Master Degree / Yüksek Lisans Tezleri

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

Browse

Filters

1997 - 199992000 - 2009522010 - 201972

Settings

End date: 2019Department: search.filters.department.Thesis (Master)--İzmir Institute of Technology, Computer Engineering

Search Results

Now showing 1 - 10 of 133
  • Master Thesis
    Robustness of Fingerprint Verification Algorithms Against Synthetic Deformations
    (Izmir Institute of Technology, 2019) Cantürk, Sinem; Erdoğmuş, Nesli
    Fingerprint recognition is one of the biometric techniques used for the identification of humans. The developments and research about fingerprint recognition to date are of great importance in advancing fingerprint recognition and verification scenarios. The fact that fingerprint recognition systems are used almost everywhere and are easily accessible is directly proportionate to a large amount of research in these areas. During the acquisition of the fingerprint, there are many environmental factors that may affect the quality of the print and eventually, its ability to be recognized. For a fingerprint recognition algorithms, it is important to handle the difficulties that arise due to those variations. The aim of the thesis is to obtain and compare the results of not only an existing feature-based fingerprint recognition techniques but a fingerprint recognition technique that uses deep learning. The main focus is on how fingerprint verification algorithms behave under the circumstances of synthetically distorted fingerprint images. After developing two different verification systems, the goal is to compare system results with and without distorted images. The results of the two methods with and without externally added deformations effect on the fingerprint image is compared. The first system has a feature-based approach comparing the images via local features on the fingerprint. In order to do this two different descriptors that are called ORB and SIFT are used. In the feature-based approach, there is also a matching part and this part is tried with two different matching algorithms that are called Brute Force Matcher and Approximate Nearest Neighbor (ANN) matcher. The second algorithm makes the decision of match or non-match by feeding the raw fingerprint images as an input to a deep neural network and comparing the feature vectors calculated by the network. This study has revealed that deep neural network approach has given more robust and faster results on both the original dataset and distorted versions of the dataset.
  • Master Thesis
    Block-Chain Based Remote Update for Embedded Devices
    (Izmir Institute of Technology, 2019) Kaptan, Melike; Ayav, Tolga; Erten, Yusuf Murat
    This research work is an attempt to devise a platform to send automatic remote updates for embedded devices. In this scenario there are Original Equipment Manufacturers (OEMs), Software suppliers, Block-Chain nodes, Gateways and embedded devices. OEMs and software suppliers are there to keep their software on IPFS (Inter Planetary File System) and send the meta-data and hashes of their software to the Block-Chain nodes in order to keep this information distributed and ready to be requested and used. There are also gateways which are also the members of the Block-Chain and IPFS network. Gateways are responsible for asking for a specific update for specific devices from IPFS database using the meta-data standing on the Block-Chain. And they will send those hashed secure updates to the devices. In order to provide a traceable data keeping platform gateway update operations are handled as a transactions in the second block-chain network which is the clock-chain of the gateways. In this study implementation of the two block chain shows us that, even though the calculation overhead of the member devices, with regulations specific to the applications block-chains provide applicable platforms.
  • Master Thesis
    Implementation and Performance Analysis of Contex-Aware Role-Based Access Controls for Cloud-Based Iot Platform
    (Izmir Institute of Technology, 2019) Döşemeci, Mete Merthan; Ayav, Tolga
    IoT has received substantial attention in both industry and the scholarly world in the recent years. The main idea is to interconnect the physical world with the digital world. Sensors read physical world and present processible data. This data needs to be secured. Currently, most of the cloud based IoT platforms use some sort of Role-Based Access Control (RBAC) , which is one of the approaches to control access to the devices, hence the data. In some cases RBAC is insufficient for fulfilling constantly changing requirements of IoT. ABAC (Attribute Based Access Control) can be flexible enough for fulfilling. However ABAC requires higher level of maintenance. We wanted to implement a access control method that uses both RBAC’s and ABAC’s advantages. We called it OBAC(Operation Based Access Control). Authorization is being implemented in a plug and play manner. We implemented that way because; It is designed for cloud platforms and we wanted to switch between access control methods easily. The results of the experiment shows that proposed access control(OBAC) had minimum latency and management steps across other access control methods.
