{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T13:53:10Z","timestamp":1768312390416,"version":"3.49.0"},"reference-count":49,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Traditional clustering methods are often ineffective in extracting relevant features from high-dimensional, nonlinear near-infrared (NIR) spectra, resulting in poor accuracy of detecting lactose-free milk adulteration. In this paper, we introduce a clustering model based on Gram angular field and convolutional depth manifold (GAF-ConvDuc). The Gram angular field accentuates variations in spectral absorption peaks, while convolution depth manifold clustering captures local features between adjacent wavelengths, reducing the influence of noise and enhancing clustering accuracy. Experiments were performed on samples from 2250 milk spectra using the GAF-ConvDuc model. Compared to K-means, the silhouette coefficient (SC) increased from 0.109 to 0.571, standardized mutual information index (NMI) increased from 0.696 to 0.921, the Adjusted Randindex (ARI) increased from 0.543 to 0.836, and accuracy (ACC) increased from 67.2% to 88.9%. Experimental results indicate that our method is superior to K-means, Variational Autoencoder (VAE) clustering, and other approaches. Without requiring pre-labeled data, the model achieves higher inter-cluster separation and more distinct clustering boundaries. These findings offer a robust solution for detecting lactose-free milk adulteration, crucial for food safety oversight.<\/jats:p>","DOI":"10.3390\/info16060498","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T06:40:27Z","timestamp":1750056027000},"page":"498","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["From Spectrum to Image: A Novel Deep Clustering Network for Lactose-Free Milk Adulteration Detection"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0375-1757","authenticated-orcid":false,"given":"Chong","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Electronics and Information, Qingdao University, Qingdao 266071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4075-5582","authenticated-orcid":false,"given":"Shankui","family":"Ding","sequence":"additional","affiliation":[{"name":"College of Electronics and Information, Qingdao University, Qingdao 266071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-7636","authenticated-orcid":false,"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"College of Electronics and Information, Qingdao University, Qingdao 266071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6000","DOI":"10.3168\/jds.2014-8127","article-title":"Detection of cow milk adulteration in yak milk by ELISA","volume":"97","author":"Ren","year":"2014","journal-title":"J. Dairy Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1111\/1471-0307.12274","article-title":"Detection of adulteration in milk: A review","volume":"70","author":"Poonia","year":"2017","journal-title":"Int. J. Dairy Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"52","DOI":"10.5539\/jfr.v8n4p52","article-title":"Milk Adulteration: Detection of Bovine Milk in Caprine Dairy Products by Real Time PCR","volume":"8","author":"Tsakali","year":"2019","journal-title":"J. Food Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"115810","DOI":"10.1016\/j.optmat.2024.115810","article-title":"A novel refractive index based-fiber optic sensor for milk adulteration detection","volume":"154","author":"Harini","year":"2024","journal-title":"Opt. Mater."},{"key":"ref_5","first-page":"838","article-title":"Rapid ATR-FTIR Principal Component Analysis of Commercial Milk","volume":"43","author":"Feng","year":"2023","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_6","first-page":"65","article-title":"Quantitative Analysis of Urea Adulteration in Milk by Near-Infrared Spectroscopy","volume":"43","author":"Huang","year":"2023","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_7","first-page":"48","article-title":"Near-Infrared Spectroscopy Pattern Recognition of Melamine-Adulterated Milk","volume":"44","author":"Wei","year":"2016","journal-title":"China Dairy Ind."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"107585","DOI":"10.1016\/j.foodcont.2020.107585","article-title":"Differential scanning calorimetry coupled with machine learning technique: An effective approach to determine the milk authenticity","volume":"121","author":"Farah","year":"2021","journal-title":"Food Control"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107571","DOI":"10.1016\/j.jfca.2025.107571","article-title":"Near-infrared (NIR) spectroscopy combined with chemometrics for qualitative and quantitative detection of camel milk powder adulteration","volume":"143","author":"Cai","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Wu, X., Fang, Y., Wu, B., and Liu, M. (2023). Application of Near-Infrared Spectroscopy and Fuzzy Improved Null Linear Discriminant Analysis for Rapid Discrimination of Milk Brands. Foods, 12.","DOI":"10.3390\/foods12213929"},{"key":"ref_11","first-page":"3701","article-title":"Discrimination Method of Pesticide Residues on Hami Melon Surface Based on GADF Transform and Multi-scale CNN Using Visible-Near Infrared Spectroscopy","volume":"41","author":"Yu","year":"2021","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13040-019-0200-5","article-title":"On the utilization of deep and ensemble learning to detect milk adulteration","volume":"12","author":"Neto","year":"2019","journal-title":"BioData Min."