{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:06:31Z","timestamp":1788930391501,"version":"build-2803163510"},"reference-count":45,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Molecules"],"abstract":"<jats:p>Geographical authentication of medicinal plant materials remains challenging because multispectral variables are often highly collinear and sample grouping can complicate reliable model validation. Existing correlation-based feature-selection strategies also require careful adaptation to multiclass problems to avoid artificial ordering of class labels and information leakage during model development. Therefore, this study aimed to develop a compact and leakage-controlled multispectral learning framework for geographical-origin discrimination. This study analyzed 800 physical Pinellia ternata samples from Gansu Xihe, Sichuan Neijiang, Sichuan Chengdu, and Chongqing Dianjiang (200 samples per origin). Each physical sample was represented by 31 mean grayscale intensities calculated from Otsu-segmented multispectral regions of interest. A Pearson-correlation-guided deep multilayer perceptron (PCG-DeepMLP) was constructed by estimating one-vs-rest band relevance and inter-band redundancy only within the training data. The key methodological innovation is a unified multiclass-aware, relevance\u2013redundancy spectral-learning framework in which class-specific one-vs-rest Pearson relevance is coupled with inter-band redundancy control and embedded within leakage-controlled grouped model development. By learning the spectral subset exclusively from each training partition before nonlinear classification, the framework produces compact and complementary multispectral signatures while preserving multiclass structure and strict independence of held-out groups. Model and feature-selection settings were chosen by three-fold grouped cross-validation within each training partition. PCG-DeepMLP retained 9\u201321 bands and achieved the highest mean accuracy (0.9812 \u00b1 0.0135), macro-F1 (0.9812 \u00b1 0.0135), Matthews correlation coefficient (MCC; 0.9752 \u00b1 0.0179), and macro-AUC (0.9994 \u00b1 0.0006) among seven models. Its macro-F1 was higher than that of 1D-CNN, 1D-ResNet, full-band MLP, PLS-DA, and random forest after Holm correction. Performance was estimated through a strict nested group-wise internal validation scheme, with every outer test fold remaining isolated from feature selection, preprocessing, and model optimization. These findings demonstrate that multiclass-aware relevance\u2013redundancy learning can retain complementary Pinellia ternata origin-discriminative information in a compact and stable spectral representation, enabling accurate geographical-origin authentication while providing a principled basis for reduced-channel acquisition and future independent multi-batch validation.<\/jats:p>","DOI":"10.3390\/molecules31173138","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T16:30:02Z","timestamp":1788798602000},"page":"3138","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Compact Multispectral Signatures for Geographical-Origin Authentication of Pinellia ternata via Correlation-Guided Deep Modeling"],"prefix":"10.3390","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2805-4750","authenticated-orcid":false,"given":"Zhihui","family":"Fan","sequence":"first","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowen","family":"Jing","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Wang","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Department, Yuxin Electronic Technology Group Co., Ltd., Zhengzhou 450000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenzhen","family":"Chen","sequence":"additional","affiliation":[{"name":"Artificial Intelligence Department, Yuxin Electronic Technology Group Co., Ltd., Zhengzhou 450000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, South China University of Technology, Guangzhou 510641, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2797-8781","authenticated-orcid":false,"given":"Mingkun","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Henan University of Science and Technology, Luoyang 471023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, J., Cui, J., Liu, Z., Yang, Y., Li, Z., and Liu, H. (2024). Untargeted Metabolomics Based on Ultra-High-Performance Liquid Chromatography Coupled with Quadrupole Orbitrap High-Resolution Mass Spectrometry for Differential Metabolite Analysis of Pinelliae Rhizoma and Its Adulterants. Molecules, 29.","DOI":"10.3390\/molecules29092155"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Wang, J., Han, X., Zheng, Y., Zhao, Y., Wang, W., Ma, D., and Sun, H. (2024). Spatial Metabolomic Profiling