  • Master Thesis
    Container Damage Detection and Classification Using Container Images
    (Izmir Institute of Technology, 2019) İmamoğlu, Zeynep; Tuğlular, Tuğkan; Baştanlar, Yalın
    In the logistics sector, digital transformation is of great importance in terms of competition. In the present case, container warehouse entry / exit operations are carried out manually by the logistics personnel including container damage detection. During container warehouse entry / exit process, the process of detecting damaged containers is carried out by the personnel and several minutes are required to upload to the system. The aim of this thesis is to automate detection of damaged containers. This way, the mistakes made by the personnel in this stage will be eliminated and the process will be accelerated. In this thesis, we propose a machine learning method which detects damaged containers using the container images to perform statistical damaged / undamaged estimation. We modeled the problem as a binary classification problem, which considers a container as damaged or undamaged. The result obtained from the undertaken studies shows that there is no single best method for visual classification. It is shown how the dataset was created and how the parameters used in the layered structure impact the most suitable model could be created for this study.
  • Master Thesis
    Estimation of Low Sucrose Concentrations and Classification of Bacteria Concentrations With Machine Learning on Spectroscopic Data
    (Izmir Institute of Technology, 2019) Mezgil, Bahadır; Baştanlar, Yalın; Baştanlar, Yalın
    Spectroscopy can be used to identify elements. In a similar way, there are recent studies that use optical spectroscopy to measure the material concentrations in chemical solutions. In this study, we employ machine learning techniques on collected ultraviolet-visible spectra to estimate the level of sucrose concentrations in solutions and to classify bacteria concentrations. Some metal nanoparticles are very sensitive to refraction index changes in the environment and this helps to detect small refraction index changes in the solution. In our study, gold nanoparticles are used and we benefited from this property to estimate sucrose concentrations. The samples in different low sucrose concentration solutions are obtained by mixing the sucrose measured with precision scales with pure water and then the UV-Vis spectrum of each sample is measured. For the bacteria concentration solutions, spectra for six different bacteria concentrations are captured. Spectra of the same solutions are also captured before adding the bacteria. For each of these solutions, four sets are prepared where gold nanoparticles are not grown (minute 0) and grown for 4 minutes, 10 minutes and 12 minutes. After the dataset preparation, these spectrum measurements are transferred into MATLAB environment as sucrose concentration dataset and bacteria solution dataset. Then the necessary preprocessing steps are performed in order to get the most informative and distinguishing information from these datasets. The raw measurement values and processed spectrum measurements are trained with shallow Artificial Neural Networks (ANN) on MATLAB Deep Learning Toolbox and Support Vector Machine (SVM) on MATLAB Statistics and Machine Learning Toolbox. When the results of the conducted machine learning experiments are examined, success rate is promising for the estimation of sucrose concentrations and very high for classification of bacteria concentrations in pure water solution.
  • Master Thesis
    Effectiveness of Using Clustering for Test Case Prioritization
    (Izmir Institute of Technology, 2019) Günel, Can; Ayav, Tolga; Ayav, Tolga
    Software testing is one of the most important processes in the software development life cycle. As software evolves, previous test cases need to be re-executed to make sure that there is no new bugs introduced and nothing is broken in the existing behaviours. However, re-execution of all test cases could be expensive. That is why, test case prioritization method can be used to detect faults earlier by prioritizing the test cases which could have the higher possibility than others to find faults. Studying different approaches, implementing different techniques or putting these techniques to test on different programs could make it easier to answer which technique should be used for which kind of programs or faults. We address this issue, focusing on selecting different test case prioritization approaches and calculating the average fault detection ratios of prioritized test suites. As a novelty, we propose to perform an optimization algorithm on one of the approaches called `Clustering` to increase its efficiency. To do that, our main objective is determined as maximizing the distance between each clusters by using the coverage information. The distance is measured as the difference of covered functions of test cases in a test suite. In the end, this study will give a hint about selection of test case prioritization technique to be used by checking the empirical results of the experiments.
  • Master Thesis
    A Learning-Based Demand Classification Service With Using Xgboost in Institutional Area
