Journal of Chemometrics最新文献

{"title":"Temporal Chemometric Modelling of Result-Level Proficiency-Testing Risk in AQUACHECK Water-Chemistry Data","authors":"Selman Kander","doi":"10.1002/cem.70165","DOIUrl":"https://doi.org/10.1002/cem.70165","url":null,"abstract":"<div>\u0000 \u0000 <p>Recurrent proficiency-testing (PT) and external quality-assessment (EQA) records are temporally ordered, mixed-type and clustered chemical-laboratory data because the same laboratories reappear across rounds, analytes, matrices and methods. Using LGC AQUACHECK ‘Nutrients and other components’ core-water records, this study evaluated whether strictly prior PT information can support result-level risk ranking under temporal validation. The modelling cohort comprised 27,123 scored submissions from 18 rounds and 1293 laboratories. Two binary endpoints were analysed: problematic performance (|<i>z</i>| &gt; 2, where <i>z</i>-scores are standardized deviations from assigned values) and unsatisfactory performance (|<i>z</i>| ≥ 3). CatBoost (a gradient-boosted decision tree framework) was compared with a full feature-parity logistic-regression baseline, a supplementary numeric-subset generalized estimating equations (GEE) baseline and a numeric-subset partial least squares discriminant analysis (PLS-DA) comparator. CatBoost gave the highest discrimination, but its gain over logistic regression was modest: Test-set area under the receiver operating characteristic curve (ROC-AUC)/area under the precision-recall curve (PR-AUC) were 0.756/0.295 versus 0.723/0.252 for problematic performance and 0.758/0.221 versus 0.731/0.190 for unsatisfactory performance. Against no-skill precision-recall baselines equal to endpoint prevalence (0.115 and 0.080), CatBoost PR-AUC values corresponded to 2.57- and 2.76-fold enrichment, indicating modest but above-chance retrieval. Feature-block ablation showed that laboratory-specific history was the dominant signal source, whereas population-level analytical priors and static context were weaker. No configuration exceeded approximately ROC-AUC 0.76, indicating a bounded prediction ceiling under the available data. Isotonic calibration was essential for the unsatisfactory endpoint, reducing the Brier score from 0.172 to 0.068. Performance fell for laboratories absent from training, and one expanding-window fold collapsed to chance-level discrimination. Recurrent PT records therefore contain usable but bounded chemometric signal for within-scheme review prioritization, not standalone failure prediction or cross-scheme generalization without external validation, recalibration and prospective monitoring.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 8","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148615811","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}

{"title":"L-Probe: New Approach for Spike Removal in Raman Hyperspectral Imaging Based on Local Prominence Peak Filtering","authors":"Leonardo Francisco Rafael Lemes,&nbsp;Victor Klassen de Oliveira,&nbsp;Frederico Luis Felipe Soares","doi":"10.1002/cem.70164","DOIUrl":"https://doi.org/10.1002/cem.70164","url":null,"abstract":"<p>Raman hyperspectral imaging is an indispensable analytical technique that can provide simultaneous chemical and spatial information of a sample, enabling a higher comprehension and sampling of the analyzed material. However, a known challenge in processing large hyperspectral Raman datasets is the effective removal of spurious, high-intensity peaks caused by cosmic rays (<i>cosmic spikes</i>). Correcting cosmic spikes in complex hyperspectral images is particularly difficult due to the sheer volume of data, the inherent chemical heterogeneity of pixels, variations in background intensity, and the shape of authentic Raman bands. To address this, we propose a novel cosmic spike correction algorithm specifically engineered for Raman hyperspectral imaging. The L-probe algorithm employs the concept of local prominence for the reliable identification of suspicious peaks and spike removal based on the assumption of chemical composition homogeneity across adjacent pixels, allowing targeted and localized correction. The algorithm was rigorously evaluated using a factorial design of experiments (DoE) applied to an artificial hyperspectral image to establish its parameters. Final validation was successfully performed using real hyperspectral images acquired from complex, phase-separated samples, such as cosmetic emulsions, demonstrating the robustness of the algorithm.</p>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 8","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cem.70164","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148533583","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}

