17 results on '"Aksebzeci, Bekir Hakan"'
Search Results
2. Computer-Aided classification of breast cancer histopathological images Meme kanseri histopatolojik göröntölerinin bilgisayar destekli siniflandirilmasi
- Author
-
AKSEBZECİ, BEKİR HAKAN and Kayaalti, Omer
- Abstract
© 2017 IEEE.Nowadays, one of the most common types of cancer is breast cancer. The early and accurate diagnosis of breast cancer has great importance in the treatment of the disease. In the diagnosis of breast cancer, histopathological analysis of cell and tissue specimens taken by biopsy is considered as the gold standard. Histopathological analysis is a tedious process that is highly dependent on the knowledge and experience of the pathologists. In this study; it is aimed to develop a computer-Aided system that can reduce the workload of pathologists and help them in their diagnosis. An image set containing benign and malignant tumor images of breast cancer has been studied. To perform texture analysis on tumor images; first order statistics, Gabor and gray-level co-occurrence matrix (GLCM) feature extraction methods have been applied. Then, various classifiers were applied to the obtained feature matrices and their performances were compared. The highest classification accuracy was achieved 82.06% by Random Forests classifier with feature combination of Gabor and GLCM methods. The results presented here show that computer-Assisted diagnosis of breast cancer is a promising field.
- Published
- 2017
3. Relationship Between Neutrophil Gelatinase-associated Lipocalin and Mortality in Acute Kidney Injury
- Author
-
Kayaaltı, Selda, primary, Kayaaltı, Ömer, additional, and Aksebzeci, Bekir Hakan, additional
- Published
- 2018
- Full Text
- View/download PDF
4. A decision support system for the prediction of mortality in patients with acute kidney injury admitted in intensive care unit.
- Author
-
Kayaaltı, Selda, Kayaaltı, Ömer, and Aksebzeci, Bekir Hakan
- Subjects
ACUTE kidney failure ,REGRESSION trees ,LACTATE dehydrogenase ,LIPOCALIN-1 ,ALKALINE phosphatase - Abstract
Intensive care unit (ICU) is a very special unit of a hospital, where healthcare professionals provide treatment and, later, close followup to the patients. It is crucial to estimate mortality in ICU patients from many viewpoints. The purpose of this study is to classify the status of patients with acute kidney injury (AKI) in ICU as early mortality, late mortality, and survival by the application of Classification and Regression Trees (CART) algorithm to the patients' attributes such as blood urea nitrogen, creatinine, serum and urine neutrophil gelatinase-associated lipocalin (NGAL), alkaline phosphatase, lactate dehydrogenase (LDH), gamma-glutamyl transferase, laboratory electrolytes, blood gas, mean arterial pressure, central venous pressure and demographic details of patients. This study was conducted 50 patients with AKI who were followed up in the ICU. The study also aims to determine the significance of relationship between the attributes used in the prediction of mortality in CART and patients' status by employing the Kruskal--Wallis H test. The classification accuracy, sensitivity, and specificity of CART for the tested attributes for the prediction of early mortality, late mortality, and survival of patients were 90.00%, 83.33%, and 91.67%, respectively. The values of both urine NGAL and LDH on day 7 showed a considerable difference according to the patients' status after being examined by the Kruskal--Wallis H test. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF
5. Computer-aided classification of breast cancer histopathological images
- Author
-
Aksebzeci, Bekir Hakan, primary and Kayaalti, Omer, additional
- Published
- 2017
- Full Text
- View/download PDF
6. Akut Böbrek Hasarında Nötrofil Jelatinaz İlişkili Lipokalin ile Mortalite İlişkisi.
- Author
-
Kayaaltı, Selda, Kayaaltı, Ömer, and Aksebzeci, Bekir Hakan
- Subjects
CENTRAL venous pressure ,INTENSIVE care patients ,BLOOD urea nitrogen ,INTENSIVE care units ,ACUTE kidney failure - Abstract
Copyright of Turkish Journal of Intensive Care is the property of Galenos Yayinevi Tic. LTD. STI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
- Published
- 2018
- Full Text
- View/download PDF
7. Staging of The Liver Fibrosis From Ct Images Using Texture
- Author
-
YILMAZ, Bülent, ASYALI, Musa Hakan, ÖZTÜRK, Mehmet, KAYAALTI, Ömer, KARAHAN, Ökkeş Ibrahim, AKSEBZECİ, Bekir Hakan, DENİZ, Kemal, and KARA, Sadık
- Published
- 2012
8. KÖK KANALLARINDA SIKLIKLA GÖRÜLEN ÜÇ MİKROORGANİZMANIN ELEKTRONİK BURUN SİSTEMİ KULLANILARAK SINIFLANDIRILMASI
- Author
-
KAHRAMAN, Yasemin, AKSEBZECİ, Bekir Hakan, KAYA, Esma, ER, Özgür, and ÖZBİLGE, Hatice
- Subjects
otorhinolaryngologic diseases ,Electronic nose,root canal infection,microbiology,bacteria,fungi ,Elektronik burun,kök kanal enfeksiyonu,mikrobiyoloji,bakteri,mantar - Abstract
Pulpa ve periradiküler doku hastalıklarının çoğu hem aerop hem de anaerop mikroorganizmaları içeren karışık bir mikroflora ile ilişkilidir. Hekim tedavi ile ilgili etkili bir yöntem belirleyebilmek için mikroorganizma varlığı ile endodontik hastalık arasındaki yakın ilişkiyi kavramalıdır. Endodontik enfeksiyonlardaki bakteri türlerini ortaya çıkarmak kullanılmaktadır. Son yıllarda moleküler yöntemlerdeki gelişmelere rağmen her iki metodun da bir takım dezavantajları bulunmaktadır. Elektronik burun (EB) terimi, insan koku duyusunu taklit edebilen bir elektronik sistemi tanımlar. Elektronik burun sistemleri tıp alanında ve kullanılmaktadır. Bu sistemlerinin en önemli özelliği, koku çeşitlerini çok kısa bir süre içerisinde insan burnundaki hassasiyet derecesinde algılayıp ayrıştırabilmesi ve sonucu objektif olarak sunmasıdır. Bu çalışmada, kök kanal mikroorganizma türünün saf kültüründen elektronik burun sistemi kullanılarak koku verileri alınmıştır. Bu veriler Ayırma sınıflandırılmış, Mahalanobis ve ikinci dereceden fonksiyonlar (quadratic) olmak üzere 3 ayrı metodun performansı incelenmiştir. Mahalanobis ve ikinci dereceden fonksiyonlar kullanarak gerçekleştirilen AA ile sınıflandırmada % 100 başarı elde edilmiştir. Bu çalışma ile EB cihazının, mikroorganizma süspansiyonlarının araştırılmıştır, Most diseases of pulp and periradicular tissues are associated with mixed microflora including both aerobic and anaerobic microorganisms. Clinicians must understand the close relationship between the presence of microorganisms and endodontic disease process to determine an effective procedure with respect to the treatment. Culture and molecular methods are used to detect bacterial species in root canal infections. Despite the advances in molecular methods recently, both the culture and the molecular methods have several disadvantages. The term electronic nose describes an electronic system that is able to mimic the human sense of smell. Electronic nose systems have already been used with success in the medical science and microbiological research. The most important property of electronic nose systems is the ability to detect different odour types in a short period of time with almost sensivity of human nose. Furthermore, the result of process using electronic nose system is objective. In this study, odour data was taken by using an electronic nose equipment from pure cultures of three microorganisms which are frequently seen in root canal infections.These datas were classified using Discriminant Analysis (DA) and investigated the performance of several subtypes of DA algorithm namely linear, Mahalanobis and quadratic. The success rate acquired from the classification using Mahalonobis and quadratic approach of DA was 100%. In this study, the use of electronic nose in the classifacation of microorganism suspensions was investigated
