Theses supervised by Prof. Dr. Yalçın Çebi
12 theses · Dokuz Eylül University
Text conversion system between Turkic dialects
Turkic communities come from a common culture; however the interaction with other communities over years caused diversion especially in written language. A system which can automatically translate documents written in different Turkic languages will be an important step towards eliminating the disunity of Turkic communities on written work of art over past ninety years and obtaining fusion of Turkic communities. In this study, a rule-based and semi-supervised machine translation system (MT-Turk), which is designed for closely related Turkic languages and implemented on Turkish, Kirghiz and Kazan Tatar, is presented. MT-Turk is an extensible bidirectional translation infrastructure in which new Turkic dialects can be added by just adding the lexicon of roots/stems, suffixes, and the rules. Furthermore, it is open to extension by suggestion. In order to form a multilingual machine translation infrastructure, two subsets of rule-based approach, the interlingual machine translation approach and transfer-based approach were used in combination to achieve extensibility and interoperability. The success of the translation process was evaluated using both BLEU and NIST metrics. The evaluated scores were between 5.04 and 15.12 for BLEU, between 3.12 and 4.64 for NIST in unsupervised translation and between 7.20 and 21.71 for BLEU, between 3.52 and 4.77 for NIST in semi-supervised translation for various language pairs and translation directions. Depending on these results, it was seen that the efficiency of the translation process is extremely dependent on the size of the lexicon and the rule base. Keywords: Machine translation, natural language processing, rule-based machine translation, multi-word expressions, Turkic dialects, Turkish, Kirghiz, Kazan Tatar
Network security parameters and their optimization
Security in computer networks and Internet comprise serious issues in today's dynamic work environment. Besides increasing new vulnerabilities and exploits, sometime even a fully patched system or network have security gaps,therefore network and system administrators should focus on the best setting for decreasing vulnerabilities in the network. In order to protect single users, companies, customers and business partners from the attacks of hackers, it is needed to think just like a hacker.It is also essential to decrease and stop loopholes of network and set Operating System and third party devices in a best optimized situation. In order to find these weaknesses penetration testsshould be used. Due to the daily development of the information technology, a certain vulnerability or attack refuses to workafter a certain time but the knowledge about the software and third party devices can help identifying similar behaviors in the future. In this thesis, it is aimed to give basic information to network administrators about network security and common network vulnerabilities to identify and explain a suitable penetration testing methodology. Besides illustrate some free and open source network surveying tools, port scanners, vulnerability scanners to simulate possible attacks that network and system administrators can use against their network or system during a penetration test were also given. For this purpose, the network scanning and penetrating tools were analyzed and Nmap, Nessus and Metasploit open source software are selected. The testbedused in this thesis consists of one firewall andtwo systems representing two hosts which are located in two different networks.The experiments were carried out on these networks and found that, there were some vulnerabilities existingin the testbed.
Obtaining the three-dimensional structure of the current environment by using fiber grating laser system
It is a necessity that the mobile robots should determine first the obstacles in the environment in which they are located, and then depending on their dimensions, the free areas between the obstacles. For this aim, determination of the mobile robots position is a necessity. In order to find the position of the mobile robot and the locations of the obstacles around it, systems which sense the environment with the help of the camera and provide facilities for self guidance of the mobile robot, were developed based on the development of information technologies.In the scope of this project, an omnidirectional vision system, which can be used for mobile robots and was intended to determine both the obstacles in the environment and the places through which a mobile robot can pass, by sensing the environment in a three dimensional manner, was developed. During the experiments carried out by using both the mathematical model developed to reduce the errors occurred from the hardware used in the system, and the developed software based on this model, much wider three dimensional structure of the environment was obtained, when compared with classical cameras.It was seen that, the error rates in the developed system was remained under 10 percent for all three coordinate axes. Since the location computations are continuously carried out by using the images taken consecutively, and the error rates are acceptable for the close distances, it was seen that this system can be used in mobile robots.
Rule-based natural language processing methods for Turkish
In order to determine morphological properties of a language, a corpus which represents that language should be created. Many large scale corpora generated and have been used for Natural Language Processing (NLP) applications on many languages, such as English, German, Czech, etc, but any large scale Turkish corpora have not be generated yet.In this study, natural language processing methods for Turkish were developed by using rule-based approach, and also an infrastructure, Rule-Based Automatical Corpus Generation (RB-CorGen), to use the new developed methods was implemented. For testing RB-CorGen on Turkish, the roots, stems and suffixes were obtained from Turkish Linguistic Association (Türk Dil Kurumu, TDK) and Dokuz Eylul University, College of Literature Linguistic Department, the defined tags and grammatical rules were stored in XML formatted file, and documents, include nearly 95 million wordforms, were collected from five Turkish newspapers in electronic environment. The average success rates of Rule-Based Sentence Boundary Detection (RB-SBD) and Rule-Based POS Tagging (RB-POST) methods were determined as 99.66% and 92% respectively. It was seen that the success rate of RB-CorGen increases with the increasing number of rules.
