Yazar "Elen, Abdullah" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An Application to Control Media Player with Voice Commands(Gazi Univ, 2020) Avuclu, Emre; Ozcifci, Ayhan; Elen, AbdullahUsing technology today is of great importance in terms of making people's lives easier. It has become very easy to run some applications with technology. In this study, an application that provides media player control with voice commands was developed. This application was developed to address the needs of people who cannot listen to music on their own due to any disability. The application was implemented in C# programming language. In order to manage the media player with voice commands, voice recognition libraries were first used. In the developed application, operations with keyboard and mouse can be done with voice commands. Voice commands can be sent with the wireless headset from anywhere in the shooting area.Öğe An application to control media player with voice commands(2020) Avuçlu, Emre; Özçıfçı, Ayhan; Elen, AbdullahUsing technology today is of great importance in terms of making people's lives easier. It has become very easy to run someapplications with technology. In this study, an application that provides media player control with voice commands was developed.This application was developed to address the needs of people who cannot listen to music on their own due to any disability. Theapplication was implemented in C# programming language. In order to manage the media player with voice commands, voicerecognition libraries were first used. In the developed application, operations with keyboard and mouse can be done with voicecommands. Voice commands can be sent with the wireless headset from anywhere in the shooting area.Öğe Auto-detection of intermetallic and eutectic phases in microstructure of the az91 mg-alloys by image processing techniques(2022) Elen, Abdullah; Elen, LeventAZ91, which is used in the production of parts in the aerospace, defense and automotive industries, can be enhanced by the addition of an alloying element or the cooling rate, due to the weak strength and formability properties of advanced technology Mg-alloys. The microstructure change in Mg alloys significantly affects the mechanical properties. By analyzing the microstructure of these alloys, a close estimate of the mechanical properties can be made. In this study, an image processing-based model is proposed that automatically recognizes the intermetallic and eutectic phases required for the analysis of microstructural properties in AZ91 Mg-alloys. The proposed method consists of two stages; In the first step, the eutectic phase template is obtained as a binary image. In the second step, the binary image containing the intermetallic and eutectic phases is obtained and the result image with only the intermetallic phases is obtained by taking the difference of these two patterns. Experimental studies have shown that the proposed method gives a result close to the real value in the detection of eutectic phases.Öğe Automatic detection of petiole border in plant leaves(Sage Publications Ltd, 2021) Elen, Abdullah; Avuclu, EmrePlants are our source of oxygen and nutrients on earth. Therefore, conservation of biodiversity is vital for the survival of other species. With the developing technology, plant species can be examined more closely. Image processing, which is a subject of computer science, has an important role in this field. In this study, an image processing-based method has been developed to automatically separate the petiole region of the plant leaves. To determine the boundary line of the petiole region, the cumulative pixel distributions of the input images in binary format according to the X- and Y-axis are analyzed. Accordingly, optimum thresholds and petiole boundary points are determined. The proposed method was tested on 795 leaf images from 90 different plant species that grow both as trees and shrubs in the Czech Republic. According to the results obtained in experimental studies, it is thought that the proposed method will make an important contribution especially in studies such as automatic classification of plants and leaves and determination of plant species in botanical science.Öğe Çizelgeleme probleminin sezgisel optimizasyon yaklaşımıyla çözümü(Karabük Üniversitesi, 2011) Elen, Abdullah; Çayıroğlu, İbrahimBu çalışmada, üniversitelerde kullanılan öğrenci işleri otomasyonu içerisindeki Ders Çizelgeleme probleminin çözümü, Sezgisel Optimizasyon yaklaşımlarından olan Genetik Algoritma yöntemi kullanılarak gerçekleştirilmiştir. Çizelgeleme problemi, yapılacak işlerin belirlenen kısıtlar dahilinde zaman aralıklarına optimum düzeyde yerleştirilmesi işlemidir. Üniversitelerde bu problemin çözümü, çözüm uzayının büyük olması ve kısıtlamaların çok sayıda bulunması nedeniyle analitik yöntemlerle imkânsız hale gelmektedir. Bu nedenle bu türden problemler için çok iyi sonuçlar veren Genetik Algoritma yöntemi yeni bir yaklaşımla, en iyi sonucu veren parametreler araştırılarak kullanılmıştır.