of Pinelliae Rhizoma from Different Leaf Types Using Matrix-Assisted Laser Desorption\/Ionization Mass Spectrometry Imaging. Molecules, 29.","DOI":"10.3390\/molecules29174251"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"115650","DOI":"10.1016\/j.jep.2022.115650","article-title":"A comprehensive review on ethnopharmacological, phytochemical, pharmacological and toxicological evaluation, and quality control of Pinellia ternata (Thunb.) Breit","volume":"298","author":"Bai","year":"2022","journal-title":"J. Ethnopharmacol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"40460","DOI":"10.1038\/s41598-025-24185-3","article-title":"Optimizing planting depth and propagule characteristics for efficient cultivation of Pinellia ternata","volume":"15","author":"Liao","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20220287","DOI":"10.1515\/chem-2022-0287","article-title":"Comparative analysis of the metabolites in Pinellia ternata Two Prod. Reg. Using Ultra-High Liq. Chromatogr.-Electrospray Ioniz.-Tandem Mass Spectrometry","volume":"21","author":"Li","year":"2023","journal-title":"Open Chem."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wang, Y., Luo, Y., Gan, J., Wang, L., Fang, C., Zhang, L., Zhen, C., and Chen, B. (2026). From Activity Screening to Quality Control: UHPLC-MS\/MS Analysis of Anti-Inflammatory Cyclodipeptides in Pinellia ternata. Molecules, 31.","DOI":"10.3390\/molecules31081322"},{"key":"ref_7","first-page":"1","article-title":"Pinelliae Rhizoma: A systematic review on botany, ethnopharmacology, phytochemistry, preclinical and clinical evidence","volume":"23","author":"Liang","year":"2025","journal-title":"Chin. J. Nat. Med."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yang, R., Wang, Y., Wang, J., Guo, X., Zhao, Y., Zhu, K., Zhu, X., Zou, H., and Yan, Y. (2024). Geographical Origin Traceability of Atractylodis Macrocephalae Rhizoma Based on Chemical Composition, Chromaticity, and Electronic Nose. Molecules, 29.","DOI":"10.3390\/molecules29214991"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tatini, D., Bisozzi, F., Costantini, S., Fattori, G., Boldrini, A., Baglioni, M., Bonechi, C., Donati, A., Tozzi, C., and Riccaboni, A. (2025). Geographical Origin Authentication of Leaves and Drupes from Olea europaea via 1H NMR and Excitation-Emission Fluorescence Spectroscopy: A Data Fusion Approach. Molecules, 30.","DOI":"10.3390\/molecules30153208"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"M\u00fcller, M.-S., Er\u00e7etin, E., Cvancar, L., Oest, M., and Fischer, M. (2024). Elemental Profiling for the Detection of Food Mixtures: A Proof of Principle Study on the Detection of Mixed Walnut Origins Using Measured and Calculated Data. Molecules, 29.","DOI":"10.3390\/molecules29143350"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Nyarko, K., Mensah, S., and Greenlief, C.M. (2024). Examining the Use of Polyphenols and Sugars for Authenticating Honey on the U.S. Market: A Comprehensive Review. Molecules, 29.","DOI":"10.3390\/molecules29204940"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, W., Zhang, Z., Liu, Y., Jiang, L., Li, P., and Fan, W. (2025). A Novel Pattern Recognition Method for Non-Destructive and Accurate Origin Identification of Food and Medicine Homologous Substances with Portable Near-Infrared Spectroscopy. Molecules, 30.","DOI":"10.3390\/molecules30173565"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Paz, M.L., and Sousa, C. (2024). Discrimination and Quantification of Cotton and Polyester Textile Samples Using Near-Infrared and Mid-Infrared Spectroscopies. Molecules, 29.","DOI":"10.3390\/molecules29153667"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kisalaei, A., Sharabiani, V.R., Banakar, A., Taghinezhad, E., Szymanek, M., and Dziwulska-Hunek, A. (2026). Machine Learning and the Use of Spectroscopy for Adulteration Detection in Turmeric Powder. Molecules, 31.","DOI":"10.3390\/molecules31101774"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Fan, Z., Ma, C., Jing, S., Huang, J., and Zhang, M. (2026). Interpretable Spectral Evidence Learning from Vis\/NIR Imaging for Non-Destructive Authentication of Herbal Medicines. Molecules, 31.","DOI":"10.3390\/molecules31142444"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"106080","DOI":"10.1016\/j.jfca.2024.106080","article-title":"Accurate and non-destructive identification of origins for lily using near-infrared hyperspectral imaging combined with machine learning","volume":"129","author":"Zhao","year":"2024","journal-title":"J. Food Compos. Anal."