Chemometrics and Intelligent Laboratory Systems最新文献

{"title":"Classification of maize leaf diseases with deep learning: Performance evaluation of the proposed model and use of explicable artificial intelligence","authors":"Feyyaz Alpsalaz ,&nbsp;Yıldırım Özüpak ,&nbsp;Emrah Aslan ,&nbsp;Hasan Uzel","doi":"10.1016/j.chemolab.2025.105412","DOIUrl":"10.1016/j.chemolab.2025.105412","url":null,"abstract":"<div><div>Maize leaf diseases pose significant threats to global agricultural productivity, yet traditional diagnostic methods are slow, subjective, and resource-intensive. This study proposes a lightweight and interpretable convolutional neural network (CNN) model for accurate and efficient classification of maize leaf diseases. Using the ‘Corn or Maize Leaf Disease Dataset’, the model classifies four disease categories Healthy, Gray Leaf Spot, Common Rust, and Northern Leaf Blight with 94.97 % accuracy and a micro-average AUC of 0.99. With only 1.22 million parameters, the model supports real-time inference on mobile devices, making it ideal for field applications. Data augmentation and transfer learning techniques were applied to ensure robust generalization. To enhance transparency and user trust, Explainable Artificial Intelligence (XAI) methods, including LIME and SHAP, were employed to identify disease-relevant features such as lesions and pustules, with SHAP achieving an IoU of 0.82. The proposed model outperformed benchmark models like ResNet50, MobileNetV2, and EfficientNetB0 in both accuracy and computational efficiency. Robustness tests under simulated environmental challenges confirmed its adaptability, with only a 2.82 % performance drop under extreme conditions. Comparative analyses validated its statistical significance and practical superiority. This model represents a reliable, fast, and explainable solution for precision agriculture, especially in resource-constrained environments. Future enhancements will include multi-angle imaging, multimodal inputs, and extended datasets to improve adaptability and scalability in real-world conditions.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105412"},"PeriodicalIF":3.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143874963","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":"Visualized correlation and distance preserving dimensionality reduction method","authors":"Zhonghai He ,&nbsp;Zhanbo Feng ,&nbsp;Haoxiang Zhang ,&nbsp;Xiaofang Zhang","doi":"10.1016/j.chemolab.2025.105406","DOIUrl":"10.1016/j.chemolab.2025.105406","url":null,"abstract":"<div><div>A large of existing dimensionality reduction methods are aimed at preserving some properties of data, which cannot take label information into account. With the aim of reduced low-dimensional coordinate is used as tool for timing judgment of model updating, the concentration information should be incorporated into dimensionality reduction procedure, which is presented and named as Visualized Correlation and Distance Preserving dimensionality reduction method. To address the difficulty of 2D coordinate and 1D label correlation computation, pairwise distance matrices in both the subspace and label space are computed and the strictly lower triangular parts of these matrices are extracted and vectorized in column-major order, resulting in two vectors so that correlation can be computed. Distance preservation term is included as sub-objective function to ensure the low distance dissimilarity between high and low coordinates. To reduce structural loss caused by sequential dimensionality reduction method, the projection matrix is concatenated to vector then optimized to ensure projection vectors are optimized synchronously. PCA transformation is continued to adjust the reduced coordinates to better suited for visual judgment.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105406"},"PeriodicalIF":3.7,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850369","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":"Chemometric modeling of the adsorption mechanism of Cu(II) in aqueous solution onto functionalized materials: Integrating artificial neural networks and porous structure characterization","authors":"Walter M. Warren-Vega ,&nbsp;Sofia Cornejo-León ,&nbsp;Ana I. Zárate-Guzmán ,&nbsp;Francisco Carrasco-Marín ,&nbsp;Luis A. Romero-Cano","doi":"10.1016/j.chemolab.2025.105405","DOIUrl":"10.1016/j.chemolab.2025.105405","url":null,"abstract":"<div><div>Traditional methods for evaluating adsorption mechanisms rely on material characterization and its linear relationship with adsorption capacity. However, this approach has limitations, as it assumes a linear correlation, and when this fails, it is often speculated that multiple mechanisms are involved without detailing their contributions. This study overcomes these challenges by using artificial intelligence to analyze the adsorption of Cu(II) onto alternative adsorbents. An Artificial Neural Network (ANN) combined with 3D porous texture simulations, based on mercury intrusion porosimetry, established non-linear correlations among 13 textural and chemical characteristics and adsorption capacity.