Bilgisayar Mühendisliği Bölümü Tezleri

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

Browse

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

Filter results by typing the first few letters
Now showing 1 - 9 of 9
  • Item
    Citation Count: ASLAN, A. (2014). A performance and functional analysis tool for testing and maintenance of web-based application from the user perspective. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    A performance and functional analysis tool for testing and maintenance of web-based application from the user perspective
    (2014) Aslan, Alper; Çankaya Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Bölümü
    This thesis focuses on the performance stability score (PSS) of the Web-Based Application Workflow (WBAW) and gathers the automated virtual user response times, repeated with scheduled periods, to calculate the best successful response interval heuristically. The lack of server-side hardware, network and application resources can affect the end-user Internet browsing experience negatively. This kind of negative effects can be monitored only on the end-user web browser. The virtual user browser scripts can be used to monitor the problems. The name of the application, developed, is called "MyToolset". It is designed and implemented by using the open source technologies. The research on this subject aims to monitor the performance degradation and failures on WBAW weekly, raise appropriate alerts and calculate the performance stability score. Furthermore, MyToolset reports the WBAW failures by taking the snapshot of the end-user browser perspective as evidence. The entire mathematical model is based on the calculation of this idea. Live graphics and comparable charts are used to report the results. After custom consecutive performance degradations and failures occur, MyToolset will raise the alerts. The thesis concludes that the WBAW and PSS is used for monitoring, test automation and helping the capacity planning of server-side resources, WBAW works on, such as hardware, network and applications
  • Item
    Citation Count: Al-Shaikh, Nawfal Fathi Abdulqader (2018). Active defense strategy against jamming attack in wireless sensor networks / Kablosuz sensör ağlarında karıştırma saldırılarına karşı aktif savunma stratejisi. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Active defense strategy against jamming attack in wireless sensor networks
    (Çankaya Üniversitesi, 2018) Al-Shaikh, Nawfal Fathi Abdulqader; Çankaya Üniveristesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı
    Wireless Sensor Network WSN been utilized increasingly nowadays due to its benefits and its ability of collecting data from reachable or unreachable fields also if fields fixed or movable. Progressive developments in WSN techniques adds efficiency, reliability and better power management but it still vulnerable and sensitive to some kinds security threats. The most effective threat to WSN is DOS attacks which is detectable but unpreventable yet. An authentication defense approach against DOS attack with additional Jamming attack that prevents transferring data between attacked node in a cluster and cluster head node is considered as a base to develop an algorithm with ability of bypassing attacked path via alternative safe one under control of cluster head to mitigate the False Node Excluding DOS due to jamming attack. Both original and enhanced methods implemented using MATLAB and tested by comparing both results and behavior with arbitrary study case. Enhanced algorithm shows good response in mitigating FNEDOS attack.
  • Item
    Citation Count: Hawi, Mohammed Kadhim (2016). An approach to improve the time complexity of dynamic provable data possession / Dinamik kanıtlanabilir veri depolanmasında zaman karmaşıklığını geliştirmek için bir yaklaşım. Yayımlanmamış yüksek lisans tezi. Ankara. Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    An approach to improve the time complexity of dynamic provable data possession
    (Çankaya Üniversitesi, 2016) Hawi, Mohammed Kadhim; Çankaya Üniveristesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı
    In this thesis, we aim to take some actions for alleviating the fears when the data storage over outsourcing, and guarantee the integrity of the files in cloud computing. In this study, we have suggested some ideas to improve FlexDPDP scheme [13]. Particularly, proposed scheme successfully reduces the time complexity for verifying operations between the client and the server. The proposed scheme is a fully dynamic model. We involved some parameters to ensure the integrity of the metadata. In spite of the fact that auxiliary storage expenditure by Client-side (the client stores approximately 0.025% size of the raw file). The remarkable enhancement in this proposed scheme is reducing the complexity. The complexity of the communications and the computations decreased to O(1) in both Client-side and Server-side during the dynamically update (insertion, modification and deletion operations) and challenge operations.
  • Item
    Citation Count: Alfalahi, Mohammed Abdulmunem Nsaif (2017).Automatic scoring approach for Arabic short answers essay questions / Arap dilinde metin sorularını kısa sürede cevaplamak için otomatik puanlama yaklaşımı. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Automatic scoring approach for Arabic short answers essay questions
    (Çankaya Üniversitesi, 2017) Alfalahi, Mohammed Abdulmunem Nsaif; Çankaya Üniveristesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı
    There are different types of questions produced by the students in their exams, such as multiple-choice questions, true/false questions, and essay questions which require free text answers. Evaluation and scoring these types of exams traditionally are an exhausting process that takes from the instructors a lot of efforts, time and activities. In this regard, applying automated approaches to evaluate and score exams are essentially required to reduce time and efforts. Although there are many commercial tools for scoring multiple-choice and true/false questions, yet there is lack of approaches and tools for evaluating and scoring essay questions, especially for the Arabic language. In this research, the aim is to propose an automated scoring approach for short answers to Arabic essay questions. The scoring process is based on the similarity between the student's answer and model answer which is provided by the instructor. Cosine similarity measures will be used for this purpose. Cosine similarity is a heuristic evolutionary measure that has succeeded to solve text to text similarity problems. In this research, we will use the word root for each keyword in the student's answer and the model answer in order to achieve accurate results. The proposed approach will be tested on a data set proposed and will be compared to other approaches.
  • Item
    Citation Count: ÖZÇETİN, M. (2013). Developing a GIS based crime analysis system. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Developing a GIS based crime analysis system
    (2013) Özçetin, Mustafa; Çankaya Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Bölümü
