Bilgisayar Mühendisliği Bölümü Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/58

Browse

Now showing 1 - 20 of 206

An energy-efficient clustering based communication protocol with dividing the overall network area for wireless sensor networks
(2014) Khalaf, Abdulrahman Zaidan
In this thesis, the energy efficient and connectivity problem in wireless sensor networks (WSNs) is presented. There are more difference between energy levels of near nodes and far nodes of cluster heads. This problem compensated by dividing the entire network (sensor field) into equal area and applies different clustering policies to each section. The results compared with results of LEACH (Low Energy Adaptive Clustering Hierarchy). The performance of proposal system overcomed the previous studies. Also this protocol guaranted transmitting data and transmission in high traffic networks to reduce energy consumption and packet failure
Machine learning in artificial intelligence
(2006) Ercan, Tardu
In today’s world, learning is a process of computers as well as human being. “Learnable” systems and computers will become more important in following years and affect our lives in many ways. In this thesis, a survey has been carried out in the field of artificial intelligence, machine learning and especially on decision tree learning algorithms. Some of the decision tree learning algorithms was used to learn rules which are extracted from a dataset. The dataset which consists of water consumption of Ankara for one year and meteorological data of Ankara was used. The results indicate that which learning method is more efficient and have better performance.
Selection of the software development process measurement component on scrum software development: An analytic hierarchy process approach
(2019) Tekin, Muhammed Nesib
In today's world, software evolves faster than software production can respond; therefore, software development organizations not only deal with the uncertainties inherited from requirements but also work continuously to deal with deployment issues. Scrum is the most widely known and used agile development framework that guides the development process with its ability to create customer-valued software artifacts iteratively and incrementally, while seeking best practices to provide continuous measurement during the production. However, measuring success in Scrum is a challenging endeavor. In particular, it is hard to select the best fitting agile metric during consecutive Scrum sprints. The goal of this industrial case study was to utilize a multi-criteria decision-making by using the Analytic Hierarchy Process. To this end, a systematic selection process was designed for selecting appropriate software measurement component related to the project process management with the TÜBİTAK SAGE software development group. The set of criteria, which was used for selecting the software development process measurement components, determined as relevance, experience, functionality and feasibility & usability. According to results of this study, it was determined that the criterion of relevance has the most precedence by the ratio 49.225%, this was followed by experience criterion with 22.512%, feasibility & usability criterion with 17.040%, and criterion of functionality as 11.223%. Moreover, the distribution of the process metrics preferences of the software developers was analyzed according to their characteristic features and defense industry structure by using different distribution charts. Finally, the software process measurement components, which can be easily integrated the agile software process tool that is used by TÜBİTAK SAGE software development group are determined alternatives for performing selection process with Analytic Hierarchy Process method. Among the other options, Alternative-1 was chosen as the first with 40.259%, followed by Alternative-3 with 23.632%.
Web services based real time data warehouse
(2012) Obalı, Murat
Today's business environment is quickly changing and business decision makers need for a historical picture of what happened and a picture of what was happening today. Traditional data warehouses provide a historical picture, but there is lack of fresh data. However, fresh data in data warehouses is a strong feature from the part of the users. The aim of this study is building a real time data warehouse using web services. First, we modelled both the conceptual and the logical design of real time data warehouse. For change data capture from source systems, we implemented web services based server and client software. Then, we used real time partition for real time data which is merged into data warehouse in a daily fashion. We, also, implemented a data integration service using query re-write approach to integrate data warehouse and real time partition data.