- Published
- 2011
9. Mikroorganizmaların elektronik burun teknolojisi kullanılarak tanımlanması ve sınıflandırılması
- Author
-
Aksebzeci, Bekir Hakan, Asyalı, Musa Hakan, Kara, Sadık, and Elektrik-Elektronik Mühendisliği Anabilim Dalı
- Subjects
Elektrik ve Elektronik Mühendisliği ,Electrical and Electronics Engineering - Abstract
Enfeksiyon hastalıklarının tedavisinde, enfeksiyona yol açan hastalık etkeni patojen mikroorganizmanın, en kısa sürede doğru olarak tanımlanması büyük öneme sahiptir. Bazı durumlarda patojen mikroorganizmaların tanımlanması; zahmetli ve zaman alıcı olabilmektedir. Bundan dolayı araştırmacılar, patojen mikroorganizmaları rutin mikrobiyolojik tekniklere göre daha hızlı tespit edebilen yöntemler üzerine yönelmişlerdir. Bu yöntemlerden birisi de, mikroorganizma kültürlerinin ortama yaydıkları kokulardan yararlanarak, elektronik burun cihazı ile mikroorganizma türünün tespiti üzerinedir.Bu tezde; üç ayrı mikroorganizma seti üzerinde, elektronik burun cihazı kullanılarak, mikroorganizma türüne göre sınıflandırma çalışmaları yapılmıştır. Mikroorganizma setlerinden birincisi, çeşitli enfeksiyon hastalıklarına sebep olan ve rutinde sıklıkla karşılaşılan 8 mikroorganizmadan meydana gelmektedir. İkinci ve üçüncü setler ise, diş kök kanal enfeksiyonlarına sebep olan 7 mikroorganizmadan oluşmaktadır. Mikroorganizma setlerinden elektronik burun cihazı ile elde edilen koku verilerine, sınıflandırma performansına etkilerini incelemek amacıyla; farklı veri ön-işleme, boyut azaltım ve ölçekleme yöntemleri uygulanmıştır. Sınıflandırma aşamasında ise; k-en yakın komşuluk algoritması (k-NN), Ayırma Analizi (DA) ve Destek Vektör Makineleri (SVM) yöntemleri kullanılmıştır.Bu tez kapsamında gerçekleştirilen çalışmalarda, en başarılı sınıflandırma sonuçlarının genellikle SVM yöntemi ile sağlandığı görülmüştür. Elde edilen sonuçlar, patojen mikroorganizmaların tespitinde, elektronik burun cihazının rutin mikrobiyolojik tekniklere alternatif veya destekleyici bir yöntem olarak kullanılabileceğini göstermiştir. In the treatment of infectious diseases, as soon as the correct identification of pathogenic microorganisms that cause infection, has a great importance. In some cases, identification of pathogenic microorganisms can be laborious and time consuming. Therefore, researchers have tried to improve methods that can detect pathogenic microorganisms more rapidly than the routine microbiological techniques. One of these methods is the identification of microorganism species using an electronic nose device by means of the culture odors that they emit to environment.In this thesis, classification studies were carried out according to the species of microorganism on the 3 different microorganism sets using an electronic nose device. The first of microorganism sets consists of 8 microorganisms which cause various infectious diseases and are frequently encountered in routine. Both the second and third sets were comprised of the 7 microorganisms which caused root canal infections. Odor data which were obtained from microorganism sets using the electronic nose device were applied to different data pre-processing, dimension reduction, and scaling methods in order to investigate the effects on classification performance. In classification stage, k-nearest neighbor algorithm (k-NN), Discriminant Analysis (DA) and Support Vector Machines (SVM) methods were used.In studies within the scope of this thesis, the most successful classification results have been generally obtained by SVM method. The results obtained have shown that electronic nose devices can be used as an alternative or supportive method of routine microbiological techniques in identification of pathogenic microorganisms. 122