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"108050","DOI":"10.1016\/j.jfca.2025.108050","article-title":"Research on rapid and non-destructive detection of adulterated wheat flour using hyperspectral imaging and machine learning","volume":"147","author":"Bai","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"109334","DOI":"10.1016\/j.jfca.2026.109334","article-title":"Non-destructive origin traceability of functional food raw materials using portable near-infrared spectroscopy and variable selection-random forest algorithm","volume":"156","author":"Wang","year":"2026","journal-title":"J. Food Compos. Anal."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"107107","DOI":"10.1016\/j.jfca.2024.107107","article-title":"Geographical origin traceability of chrysanthemum using hyperspectral imaging with class information-guided evolutionary multitasking wavelength selection and spatial feature extraction","volume":"139","author":"Wei","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107625","DOI":"10.1016\/j.jfca.2025.107625","article-title":"Application of hyperspectral imaging technology combined with ECA-MobileNetV3 in identifying different processing methods of Yunnan coffee beans","volume":"143","author":"Xin","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107684","DOI":"10.1016\/j.jfca.2025.107684","article-title":"Fingerprinting lime juice: When portable spectroscopy meets chemometrics - An innovative technique for fraud identification","volume":"144","author":"Hamidi","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"108871","DOI":"10.1016\/j.jfca.2026.108871","article-title":"Data fusion of HSI and FHSI combined with improved deep learning models to identify the geographical origin of Lycium barbarum","volume":"150","author":"Zou","year":"2026","journal-title":"J. Food Compos. Anal."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"113453","DOI":"10.1016\/j.postharvbio.2025.113453","article-title":"Hyperspectral imaging with multivariate analysis for detection of exterior flaws for quality evaluation of apples and pears","volume":"223","author":"Akter","year":"2025","journal-title":"Postharvest Biol. Technol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"105216","DOI":"10.1016\/j.infrared.2024.105216","article-title":"Leafy vegetable freshness identification using hyperspectral imaging with deep learning approaches","volume":"138","author":"He","year":"2024","journal-title":"Infrared Phys. Technol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"116945","DOI":"10.1016\/j.microc.2026.116945","article-title":"Explainable AI-driven detection of mildew in fructus Aurantii using hyperspectral imaging","volume":"221","author":"Li","year":"2026","journal-title":"Microchem. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"107835","DOI":"10.1016\/j.jfca.2025.107835","article-title":"Hyperspectral imaging combined with chemometrics for rapid detection of Poria cocos adulteration: A qualitative and quantitative approach","volume":"145","author":"Luan","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_27","first-page":"102001","article-title":"Integrated deep learning neural network and hyperspectral imaging for non-destructive prediction of biochemical properties of plant organs","volume":"21","author":"Mohtashami","year":"2025","journal-title":"J. Agric. Food Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"124700","DOI":"10.1016\/j.saa.2024.124700","article-title":"Hyperspectral imaging for in situ visual assessment of Industrial-Scale ginseng","volume":"321","author":"Zhang","year":"2024","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105625","DOI":"10.1016\/j.infrared.2024.105625","article-title":"Detection of black tea fermentation quality based on optimized deep neural network and hyperspectral imaging","volume":"143","author":"Huang","year":"2024","journal-title":"Infrared Phys. Technol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"108389","DOI":"10.1016\/j.jfca.2025.108389","article-title":"Classification of rice varieties using hyperspectral imaging with multi-dimensional fusion convolutional neural networks","volume":"148","author":"Jin","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"119151","DOI":"10.1016\/j.measurement.2025.119151","article-title":"Simultaneous prediction of Panax ginseng origin and ginsenoside Re content using hyperspectral imaging and a multi-task one-dimensional convolutional neural network","volume":"258","author":"Shen","year":"2026","journal-title":"Measurement"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"106067","DOI":"10.1016\/j.fitote.2024.106067","article-title":"Differential distribution of characteristic constituents in peel and pulp of Aurantii Fructus Immaturus (Citrus aurantium L.) using MALDI mass spectrometry imaging","volume":"177","author":"Cai","year":"2024","journal-title":"Fitoterapia"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"116807","DOI":"10.1016\/j.foodres.2025.116807","article-title":"Study on multi-dimensional dynamic changes and quality control of Aurantii fructus during the stir-frying with bran process","volume":"217","author":"Gao","year":"2025","journal-title":"Food Res. Int."