Üniversitedeki gerçek veriler üzerinden (504 öğretim elemanı, 4163 ders, 203 derslik ve 10525 öğrenci) uygulamalar yapılıp Algoritmanın performansı ölçülmüştür.Algoritmanın Üniversite ortamında gerçek olarak uygulanabilmesi, veri girişlerinin yapılabilmesi ve sonuçlarının raporlanabilmesi için ihtiyaç duyulan gerekli diğer tüm modülleri programlanarak komple bir paket program haline getirilmiştir. Bu amaçla geliştirilen yazılım üç ayrı modülden oluşmaktadır. Bunlar Sistem Yönetim Modülü, Ders Modülü ve Sınav Modülüdür.Bütün bu modüllerin ara yüzleri, veritabanı tabloları, bu tablolar arasındaki bağlantılar ve sorgular programlanarak kullanıma hazır hale getirilmiştir. Programlama alt yapısında veri girişleri ve raporlama kısımları internet ortamında ASP.NET, C# Programlama Dili ve SQL Server veritabanı kullanılarak gerçekleştirilmiştir. Geliştirilen algoritma ise C# Programlama Dili ve SQL Server veritabanı kullanılarak Windows Application uygulaması şeklinde gerçekleştirilmiştir.Öğe Classifying white blood cells using machine learning algorithms(2019) Elen, Abdullah; Turan, M. KamilBlood and its components have an important place in human life and are the best indicator tool in determining many pathologicalconditions. In particular, the classification of white blood cells is of great importance for the diagnosis of hematological diseases.In this study, 350 microscopic blood smear images were tested with 6 different machine learning algorithms for the classificationof white blood cells and their performances were compared. 35 different geometric and statistical (texture) features have beenextracted from blood images for training and test parameters of machine learning algorithms. According to the results, theMultinomial Logistic Regression (MLR) algorithm performed better than the other methods with an average 95% test success.The MLR can be used for automatic classification of white blood cells. It can be used especially as a source for diagnosis ofdiseases for hematologists and internal medicine specialists.Öğe Design of a low-cost and fully automated digital microscope system(Springer, 2023) Elen, Abdullah; Turan, M. KamilMicroscopes are indispensable devices of laboratories. They are widely used in industry and science, such as medicine, geology, biology, chemistry and so on. Thanks to the developing technology, manual microscopes are leaving their place to automatic systems. However, automatic microscopy systems are difficult to obtain due to their high costs. The best way to circumvent this problem is to reduce device costs as much as possible. Based on this idea, a fully automated digital microscope system (FADMS) has been proposed as a low-cost prototype. The FADMS can scan and autofocus for various microscopic samples. In addition, it can be controlled over the internet thanks to a developed software and can store scanned microscopic images. The total cost of the developed system is around 2500 US dollars. In experimental studies, mechanical motion sensitivity and focusing tests of the FADMS were performed. Five different methods were tested on peripheral blood smear images for autofocus. According to the results obtained based on six different measurement criteria, Brenner's and Geusebroek's method showed the best performance. In positioning tests for the mechanical stage (X and Y axes), the motors in the driving system were moved forward and backward for a distance of 100 mu m. The results obtained showed a deviation of 2.6 mu m for the X-axis and 3.6 mu m for the Y-axis. Experimental results show that micron-sized biological cells can be observed in detail. The FADMS has been designed in a modular structure that allows it to be replaced with lighting, optical system and imaging device alternatives. In terms of performance/cost ratio, the FADMS is attractive for high-throughput microscopy applications ranging from digital pathology to health screening in low-income countries and is considered to be an alternative solution for many industries.