- Published
- 2011
10. Kök Kanallarında Sıklıkla Görülen Üç Mikroorganizmanın Elektronik Burun Sistemi Kullanılarak Sınıflandırılması
- Author
-
ÖZBİLGE, HATİCE, ER, ÖZGÜR, KAYA, ESMA, AKSEBZECİ, BEKİR HAKAN, and KAHRAMAN, YASEMİN
- Published
- 2011
11. Aritmi Sınıflandırmada Kullanılan Yapay Sinir Ağlarının Karmaşıklığının Azaltılması
- Author
-
DANIŞMAN, Kenan, ÖZDEMİR, Ahmet Turan, Asyalı, Hakan Musa, and Aksebzeci, Bekir Hakan
- Abstract
Aritmi insan kalbindeki ritim bozukluğunu ifade etmektedir. Elektrokardiyogram kayıtlarından aritmilerin belirlenmesi, kalp rahatsızlıkların teşhis ve tedavinin sonuçlarının takibi açısından önemlidir. Yapay Sinir Ağları (YSA) aritmi sınıflandırmada kullanılan çok yaygın bir yöntemdir. Bu konuda yapılmış birçok çalışma bulunmaktadır. Bu çalışmalarda genellikle onlarca hatta bazen yüzlerce giriş nöronundan ve çok sayıda ara katmandan oluşan YSA modelleri önerilmektedir. Neticede işlemsel karmaşıklığı yüksek bu YSA modelleri ancak çevrimdışı olarak, pahalı işlemciler üzerinde çalıştırılabilir. Böyle modellerin, yoğun bakım ve acil üniteleri gibi anında karar verme gerektiren gerçek zamanlı (çevrimiçi) uygulamalarda kullanılması ise zordur. Bu çalışmada sınıflandırma hata oranını %2-3 gibi kabul edilebilir bir seviyede tutarak, YSA karmaşıklığını azaltmayı hedefledik. Giriş sayısını azaltmak için temel bileşen analizi kullandık. MIT BIH veritabanından elde edilen veriler üzerinde yaptığımız çalışmalar sonucunda, 5 girişli 4 neronlu tek ara katman kullanan bir YSA yapısının yeterli olduğunu belirledik. Bu optimal yapı, alan programlanabilir kapı dizileri üzerinde kolayca gerçekleştirilebilecektir. Bu da gerçek zamanlı, düşük güç tüketimli ve mobil aritmi detektörlerinin donanım gerçeklemeleri için kolaylık sağlayacaktır., Arrhythmias that can be captured on the electrocardiogram signal, correspond to creation heart diseases. Therefore detection of arrhythmias is an important issue for the diagnosis and treatment follow-up of such diseases. Artificial Neural Networks (ANN) is a commonly used tool for detection and classification of arrhythmias. There exist plenty of studies in the literature, concerning ANN based arrhythmia detection. However, the suggested ANN architectures are quite complex, involving hundreds of inputs and many hidden layers. Consequently, these models with high computational complexity can only be run offline, on relatively expensive processors. This approach is not practical for emergency and intensive care applications which demand high speed online processing and decision making capability. In this study, we aimed at reducing the complexity of the ANN model, while keeping the classification error rate at an acceptable level (e.g., 2-3 %). We used principal component analysis to decrease the number of inputs. The results of the trials that we have carried on MIT BIH data indicate that an ANN with 5 inputs a single hidden layer with 4 neurons is sufficient. This optimal ANN architecture can easily be implemented on a field programmable gate array which offers advantages such as high speed, low power consumption, and suitability for mobile applications.
