Design of Tobacco Leaves Classifier Through Fuzzy Clustering-Based Neural Networks With Multiple Histogram Analyses of Images

Basit Öğe Kaydı
dc.authoridLiu, Donghua/0000-0002-5830-9540
dc.authoridJiang, Ziwu/0000-0003-2807-299X
dc.authoridFu, Zunwei/0000-0001-9109-4142
dc.authoridWang, Zheng/0000-0003-2160-8608
dc.authorwosidli, feiyang/KHW-5210-2024
dc.authorwosidZhou, Xinyi/KGM-6689-2024
dc.authorwosidWANG, YANAN/KCL-4840-2024
dc.authorwosidren, jun/KHG-7717-2024
dc.authorwosidLiu, Donghua/KEJ-1974-2024
dc.authorwosidxie, jing/KDO-9486-2024
dc.authorwosidHuang, Yong/KFA-1191-2024
dc.contributor.authorKim, Eun-Hu
dc.contributor.authorWang, Zheng
dc.contributor.authorZong, Hao
dc.contributor.authorJiang, Ziwu
dc.contributor.authorFu, Zunwei
dc.contributor.authorPedrycz, Witold
dc.date.accessioned2024-05-19T14:42:37Z
dc.date.available2024-05-19T14:42:37Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractThis article is concerned with designing a tobacco leaves classifier through fuzzy clustering-based neural networks, which leverage multiple histogram analyses of images. The key issue of the study is to recognize high-quality and low-quality tobacco leaves only by using color images obtained from real industrial areas. This study applies multiple histogram analyses from different color spaces as image preprocessing to extract the meaningful features from high-resolution images. Dimensionality reduction is performed through principal component analysis to extract essential features to reduce model complexity and alleviate overfitting problems. In a classifier, we apply fuzzy clustering-based neural networks that incorporate fuzzy clustering techniques, especially fuzzy C-means clustering, along with a cross-entropy loss function and its learning mechanism. The process of setting and training the membership function of node in the hidden layer is substituted with fuzzy C-means clustering. Also, Softmax function produces the model's output in terms of class probabilities. The cost function of the networks is determined using the cross-entropy loss function, while the learning process involves Newton's method-based iterative nonlinear least square error estimation. The experiment validates the competitiveness of the proposed design methodology using real tobacco images obtained from the industry. The performance of the proposed classifier is compared against other classifiers previously reported in the literature to demonstrate its effectiveness.en_US
dc.description.sponsorshipShandong Excellent Young Scientists Fund Program (Overseas) [2023HWYQ-098]; Taishan Young Scholar Experts Project [tsqn202211243]; Basic Science Research Program through the National Research Foundation of Korea - Ministry of Education [2022R1I1A1A01071671]; Key Projects of China Tobacco Corporation [KN266]en_US
dc.description.sponsorshipThis work was supported in part by Shandong Excellent Young Scientists Fund Program (Overseas) under Grant 2023HWYQ-098, in part by Taishan Young Scholar Experts Project under Grant tsqn202211243, in part by the Basic Science Research Program through the National Research Foundation of Korea funded by the Ministry of Education under Grant 2022R1I1A1A01071671, and in part by the Key Projects of China Tobacco Corporation under Grant KN266. Paper no. TII-23-2577.en_US
dc.identifier.doi10.1109/TII.2023.3326533
dc.identifier.endpage4709en_US
dc.identifier.issn1551-3203
dc.identifier.issn1941-0050
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85177075006en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage4698en_US
dc.identifier.urihttps://doi.org10.1109/TII.2023.3326533
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5264
dc.identifier.volume20en_US
dc.identifier.wosWOS:001103664500001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Transactions on Industrial Informaticsen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectImage Color Analysisen_US
dc.subjectHistogramsen_US
dc.subjectFeature Extractionen_US
dc.subjectShapeen_US
dc.subjectNeural Networksen_US
dc.subjectPrincipal Component Analysisen_US
dc.subjectColored Noiseen_US
dc.subjectFuzzy Clusteringen_US
dc.subjectFuzzy Neural Networksen_US
dc.subjectHistogram Analysisen_US
dc.subjectIterative Nonlinear Least Square Erroren_US
dc.titleDesign of Tobacco Leaves Classifier Through Fuzzy Clustering-Based Neural Networks With Multiple Histogram Analyses of Imagesen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu