereas firm sourdoughs showed stronger amino acid and aromatic alcohol features. In Experiment 2 (256 samples), flour type and fermentation time significantly (p ≤ 0.05) affected pH, TTA and the spectral profiles, with refined flours producing more compositionally stable sourdoughs over time. In firm sourdough, all three factors were significant (p ≤ 0.05); in liquid sourdough, only flour type was significant, indicating greater temporal stability. Across both experiments, fermentation time contributed to progressive biochemical changes reflected in shifts from moisture-dominated to metabolite-associated spectral regions. These findings demonstrate the capability of ASCA to resolve complex multivariate effects in sourdough fermentation and highlight the importance of hydration and flour refinement in determining sourdough stability and biochemical evolution.","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.1,"publicationDate":"2026-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cem.70153","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148238273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From Design of Experiments to Analysis of Variance of Multivariate Data: A Tutorial Review on ANOVA Simultaneous Component Analysis 从实验设计到多变量数据的方差分析：ANOVA同时成分分析教程综述

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-06-12 DOI: 10.1002/cem.70151

José Camacho, Jokin Ezenarro, Daniel Schorn-García, Johan A. Westerhuis

引用次数: 0

High-Accuracy Classification of Peanut Origin via Feature-Level Fusion of Multimodal Spectroscopy 基于多模态光谱特征级融合的花生产地高精度分类

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-06-09 DOI: 10.1002/cem.70155

Wenlong Su, Limin Suo, Lili Qian, Zhaowei Wang

{"title":"High-Accuracy Classification of Peanut Origin via Feature-Level Fusion of Multimodal Spectroscopy","authors":"Wenlong Su, Limin Suo, Lili Qian, Zhaowei Wang","doi":"10.1002/cem.70155","DOIUrl":"https://doi.org/10.1002/cem.70155","url":null,"abstract":"<div>\u0000 \u0000 The geographical origin of peanuts directly determines their quality and market value. To overcome the destructive and time-consuming nature of conventional detection methods, this study proposes a novel nondestructive traceability strategy by integrating near-infrared (NIR) spectroscopy and low-field nuclear magnetic resonance (LF-NMR). Whole kernels of the peanut cultivar “LuhuaNo.9” were examined, from which NIR spectra reflecting chemical composition and LF-NMR signals characterizing moisture–lipid dynamics were simultaneously acquired. Two fusion strategies combined with several classifiers were evaluated: (1) low-level fusion, in which the original NIR and LF-NMR spectra were concatenated and modeled using support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), and a self-designed squeeze-and-excitation convolutional neural network (SE-CNN); (2) feature-level fusion, where informative spectral variables were selected using competitive adaptive reweighted sampling (CARS) to eliminate redundancy and noise. The results demonstrate that multisource data fusion substantially outperforms single-modality analysis, and the SE-CNN exhibits superior discriminatory ability compared with traditional machine learning models. In particular, the combination of CARS-based feature-level fusion and the SE-CNN achieved 100% classification accuracy on the test set, highlighting its outstanding performance. Overall, this work establishes a high-precision traceability strategy that integrates multidimensional spectral information with deep learning, markedly improving identification efficiency while preserving sample integrity. The proposed approach holds significant promise for the protection of geographical indications and quality monitoring of agricultural products.\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.1,"publicationDate":"2026-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148237696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Conceptual Differences Between Hyperspectral Unmixing, PCA, and Clustering: A Practical Demonstration Using Single-Cell Raman Imaging 高光谱解混、PCA和聚类之间的概念差异：使用单细胞拉曼成像的实际演示

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-06-02 DOI: 10.1002/cem.70152

Rustam R. Guliev, Ute Neugebauer

{"title":"Conceptual Differences Between Hyperspectral Unmixing, PCA, and Clustering: A Practical Demonstration Using Single-Cell Raman Imaging","authors":"Rustam R. Guliev, Ute Neugebauer","doi":"10.1002/cem.70152","DOIUrl":"https://doi.org/10.1002/cem.70152","url":null,"abstract":"Hyperspectral unmixing is a well-established approach for analyzing spectroscopic images by recovering chemically interpretable component spectra and their spatial distributions. Despite its distinct analytical objective, unmixing is frequently discussed alongside or directly compared with more familiar multivariate techniques such as principal component analysis (PCA) and clustering, which address fundamentally different questions. Although these conceptual distinctions have long been recognized in chemometrics and hyperspectral imaging, they are often treated implicitly and are not always demonstrated side by side in a single, accessible framework, particularly for nonexpert users of spectroscopic imaging methods. In this work, we provide a concise qualitative illustration of these established principles using a Raman spectroscopic image of a single eukaryotic cell. Employing classical implementations of PCA, k-means and fuzzy c-means clustering, and hyperspectral unmixing based on the N-FINDR end-member extraction algorithm, we show how unmixing yields chemically interpretable pure component spectra and abundance maps, whereas PCA and clustering produce complementary but fundamentally different types of outputs. This contribution serves as a practical reference, clarifying the principles of unmixing and supporting its proper application and communication in spectroscopic studies.","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.1,"publicationDate":"2026-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cem.70152","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148173686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Risk-Adjusted Robust Classification of Coagulation Potential in the Regeneration of Waste Lubricant Oil 废润滑油再生中凝血电位的风险校正鲁棒分类