Parallelization study on the clustering technique to mine large datasets
(2011) Yıldırım, Ahmet Artu
Parallel clustering algorithm implementations concerning message passing interface (MPI) and compute unified device architecture (CUDA) model with their applications to very large datasets have been presented in the thesis. WaveCluster is a novel clustering approach based on wavelet transforms. Despite it?s novelty, it requires considerable amount of time to collect results for large sizes of multidimensional datasets. In the MPI algorithm; divide and conquer approach has been followed and communication among processors are kept at minimum to achieve high efficiency. Developed parallel WaveCluster algorithm exposes high speedup and scales linearly with the increasing number of processors. Parallel behavior of WaveCluster approach has been also investigated by executing the algorithm on graphical processing unit (GPU). High speedup values have been obtained in the computation of wavelet transform and connected component labeling algorithms in the GPUs with respect to the sequential algorithms running on the CPU
Determining rheumatoid arthritis and osteoarthritis diseases with plain hand x-rays using convolutional neural network
(2019) Üreten, Kemal
Recent advances in computer technology have facilitated the acquisition of high-resolution images and processing of images. Convolutional neural network (CNN) is a branch of deep learning. CNN was first introduced in 1995 by LeCun, and in 2012, AlexNet won the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC), after which there was rapid growth in deep learning applications. There are many successful studies using CNN especially in dermatology, pathology, radiology and ophthalmology. CNN highly successful in feature extraction and classification and requires less pre-processing. But in the CNN method, overfitting is an important problem that needs to be addressed and requires a large data set for training. If there is not enough data for CNN training from scratch, previously trained CNN network from the natural image data set are used for transfer learning. Transfer learning is the use of a pre-trained model for a new problem. In recent years, there have been a few studies showing that CNN models trained with natural images have achieved successful results in the medical field. Rheumatoid arthritis (RA) and hand osteoarthritis (OA) are two different diseases that cause pain, swelling, tenderness, loss of function in hand joints. In these diseases, affected joints and radiologic lesions show some differences. Treatment of both diseases is also different. Conventional plain hand X-Rays (CR) are often used to diagnosis, differential diagnosis of RA and OA. The aim of this study is to develop a software that will help physicians for differential diagnosis of RA and OA from CR. To the best our knowledge, this is the first study to distinguish between normal, hand OA and RA using plain hand radiographs. The efficiency of the created models was evaluated by using performance metrics such as accuracy, sensitivity, specificity and precision. In this study, pre-trained GoogLeNet, ResNet50 and VGG16 networks were used, transfer learning was applied. Successful results were obtained from all three pre-trained networks. In this study, data augmentation, droupout, fine tuning, learning rate decay was applied to prevent overfitting. And during the training, no signs of overfitting were observed in the training chart.
Structural risk management of disasters
(2007) Battal, Fulya
In this thesis, an expert system that evaluates the risk of damage of buildings during an earthquake is studied. The system asks some critical questions about the ground type and structural properties of the buildings. The answers to these questions are evaluated to conclude on the risk of damage of the buildings and advise for the necessary precautions to decrease the damage of the building to the user. The rules and parameters are determined due to a predefined knowledgebase and utilized in the expert system called, Structural Risk Management of Disaster prepared by the software Exsys Corvid. This expert system may be used in determining the risk of damage of buildings including government buildings, hospitals, residences etc. The determination of the risk of damage is important to get ready for any possible earthquake
Blind linear correlation technique for image watermarking
(2014) Baba Ahmadi, Sajjad Bagheri
In digital environment, make, change, update, distribute and store digital data are convenient, therefore as much abuse of digital data is added. This calls for a method to prove the ownership right on digital contents and to avoid unauthorized users to tamper and distribute digital data. Thereby to achieve this security requirement, watermarking schemes are introduced that have applications in all three forms of media, i.e., video, music and image. This thesis aims to test blind linear correlation technique by Stirmark benchmark 4.0 that contains sixteen different tests, such as attacks and distortions which are well-known in image processing. Those tests are applied on the images which are watermarked by blind linear correlation technique. In this thesis, results of this experiment are discussed and analyzed.
Detecting location of hidden messages on digital images using RS steganalysis method
(2013) Çiftçi, Efe
Steganography is a branch of methods that deal with hiding information in cover media. The result of the hiding process should resist detection by any means. To detect the hidden information, several analysis methods have been developed (named as steganalysis methods). Steganalysis of Regular and Singular Groups (RS) is a method which aims to detect hidden information on digital images. This method is helpful for estimating length of the hidden message but it does not find over which section of the image the hidden message is. The aim of this thesis is to locate in which part(s) of the image the message is hidden by utilizing this steganalysis method and quadtree data structure.
Evaluation of terrain rendering algorithms
(2005) İnam, Emin
errain rendering plays an important role in outdoor virtual reality applications, games, Geographic Information System (GIS), military mission planning's and flight simulations, etc. Many of these applications require real-time dynamic interaction from end users and thus are required to rapidly process terrain data to adapt to user input. Typical height fields consist of a large number of polygons, so that even most high performance graphics computers have great difficulties to display even moderately sized height fields at interactive frame rates. The common solution is to reduce the complexity of the scene while maintaining a high image quality. This thesis is an evaluation of three real-time continuous terrain levels of detail algorithms described in the papers ROAMing Terrain: Real-time Optimally Adapting Meshes by Duchaineau, Real-Time Generation of Continuous Levels of Detail for Height Fields by Röttger and Fast Terrain Rendering Using Geometrical MipMapping by Willem H. de Boer. The evaluation and comparison of the algorithms is based on the trade- off of polygon count to terrain accuracy over separate test data sets. The main aim of this thesis is research on terrain rendering algorithms that is generate high quality image in real-time with using height data.