- Published
- 2008
12. E-burun sistemi kullanılarak çeşitli mikroorganizmaların ana bileşenler metodu ile analizi
- Author
-
HIZLISOY, Harun, Aksebzeci, Bekir Hakan, Kara, Sadık, and ÖZBİLGE, Hatice
- Published
- 2006
13. Bir asansör kontrol sisteminin petri netler yardımıyla modellenmesi ve xilinx XC2S200E FPGA'sı ile gerçekleştirilmesi
- Author
-
Aksebzeci, Bekir Hakan, Uzam, Murat, and Elektrik-Elektronik Mühendisliği Ana Bilim Dalı
- Subjects
Elektrik ve Elektronik Mühendisliği ,Electrical and Electronics Engineering - Abstract
ÖZET BİR ASANSÖR KONTROL SİSTEMİNİN PETRİ NETLER YARDIMIYLA MODELLENMESİ VE XILINX XC2S200E FPGA'SI İLE GERÇEKLEŞTİRİLMESİ AKSEBZECİ, Bekir Hakan Niğde Üniversitesi Fen Bilimleri Enstitüsü Elektrik - Elektronik Mühendisliği Anabilim Dalı Danışman: Doç. Dr. Murat UZAM Temmuz 2005, 125 Sayfa Bu çalışmanın amacı, dört katlı bir model asansör için gerekli olan kontrol sisteminin, Petri netler yardımıyla modelienmesi ve bir Xilinx XC2S200E FPGA'sı ile gerçekleştirilmesidir. Bu çalışmada bir asansör kontrol sistemini incelemek amacıyla, dört katlı bir model asansör kullanılmıştır. Bu model asansör için gerekli olan kontrol sisteminin modellenmesinde Otomasyon Petri netlerin bir alt kümesi olan Basit Otomasyon Petri netlerden (BOPN) faydalanılmıştır. BOPN'lerin tercih edilmesinin sebebi; bir kontrol sisteminin görsel bir biçimde modellenebilmesi ve elde edilen BOPN modellerinin kolaylıkla gerçekleştirilebilmesidir. Bu çalışmada, model asansörün toplamasız ve toplamalı olarak kontrolü için iki ayrı BOPN modeli tasarlanmıştır. Tasarlanan bu BOPN modelleri, VHDL diline çevrilerek, Xilinx XC2S200E FPGA'sında ayrı ayrı sentezlenmiş ve model asansör başarıyla kontrol edilmiştir. Anahtar sözcükler: Asansör kontrolü, Petri net, FPGA, VHDL 111 SUMMARY MODELLING AN ELEVATOR CONTROL SYSTEM USING PETRI NETS AND ITS IMPLEMENTATION BY MEANS OF A XILINX XC2S200E FPGA AKSEBZECİ, Bekir Hakan Niğde University Institute of Natural and Applied Sciences Department of Electrical and Electronics Engineering Supervisor: Assoc. Prof. Dr. Murat UZAM July 2005, 125 pages The aim of this work is to model a control system necessary for a four storey elevator model and to implement it by using a Xilinx XC2S200E FPGA. In this work, in order to study an elevator control system, a four storey elevator model is utilized. To model the control system, necessary for controlling this elevator model, simple automation Petri nets (SAPN), which are a sub-set of automation Petri nets, are used. The first reason for chosing SAPNs is that they allow us to visualize the control system. The second one is that it is easy to implement SAPN models. In this study, two SAPN models are designed to control the elevator model for two different operation scenarios, namely traditional and collective type. These two SAPN models are then synthesized seperately with a Xilinx XC2S200E FPGA by using VHDL language. Finally, the elevator model is controlled successfully. Keywords: Elevator control Petri net, FPGA, VHDL iv 141
- Published
- 2005
14. Design and implementation of a voice-controlled prosthetic hand
- Author
-
ASYALI, MUSA HAKAN, primary, YILMAZ, MUSTAFA, primary, TOKMAKÇI, MAHMUT, primary, SEDEF, KANBER, primary, AKSEBZECİ, BEKİR HAKAN, primary, and MITTAL, ROHIN, primary
- Published
- 2011
- Full Text
- View/download PDF
15. Classification of microorganism species using Discriminant Analysis
- Author
-
Aksebzeci, Bekir Hakan, primary, Kara, Sadik, additional, Asyali, Musa Hakan, additional, Kahraman, Yasemin, additional, Er, Ozgur, additional, Kaya, Esma, additional, and Ozbilge, Hatice, additional