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-06-01 DOI: 10.1002/cem.70150

Rúben Gariso, Tiago J. Rato, Margarida J. Quina, Marco S. Reis

{"title":"Risk-Adjusted Robust Classification of Coagulation Potential in the Regeneration of Waste Lubricant Oil","authors":"Rúben Gariso, Tiago J. Rato, Margarida J. Quina, Marco S. Reis","doi":"10.1002/cem.70150","DOIUrl":"https://doi.org/10.1002/cem.70150","url":null,"abstract":"<div>\u0000 \u0000 Despite their ubiquitous presence in scientific publications and media, the number of artificial intelligence and machine learning (AI/ML) systems installed and operating in industry is still incipient. Issues such as robustness, memory requirements, maintenance, and interpretability hinder their diffusion and wider adoption. In this article, we report a system developed to operate in the circular economy of lubricant oil that cleared all of these requirements and is now under supervised adoption in industry. We also share important refinement stages that were crucial for the ML algorithm to work properly and deliver the aimed aided-value for decision-making. More specifically, to expedite decision-making and mitigate safety risks, a robust classification method is proposed to predict the coagulation potential of waste lubricant oil (WLO), a hazardous waste according to the European legislation. The occurrence of the coagulation phenomena renders WLO regeneration into base oil production unfeasible. Leveraging on Fourier-transform infrared (FTIR) spectroscopy and ML, the proposed methodology comprises three key modules: feature extraction and validation of the model, robust classification using risk-adjusted rules, and soft validation of negative predictions. The original PAT-based ML classification model achieved only 70% accuracy, mostly due to misclassification of WLO that coagulates, which represents the highest risk for the process operation. In turn, the proposed methodology was able to reliably classify the WLO samples, showcasing its value for decision-making together with a significant reduction in laboratory workload.\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148173678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The FTIR-ATR Spectroscopy as a Biosensing Strategy for Thermal Effects in Permissibility Verification of Lard-Adulterated Palm Oil FTIR-ATR光谱作为生物传感策略在猪油掺假棕榈油允许度验证中的热效应

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-05-31 DOI: 10.1002/cem.70137

Muhammad Zulhelmi Nazri, Dayang Norulfairuz Abang Zaidel, Muhamad Shirwan Abdullah Sani, Hajar Aminah A. Karim, Siti Nor Azlina Abd Rashid, Anjar Windarsih

{"title":"The FTIR-ATR Spectroscopy as a Biosensing Strategy for Thermal Effects in Permissibility Verification of Lard-Adulterated Palm Oil","authors":"Muhammad Zulhelmi Nazri, Dayang Norulfairuz Abang Zaidel, Muhamad Shirwan Abdullah Sani, Hajar Aminah A. Karim, Siti Nor Azlina Abd Rashid, Anjar Windarsih","doi":"10.1002/cem.70137","DOIUrl":"https://doi.org/10.1002/cem.70137","url":null,"abstract":"<div>\u0000 \u0000 Ensuring authenticity of edible oils is vital for consumer trust, regulatory compliance and permissibility assurance, particularly for Muslim consumers. This study introduces a spectral biosensing strategy using Fourier transform infrared spectroscopy coupled with attenuated total reflectance (FTIR-ATR) and chemometric modelling to detect lard adulteration in palm oil (PO) under thermal stress. PO samples spiked with 1%–50% v/v lard were heated from 25°C to 200°C for 30 min, simulating industrial and culinary conditions. FTIR-ATR spectra showed distinct shifts in carbonyl and fingerprint regions due to lard incorporation and heat-induced lipid degradation. Discriminant analysis (DA) achieved 100% classification accuracy across the full spectrum (4000–650 cm−1), demonstrating strong discriminatory power. Partial least squares–discriminant analysis (PLS-DA) identified the fingerprint region (1000–650 cm−1) as most diagnostic, yielding robust performance with R2Y = 0.895, R2X = 1.000, Q2 = 0.893 and 100% correct classification in both training and validation datasets. Principal component analysis (PCA) revealed clear clustering of pure and adulterated samples, even under severe thermal conditions. Moreover, using the optimised FTIR-ATR/PLS model, the lard adulteration in thermally treated PO could be reliably detected at levels as low as 1% v/v with LOD and LOQ ranges of 0.01%–1.14% and 0.02%–3.34% v/v, respectively. These findings position FTIR-ATR with multivariate chemometrics as a rapid, nondestructive and thermally resilient platform for lard detection in PO. The approach extends to broader food quality and safety monitoring in real-world processing scenarios.\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 6","pages":""},"PeriodicalIF":2.1,"publicationDate":"2026-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148166913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-05-26

引用次数: 0

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-05-26

引用次数: 0

IF 2.1 4区化学

Journal of Chemometrics Pub Date : 2026-05-25

引用次数: 0