Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

1997 - 199992000 - 200952

Settings

End date: 2009Department: search.filters.department.Thesis (Master)--İzmir Institute of Technology, Computer Engineering

Search Results

Now showing 1 - 10 of 61
  • Master Thesis
    Trajectory Prediction of Moving Objects by Means of Neural Networks
    (Izmir Institute of Technology, 1997) Barışık, Hakan; Aytaç, İsmail Sıtkı; Aytaç, İsmail Sıtkı
    Estimating the three-dimensional motion of an object from a sequence of object positions and orientation is of significant importance in variety of applications in control and robotics. For instance, autonomous navigation, manipulation, servo, tracking, planning and surveillance needs prediction of motion parameters. Although "motion estimation" is an old problem (the formulations date back to the beginning of the century), only recently scientists have provided with the tools from nonlinear system estimation theory to solve this problem eural Networks are the ones which have recently been used in many nonlinear dynamic system parameter estimation context. The approximating ability of the neural network is used to identifY the relation between system variables and parameters of a dynamic system. The position, velocity and acceleration of the object are estimated by several neural networks using the II most recent measurements of the object coordinates as input to the system Several neural network topologies with different configurations are introduced and utilized in the solution of the problem. Training schemes for each configuration are given in detail. Simulation results for prediction of motion having different characteristics via different architectures with alternative configurations are presented comparatively.
  • Master Thesis
    Image Classifcation by Means of Pattern Recognition Techniques
    (Izmir Institute of Technology, 1997) Güzel, Cumhur; Püskülcü, Halis
    Image classification plays an important role in many computer vision tasks such as surface inspection, shape determination etc. Various 2-D image classification techniques are investigated, assessed and a computational method to classifY the 2-D X-ray images is developed and evaluated in this study. Various pattern recognition techniques are devised for the solution of the image classification. Those techniques may be divided into mainly two groups. First one, is mathematical and statistical model based, second one, is the artificial neural network based techniques. We have concentrated on artificial neural network techniques. In the experiments, both techniques were applied for the classification of the VUR (vesico ureteral reflux) images, in this study. However, according to the experiments performed on VUR case study, neural network technique was more successful than others, in terms of classifier. A hybrid method is proposed in this study, rather than pure artificial neural network solution. Representation of images is performed via transformation invariant mathematical structure called Fourier Descriptors and these structures are used as input to train the neural network for the classification part.The application is performed as follows: Feature extraction is performed first, then extracted features are used as pattern vectors for training the neural network. Representation of the shapes in X-ray images is performed by using Fourier Descriptors. Usage of Fourier descriptors as a method of representation of the shapes, provides the transformation invariant' (translation, rotation, scaling invariant structure) representation of X-ray images. These new vector representation is fed to the neural network. Backpropagation is used as a training algorithm. After training is finished, system is readyfor questioning. The minimum-mean-distance and nearest neighbor rules are also applied for the pattern vectors generated for the experiments. But the multilayer perceptron trained by backpropagation outperforms both of these statistical classifiers.
  • Master Thesis
    Intrusion Detection System Alert Correlation With Operating System Level Logs
    (Izmir Institute of Technology, 2009) Toprak, Mustafa; Aytaç, İsmail Sıtkı
    Internet is a global public network. More and more people are getting connected to the Internet every day to take advantage of the Internetwork connectivity. It also brings in a lot of risk on the Internet because there are both harmless and harmful users on the Internet. While an organization makes its information system available to harmless Internet users, at the same time the information is available to the malicious users as well. Most organizations deploy firewalls to protect their private network from the public network. But, no network can be hundred percent secured. This is because; the connectivity requires some kind of access to be granted on the internal systems to Internet users. The firewall provides security by allowing only specific services through it. The firewall implements defined rules to each packet reaching to its network interface. The IDS complements the firewall security by detected if someone tries to break in through the firewall or manages to break in the firewall security and tried to have access on any system in the trusted site and alerted the system administrator in case there is a breach in security. However, at present, IDSs suffer from several limitations. To address these limitations and learn network security threats, it is necessary to perform alert correlation. Alert correlation focuses on discovering various relationships between individual alerts. Intrusion alert correlation techniques correlate alerts into meaningful groups or attack scenarios for ease to understand by human analysts. In order to be sure about the alert correlation working properly, this thesis proposed to use attack scenarios by correlating alerts on the basis of prerequisites and consequences of intrusions. The architecture of the experimental environment based on the prerequisites and consequences of different types of attacks, the proposed approach correlates alerts by matching the consequence of some previous alerts and the prerequisite of some later ones with OS-level logs. As a result, the accuracy of the proposed method and its advantage demonstrated to focus on building IDS alert correlation with OS-level logs in information security systems.
  • Master Thesis
    Solving the Course Scheduling Problem by Constraint Programming and Simulated Annealing
    (Izmir Institute of Technology, 2008) Aycan, Esra; Ayav, Tolga