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"124630","DOI":"10.1016\/j.jchromb.2025.124630","article-title":"Machine learning and chemometric methods for high-throughput authentication of 53 Root and Rhizome Chinese Herbal using ATR-FTIR fingerprints","volume":"1260","author":"Liu","year":"2025","journal-title":"J. Chromatogr. B"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"125426","DOI":"10.1016\/j.saa.2024.125426","article-title":"Rapid qualitative and quantitative detection for adulteration of Atractylodis Rhizoma using hyperspectral imaging combined with chemometric methods","volume":"327","author":"Wang","year":"2025","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"108941","DOI":"10.1016\/j.jfca.2026.108941","article-title":"Comparison and analysis of four Citrus aurantium varieties used in Aurantii fructus in terms of chemical profiles","volume":"151","author":"Wang","year":"2026","journal-title":"J. Food Compos. Anal."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"110777","DOI":"10.1016\/j.foodcont.2024.110777","article-title":"Influence of the peel on online detecting soluble solids content of pomelo using Vis-NIR spectroscopy coupled with chemometric analysis","volume":"167","author":"Wang","year":"2025","journal-title":"Food Control"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"3387","DOI":"10.1021\/acs.analchem.5c03972","article-title":"Applications and Advances in Hyperspectral Imaging for Detecting Three Major Natural Plant Pigments in Food: A Review","volume":"98","author":"Zhang","year":"2026","journal-title":"Anal. Chem."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"121467","DOI":"10.1016\/j.indcrop.2025.121467","article-title":"Deep learning time-series prediction method for cotton nitrogen content based on small sample hyperspectral data","volume":"233","author":"Qin","year":"2025","journal-title":"Ind. Crop. Prod."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"110455","DOI":"10.1016\/j.foodcont.2024.110455","article-title":"Fast prediction of diverse rare ginsenoside contents in Panax ginseng through hyperspectral imaging assisted with the temporal convolutional network-attention mechanism (TCNA) deep learning","volume":"162","author":"Wang","year":"2024","journal-title":"Food Control"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107563","DOI":"10.1016\/j.jfca.2025.107563","article-title":"Classification of quality grading of Anji white tea using hyperspectral imaging and data fusion techniques","volume":"142","author":"Wu","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"108240","DOI":"10.1016\/j.jfca.2025.108240","article-title":"Vis\/NIR spectroscopy and machine learning model for counterfeit Citri Reticulatae Pericarpium identification","volume":"148","author":"Zhang","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"122110","DOI":"10.1016\/j.indcrop.2025.122110","article-title":"Fusing band and feature attention in CNN-LSTM: A dual-attention framework for Hyperspectral-based precise prediction of nicotine levels in cured tobacco leaves","volume":"236","author":"Xing","year":"2025","journal-title":"Ind. Crop. Prod."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"110831","DOI":"10.1016\/j.foodcont.2024.110831","article-title":"Qualitative and quantitative analysis of Nanfeng mandarin quality based on hyperspectral imaging and deep learning","volume":"167","author":"Zhang","year":"2025","journal-title":"Food Control"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"124812","DOI":"10.1016\/j.saa.2024.124812","article-title":"Identification of chrysanthemum variety via hyperspectral imaging and wavelength selection based on multitask particle swarm optimization","volume":"322","author":"Wei","year":"2024","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."}],"container-title":["Molecules"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/17\/3138\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T04:14:33Z","timestamp":1788927273000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1420-3049\/31\/17\/3138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":45,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["molecules31173138"],"URL":"https:\/\/doi.org\/10.3390\/molecules31173138","relation":{},"ISSN":["1420-3049"],"issn-type":[{"value":"1420-3049","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]}}}