Yazar "Ucar, M." seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Classification of Different Tympanic Membrane Conditions Using Fused Deep Hypercolumn Features and Bidirectional LSTM
    (Elsevier Science Inc, 2022) Ucar, M.; Akyol, K.; Atila, U.; Ucar, E.
    Objectives: Middle ear inflammatory diseases are global health problem that can have serious consequences such as hearing loss and speech disorders. The high cost of medical devices such as otoendoscope and oto-microscope used by the specialists for the diagnosis of the disease prevents its widespread use. In addition, the decisions of otolaryngologists may differ due to the subjective visual examinations. For this reason, computer-aided middle ear disease diagnosis systems are needed to eliminate subjective diagnosis and high cost problems. To this aim, a hybrid deep learning approach was proposed for automatic recognition of different tympanic membrane conditions such as earwax plug, myringosclerosis, chronic otitis media and normal from the otoscopy images. Materials and methods: In this study we used public Ear Imagery dataset containing 880 otoscopy images. The proposed approach detects keypoints from the otoscopy images and following the obtained keypoint positions, extracts hypercolumn deep features from 5 different layers of the VGG 16 model. Classification of tympanic membrane conditions were realized by feeding the deep hypercolumn features to Bi-LSTM network in the form of non-time related data. Results: The performance of the proposed model was evaluated in three different color spaces as RedGreen-Blue (RGB), Hue-Saturation-Value (HSV) and Haematoxylin-Eosin-Diaminobenzidine (HED). The proposed model achieved acceptable results in all color spaces, moreover it showed a very successful performance in classifying tympanic membrane conditions especially in RGB space. Experimental studies showed that the proposed model achieved Acc of 99.06%, Sen of 98.13% and Spe of 99.38%. Conclusion: As a result, a robust model with high sensitivity was obtained for classification of tympanic membrane conditions and it was shown that Bi-LSTM network, which is generally used with time-related data, could also be used successfully with non-time related data for diagnosis of tympanic membrane conditions.(C) 2021 AGBM. Published by Elsevier Masson SAS. All rights reserved.
  • Küçük Resim Yok
    Öğe
    A novel classification and estimation approach for detecting keratoconus disease with intelligent systems
    (IEEE Computer Society, 2013) Ucar, M.; Sen, B.; Cakmak, H.B.
    Keratoconus is an eye disease characterized by progressive thinning of cornea which is the front based transparent layer of the eye. In other words, it is a progressive distortion of corneal layer and at least getting conical shape that should be like a dome camber. The vision reduces more and more while cornea gets shape of cone which should be like a sphere normally. The aim of this study is to define a new classification method for detecting keratoconus based on statistical analysis and to realize the prediction of these classified data with intelligent systems. 301 eyes of 159 patients and 394 eyes of 265 refractive surgery candidates as the control group have been used for this study. Factor analysis, one of the multivariate statistical techniques, has been mainly used to find more meaningful, easy to understand, and independent factors amongst the others. Later, a new classification method has been defined using clustering analysis techniques on these factors and finally estimated by using artificial neural networks and support vector machines. © 2013 The Chamber of Turkish Electrical Engineers-Bursa.
  • Küçük Resim Yok
    Öğe
    Novel molding technique for ECAP process and effects on hardness of AA7075
    (Kaunas Univ Technol, 2014) Kaya, H.; Ucar, M.; Cengiz, A.; Samur, R.; Ozyurek, D.; Caliskan, A.
    In this study, a novel Equal channel angular pressing (ECAP) die which named Hexa die, designed and manufactured in order to reduce process duration and eliminate manual sample rotation problems. For this reason, the surfaces of die was machined to get the cylindrical channels be able to extract out of ECAP samples. These channels provide 100% accuracy for angular routes for cylindrical samples. Experiments are carried out with the same sample materials (AA7075) at a constant temperature (210 degrees C) and C rotation. In the study, process time scenarios for traditional and novel Hexa die techniques have been compared in a theoretical time table. It has been shown that Hexa die has crucial time advantages in order to eliminating the old die process steps such as cooling and reheating time, disassembly and re-assembly of the dies, manually rotation of samples and many of others. And finally ECAP'ed samples hardness have been measured.