{"title":"Multimodal Interaction Enhanced Immersive Analytics: Enabling Accessible Virtual Reality Data Analysis for Blind and Visually Impaired Users","authors":"Rajiv Khadka,&nbsp;Rifat Ara Tasnim,&nbsp;Hyrum Redd,&nbsp;John Kalivas","doi":"10.1002/cem.70163","DOIUrl":"https://doi.org/10.1002/cem.70163","url":null,"abstract":"<div>\u0000 \u0000 <p>Virtual reality has become a powerful tool for analyzing complex chemical data, allowing researchers to make better decisions than automated algorithms alone. However, these systems rely almost entirely on vision, excluding blind users, some of whom demonstrate strong abilities in spatial reasoning and pattern recognition, though these abilities vary considerably across individuals. We developed a haptic-first VR system that makes immersive data analysis accessible to blind users through touch-based feedback via haptic gloves combined with spatial audio cues. The system translates visual data representations into tactile experiences where users can physically explore and manipulate data objects. We encoded hundreds of sample similarity measures into glyph features including vibration patterns, force feedback, and musical tones, enabling users to perform sophisticated analytical tasks like detecting outliers, identifying clusters, and classifying samples. Our pilot feasibility study with four blind university students explored a real chemical dataset with known structure, demonstrating that users could engage with and reason about chemometric data through haptic and audio modalities. Audio feedback proved consistently effective across all users, while haptic feedback varied in usefulness depending on the specific tactile channel and individual preferences. Navigation emerged as the main challenge, although participants demonstrated genuine analytical engagement and could articulate their decision-making process. This work provides proof-of-concept evidence and design insights indicating that complex chemical analysis can be explored through coordinated touch and sound, identifying navigation and calibration challenges that must be resolved before practical deployment.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467034","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}

{"title":"Dynamic Entropy-Guided Mixup for Data Augmentation in High-Dimensional Small-Sample Spectral Analysis: Application to Geographical Origin Classification of Euryales Semen","authors":"Can Zhou,&nbsp;Daixin Yu,&nbsp;Wenyan Hu,&nbsp;Lu Cui,&nbsp;Jiabin Zheng,&nbsp;Yi Li,&nbsp;Kongfa Hu,&nbsp;Caiyan Dai,&nbsp;Cheng Qu,&nbsp;Youwei Ding","doi":"10.1002/cem.70162","DOIUrl":"https://doi.org/10.1002/cem.70162","url":null,"abstract":"<div>\u0000 \u0000 <p>Near-infrared spectroscopy (NIRS) is a non-destructive analytical technique. It measures absorption signals generated by overtone and combination vibrations of chemical bonds in hydrogen-containing functional groups. Owing to its rapid and efficient analytical capability, NIRS has been widely used for quality evaluation of agricultural products and traditional Chinese medicinal materials. However, NIRS is often limited by weak absorption intensity and severe spectral band overlap. NIRS data are usually high-dimensional, highly collinear, and information-redundant. These features increase the difficulty of model development and may reduce analytical accuracy. This study developed a dynamic entropy-guided Mixup data augmentation method to enhance feature representation and improve classification accuracy in small-sample near-infrared spectral analysis. The proposed method was further applied to the geographical origin identification of Euryales Semen (ES, <i>Euryale ferox</i> Salisb.). Information entropy was used to quantify sample uncertainty and identify high-uncertainty samples near classification boundaries. Based on these samples, a targeted Mixup data augmentation strategy was developed and combined with deep learning classifiers to improve the learning capacity and generalization performance of models for small-sample spectral data. The results demonstrate that the overall performance of three deep learning models, namely multilayer perceptron (MLP), one-dimensional convolutional neural network (1D-CNN), and long short-term memory (LSTM), was improved to varying degrees after applying data augmentation strategies for the geographical origin classification of ES. Among them, the proposed dynamic entropy-guided Mixup (DEG-Mixup) method achieved the best performance, with test accuracies of 86.8%, 83.27%, and 83.24% for MLP, 1D-CNN, and LSTM, respectively. Compared with models without augmentation, the accuracies were improved by 10.26%, 10.88%, and 12.47%, respectively. Compared with conventional Mixup, the improvements were 7.20%, 7.79%, and 8.46%, respectively. These results indicate that DEG-Mixup effectively enhances the discriminative ability and generalization performance of models for small-sample spectral data, enabling accurate geographical origin identification of ES. This study established a rapid, effective, and reliable near-infrared spectral classification strategy based on entropy-guided data augmentation. The proposed strategy provides a new methodological reference for the geographical origin identification and quality evaluation of traditional Chinese medicinal materials under small-sample conditions, and shows promising potential for broader spectral analysis tasks.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462735","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}

{"title":"Partial Least Squares Regression Models for Outdoor Air Pollutant Forecasting","authors":"Beatriz Galindo-Prieto,&nbsp;Alexandra Papanicolaou,&nbsp;Ian S. Mudway","doi":"10.1002/cem.70156","DOIUrl":"https://doi.org/10.1002/cem.70156","url":null,"abstract":"<p>Atmospheric pollution presents a significant global health burden, yet the establishment and maintenance of extensive ‘gold standard’ monitoring networks remain prohibitively expensive. We explore the potential of machine learning to create virtual monitoring sites for predicting and reconstructing urban air pollutant concentrations, offering a cost-effective alternative. Partial least squares (PLS) and support vector regression (SVR) models were developed and validated for daily concentrations of nitrogen dioxide (NO₂) and particulate matter (PM_2.5 and PM₁₀) within a well-monitored central London area. Our methodology involved comprehensive data pre-processing, including normalization, and rigorous model validation using RMSE, MSE, MAE, bias and <i>R</i>² metrics. A key finding was the superior predictive performance of PLS models incorporating meteorological data alongside pollutant concentrations, compared to models including land-use data. Specifically, these PLS models exhibited lower error metrics across all pollutants, with NO₂ and PM_2.5 predictions showing <i>R</i>² = 0.891 and <i>R</i>² = 0.688, respectively, in the transformed space. Upon back-transformation to original units (μg/m³), the PLS models maintained high performance, particularly for PM_2.5 (RMSEP = 2.261, <i>R</i>² = 0.796). Whereas SVR models occasionally showed slightly higher <i>R</i>² values in the transformed space, their error metrics were consistently larger than those of PLS models, especially for PM_2.5. This research underscores the effectiveness of PLS for accurate urban air pollutant prediction and highlights the critical influence of meteorological data over land-use data in densely built-up areas. The <i>Air-01 London dataset</i>, a compilation of air pollutant, meteorological and land-use data created for this study, has been made openly available to facilitate further research.</p>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/cem.70156","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148462984","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}

{"title":"Multirate Variational Bayesian Decomposed State Space Model for Fault Detection in Multirate Processes","authors":"Ilia Bychkov,&nbsp;Yuting Lyu","doi":"10.1002/cem.70161","DOIUrl":"https://doi.org/10.1002/cem.70161","url":null,"abstract":"<div>\u0000 \u0000 <p>Effective fault detection is essential for modern industry to mitigate equipment damage and safety risks. Due to heterogeneous sampling requirements and practical technical limitations, conventional single-rate fault detection methods encounter significant performance bottlenecks in practical multirate processes. Furthermore, industrial processes are inherently dynamic, requiring the extraction of both auto-correlations and cross-correlations within the data. To tackle these issues, this paper proposes a novel multirate variational bayesian decomposed state space model (Mr-VBDSSM). It decomposes the latent state into global and sampling-rate-specific local components. The former characterize broad system-wide dynamics, while the latter capture individual fluctuations within specific subsystems. Additionally, local static factors are also designed for each sampling rate to capture steady-state characteristics. Finally, the effectiveness of the proposed method is verified using the Tennessee Eastman benchmark and a real-world wastewater treatment process.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148386649","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}