    Geographic Information Systems (GIS) have a lot of applications that are getting more and more importance in our daily life. One of the hot and crucial application areas of GIS is crime mapping. Nowadays, crime rates tend to increase and thus analyzing the crime trends and taking preventive precautions are very important. Often, crimes display spatial or temporal patterns. For instance, some crime types are committed in some areas with a relatively higher density rate. Some others may occur in particular time ranges in a day. Adding geographic support to crime analysis methods can provide extremely valuable and exclusive benefits which tabular or statistical analyses cannot provide. For example, seeing the spatial distribution of a particular crime type or comparing different types of crimes on the map can give critical and important decision making tips for managers. Hence, adding spatial dimension to crime analysis techniques help provide great contributions to police departments. In this study, after doing some researches about crime mapping, a GIS-based crime analysis system, namely Crime Analyzer, has been developed from scratch. Crime Analyzer not only provides various spatial and temporal analysis tools but also presents a flexible method to extract data from various sources such as database systems to solve crime mapping problems. Keywords: GIS Based Crime Analysis, Crime Mapping Software
  • Item
    Citation Count: ALJADİR, T. (2015). Measurement of system security issues of private computer networks for different types of attacks. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Measurement of system security issues of private computer networks for different types of attacks
    (2015) Aljadir, Taha; Çankaya Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Bölümü
    In this thesis, two different types of Remote Access Virtual Private Network protocols (PPTP and SSL) have been established virtually using Virtual Lab. In addition, different types of security attacks have been applied to each protocol under the same conditions. For each attack, different tools were applied separately to each protocol. Moreover, the attacks were used to target different components for each VPN. The results were studied carefully, which led to obtaining a good security analysis used later to compare between those protocols under the test conditions and to give recommendations to use each of those protocols
  • Item
    Citation Count: ALMALLAHMED, O.M. (2015). Noise cancellation using adaptive filter algorithms. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Noise cancellation using adaptive filter algorithms
    (2015) Almallahmed, Omar Mohyalden; Çankaya Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Bölümü
    The aim of this research is to study the theoretical adaptive filters for noise canceling problem. Firstly, it describes the notion using adaptive filters. Secondly, it presents three more common adaptive filters the RLS, NLMS and LMS algorithms. In addition, it describes the implementation of adaptive filters. Furthermore, the aim of this study is to solve some of the noise problems that affect the performance of the systems. The use of Noise Canceling theories is the most important solution for this problem, and for that research adaptive filters are used to solve these problems. The most important algorithms for these filters are RLS, NLMS and LMS algorithms. The research tests these algorithms with adaptive filters applications (noise cancellation, signal prediction, system identification, echo cancellation), and have chosen the best algorithm based on the value of Mean Square Error (MSE). The research presents two examples of a solution for the noise problem of the voice signal using Simulink MATLAB for different environments. The first example is active noise canceling theory, where, the color noise and then white noise (Gaussian noise) on the audio signal is used, after that three algorithms RLS, LMS, NLMS are applied to the audio signal to detect and cancel both noises. The second example is Channel Equalization, which also applies the three algorithms to solve the very same problem. Finally, the results of this Simulink are discussed and future work is present
  • Item
    Citation Count: Alsamurai, Ather Abdulrahem Mohammedsaed (2017). Text categorization based on semantic similarity with word2vector / Word2vector ile semantik benzerliğe dayanan metin kategorizasyonu. Yayımlanmış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Text categorization based on semantic similarity with word2vector
    (Çankaya Üniversitesi, 2017) Alsamurai, Ather Abdulrahem Mohammedsaed; Çankaya Üniveristesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı
    With an increase in online information, which is mostly in the form of a text document, there was a need to organize it so that management and retrieval by the search engine became easier. It is difficult to manually organize these documents, therefore, machine-learning algorithms can be used to classify and organize them. Mostly, they are faster, more accurate and less expensive than manual classification. Most traditional approaches of machine learning algorithms depend on the term frequency in determining the importance of the term within a document and neglect semantically similar words. For this reason, we proposed to build a classifier based on semantically similar words in text classification by using the Word2Vector model as a tool to compute the similarity between documents and capture the correct topic. So we built two models by applying three phases: the first phase, we applied preprocessing steps and the second phase, we created a dictionary for top ten categories of Reuters 21578 datasets and the final phase we trained Word2Vector model on the Wikipedia English dataset and use it to compute similarity v between documents. Depending on the results of our study, we found that the second model (the most similar predicted topic) is better than the first model (average based predicted topic) in all categories. When we compare the results of our study with other studies, we found that result of our study is a parallel to the results of other studies, but not overcome them, although these studies use feature selection in the improvement of their results while we use feature extraction in explaining of our results.
  • Item
    Citation Count: Karadeniz, Talha (2016). Writer identification based on covariance features / Kovaryans niteliklerine dayalı yazar belirleme. Yayımlanmamış yüksek lisans tezi. Ankara: Çankaya Üniversitesi Fen Bilimleri Enstitüsü.
    Writer identification based on covariance features
    (Çankaya Üniversitesi, 2016) Karadeniz, Talha; Çankaya Üniveristesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Anabilim Dalı
    Local descriptors have been widely utilized in image analysis for automatic object categorization. In this work, an algorithm based on empirical covariance estimation of region descriptor vectors is formulated and developed. This technique is then specialized in order solve to the task of writer identification via a tricky way of keypoint extraction. Experiment results are reported for ETH-80 and ICFHR 2012 Writer Identification Contest datasets.