Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
Search Results
Article Citation - Scopus: 5Hyperplastic and Tubular Polyp Classification Using Machine Learning and Feature Selection(Elsevier B.V., 2024) Doǧan, Refika Sultan; Akay, Ebru; Doǧan, Serkan; Yilmaz, BulentPurpose: The aim of this study is to develop an effective approach for differentiating between hyperplastic and tubular adenoma colon polyps, which is one of the most difficult tasks in colonoscopy procedures. The main research challenge is how to improve the classification of these polyp subtypes applying various focusing levels on the polyp images, data preprocessing approaches, and classification algorithms. Methods: This study employed 202 colonoscopy videos from a total of 201 patients, focusing on 59 videos containing hyperplastic and tubular adenoma polyps. Manually extract key frames and several feature extraction and classification techniques were applied. The influence of different datasets with various focuses as well as data preprocessing steps on the performance of classification was examined, and AUC values were calculated using ten classifiers. Results: The study discovered that the optimal dataset, data preprocessing method, and classification algorithm all had significant effects on classification results. The Random Forest model with the Recursive Feature Elimination (RFE) feature selection approach, for example, consistently outperformed other models and achieved the highest AUC value of 0.9067. In terms of accuracy, F1 score, recall, and AUC, the suggested model outperformed a gastroenterologist, nevertheless precision remained slightly lower. Conclusion: This study emphasizes the importance of dataset selection, data preprocessing, and feature selection in enhancing the classification of difficult colon polyp subtypes. The suggested model offers a promising model for the clinical differentiation of hyperplastic and tubular adenoma polyps, potentially improving diagnostic accuracy in gastroenterology. © 2024 Elsevier B.V., All rights reserved.Article Citation - WoS: 6Citation - Scopus: 6Experimental and Statistical Damage Analysis in Milling of S2-Glass Fiber/Epoxy and Basalt Fiber/Epoxy Composites(Wiley, 2024-07-30) Sayin, Ahmed Cagri; Danisman, Sengul; Ersoy, Emin; Yilmaz, Cagatay; Kesriklioglu, SinanS2-glass fiber reinforced plastics (S2-GFRP) and basalt fiber reinforced plastics (BFRP) have emerged as crucial materials due to their exceptional mechanical properties, and milling of composite materials plays an important role in achieving desired properties. However, they have proven challenges due to relative inhomogeneity compared with metals, resulting unpredictability in quality of milling operations. The objective of this work is to investigate the effect of cutting parameters, tool geometry and tool surface materials on the surface quality of composites using burrs as a metric. S2-GFRP and BFRP composites were produced by the vacuum infusion method. Helical and straight flute end mills were manufactured from high-speed steel (HSS) and carbide rounds, and half of them were coated with titanium nitride using reactive magnetron sputtering technique. Taguchi L18 orthogonal array is used to determine the effect of tool material, tool angle, coating, cutting direction, spindle speed, and feed rate on the machining quality of S2-GFRPs and BFRPs with respect to burr formations. Milling experiments were conducted under dry conditions and then the burrs were imaged to calculate the total area and length. Statistical analysis was also performed to optimize the machining parameters and tool type for ensuring the structural integrity and performance of the final composite parts. The results showed that the selection of tool material has the most significant impact on the burr area and length of the machined surface. The novel image analysis allows to analyze the extent of the burr size with a desirable operation speed for industrial applications.