{"title":"Semi-Supervised Gaussian Mixture Regression With Gaussian Mixture Model Pretraining With Unlabeled Data","authors":"Hiromasa Kaneko","doi":"10.1002/cem.70160","DOIUrl":"https://doi.org/10.1002/cem.70160","url":null,"abstract":"<div>\u0000 \u0000 <p>Gaussian mixture regression (GMR) is a useful framework for both forward prediction and direct inverse analysis because it models the joint probability distribution of input variables x and output variables y. However, when full covariance matrices are used, the number of fitting parameters increases rapidly with dimensionality, making estimation unstable when only a limited number of paired (x, y) samples are available. In this study, two semi-supervised extensions of GMR are proposed to exploit abundant unlabeled x data. The first method, semi-supervised GMR with x-only GMM pretraining (ssGMR-xGMM), builds a Gaussian mixture model (GMM) using only x samples and uses the obtained parameters to initialize the joint GMM for GMR. The second method, semi-supervised GMR with x-only GMM pretraining and x-mean anchoring (ssGMR-xGMM-xMA), further fixes the x-side mean vectors during training to preserve the mixture structure learned from unlabeled x data. The proposed methods were evaluated using numerical simulation data and real molecular and spectral datasets, including boiling point, aqueous solubility, pharmacological activity, environmental toxicity, and tablet spectral datasets. Compared with conventional GMR, both proposed methods improved predictive performance, and ssGMR-xGMM-xMA showed the best overall performance. Under the transductive semi-supervised setting examined in this study, these results indicate that leveraging unlabeled x data can be effective for stabilizing parameter estimation and improving GMR accuracy in data-scarce settings.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148325043","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}

{"title":"Study of the Relationship Between Peptide Sequences and Antioxidant Activity Based on Logic Gates and Huffman Coding","authors":"Xiaowei Zhu,&nbsp;Yan Wang,&nbsp;Zhanchao Li","doi":"10.1002/cem.70159","DOIUrl":"https://doi.org/10.1002/cem.70159","url":null,"abstract":"<div>\u0000 \u0000 <p>Accurate identification of antioxidant peptides is crucial for the fields of drug discovery and functional food development. Nevertheless, the effective numerical representation of their variable-length sequences remains challenging. To address this issue, a novel feature-engineering framework is proposed, which is based on logic gates and Huffman coding. The development of two novel descriptors was initiated through the utilization of these methodologies. Subsequently, a robust composite descriptor was formulated by integrating these with classical one-hot encoding. Predictive models constructed on this combined descriptor demonstrated excellent performance in identifying antioxidant peptides. A comparative analysis was conducted, which demonstrated the method's superior accuracy and significant performance enhancement over existing mainstream sequence characterization methods. These results validate the proposed framework as an effective and interpretable approach for deciphering the relationship between peptide sequences and their antioxidant activity.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148325042","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}

{"title":"Adaptive Interval Selection for Near-Infrared Spectra via Fused Lasso and Backward Interval PLS","authors":"Tongyuan Bai,&nbsp;Xiaoling Peng,&nbsp;Baojun Xu,&nbsp;Ping He","doi":"10.1002/cem.70157","DOIUrl":"https://doi.org/10.1002/cem.70157","url":null,"abstract":"&lt;div&gt;\u0000 \u0000 &lt;p&gt;Near-infrared (NIR) spectra exhibit strong local collinearity and smooth absorption patterns, requiring variable selection to mitigate overfitting in multivariate calibration. Point-wise methods yield scattered subsets that do not account for spectral ordering, whereas fixed-window approaches lack the adaptability to capture the varying widths of physical absorption bands. To address these limitations, we propose Fused-BiPLS, a two-stage wavelength-interval selection framework that decouples spectral segmentation from predictive coefficient estimation. First, a fused lasso penalty is applied to adjacent coefficient differences and is solved along its exact solution path. Guided by Mallows' &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;C&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;p&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {C}_p $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; criterion, this yields a piecewise-constant coefficient profile that forms data-driven, contiguous segments, replacing manually defined interval widths. Second, backward interval partial least squares (BiPLS) identifies a subset of these intervals without further &lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;msub&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;ℓ&lt;/mi&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mn&gt;1&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;/msub&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ {ell}_1 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt; shrinkage. Evaluated across six benchmark NIR datasets spanning agricultural, petrochemical, biological, and pharmaceutical materials, Fused-BiPLS achieved prediction errors comparable to or lower than those of established chemometric models. The method yielded medium to large positive effect sizes (&lt;span&gt;&lt;/span&gt;&lt;math&gt;\u0000 &lt;semantics&gt;\u0000 &lt;mrow&gt;\u0000 &lt;mi&gt;d&lt;/mi&gt;\u0000 &lt;mo&gt;≥&lt;/mo&gt;\u0000 &lt;mn&gt;0&lt;/mn&gt;\u0000 &lt;mo&gt;.&lt;/mo&gt;\u0000 &lt;mn&gt;5&lt;/mn&gt;\u0000 &lt;/mrow&gt;\u0000 &lt;annotation&gt;$$ dge 0.5 $$&lt;/annotation&gt;\u0000 &lt;/semantics&gt;&lt;/math&gt;) against most baselines on the Diesel, Soil, and Meat datasets. The adaptive segmentation isolated contiguous blocks corresponding to known molecular overtones, demonstrating stability across sampling variations. Although the exact solution path incurs a higher off-line calibration cost, the resulting interval-based models are computationally efficient during inference. Because the selected contiguous intervals align directly with the bandwidth specifications of optical filters, the framework supports the configuration of compact, portable NIR devices.&lt;/p&gt;\u0000 ","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324573","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}

{"title":"A Novel 2D-CNN Model Integrating 2D-Transformed NIR Spectra and Attention Mechanism With Transfer Learning: A Case in SSC Prediction of Pears","authors":"Zhangwei Fan,&nbsp;Anyi Zhao,&nbsp;Jianyi Zhang,&nbsp;Xiaping Fu","doi":"10.1002/cem.70158","DOIUrl":"https://doi.org/10.1002/cem.70158","url":null,"abstract":"<div>\u0000 \u0000 <p>Near-infrared (NIR) spectroscopy technology has been widely used in agriculture, food, pharmaceuticals, petrochemical, and other fields due to its advantages of high efficiency and nondestructiveness. However, it still faces challenges such as data distribution shifts caused by factors like different spectrometers and spectral acquisition environments. In this study, we propose a GASp2DCNN model that integrates the Gramian Angular Summation Field (GASF) and the adaptive star block (ASB) to address the performance degradation of models when spectrometers or environments change. Firstly, the spectrum is transformed to two-dimensional data after piecewise aggregation approximation (PAA), polar coordinate transformation, and GASF to capture correlation features with 2D convolution. Then, an ASB module integrating star operation and channel attention mechanism is designed to enhance the model's ability to capture spectral local correlations. Finally, a feature-vector based transfer learning (FBTL) method is proposed, which dynamically weights the feature vectors of the source and target domains through an attention mechanism to enhance cross-domain adaptation. The results on a pear dataset indicate that the GASp2DCNN improves <i>R</i>² by 5.2% to 24.4% compared to machine learning models (PLSR, SVR) and 1D-CNN models. In transfer learning experiments, the proposed FBTL method improved <i>R</i>² by 4% to 12% compared to global fine-tuning and head-freezing fine-tuning methods and outperformed domain-adversarial neural networks (DANN) and maximum classifier discrepancy (MCD) by 4% to 9% across all transfer scenarios. Stable transfer effects are achieved when the target domain sample size reaches 40% of the total, reducing reliance on target samples. This also provides an interpretable and highly robust solution for fruit quality detection.</p>\u0000 </div>","PeriodicalId":15274,"journal":{"name":"Journal of Chemometrics","volume":"40 7","pages":""},"PeriodicalIF":2.0,"publicationDate":"2026-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148274758","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}