Omni-directional vision based environment sensing for movement control of mobile robots
In this thesis, a mobile robot which is equipped with an omni-directional stereo vision system using laser dots and a tilt sensor in order to achieve autonomy is presented. The proposed steps of development of the omni-directional vision system are finding the laser dot centers, developing a mathematical model for computing the depth of points in the environment, finding the feature correspondences, and error analysis for distance calculation.The vision system was comprised with two rectilinear curved mirrors and two Charge Coupled Device (CCD) cameras fitted in front of the mirrors to sense the environment in a stereo approach manner. The feature matching in stereo images was carried out by using dot-matrix laser pattern, and the pattern was obtained by using a Fiber Grating Device (FGD) scattering the laser light beam.A polynomial based algorithm was developed to find the feature pixel matching in stereo images. A mathematical model based on triangulation method was developed and used to calculate the three dimensional locations of the real points in the environment by using matched pixel pairs in two images with the help of the matching algorithm.An error calculation model based on the locations of pixels in the images was developed in order to test the vision system according to noisy data. With the help of the developed mathematical and error estimation models, the distances between the points on the objects in the environment and the vision system were determined; and by using synthetic data, the effects of noise on the error rates were analyzed.According to the results of the experiments carried out with synthetic data, it was seen that errors were occurred depending on the limitation in the resolution of the image sensors for the pixels in the images without noisy locations. After the pixel locations were corrupted by adding noise to any values of their row and column values, the resultant errors were increased.Although the error rates of X, Y and Z axes were increased according to the distance between the obstacle and the center of the vision system for the same horizontal/vertical plane, the average error rates for X (range) and Z (height) were decreased to 3.14% and 2.02%, respectively with the increasing distance between the vision system and horizontal/vertical planes for real world. In common, the main reasons of errors were the size and location of the laser points, reflection errors on the mirrors, sensitivity of the refractive lenses, misalignment of the mirror-camera pairs and limitation of the image resolution.An interface between the user and the mobile robot consisting of two control options which were joystick and tilt sensor was used to obtain the user command for movement of the robot.The system was combined with the vision system and tested in an environment having different sized and located obstacles. It was seen that, by using omni-directional vision system on a mobile robot, the obstacles can be easily detected and the mobile robot can easily pass between the obstacles.
Analysis and implementation of software test case design techniques
Software testing is a process of finding bugs in a system, and it is an essential part of the software development process. Although, software testing is still an art, numerous techniques are developed to design and implement software testing.Designing software testing requires determining software test conditions. Different software test case design techniques are used to translate test conditions into test cases. Moreover, each software test case design technique produces different test cases from the same test conditions. The test scripts, which are used during test execution, are directly formed from test conditions.The main goal of this thesis is researching software test case design techniques and their implementations. The process of determining the test conditions is described. Moreover, formal documentation of test conditions, test cases and test scripts are denoted. The requirement-based software testing, which uses software specifications to generate test cases, is analyzed. The cause-effect software test tool, which uses a requirement-based software testing method, is implemented, and its advantages and disadvantages are stated. In addition, other types of software testing tools, such as code coverage analysis tools and software test data generator tools, are described.The used software testing design and test case design techniques highly depend on the type of project. Different test design and test case design techniques can be used in each step of the software development process. Moreover, different types of tests can be applied at different test levels. In this thesis, these software test types and test levels are also mentioned.
Determination of Turkish word clauses for part of speech tagging
According to their types of duties in a sentence, the meaning of the sentence varies. Therefore, in order to determine the exact meaning of the words in a sentence, the type and duty of the words should be examined. After the type determination process, the word phrases can be obtained.In Turkish, depending on the word combinations, different word phrases can be occurred based on the types of the words. For this reason, all phrase possibilities should be considered during type determination process. After determining the word phrases, word clauses can be detected.The most common problem faced in Natural Language Processing studies for Turkish is ambiguity problem. By determining word clauses, the ambiguities can be mainly solved and most exact meanings of the words can be determined.In this study, rule based algorithm for determinant of word clauses in Turkish and software based on this algorithm was developed. It was seen that, by adding more rules to the system, the results are engetting more reliable.