- Published
- 2009
- Full Text
- View/download PDF
16. Liver fibrosis staging using CT image texture analysis and soft computing.
- Author
-
Kayaaltı, Ömer, Aksebzeci, Bekir Hakan, Karahan, İbrahim Ökkeş, Deniz, Kemal, Öztürk, Mehmet, Yılmaz, Bülent, Kara, Sadık, and Asyalı, Musa Hakan
- Subjects
LIVER disease diagnosis ,COMPUTED tomography ,TEXTURE analysis (Image processing) ,DIGITAL image processing ,MEDICAL imaging systems ,SOFT computing ,ULTRASONIC imaging - Abstract
Liver biopsy is considered to be the gold standard for analyzing chronic hepatitis and fibrosis; however, it is an invasive and expensive approach, which is also difficult to standardize. Medical imaging techniques such as ultrasonography, computed tomography (CT), and magnetic resonance imaging are non-invasive and helpful methods to interpret liver texture, and may be good alternatives to needle biopsy. Recently, instead of visual inspection of these images, computer-aided image analysis based approaches have become more popular. In this study, a non-invasive, low-cost and relatively accurate method was developed to determine liver fibrosis stage by analyzing some texture features of liver CT images. In this approach, some suitable regions of interests were selected on CT images and a comprehensive set of texture features were obtained from these regions using different methods, such as Gray Level Co-occurrence matrix (GLCM), Laws’ method, Discrete Wavelet Transform (DWT), and Gabor filters. Afterwards, sequential floating forward selection and exhaustive search methods were used in various combinations for the selection of most discriminating features. Finally, those selected texture features were classified using two methods, namely, Support Vector Machines (SVM) and k -nearest neighbors ( k -NN). The mean classification accuracy in pairwise group comparisons was approximately 95% for both classification methods using only 5 features. Also, performance of our approach in classifying liver fibrosis stage of subjects in the test set into 7 possible stages was investigated. In this case, both SVM and k -NN methods have returned relatively low classification accuracies. Our pairwise group classification results showed that DWT, Gabor, GLCM, and Laws’ texture features were more successful than the others; as such features extracted from these methods were used in the feature fusion process. Fusing features from these better performing families further improved the classification performance. The results show that our approach can be used as a decision support system in especially pairwise fibrosis stage comparisons. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
17. Asynchronous implementation of discrete event controllers based on safe automation Petri nets
- Author
-
Gökhan Gelen, B. Hakan Aksebzeci, I. Burak Koç, Murat Uzam, Uzam, Murat -- 0000-0001-9625-5523, Aksebzeci, Bekir Hakan -- 0000-0001-7476-8141, [Uzam, Murat -- Koc, I. Burak -- Gelen, Goekhan -- Aksebzeci, B. Hakan] Nigde Univ, Muhendislik Mimarlik Fak, Elekt Elekt Muhendisligi Bolumu, TR-51200 Nigde, Turkey, and 0-Belirlenecek
- Subjects
Discrete event systems ,business.industry ,Computer science ,Event (computing) ,Mechanical Engineering ,Hardware implementation ,Field programmable gate arrays (FPGA) ,Programmable logic controller ,Petri nets ,Petri net ,Automation ,Industrial and Manufacturing Engineering ,Computer Science Applications ,Control and Systems Engineering ,Asynchronous communication ,Control theory ,Embedded system ,Control system ,Manufacturing systems ,business ,Field-programmable gate array ,Discrete event control system ,Implementation ,Software - Abstract
WOS: 000263897600018, In this paper, a new method is proposed for digital hardware implementation of Petri net-based specifications. The purpose of this paper is to introduce a new discrete event control system paradigm, where the control system is modeled with extended Petri nets and implemented as an asynchronous controller using circuit elements. The applicability of the proposed method is demonstrated by an asynchronous implementation of a Petri net-based discrete event control system (DECS) for an experimental manufacturing system using a Xilinx field programmable gate array (FPGA). Unlike microprocessor, microcontroller or programmable logic controller (PLC)-based software implementations or hardware-based synchronous implementations, the implementation method used in this paper is asynchronous and based on hardware offering very high speed to control fast plants at low cost. This paper is expected to serve as a guideline to show how to obtain very high speed, concurrent and asynchronous Petri net-based controllers.
- Published
- 2008
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.