Öğe Evaluation of train and test performance of machine learning algorithms and Parkinson diagnosis with statistical measurements(Springer Heidelberg, 2020) Avuclu, Emre; Elen, AbdullahParkinson's disease is a neurological disorder that causes partial or complete loss of motor reflexes and speech and affects thinking, behavior, and other vital functions affecting the nervous system. Parkinson's disease causes impaired speech and motor abilities (writing, balance, etc.) in about 90% of patients and is often seen in older people. Some signs (deterioration of vocal cords) in medical voice recordings from Parkinson's patients are used to diagnose this disease. The database used in this study contains biomedical speech voice from 31 people of different age and sex related to this disease. The performance comparison of the machine learning algorithms k-Nearest Neighborhood (k-NN), Random Forest, Naive Bayes, and Support Vector Machine classifiers was performed with the used database. Moreover, the best classifier was determined for the diagnosis of Parkinson's disease. Eleven different training and test data (45 x 55, 50 x 50, 55 x 45, 60 x 40, 65 x 35, 70 x 30, 75 x 25, 80 x 20, 85 x 15, 90 x 10, 95 x 5) were processed separately. The data obtained from these training and tests were compared with statistical measurements. The training results of the k-NN classification algorithm were generally 100% successful. The best test result was obtained from Random Forest classifier with 85.81%. All statistical results and measured values are given in detail in the experimental studies section.Öğe Identification of column edges of DNA fragments by using K-means clustering and mean algorithm on lane histograms of DNA agarose gel electrophoresis images(Spie-Int Soc Optical Engineering, 2015) Turan, Muhammed Kamil; Sehirli, Eftal; Elen, Abdullah; Karas, Ismail RakipGel electrophoresis (GE) is one of the most used method to separate DNA, RNA, protein molecules according to size, weight and quantity parameters in many areas such as genetics, molecular biology, biochemistry, microbiology. The main way to separate each molecule is to find borders of each molecule fragment. This paper presents a software application that show columns edges of DNA fragments in 3 steps. In the first step the application obtains lane histograms of agarose gel electrophoresis images by doing projection based on x-axis. In the second step, it utilizes k-means clustering algorithm to classify point values of lane histogram such as left side values, right side values and undesired values. In the third step, column edges of DNA fragments is shown by using mean algorithm and mathematical processes to separate DNA fragments from the background in a fully automated way. In addition to this, the application presents locations of DNA fragments and how many DNA fragments exist on images captured by a scientific camera.Öğe Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification(Elsevier Ireland Ltd, 2020) Baydilli, Yusuf Yargi; Atila, Umit; Elen, AbdullahBackground and objective: Traditional machine learning methods assume that both training and test data come from the same distribution. In this way, it becomes possible to achieve high successes when modelling on the same domain. Unfortunately, in real-world problems, direct transfer between domains is adversely affected due to differences in the data collection process and the internal dynamics of the data. In order to cope with such drawbacks, researchers use a method called domain adaptation, which enables the successful transfer of information learned in one domain to other domains. In this study, a model that can be used in the classification of white blood cells (WBC) and is not affected by domain differences was proposed. Methods: Only one data set was used as source domain, and an adaptation process was created that made possible the learned knowledge to be used effectively in other domains (multi-target domain adaptation). While constructing the model, we employed data augmentation, data generation and fine-tuning processes, respectively. Results: The proposed model has been able to extract domain-invariant features and achieved high success rates in the tests performed on nine different data sets. Multi-target domain adaptation accuracy was measured as %98.09. Conclusions: At the end of the study, it has been observed that the proposed model ignores the domain differences and it can adapt in a successful way to target domains. In this way, it becomes possible to classify unlabeled samples rapidly by using only a few number of labeled ones. (C) 2020 Elsevier B.V. All rights reserved.