    In this study it has been tackled the NP-complete problem of academic class scheduling (or timetabling). The aim of this thesis is finding a feasible solution for Computer Engineering Department of İzmir Institute of Technology. Hence, a solution method for course timetabling is presented in this thesis, consisting of two phases: a constraint programming phase to provide an initial solution and a simulated annealing phase with different neighbourhood searching algorithms. When the experimental data are obtained it is noticed that according to problem structure, whether the problem is tightened or loosen constrained, the performance of a hybrid approach can change. These different behaviours of the approach are demonstrated by two different timetabling problem instances. In addition to all these, the neighbourhood searching algorithms used in the simulated annealing technique are tested in different combinations and their performances are presented.
  • Master Thesis
    The Web-Based Application of Key Exchange Protocols for Digital and Mobile Signatures
    (Izmir Institute of Technology, 2008) Akalp, Evren; Koltuksuz, Ahmet Hasan
    Many people want to communicate and send their data securely, for this reason they use encryption methods. Symmetric cryptosystems are commonly used for securing data.They are fast and reliable. But there is a problem of exchanging keys in symmetric cryptosystems. Sender and receiver must share keys to get the plain text. In this thesis, different scenarios for key exchange protocols are developed. Solutions for securing communication to block man in the middle attack are also defined in this thesis.
  • Master Thesis
    Reconstruction of X-Ray Images
    (Izmir Institute of Technology, 1997) Aka, Hüseyin Cüneyt; Aytaç, İsmail Sıtkı
    We have presented an integrated approach in retrieving, reconstructing, and storing images obtained from noisy X-rays in this study. The X-ray images are used to detect human body's invisible parts. The problem of blurring and uneven illumination is always faced. Although it is partially solved by the physicians via lighting the X-rays, this method is not working properly in some cases such as Vesico Ureteral Reflux disease. This may cause loss of some meaningful part of the information and failure in diagnosis process. In order to decrease such errors, some computational methods has been developed by means of image processing. Due to its very nature, reconstruction, retrieving and registration of x-ray images has been chosen as a subject of this study. We have begun attacking the problem of reconstruction and extraction, then started to generate multi-layer hierarchical solutions. We have tried so many different approaches for each layer in our experiments. In each experiment, some methods produced accurate results, some methods did not. Thus, we have exerted every effort to optimize the solution for each layer. Although we have worked with limited number of sample images,(due to the problem of retrieving x-rays which is seen in this case) the results show us that, all the samples that we have processed, could have been reconstructed and stored as we have expected.Storing of the huge amount of data is an another problem in our area of interest, because of image characteristics. Every kidney image consists of nearly 120.000 (around 300x400) pixels. However, in our case, the boundaries of kidney region are sufficient for diagnosis. In other words, storing the boundaries instead of complete image has the same precision. We detected and stored the kidney's boundary coordinates on both x and y axis. Although this was sufficient for our study, we have decided to develop a much more flexible file format by ordering x and y coordinate couples in counter clockwise direction with the same information for further studies such as computer aided diagnosis systems.
  • Master Thesis
    Craniofacial Computer Assisted Surgical Planning and Simulation
    (Izmir Institute of Technology, 1999) Ekin, Emine; Aytaç, İsmail Sıtkı
    In this work, mainly, the first step of craniofacial surgical simulation and planning procedure, reconstruction of tomography images is investigated. The Direct Reconstruction techniques and algebraic methods are described in detailed mathematical formulations for both two and three-dimensional cases. And also a brief description of medical imaging techniques and the terminology of craniofacial surgical simulation and planning is given. In the last chapter the implementation details, the algorithms developed and some resulting images are given and the images are compared with respect to the used algorithms.
  • Master Thesis
    Empirical Computation of Absorbed Radiation in Medium Like Human Body and Graphical Representation of Dose Distribution
    (Izmir Institute of Technology, 2001) Gökçe, Tuncay Cemil; Aytaç, İsmail Sıtkı; Aytaç, İsmail Sıtkı
    Computers, in radiotherapy, are now widely used for calculating and displaying dose distributions for optimum therapy planning. There are lots of hardware options and commercial programs, which were developed outside Turkey, available in the market. In this study, we propose a system, which can be used with a conventional PCs running with Windows NT operating system. Our first clinical tests show that this system is very efficient and suitable for clinical requirements. Also in future developments of the software is very easy.
  • Master Thesis
    A Firewall Design for Academic Environments
    (Izmir Institute of Technology, 2001) Tok, Metin; Koltuksuz, Ahmet Hasan
    Computer networks in academic environments could have many secUlity problems if there weren't enough precaution. The source of these problems is generally vulnerabilities of TCP/IP protocol and Internet. Vulnerabilities can cause threats. These threats will be analyzed in this thesis. There are many kind of countelmeasures to prevent the assets of the academic networks. Firewalls are a kind of countermeasure against these attacks. In this thesis, these countelmeasures will be also analyzed and a firewall will be designed and proposed for academic environments against these threats.
  • Master Thesis
    A Genetic Algorithmic Approach To the Differential and Linear Cryptanalysis
    (Izmir Institute of Technology, 1999) Eminağaoğlu, Mete; Koltuksuz, Ahmet Hasan
    The two most well known and recently developed methods in cryptanalysis of DES and DES-like symmetric block ciphers are difTerential and linear cryptanalysis. But these cryptanalytic attacks need to be improved due to the computational performance and storage capacity problems On the other hand, genetic algorithms can be a good solution in cases where the optimum value or near-optimum solutions are sought in complex systems or for non-linear problems. This is a valid situation for the cryptanalysis case where DES and DES-like ciphers are non-linear in structure making dilTerential and linear cryptanalysis a complex system with a very large search landscape and extreme amount of conditional and probabilistic candidates for the key being sought. In this study, a new and promising method wit h bet ter performance is to be developed for differential/linear cryptanalysis of DES and similar symmetric cryptosystems exploiting genetic algorithms' broadened search and optimum finding capacity.