</div><div>The material with the highest adsorption capacity (107 mg g⁻¹) featured an accessible porous texture rich in –COOH groups. The ANN quantified the contributions of two governing mechanisms: diffusion through the porous texture (67.07 %) and interaction with –COOH sites (32.93 %). Chemometric analysis revealed that the greatest weight in the ANN model was attributed to the average pore diameter (17.11 %), which was consistent with the characterization of the saturated material by SEM-EDX, showing that adsorption occurs primarily in the exposed cavities of the material.</div><div>The adsorption mechanism proposed by the ANN study explains the atypical points observed in the different materials, showing that the adsorption process is governed by a combination of two mechanisms: one associated with the porous texture and the other with surface chemistry. The findings provide a deeper understanding of the key variables influencing adsorption and offer guidance for optimizing material synthesis.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105405"},"PeriodicalIF":3.7,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143844324","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":"Spectral investigation of aspartame and acesulfame utilizing PXRD, Raman, FTIR, and THz technologies","authors":"Zeyu Hou ,&nbsp;Bingxin Yan ,&nbsp;Yuhan Zhao ,&nbsp;Shengbo Zhang ,&nbsp;Bo Su ,&nbsp;Kai Li ,&nbsp;Cunlin Zhang","doi":"10.1016/j.chemolab.2025.105408","DOIUrl":"10.1016/j.chemolab.2025.105408","url":null,"abstract":"<div><div>Artificial sweeteners, as a type of food additive, have vibration frequencies mostly concentrated in the terahertz (THz) band, which enables us to utilize THz technology to deeply analyze their molecular properties. To gain a more comprehensive understanding of the features of artificial sweeteners, this study specifically chose aspartame and acesulfame as representatives. Initially, we employed PXRD and Raman spectroscopy techniques to carry out a thorough examination and verification of the crystalline structure as well as the purity levels of these two synthetic sweeteners. Then, with the aid of Fourier transform infrared spectroscopy (FTIR) technology and terahertz time-domain spectroscopy (THz-TDS) system, the spectral characteristics of aspartame and acesulfame were precisely measured. Moreover, the crystal configurations of these two artificial sweeteners were simulated using solid-state density functional theory (DFT), and the simulation results were in good agreement with the experimental results, further validating the effectiveness of our research methods. Finally, using microfluidic chip technology, the THz spectral characteristics of aspartame and acesulfame in solution were determined, and were compared with their spectra in solid state. We found that the THz spectra of the two artificial sweeteners in solid and solution states have significant correlations. In addition, the research further elucidated that the THz spectrum of a substance dissolved in a solution exhibits a close correlation with its concentration within that solution. These findings provide new perspectives and value for our in-depth research on artificial sweeteners.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105408"},"PeriodicalIF":3.7,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838713","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":"Optimizing soft sensor costs through feature selection: A comparative study of sensory and chemical parameters in wine grade prediction","authors":"Jingxian An ,&nbsp;Zhipeng Zhang","doi":"10.1016/j.chemolab.2025.105404","DOIUrl":"10.1016/j.chemolab.2025.105404","url":null,"abstract":"<div><div>Traditional wine grade evaluation, typically conducted by world-renowned wine experts, was found to disadvantage emerging wineries due to its restrictive and time-consuming nature. This study proposed an alternative approach using soft sensors to predict wine grades, investigating the