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e32720","DOI":"10.1016\/j.heliyon.2024.e32720","article-title":"Rapid detection and quantification of melamine, urea, sucrose, water, and milk powder adulteration in pasteurized milk using Fourier transform infrared (FTIR) spectroscopy coupled with modern statistical machine learning algorithms","volume":"10","author":"Chu","year":"2024","journal-title":"Heliyon"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107424","DOI":"10.1016\/j.jfca.2025.107424","article-title":"Quality detection of common beans flour using hyperspectral imaging technology: Potential of machine learning and deep learning","volume":"142","author":"Rashvand","year":"2025","journal-title":"J. Food Compos. Anal."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ninh, D.K., Phan, K.D., Vo, C.T., Dang, M.N., and Thanh, N.L. (2024). Classification of Histamine Content in Fish Using Near-Infrared Spectroscopy and Machine Learning Techniques. Information, 15.","DOI":"10.3390\/info15090528"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.foodcont.2016.02.015","article-title":"Milk authentication and discrimination via metal content clustering\u2014A case of comparing milk from Malaysia and selected countries of the world","volume":"66","author":"Zain","year":"2016","journal-title":"Food Control"},{"key":"ref_17","first-page":"1945","article-title":"Cluster Analysis for IR and NIR Spectroscopy: Current Practices to Future Perspectives","volume":"69","author":"Crase","year":"2021","journal-title":"Comput. Mater. Contin."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Buoio, E., Colombo, V., Ighina, E., and Tangorra, F. (2024). Rapid Classification of Milk Using a Cost-Effective Near Infrared Spectroscopy Device and Variable Cluster-Support Vector Machine (VC-SVM) Hybrid Models. Foods, 13.","DOI":"10.3390\/foods13203279"},{"key":"ref_19","first-page":"2506","article-title":"Research on Split-Type LIBS Detection Method for Soil Heavy Metals Based on Clustering Analysis","volume":"44","author":"Guan","year":"2024","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"ref_21","unstructured":"Kingma, D.P., and Welling, M. (2013). Auto-encoding variational bayes. arXiv."},{"key":"ref_22","unstructured":"Xie, J., Girshick, R.B., and Farhadi, A. (2015). Unsupervised Deep Embedding for Clustering Analysis. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"127332","DOI":"10.1016\/j.foodchem.2020.127332","article-title":"Evaluation of an autoencoder as a feature extraction tool for near-infrared spectroscopic discriminant analysis","volume":"331","author":"Jo","year":"2020","journal-title":"Food Chem."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.isatra.2024.07.039","article-title":"Planetary gearbox fault classification based on tooth root strain and GAF pseudo images","volume":"153","author":"Hu","year":"2024","journal-title":"ISA Trans."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3315","DOI":"10.1007\/s12206-024-0606-y","article-title":"Rolling bearing fault diagnosis method based on MTF and PC-MDCNN","volume":"38","author":"Lei","year":"2024","journal-title":"J. Mech. Sci. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"105575","DOI":"10.1016\/j.infrared.2024.105575","article-title":"Identification of apple watercore based on ConvNeXt and Vis\/NIR spectra","volume":"142","author":"Zhao","year":"2024","journal-title":"Infrared Phys. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"112394","DOI":"10.1016\/j.microc.2024.112394","article-title":"Discriminating moisture content in Fraxinus mandshurica Rupr logs using fusion of 2D GADF spectral images and 1D NIR spectra","volume":"208","author":"Liu","year":"2025","journal-title":"Microchem. J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"110808","DOI":"10.1016\/j.foodcont.2024.110808","article-title":"High-precision detection of dibutyl hydroxytoluene in edible oil via convolutional autoencoder compressed Fourier-transform near-infrared spectroscopy","volume":"167","author":"Deng","year":"2025","journal-title":"Food Control"},{"key":"ref_29","first-page":"3637","article-title":"Near-Infrared Spectroscopy Measurement with Contrasted Variational Autoencoders and Its Application in Liquid Sample Detection","volume":"42","author":"Yuan","year":"2022","journal-title":"Spectrosc. Spectr. Anal."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Du, S., Han, W., Kang, Z., Liao, Y., and Li, Z. (2024). A Convolution Auto-Encoders Network for Aero-Engine Hot Jet FT-IR Spectrum Feature Extraction and Classification. Aerospace, 11.","DOI":"10.3390\/aerospace11110933"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"23489","DOI":"10.1007\/s11042-023-16456-w","article-title":"Two-stage multi-dimensional convolutional stacked autoencoder network model for hyperspectral images classification","volume":"83","author":"Bai","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s11063-024-11586-0","article-title":"Deep Embedding Clustering Based on Residual Autoencoder","volume":"56","author":"Li","year":"2024","journal-title":"Neural Process. Lett."