Multifunction robot controlled by computer vision system
(2014) Mustafa, Mohammed Sulaiman
In this thesis, we try to come up and build a robot platform with multifunction capabilities, easy to add, modify and delete those functions without redesigning, by using easy use technology that can create a suitable efficient platform. The process of building platform is by using figures, tables and programming code to make this thesis capable to apply and implement in real world, showing obstacles and challenges that lead to the key of success until it reaches the final goal. This thesis requires only basic level in electronic and computer programming because we are using a simplified way for building robot. The multifunction platform is a unique idea and opens new space to experimenters to get benefits from this opinions or ideas to use these functions in raw state, with no need to study hardware and software material of robot. The final robot form is shown in the last pages of this thesis as appendix
Classification of diabetic retinopathy using pre-trained deep learning models
(2019) Al-Kamachy, Inas Mudheher Raghib Kafı
Diabetic Retinopathy (DR) is considered to be the first factor that leads to blindness. If it is not detected early, many people around the world would suffer from the diabetic disease that may lead to DR in their eyes. Any delay in regular monitoring and screening by ophthalmologists may cause rapid and dangerous progress of this disease which finally leads to human vision loss. The imbalance between the numbers of doctors required to monitor this disease and the number of patients around the world increasing year by year shows a major problem leading to poor regular monitoring and loss vision in many cases which could have been detected had there been good treatment in the earlier stages of DR. In order to solve this problem, serious aid was needed for a computer aid diagnosis (CAD). Deep learning pre-trained models are state-of-art in image recognition and image detection with good performance. In this research, we used image pre-processing and we built several convolution neural network models from scratch and fine-tuned five pre-trained deep learning models which used ImageNet as the dataset for medical images of diabetic retinopathy in order to classify diabetic retinopathy into five classes. After that, we selected the model that showed good performance to build a diabetic retinopathy web application using Flask as a framework web service. We used the KAGGLE kernel website with Jupyter as a notebook as well as Flask to build our web application. The final result of the AUC was 0.68 using InceptionResNetV2.
Integrating computer vision with a robot arm system
(2014) Yosif, Zead Mohammed
During last decades, robotic system has been employed in different fields, such as, industrial, civil, military, medical, and many other applications. Vision system is integrated with robot systems to enhance the controlling performance of the robot system. A great deal of features can be computed using the information have been gotten from vision sensors (camera). The extracted information from vision system can be used in the feedback to have the ability to control the robot armtor motion, but the operation of extracting this information from vision system is time consuming. This thesis addressed the problem of following (tracking) and grasping of moving target (object) with limited velocity in real time by employing the technology of Eyein- Hand, whereas a camera attached (mounted) to the robot arm end effector. This done by using a predictor (Kalman filter) that estimates the positions of the target in the future, an algorithm was designed to track an object move in different trajectories, within the camera field of view. The Kalman filter uses the measured position of the target as well as previous state estimates to fix the location of thetarget object at the next time step, in other word, the Kalman filter is applied to keep observing the object till grasp it. The employing of vision system information in the feedback control of the robot systems have been the major research in robotics and Mechatronic systems. The utilizing from this information has been proposed to handle stability and reliability issues in vision-based control system.
A computational analysis of a language structure in natural language text processing
(2005) Eş, Sinan
Text categorization or classification is a general task of classifying un-organized natural language texts according to specific subject matter or category. Electronic mail (e-mail) filtering is a binary text classification problem which the user emails can be classified as legitimate (non-spam) or un-wanted mail (spam). In this study, we tried to find a filtering solution that is able to automatically classify emails into spam and legitimate categories. In order to automatically and efficiently classify emails as spam or legitimate we took advantage of some Machine Learning methods and some novel ideas from Information Retrieval
A GIS-based decision support system for tourism planning and development
(Çankaya Üniversitesi, 2018) Yıldırım, Pınar
In the past twenty years, pioneering developments in information technology and communication systems worldwide have not only offered many opportunities in the fields of marketing, management and the promotion of tourism and recreational areas to businesses interested in tourism, but have also provided a sustainable advantage in competition with other businesses. Turkey has more potential for tourism and more resources than many countries, thanks both to its natural beauty and its historical and cultural wealth. The aim of this thesis is to build a web portal that is able to enhance its attractiveness through photographs or videos taken in all regions of Turkey, increase interest from domestic and foreign tourists through detailed articles about the country, and improve the accessibility of the country's resources through a system based on GIS. Developed within the scope of this thesis, the Turkey Tourist Portal can promote the country to tourists by presenting both its natural beauty and its historical and cultural wealth on a map, together with images and articles.
Calculation of textual similarity using semantic relatedness function
(2015) Kairaldeen, Ammar Riadh
Finding the similarity between two sentences is an essential task in different fields such as natural language processing (NLP) and information retrieval (IR). Semantic relatedness similarity between two sentences is concerned with measuring how two sentences share the same meaning. Over the last decade, different methods for measuring sentence similarity have been proposed in the literature. Some methods use word semantic relatedness function in sentence similarity calculations. This thesis aims to compare these methods using four data sets selected from different fields, providing a testable of a various range of writing expressions to challenge the selected methods. Results show that the use of corpus-based word semantic similarity function has significantly outperformed that of WordNet-based word semantic similarity function in sentence similarity methods. Moreover, we propose a new sentence similarity measure method by extending an existing method in the literature called Overall similarity. Furthermore, the results show that the proposed method has significantly improved the performance of the Overall method. All the selected methods are tested and compared with other state-of-the-art methods.
