Omer Deperlioglu | Afyon Kocatepe University (original) (raw)
Papers by Omer Deperlioglu
Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, Jun 1, 2010
Mühendislik bilimleri ve tasarım dergisi, Mar 27, 2023
DergiPark (Istanbul University), Dec 1, 2001
DergiPark (Istanbul University), Jun 1, 2009
BRAIN. Broad Research in Artificial Intelligence and Neuroscience, May 8, 2018
Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, Dec 1, 2001
INTERNATIONAL JOURNAL OF INFORMATICS TECHNOLOGIES, 2009
Turkiye uzaktan egitim uygulamasina yeni adapte olmus ve hizli bir sekilde gundemine alarak kulla... more Turkiye uzaktan egitim uygulamasina yeni adapte olmus ve hizli bir sekilde gundemine alarak kullanima baslamistir. Universiteler bu uygulamanin en cok yapildigi egitim kurumlarindan biridir, ancak her kurum kendi ogrenim yonetim sistemini (OYS) kullanmaktadir. Şimdiye kadar SCORM standartlarina uyumlu, her ders ve konu modeline uygun, evrensel ve herkesin faydalanabilecegi tam iliskisel bir veritabani tasarimi yapilmamistir. Bu calismada Microsoft SQL Server 2005 veritabani tasarim yazilimi kullanilarak tum ogretim yonetim sistemleri icin tam iliskisel evrensel bir veritabani tasarlanmistir. Veri tabani her kurum ve kurulusa uyumludur, ayrica yonetimi kolay 153 tablo ile her ders icin uyarlanabilir. OYS Veritabani tam iliskisel evrensel bir veritabanidir ve ogrenci kaydi, kullanici rolleri, dersler, sinavlar, guvenlik girisleri ve sorgulamalar vb. gibi bircok uygulamayi icermektedir. Bu veritabanina Windows form veya WEB formu gibi farkli ara-yuzler istenildigi sekilde uyarlanabilme...
Elsevier eBooks, 2021
Abstract The most prominent research area in the field of advanced machine vision paradigm for me... more Abstract The most prominent research area in the field of advanced machine vision paradigm for medical imaging applications is brought by the content-based image retrieval (CBIR) technique. With the help of emerging medical imaging systems, a patient's medical background can be easily obtained in the form of digitized data such as X-rays, magnetic resonance imaging (MRI), computed tomography, ultrasound, nuclear imaging, and so on. In the past, radiologists manually analyzed the patient's health condition. Now, the medical imaging process provides better information and depiction of the different cases. However, the conventional techniques have created some controversies among the various literatures including insufficient feature set, high semantic gap, and computational time complexity. The methods we have used for content retrieval are gray-level cooccurrence matrix, local binary pattern, color cooccurrence matrix, and support vector machine. MRI data were used for the completion of texture and shape-based retrieval. On improvising the previously ordained results, an algorithm is proposed using semantic image retrieval-based CBIR by combining three-dimensional features. This chapter also emphasizes a detailed comparative analysis of various techniques with the proposed method.
Future Generation Computer Systems, Apr 1, 2022
Nowadays, neural networks have a remarkable importance for medical applications. Because of their... more Nowadays, neural networks have a remarkable importance for medical applications. Because of their advantages such as dealing changing amount of data and resulting to higher accuracies at the end, they are widely used for especially medical diagnosis. At this point, there are different kinds of neural networks already provided successful results to the literature. In this study, it is explained that the classification rate (considering the medical diagnosis) can be increased by using intelligent optimization for feature selection and Autoencoder Based Recurrent Neural Network for performing the diagnosis. In this context, the Electro-Search Algorithm (ES) and Autoencoder Based Recurrent Neural Network (ARNN) have been employed for ensuring practical diagnosis over some known disease data sets from the active literature. The obtained findings by the ES-ARNN approach were compared with the findings by alternative techniques. Along the related evaluations, it was seen that the ES-ARNN resulted to high classification success rates for target medical diagnosis data sets and it also had higher diagnosing rates according to alternative techniques. The study also reports some real world experiences from physicians used the introduced solution over original data.
Applied Mathematics & Information Sciences, 2015
Interdisciplinary journal of e-skills and lifelong learning, 2012
Approaches performed based on computer supported systems within the medical field gain more popul... more Approaches performed based on computer supported systems within the medical field gain more popularity day by day. In such systems, Artificial Intelligence techniques are often used for several disease diagnostics. Diabetes is one of these diseases. In this study, a diabetes diagnosis system based on Support Vector Machines has been proposed. Along training of SVM, Vortex Optimization Algorithm was used for determining the sigma parameter of the Gauss (RBF) kernel function, and a classification process has been done over the diabetes data set related to Pima Indians.