cost-effectiveness of both chemical and sensory evaluation methods through various machine learning approaches. A dataset of 23 unique wine samples in duplicate (totaling 46 bottles of New Zealand Pinot Noir wines), classified across all five stars of the Jukes-Stelzer system, was analyzed using 13 chemical parameters and 35 sensory attributes. The research employed classification algorithms, including naïve Bayes, k-nearest neighbors, decision trees, and support vector machines, to predict wine grades. Additionally, multiple feature selection methods—such as PCA distance analysis, ensemble tree-based feature selection, decision tree-based feature selection, Fisher score, relief-F score analysis, and one-way ANOVA—were used to identify the most significant predictive variables while minimizing analytical costs. Results demonstrated that chemical parameters, particularly those related to wine color and total phenolics, served as strong indicators of wine grade, with soft sensors using all 13 chemical parameters achieving prediction accuracies up to 93.48 %. Sensory attributes, particularly oak influence and tertiary aromas related to wine storage, also proved to be effective predictors. Soft sensors utilizing all 35 sensory attributes achieved accuracies of 97.83 %. Through feature selection methods, costs could be reduced by up to 100 % while maintaining acceptable prediction accuracy (above 65 %). Similarly, accuracies above 65 % were achieved using sensory attributes as input data, alongside a 97 % cost reduction. Additionally, in scenarios where chemical measurements were taken only once and sensory attributes were evaluated by a single wine expert, a comparative cost analysis revealed that sensory attributes were more economical for high-accuracy predictions (&gt;70 %), while chemical parameters proved more cost-effective for moderate accuracy levels (&lt;70 %). For higher accuracy requirements (&gt;70 %), sensory evaluation emerged as the optimal choice, offering both high accuracy and cost-effectiveness. This study proposed a practical framework for cost-effective wine grade prediction methods that could benefit both established and emerging wine producers, offering an accessible alternative to traditional expert-based evaluation systems.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105404"},"PeriodicalIF":3.7,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143858815","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":"Integration of multifactorial omics data from several sources using multiblock methods","authors":"Miguel de Figueiredo ,&nbsp;Serge Rudaz ,&nbsp;Julien Boccard","doi":"10.1016/j.chemolab.2025.105403","DOIUrl":"10.1016/j.chemolab.2025.105403","url":null,"abstract":"<div><div>With advances in data acquisition methods and technical platforms, omics measurement collection yields increasingly complex data structures. While high-dimensional matrices with more variables than samples can be handled via multivariate methods, extracting information is more challenging in the case of experimental designs involving several factors. Multifactorial models combining ANOVA and multivariate approaches have been developed for this purpose, but analyzing unbalanced designs remains challenging, especially when several data blocks are integrated.</div><div>This study introduces integrative AComDim (iAComDim) and integrative AMOPLS (iAMOPLS) for the analysis of multifactorial data from multiple sources. These methods implement a rebalancing strategy tailored for multiblock settings, ensuring unbiased effect estimators and orthogonal effect matrices even with unbalanced designs. When applied to a multiomics benchmark dataset with two experimental factors, these approaches effectively separate the sources of variation related to the effects in the design while summarizing information into a single multiblock model. Rebalancing strategies prevent the mixing of variation sources in extracted components, and their integration with multiblock chemometric methods offers an efficient and versatile solution for analyzing complex data structures.</div><div>This work establishes a novel framework for analyzing data from single or multiple sources within multifactorial experimental designs. Furthermore, the proposed methods are flexible enough to analyze unbalanced designs with heterogeneously missing replicates across multiple tables, making them broadly applicable for handling multiomics or other datasets in various application domains.