Öğe Making Inferences About Settlements from Satellite Images Using Glowworm Swarm Optimization(Springer Singapore Pte Ltd, 2020) Avuclu, Emre; Elen, Abdullah; Ornek, Humar KahramanliOptimization is the process of choosing the best one among existing possibilities under particular circumstances in a problem. There are various algorithms for optimization problems nowadays. Metaheuristic algorithms are the algorithms giving almost optimum solutions at an acceptable duration for the problems of large dimension. Heuristic optimization algorithms with general aim are evaluated in different groups. Swarm intelligence-based optimization algorithms were developed through examining the behaviors and movements of living flocks such as birds, fish, cats, and bees. With these algorithms, some estimating processes are carried out successfully in all areas. In this study a new approach was presented with a novel idea, by inspiring from the behavior type of Glowworm Swarm Optimization; and an application estimating the total population, square measurement and electricity quantity that was consumed by the chosen areas in a region was developed. The developed application works as a real-time and animated display. When all calculations are finished, the animation ends. Estimates also examined England as an example. The difference between the estimated value of the actual population of England is calculated as 1.7%. In the estimates for the values of the surface area of England with an error of 1.4%, the estimated values were very close to the actual values. Some other obtained estimation results are presented in the results section.Öğe A new approach for fully automated segmentation of peripheral blood smears(Inst Advanced Science Extension, 2018) Elen, Abdullah; Turan, Muhammed KamilPeripheral blood smear is microscopically examining technique for blood samples from patients by painting special dyes in clinic laboratories. Blood diseases can be diagnosed by examining morphology, numbers and percentages of leukocyte, erythrocyte and thrombocyte cells in blood samples. However, this method is a considerably time-consuming process and requires an evaluation performed by a hematology specialist. It is not often provided a definitive assessment due to the expert's clinical experience and judgment during review. Although there are considerable studies about the segmentation of blood smear images in the literature, there is no method to segment all blood cells. In this study, a new segmentation algorithm is proposed, which automatically extracts leukocyte, erythrocyte and thrombocyte cells from peripheral blood smear images. Purpose of this study here is to make highly accurate and complete blood count. The algorithm treats each image as a universal set and represents each object in the image as a subset as a result of the applied operations. In the developed method, leukocytes and thrombocytes achieve better success than other studies. However, it has been observed that the average success rate of stacked erythrocytes decreases. Statistical tests of the developed method were performed using 200 blood smear images in experimental studies. According to the obtained results, it is seen that high accuracy (leukocyte 99.86%, thrombocyte 98.4%, erythrocyte 93.4%) and precision (leukocyte 94.77%, thrombocyte 90.14%, erythrocyte 95.88%) were achieved in all three blood cells. (C) 2017 The Authors. Published by IASE.Öğe A new dynamic feature extraction method for biometric images(Gazi Univ, 2021) Avuclu, Emre; Elen, Abdullah; Ozcifci, AyhanAim The aim of this study is to develop an algorithm that performs automatic and dynamic image segmentation. Design & Methodology A fingerprint database with a total of 80 images and 10 different classes was used. Originality The features of the images were extracted with the feature extraction method originally developed. Findings The 300x300 images were divided into 25x25 sub-images and the feature vector was obtained. Conclusion The developed segmentation and feature extraction algorithm can be applied to any image of equal size. Declaration of Ethical Standards The author(s) of this article declare that the materials and methods used in this study do not require ethical committee permission and/or legal-special permission.