Effect of noise on edge detection techniques
(2014) Mahmood, Alaa
The subject of identification edge in images has a wide application in various fields for that it’s considered one of the important topics in a digital image processing. There are many algorithms to detect the edge in images, but the performance of these algorithms depends on the type of image, the environment of the image and the threshold value of the edge algorithm. In this thesis five edge detection algorithms were evaluated by using several types of original images, these images were placed in multi-environments (clean, noisy, and de-noised). According to this evaluation results, the best edge detection algorithm and the best threshold value were found in each environment
Performence enhancement analysis of modern wireless networks using mimo technique
(2014) Abdulla, Ayad
The systems that utilizing multiple transmit and multiple receive antennas are commonly known as Multiple - Input Multiple - Output (MIMO) systems. This wireless networking technology can greatly improves wireless communication system by exploiting the multipath propagation constructively. These paths can be exploited to provide redundancy of transmitted data, thus improving the reliability of transmission (diversity gain) or increasing the number of simultaneou sly transmitted data streams and increasing the capacity of the wireless system (multiplexing gain) and decreasing bit error rate. This thesis introduces a comparative studies that determines the diversity and channel capacity enhancements, resulting from using our proposed MIMO wireless model. The antenna configurations for this model uses new microstrip bandpass filter to prevent the lower image sideband as far as possible for these antennas.These enhancements has been analysed in term of Bit Error Rate (BER) and bit rate of data transmission for the diversity and capacity enhancements, respectively.
Performance comparison of multi-core smartphones
(2018) Al-Sabbagh, Mustafa Maan Ezzulddin
Akıllı telefonlar önemli bir iletişim aracıdır ve bireylerin ihtiyaç duyabileceği tüm özellikleri sunan taşınabilir bir bilgisayar haline gelme eğilimindedirler. Bunun sonucunda, çok çekirdekli akıllı telefonlar üretilmiş ve bu nedenle bu cihazlarda paralel işleme uygulaması mümkün hale gelmiştir. Akıllı telefonlarda paralel işlemenin kullanılmasının işleme süresinin kısaltılması, güç optimizasyonu, akıllı telefonun tam gücünü kullanma ve daha verimli uygulamalar yazabilme yeteneği sağlaması gibi birçok avantajı bulunmaktadır. Bu tezde, paralel uygulamalar yazmanın yolu çok çekirdekli akıllı telefon üzerinde incelenecek ve paralel olarak uygulanacak uygulama içerisinde kodun bölümlerini belirlemek için uygulamalara olan bağımlılık analiz edecektir. İki program parçasının paralel olarak yürütülebileceği zamanı tanımlayan Bernstein koşulları uygulanacaktır. Optimum sayıda iş parçacığını belirleyen yol paralel uygulamada kullanılmak üzere gösterilecektir. Uygulamayı çalıştırarak elde edilecek performans kazanımı, Speedup (hızlanma) olarak adlandırılan çoklu işlemciler üzerinde paralel olarak gösterilecektir.Cep telefonu uygulamalarını geliştirmek amacıyla programlama dili olarak Java 2 Micro Edition (J2ME), geliştirme ortamı olarak ise Android Studio kullanılacaktır.
Deep learning based log anomaly detection with time differences
(2020) Sağında, Baransel
Sürekli büyüyen dijital hizmetler ve yeni mikro hizmetlerin adaptasyonu ile birlikte yeni bilgi işlem sistemleri ile oluşturulan kayıtlarin miktarı muazzam bir şekilde artmaktadır. Bu büyük kayıtların izlenmesi ve değerlendirilmesi, sistem günlüğü oluşturmanın boyutu ve artan hızı nedeniyle giderek zorlakmaştadır. Çoğu zaman, bu kayıtları zamanında ve verimli bir şekilde işlemek için kaynaklar yetmemektedir. Bu çalışmada, sistem günlüklerinin ayrıştırılması ve değerlendirilmesi için, günlüklerdeki meydana gelen olaylar arasındaki sürenin uzunluğuna dayalı anormallik tespitinde kullanımına bir yöntem öneriyoruz. Anormallik tespiti için özellikle Seq2seq nörön ağlarını kullanıyoruz. Sonuçlar, yöntemimizin olay kayıtlarının içeriği hakkında herhangi bir bilgi sahibi olmaksızın normal ve anormal olayları ayırt etmede başarılı olduğunu göstermektedir.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Tezleri by Access Right "info:eu-repo/semantics/openAccess"