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105403"},"PeriodicalIF":3.7,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833935","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":"GAN-ML: Advancing anticancer peptide prediction through innovative Deep Convolution Generative Adversarial Network data augmentation technique","authors":"Sadik Bhattarai ,&nbsp;Kil To Chong ,&nbsp;Hilal Tayara","doi":"10.1016/j.chemolab.2025.105390","DOIUrl":"10.1016/j.chemolab.2025.105390","url":null,"abstract":"<div><div>Limited and imbalanced data hinder anticancer peptide (ACP) prediction, often resulting in over-fitting and poor performance on unseen peptides. To address these challenges, we propose a Deep Convolution Generative Adversarial Network (DC-GAN) based data augmentation method. This approach effectively expands the training dataset by generating peptides with anticancer properties, particularly underrepresented class such as N+ type ACPs, characterized by abundant positive residues in the N-terminus, which remain amnesic problem in anticancer peptide prediction. Compared to traditional methods like Synthetic Minority Over-sampling Technique (SMOTE) and SMOTE with Edited Nearest Neighbors (SMOTEENN), DC-GAN demonstrates superior performance by addressing both limited training samples and within-class imbalances, such as those between C+ and N+ type peptides. The proposed framework, GAN-ML cascade a linear model and an ensemble model, achieving accuracy rates of 82.96% (independent test), 96.06% (independent test), and 94.06% (5-fold cross-validation) for classifying peptides as anticancer, antimicrobial, or non-anticancer across various datasets integrating ACPs motif based authentication and physio-chemical properties based validation. These results highlight the efficacy of DC-GAN-based data augmentation in enhancing model generalization, improving performance by generating a samples with minority representation, and serving as a powerful tool for generative anticancer drug discovery.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105390"},"PeriodicalIF":3.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816471","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":"Multiclass classification of leukemia cancer subtypes using gene expression data and Optimized Dueling Double Deep Q-network","authors":"R. Jayakrishnan,&nbsp;S. Meera","doi":"10.1016/j.chemolab.2025.105402","DOIUrl":"10.1016/j.chemolab.2025.105402","url":null,"abstract":"<div><div>Microarray technology aids in gene expression tracking, but diagnosing complex conditions like leukemia remains challenging due to multiple clinical factors. Deep reinforcement learning for cancer classification faces challenges related to optimization, handling high-dimensional noisy data, and interpretability. To address these limitations, this study proposes an Optimized Dueling Double Deep Q-Network (DDDQ-N) Framework, integrating advanced feature selection and DRL for robust leukemia subtype prediction. The framework begins with pre-processing, which includes data cleaning, normalization, and addressing class imbalance using the Synthetic Minority Over-sampling Technique (SMOTE). To enhance interpretability and reduce dimensionality, a novel Butterfly Optimization with Chaotic Local Search (BO-CLS) algorithm is introduced for feature selection, efficiently identifying the most discriminative genes. The selected features are then processed by a Dueling Double Deep Q-Network (DDQ-N), combining deep representation learning with reinforcement learning for sequential decision-making. The model employs a custom reward function and episode-based training to handle multi-class imbalance, adapt to tumor heterogeneity, and optimize classification strategies. Experimental results on a multi-class leukemia gene expression dataset demonstrate the model's superiority, achieving 99 % accuracy, 98.8 % precision, 99.2 % recall, and 99 % F1-score, outperforming existing methods such as Machine Learning (ML) Ensemble (94 %), Stacked Autoencoders with Grey Wolf Optimization (SAE-GWO) (98 %), and Feature Selective Neuro Evolution of Augmenting Topologies (FS-NEAT) (93 %). The proposed BO-CLS feature selection also shows significant improvements over ChisIG-SMOTE (95.5 % accuracy) and east Absolute Shrinkage and Selection Operator-Multi-Objective Genetic Algorithm (LASSO-MOGAT) (94.7 % accuracy), confirming its effectiveness in dimensionality reduction. These findings highlight the potential of the proposed framework to revolutionize leukemia diagnosis and provide a more efficient, interpretable, and accurate approach for clinical applications.