Öğe Periferik yayma sonuçlarının otomatik analizi için zeki denetimli sistem tasarımı(Karabük Üniversitesi, 2018) Elen, Abdullah; Turan, Muhammed KamilPeriferik kan yayma, hastalardan alınan kan örneklerinin klinik laboratuvarda özel boyalarla boyanarak mikroskop ile inceleme tekniğidir. Hastalara ait kan örneklerindeki lökosit, eritrosit ve trombosit hücrelerinin sayılarına ve yüzde oranlarına bakılarak, aynı zamanda morfolojileri de incelenerek kan hastalıklarının tanısı yapılabilmektedir. Ancak, bu yöntem önemli derecede zaman alıcı bir süreçtir ve hematoloji uzmanının değerlendirmesine ihtiyaç duyar. Bu inceleme esnasında uzmanın klinik tecrübesi ve yargıları nedeniyle çoğu zaman kesin bir değerlendirme de sunulmaz. Değerlendirmeler uzmandan uzamana değişiklik de gösterebilir. Bu çalışma özgün bir motorize mikroskop tasarımı, kan hücre segmentasyonu, lökosit hücrelerinin sınıflandırılması ve geliştirilen motorize mikroskop sisteminin uzaktan kontrolü olmak üzere dört aşamadan meydana gelmektedir. Tez çalışmasının ilk aşamasında, iki farklı motorize mikroskop prototipi tasarlanarak bilgisayar destekli çalışmasına imkân sağlayan dahili ve harici kontrol yazılımları geliştirilmiştir. İkinci aşamada, periferik kan yayma görüntülerindeki lökosit, eritrosit ve trombosit hücrelerinin çıkartma işlemini otomatik olarak gerçekleştirilen yeni bir segmentasyon algoritması önerilmiştir. Algoritma, her bir görüntüyü evrensel bir küme (lökositler, ertirositler ve trombositler) olarak ele alır ve uygulanan işlemler sonucunda görüntüdeki her bir nesneyi alt küme olarak değerlendirir. Deneysel çalışmalarda farklı ışık koşullarında hazırlanmış 200 kan yayma görüntüsü kullanılarak, geliştirilen yöntemin istatistiksel testleri yapılmıştır. Elde edilen sonuçlara göre her üç kan hücresi içinde yüksek derecede doğruluk ve kesinlik başarısı sağlandığı görülmüştür. Üçüncü aşamada, segmente edilen lökosit hücrelerinin Monosit, Lenfosit, Nötrofil, Bazofil ve Eozinofil olmak üzere beş farklı sınıfa ayırabilen makine öğrenme algoritmalarıyla eğitim ve test işlemleri gerçekleştirilmiştir. Dördüncü ve son aşamada ise uzman hekimlerin geliştirilen prototip cihazın uzaktan kontrol edilebilmesi ve hasta veritabanına erişimi için web tabanlı bir uygulama geliştirilmiştir. Bu tez çalışması sonucunda periferik kan yayma görüntüleri için literatüre yeni bir segmentasyon algoritması kazandırılmıştır. Makine öğrenme algoritmaları ile 350 örnek lökosit görüntüsü kullanılarak, lökosit hücrelerinin sınıflandırılması yapılmış ve algoritmaların performansları karşılaştırılmıştır. Tasarlanan elektromekanik mikroskop sistemi ile geliştirilen algoritmalar birleştirilerek, kan sayımı ve sınıflandırma işlemlerini yapabilen Hemascope isimli prototip bir cihaz üretilmiştir.Öğe Standardized Variable Distances: A distance-based machine learning method(Elsevier, 2021) Elen, Abdullah; Avuclu, EmreToday, machine learning algorithms are an important research area capable of analyzing and modeling data in any field. Information obtained through machine learning methods helps researchers and planners to understand and review systematic problems of their current strategies. Thus, it is very important to work fully in every field that facilitates human life, such as early and correct diagnosis, correct choice, fully functioning autonomous systems. In this paper, a novel machine learning algorithm for multiclass classification is presented. The proposed method is designed based on the Minimum Distance Classifier (MDC) algorithm. The MDC is variance-insensitive because it classifies input vectors by calculating their distances/similarities with respect to class-centroids (average value of input vectors of a class). As it is known, real-world data contains certain proportions of noise. This situation negatively affects the performance of the MDC. To overcome this problem, we developed a variance-sensitive model, which we call Standardized Variable Distances (SVD), considering the standard deviation and z-score (standardized variable) factors. To ensure the accuracy of the SVD, we used Wisconsin Breast Cancer Original (WBCO) and LED Display Domain (led7digit) datasets, which we obtained from UCI machine learning repository, with 5-fold cross validation. It was compared and analyzed classification performance of the SVD with Decision Tree (DT), Random Forest (RF), k-Nearest Neighbor (k-NN), Multinomial Logistic Regression (MLR), Naive Bayes (NB), Support Vector Machine (SVM), and the Minimum Distance Classifier (MDC), which are well-known in the literature. It has also been compared thirteen different studies using the same datasets over the past five years. Our results in the experimental studies have shown that the SVD can classify better than traditional and state-of-the-art methods, compared in this study. The proposed method reached over 97% classification accuracy (CACC), F-measure (FM) and area under the curve (AUC) on the WBCO dataset. On the led7digit dataset, approximately 74% CACC, 75.1% FM and 82.2% AUC scores were obtained. It has been observed that the classification scores obtained with the SVD are higher than other ML algorithms used in the experimental studies. (C) 2020 Elsevier B.V. All rights reserved.