    (Izmir Institute of Technology, 2019) Gürakın, Çağrı; Ayav, Tolga
    This study, purposes to explain the development stages and methodology of data classification service that has a text-based adaptable programming interface. One of the successful classification algorithms, XGBoost, was preferred in the study. The dataset that is used in the study obtained by 'Digital Business Tracking Application' of a name anonymized company. The dataset is tested by using different classification algorithms and detailed performance evaluation was conducted. As a result, highest accuracy rate is obtained with 'Data Classification Service' which was developed by using XGBoost algorithm.
  • Master Thesis
    Digital font generation using long short-term memory networks
    (Izmir Institute of Technology, 2019) Temizkan, Onur; Özuysal, Mustafa
    Long Short-Term Memory (LSTM) Networks are powerful models to solve sequential problems in machine learning. Apart from their use on sequence classification, LSTMs are also used for sequence prediction. Predictive features of LSTMs have been used extensively to generate handwriting, music and several other types of sequences. Configuration and training of LSTM networks are relatively more arduous than non-sequential models, especially when input data is complex. In this research, the aim is to train LSTM networks and its different variations, use their generative features on a relatively obscure and complex type of sequences in machine learning; digital fonts. Controlled experiments have been performed to find the effects of different model parameters, input encodings or network architectures on learning font based sequences. All in all, in this document; the procedure of creating a dataset from digital fonts are provided, training strategies are demonstrated and the generative results are discussed.
  • Master Thesis
    A Dedicated Server Design for Physical Web Applications
    (Izmir Institute of Technology, 2019) Abdennebi, Anes; Ayav, Tolga
    With the huge impressive technological improvements the world is witnessing where giants like Facebook, Google, Apple, Microsoft and other technology companies are offering different services to millions of clients, services which don’t take usually more than seconds to be within the users’ devices besides the Physical Web applications that makes things interacts, having entities and can be reached based on the proximity context without omitting the incoming IoT infrastructure that would make 20.4 billion devices connected by 2020, the amount of data transferred, and services provided will be enormous and along with that, the big energy consumer standing behind providing clients with the needed data and services instantly, the web servers. Although it has a magnificent performance and responds to billions of queries and requests, however, there is still a crucial point which must be highlighted, the remarkable amounts of energy consumption by these servers. Therefore, this work is proposing a new approach in order to reduce the energy consumption in such a scenario where the 18-core energy efficient computer Parallella board will be used in order to create an energy efficient server that can offer many services triggered by various devices or any ordinary web requests across any environment and to prove also that using a cluster of Parallella supercomputers may perform as other similar servers dealing with web content (e.g. Raspberry Pi server). We will show how would these boards work under low energy feeding where users can access a web content hosted on a Parallella cluster. The source codes of the project are available on GitHub.
  • Master Thesis
    Extended Topology Analysis of a Detection Mechanism Implementation Against Botnet Based Ddos Flooding Attack in Sdn
    (Izmir Institute of Technology, 2019) Karakış, Emre; Erten, Yusuf Murat; Tomur, Emrah
    When SDN comes up as a new technology, while it also brings many benefits such as high availability, scalability and performance, it also brings us new vulnerabilities that is targeted by attackers. Botnet Based DDoS Flooding Attacks have been one of the major problems for service provider networks who encountered these repeatedly since the first DDoS came into existence in the early 2000’s. In this thesis, we mainly concentrate on the source-based detection approach against Botnet Based DDoS Flooding Attack by combining the strength of SDN and s-Flow-RT technology. The main purpose of this research is to detect Botnet Based DDoS Flooding Attack that can also be performed in distributed SDN environments by using a similar approach with an available detection mechanism which is not implemented previously on an extended network with more network elements in order to observe whether the obtained successful results on the small network are compatible with a result obtained on this research. This study also includes a detection application using previously studied detection approach based on statistical inference model. The detection application is tested on virtual environments by organizing a Botnet Based DDoS Flooding Attacks on a predefined source node and then test results show that the mechanism could effectively detect the attack.