2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Oct 1, 2018
Diabetic retinopathy is a serious eye disease that originates from diabetes mellitus and is the m... more Diabetic retinopathy is a serious eye disease that originates from diabetes mellitus and is the most common cause of blindness in the developed countries. This study describes the use of image processing and deep learning to diagnose diabetic retinopathy from retinal fundus images. For retinal fundus images enhancement approach, a practical method which contains HSV, V transform algorithm and histogram equalization technics was used. Finally, Gaussian low-pass filter was applied to the retinal fundus image. After the image processing, the classification was made using the Convolutional Neural Network. The performance of the proposed method was assessed using 400 retinal fundus images in the Kaggle Diabetic Retinopathy Detection database. In experiments, classification work has been done for each stage of the image processing. The classification study performed after image processing. Twenty experiments were done for every stage and average values were found. In this experiment, the accuracy was 97%, the sensitivity was 96.67%, the specificity was 93.33%, the precision was 97.78%, the recall was 93.33%, and the Fscore was 93.33%. The obtained results show that the proposed method is very efficient and successful to diagnose diabetic retinopathy from retinal fundus images.
Zenodo (CERN European Organization for Nuclear Research), Feb 5, 2016
Studies in computational intelligence, Jun 18, 2020
The humankind has always found its way on solving problems in the real-world, by using tools and ... more The humankind has always found its way on solving problems in the real-world, by using tools and deriving solution scenarios. As the more tools designed and developed by humans, the more effective solutions and new kinds of tools for better solutions were obtained always. Eventually, the humankind started to use the concept of technology for defining all kinds of knowledge and skills employed for designing as well developing solutions for different fields.
Studies in computational intelligence, Jun 18, 2020
Advanced technologies for processing data gathered from the real world are widely used for improv... more Advanced technologies for processing data gathered from the real world are widely used for improving tasks in different fields of the life. After especially rise of computer and communication technologies, it has been important to process the data rapidly and reach to automated decisions for making some tasks more practical in the digital world.
Studies in computational intelligence, Jun 18, 2020
Nowadays, the majority of human deaths are from heart diseases. For this reason, many studies hav... more Nowadays, the majority of human deaths are from heart diseases. For this reason, many studies have been done to improve the early diagnosis of heart diseases and to reduce deaths. These studies are mostly aimed at developing computer-aided diagnostic systems using the developing technology. Some computer-aided systems are clinical decision support systems that are developed to more easily detect heart disease than heart sounds or related data
Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, Jun 1, 2010
Mühendislik bilimleri ve tasarım dergisi, Mar 27, 2023
DergiPark (Istanbul University), Dec 1, 2001
DergiPark (Istanbul University), Jun 1, 2009
BRAIN. Broad Research in Artificial Intelligence and Neuroscience, May 8, 2018
Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, Dec 1, 2001
INTERNATIONAL JOURNAL OF INFORMATICS TECHNOLOGIES, 2009
Turkiye uzaktan egitim uygulamasina yeni adapte olmus ve hizli bir sekilde gundemine alarak kulla... more Turkiye uzaktan egitim uygulamasina yeni adapte olmus ve hizli bir sekilde gundemine alarak kullanima baslamistir. Universiteler bu uygulamanin en cok yapildigi egitim kurumlarindan biridir, ancak her kurum kendi ogrenim yonetim sistemini (OYS) kullanmaktadir. Şimdiye kadar SCORM standartlarina uyumlu, her ders ve konu modeline uygun, evrensel ve herkesin faydalanabilecegi tam iliskisel bir veritabani tasarimi yapilmamistir. Bu calismada Microsoft SQL Server 2005 veritabani tasarim yazilimi kullanilarak tum ogretim yonetim sistemleri icin tam iliskisel evrensel bir veritabani tasarlanmistir. Veri tabani her kurum ve kurulusa uyumludur, ayrica yonetimi kolay 153 tablo ile her ders icin uyarlanabilir. OYS Veritabani tam iliskisel evrensel bir veritabanidir ve ogrenci kaydi, kullanici rolleri, dersler, sinavlar, guvenlik girisleri ve sorgulamalar vb. gibi bircok uygulamayi icermektedir. Bu veritabanina Windows form veya WEB formu gibi farkli ara-yuzler istenildigi sekilde uyarlanabilme...