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105402"},"PeriodicalIF":3.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833934","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":"Enhancing Albumin Detection with Chemometrics: A Multivariate Approach to Bromocresol Green-based Colorimetric Sensor Development","authors":"Guglielmo Emanuele Franceschi ,&nbsp;Lisa Rita Magnaghi ,&nbsp;Marta Guembe-Garcia ,&nbsp;Raffaela Biesuz","doi":"10.1016/j.chemolab.2025.105400","DOIUrl":"10.1016/j.chemolab.2025.105400","url":null,"abstract":"<div><div>The detection of human serum albumin (HSA) in urine is crucial for the early diagnosis of nephrotic syndromes and diabetic nephropathy. In this study, we developed a cost-effective, colorimetric sensor based on Bromocresol Green (BCG) sorbed on Color Catcher® (CC) sheets for albumin detection. The sensor undergoes a visible color change from yellow to blue upon interaction with albumin at acidic pH, enabling qualitative detection. A Design of Experiment (DoE) approach was applied to optimize sensor preparation and application and to control experimental variability within the lab-scale preparation procedure, ensuring enhanced sensitivity and robustness. Several multivariate data analysis tools, including Principal Component Analysis (PCA) and Discriminant Analysis (LDA and QDA), were merged to describe the samples, develop robust and predictive models and assess detection performance. The optimized sensor proved a detection limit as low as 0.5 μM for albumin, making it a promising candidate for rapid, low-cost, and user-friendly point-of-care (PoC) applications.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105400"},"PeriodicalIF":3.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808615","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":"Advanced breast cancer prediction using Deep Neural Networks integrated with ensemble models","authors":"Mana Saleh Al Reshan ,&nbsp;Samina Amin ,&nbsp;Muhammad Ali Zeb ,&nbsp;Adel Sulaiman ,&nbsp;Asadullah Shaikh ,&nbsp;Hani Alshahrani ,&nbsp;Khairan Rajab","doi":"10.1016/j.chemolab.2025.105399","DOIUrl":"10.1016/j.chemolab.2025.105399","url":null,"abstract":"<div><div>Breast cancer (BC) is a fatal illness that affects millions of people every year. After lung cancer, BC illness is one of the world's major causes of death for women. A breast cell-derived malignant tumor is referred to as BC. Both developed and developing countries are struggling with this widespread cancer. Machine learning (ML) and Deep Learning (DL) have appeared as effective technologies in BC predictions with the highest accuracy in the past years due to their robust taxonomy and diagnostic capabilities. This paper introduces a novel Deep Neural Networks-based Stacking Ensemble Model (DNN-SEM) enhanced with a hybrid stacking ensemble model (SEM) and Extra Tree Classifier (ETC) technique to extract the most essential features from the suggested BC datasets. The proposed DNN-SEM integrates Deep Belief Network (DBN) and Artificial Neural Network (ANN) as level-1 models, referred to as SEM-DBN and SEM-ANN, respectively. The level-1 models are designed using four traditional ML algorithms, including XGBoost Classifier (XGBC), Logistic Regression (LR), Random Forest (RF), and Support Vector Machine (SVM), which are designed as level-0 models. The proposed DNN-SEM model is trained using four BC datasets, namely Diagnostic Wisconsin Breast Cancer Dataset (WBCD) (Dataset-I), Coimbra Breast Cancer Dataset (CBCD) (Dataset-II), Original Wisconsin Breast Cancer Dataset (WDBC) (Dataset-III), and Prognostic Wisconsin Breast Cancer (WBCP) (Dataset-IV). The efficacy of the proposed DNN-SEM is assessed through established evaluation metrics, including accuracy, sensitivity, specificity, Matthew's correlation coefficient (MCC), F-score, confusion matrix, and ROC curves. To analyze the efficiency of the DNN-SEM, its performance is compared with the proposed single classifiers, ensemble, and state-of-the-art models present in the literature. The results demonstrate that DBN-SEM achieves the highest accuracy of 99.62 %, with the lowest error rate. The proposed DBN-SEM and ANN-SEM achieved promising accuracy scores against level-0 and state-of-the-art methods.</div></div>","PeriodicalId":9774,"journal":{"name":"Chemometrics and Intelligent Laboratory Systems","volume":"262 ","pages":"Article 105399"},"PeriodicalIF":3.7,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799625","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}