},{"key":"ref_33","first-page":"2104","article-title":"Clustering Analysis of Daily Load Curves Based on Deep Convolutional Embedded Clustering","volume":"46","author":"Bai","year":"2022","journal-title":"Power Syst. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1007\/s10115-020-01530-8","article-title":"Improving spectral clustering with deep embedding, cluster estimation and metric learning","volume":"63","author":"Duan","year":"2021","journal-title":"Knowl. Inf. Syst."},{"key":"ref_35","first-page":"439","article-title":"Dimensionality Reduction Method Based on Manifold Learning with Variational Autoencoder","volume":"37","author":"Feng","year":"2025","journal-title":"J. Comput.-Aided Des. Comput. Graph."},{"key":"ref_36","first-page":"645","article-title":"Improved Model of YOLOv5 Prediction Bounding Box Clustering Adaptive Loss Weight","volume":"38","author":"Nie","year":"2023","journal-title":"Control Decis."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1016\/j.egyr.2022.03.156","article-title":"Ferromagnetic resonance over-voltage identification method based on Gram angle field","volume":"8","author":"Li","year":"2022","journal-title":"Energy Rep."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"109252","DOI":"10.1016\/j.compeleceng.2024.109252","article-title":"Open-circuit fault diagnosis method of inverter in wind turbine yaw system based on GADF image coding","volume":"117","author":"Hu","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2517","DOI":"10.32604\/ee.2023.042633","article-title":"Identification of High-Risk Scenarios for Cascading Failures in New Energy Power Grids Based on Deep Embedding Clustering Algorithms","volume":"120","author":"Cheng","year":"2023","journal-title":"Energy Eng."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1038\/nbt.4314","article-title":"Dimensionality reduction for visualizing single-cell data using UMAP","volume":"37","author":"Becht","year":"2018","journal-title":"Nat. Biotechnol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"105142","DOI":"10.1016\/j.isci.2022.105142","article-title":"Dimensionality reduction by UMAP for visualizing and aiding in classification of imaging flow cytometry data","volume":"25","author":"Ireneusz","year":"2022","journal-title":"iScience"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1504\/IJWET.2020.107685","article-title":"The research on two phase pickup vehicle routing based on the K-means++ and genetic algorithms","volume":"15","author":"Zhao","year":"2020","journal-title":"Int. J. Web Eng. Technol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"111594","DOI":"10.1016\/j.asoc.2024.111594","article-title":"An End-to-end Deep Clustering Method with Consistency and Complementarity Attention Mechanism for Multisensor Fault Diagnosis","volume":"158","author":"Wu","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"4132","DOI":"10.1049\/iet-ipr.2020.0402","article-title":"Image clustering algorithm using superpixel segmentation and non-symmetric Gaussian\u2013Cauchy mixture model","volume":"14","author":"Ji","year":"2020","journal-title":"IET Image Process."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Kouser, K., Priyam, A., Gupta, M., Kumar, S., and Bhattacharjee, V. (2024). Genetic Algorithm-Based Optimization of Clustering Algorithms for the Healthy Aging Dataset. Appl. Sci., 14.","DOI":"10.20944\/preprints202405.1663.v1"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.patcog.2019.05.011","article-title":"Deep embedding learning with adaptive large margin N-pair loss for image retrieval and clustering","volume":"93","author":"Chen","year":"2019","journal-title":"Pattern Recognit."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"480","DOI":"10.1109\/TBME.2024.3458177","article-title":"Deep Clustering for Epileptic Seizure Detection","volume":"72","author":"Abdallah","year":"2025","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1007\/s00357-022-09413-z","article-title":"Understanding the Adjusted Rand Index and Other Partition Comparison Indices Based on Counting Object Pairs","volume":"39","author":"Warrens","year":"2022","journal-title":"J. Classif."},{"key":"ref_49","first-page":"1","article-title":"Reactor voiceprint clustering method based on the deep adaptive K-means++ algorithm","volume":"53","author":"Min","year":"2025","journal-title":"Power Syst. Prot. Control"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/6\/498\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:52:42Z","timestamp":1760032362000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/6\/498"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["info16060498"],"URL":"https:\/\/doi.org\/10.3390\/info16060498","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,16]]}}}