Elsevier eBooks, 2021
Abstract The most prominent research area in the field of advanced machine vision paradigm for me... more Abstract The most prominent research area in the field of advanced machine vision paradigm for medical imaging applications is brought by the content-based image retrieval (CBIR) technique. With the help of emerging medical imaging systems, a patient's medical background can be easily obtained in the form of digitized data such as X-rays, magnetic resonance imaging (MRI), computed tomography, ultrasound, nuclear imaging, and so on. In the past, radiologists manually analyzed the patient's health condition. Now, the medical imaging process provides better information and depiction of the different cases. However, the conventional techniques have created some controversies among the various literatures including insufficient feature set, high semantic gap, and computational time complexity. The methods we have used for content retrieval are gray-level cooccurrence matrix, local binary pattern, color cooccurrence matrix, and support vector machine. MRI data were used for the completion of texture and shape-based retrieval. On improvising the previously ordained results, an algorithm is proposed using semantic image retrieval-based CBIR by combining three-dimensional features. This chapter also emphasizes a detailed comparative analysis of various techniques with the proposed method.
Future Generation Computer Systems, Apr 1, 2022
Nowadays, neural networks have a remarkable importance for medical applications. Because of their... more Nowadays, neural networks have a remarkable importance for medical applications. Because of their advantages such as dealing changing amount of data and resulting to higher accuracies at the end, they are widely used for especially medical diagnosis. At this point, there are different kinds of neural networks already provided successful results to the literature. In this study, it is explained that the classification rate (considering the medical diagnosis) can be increased by using intelligent optimization for feature selection and Autoencoder Based Recurrent Neural Network for performing the diagnosis. In this context, the Electro-Search Algorithm (ES) and Autoencoder Based Recurrent Neural Network (ARNN) have been employed for ensuring practical diagnosis over some known disease data sets from the active literature. The obtained findings by the ES-ARNN approach were compared with the findings by alternative techniques. Along the related evaluations, it was seen that the ES-ARNN resulted to high classification success rates for target medical diagnosis data sets and it also had higher diagnosing rates according to alternative techniques. The study also reports some real world experiences from physicians used the introduced solution over original data.
Applied Mathematics & Information Sciences, 2015
Interdisciplinary journal of e-skills and lifelong learning, 2012
Approaches performed based on computer supported systems within the medical field gain more popul... more Approaches performed based on computer supported systems within the medical field gain more popularity day by day. In such systems, Artificial Intelligence techniques are often used for several disease diagnostics. Diabetes is one of these diseases. In this study, a diabetes diagnosis system based on Support Vector Machines has been proposed. Along training of SVM, Vortex Optimization Algorithm was used for determining the sigma parameter of the Gauss (RBF) kernel function, and a classification process has been done over the diabetes data set related to Pima Indians.
2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Oct 1, 2018
Diabetic retinopathy is a serious eye disease that originates from diabetes mellitus and is the m... more Diabetic retinopathy is a serious eye disease that originates from diabetes mellitus and is the most common cause of blindness in the developed countries. This study describes the use of image processing and deep learning to diagnose diabetic retinopathy from retinal fundus images. For retinal fundus images enhancement approach, a practical method which contains HSV, V transform algorithm and histogram equalization technics was used. Finally, Gaussian low-pass filter was applied to the retinal fundus image. After the image processing, the classification was made using the Convolutional Neural Network. The performance of the proposed method was assessed using 400 retinal fundus images in the Kaggle Diabetic Retinopathy Detection database. In experiments, classification work has been done for each stage of the image processing. The classification study performed after image processing. Twenty experiments were done for every stage and average values were found. In this experiment, the accuracy was 97%, the sensitivity was 96.67%, the specificity was 93.33%, the precision was 97.78%, the recall was 93.33%, and the Fscore was 93.33%. The obtained results show that the proposed method is very efficient and successful to diagnose diabetic retinopathy from retinal fundus images.
Zenodo (CERN European Organization for Nuclear Research), Feb 5, 2016
Studies in computational intelligence, Jun 18, 2020
The humankind has always found its way on solving problems in the real-world, by using tools and ... more The humankind has always found its way on solving problems in the real-world, by using tools and deriving solution scenarios. As the more tools designed and developed by humans, the more effective solutions and new kinds of tools for better solutions were obtained always. Eventually, the humankind started to use the concept of technology for defining all kinds of knowledge and skills employed for designing as well developing solutions for different fields.
Studies in computational intelligence, Jun 18, 2020
Advanced technologies for processing data gathered from the real world are widely used for improv... more Advanced technologies for processing data gathered from the real world are widely used for improving tasks in different fields of the life. After especially rise of computer and communication technologies, it has been important to process the data rapidly and reach to automated decisions for making some tasks more practical in the digital world.
Studies in computational intelligence, Jun 18, 2020
Nowadays, the majority of human deaths are from heart diseases. For this reason, many studies hav... more Nowadays, the majority of human deaths are from heart diseases. For this reason, many studies have been done to improve the early diagnosis of heart diseases and to reduce deaths. These studies are mostly aimed at developing computer-aided diagnostic systems using the developing technology. Some computer-aided systems are clinical decision support systems that are developed to more easily detect heart disease than heart sounds or related data