An infrastructure model for collecting electronic data to develop large scale corpus
In the Dokuz Eylül University Computer Engineering Department, different studies on Natural Language Processing (NLP) have been carried out. For NLP research grammatical rules of the language must be determined and a text sample of that language, which is called as corpus, must be prepared. These sample texts should satisfy the grammar rules of language.In this study, an infrastructure for a large scale corpus is designed and implemented. A database model, which supports 6 different document type such as newspaper, report, magazine, book, parliamentary report and official gazette, is designed.By implementing the developed application depending on the database model, 195256 articles were downloaded from 5 newspapers, and their metadata was stored for future use.
Personal data protection in Turkey: An information technology framework indented for privacy risk management
In this study, it is shown that, technology originated threats on privacy can also be avoided by privacy enhancing technologies with a risk management approach.
Derin öğrenme teknikleri kullanılarak Türk makam müziği bestelenmesi
Although music and other forms of fine arts have been accepted as a part of human existence, people have developed various methods and algorithms throughout history to create new creations in these domains. Especially in the last century, with the invention of the computer and the exponential increase in its processing capacity, new computational methods in artistic creativity have been tried and interesting results have been obtained in related fields. Artificial composers, developed with Deep Learning techniques, which is a sub-field of artificial intelligence, took part in interdisciplinary studies and their artificial compositions began to be followed by those who are interested in the subject with great curiosity and interest. However, the studies of composing music using Deep Learning techniques were mostly performed on Western Music, and Turkish Maqam Music remained untouched in this arena. In the execution of this thesis, a system that can automatically compose Turkish Makam Music using Deep Learning techniques and an easy-to-use web-browser based graphical interface has been developed. The system, called Automatic Turkish Makam Music Composer (ATMMC), takes 8 starting notes from its user and creates a composition in Aksak or Düyek Usûls in one of Hicaz or Nihâvent Makams, depending on the user's preference. Artificial compositions created by ATMMC can be stored in the user's computer to be opened with Mus2 application. Generated artificial compositions were compared with the source data set according to various metrics and it was seen that there was approximately 84% similarity between the source dataset and artificial compositions. The developed system and its user interface are shared as an open-source project.
Kemoterapi plan üretme aracı geliştirilmesi
Cancer which caused by the irregular division and proliferation of cells is becoming increasingly common today. Chemotherapy is a treatment based on the use of drugs. The forms in which the treatment processes are defined according to the type of cancer are called "plan". The plans specify the drugs, active substances, supplements, application steps and other issues to be used in the treatment. The treatment process and health status can be monitored by using chemotherapy plans. Nowadays, it is seen that the plans used in chemotherapy applications consist of written documents and are stored in electronic format only in PDF or MS-Word formats. To the best of our knowledge, there is no software for direct use of these documents in information systems in treatment centers and matching and monitoring of treatment processes and plans in electronic environment. In this study, a software has been developed which can enable the generate of chemotherapy plans jointly with the various software which used in treatment centers. This software also facilitates the rearrangement of the plans according to the patients and their treatment processes. In this software, the common and different aspects of the existing plans were taken into consideration and a user-friendly interface was designed for the plan makers. This software will make it easier for clinical managers to apply their existing chemotherapy plans, as well as making changes in plans and creating new plans for them. C # .NET, .NET MVC, .NET Entity Framework and MS-SQL were used in the development of the software.
Bilişim suçlarının incelenmesi için bir çerçeve geliştirilmesi
In recent years, as a result of the widespread use of the internet and the development of technology, the number of users meeting the needs of technological tools has increased considerably. With information systems that make a rapid entry into people's lives, users are either consciously or unconsciously committing a crime or being exposed to a crime. As these crimes take up a lot of space in daily life, there is a need to redefine information crimes. Thus, private law rules and methods of finding evidence emerged. Even though all these needs have been started to be fulfilled, the integrity of the existing order has not been achieved. In particular, there are not enough resources on the methods required to detect the offender. In this thesis, legal legislation and crime types have been examined and forensic informatics steps have been included for the determination of evidence. By gathering these data, the necessary steps to identify the perpetrator have been transformed into a chain of events and a new framework has been established for information crimes. This framework makes it easy to identify the perpetrator and makes it easier to identify gaps in cybercrime. In order to, overcome these shortcomings, which are determined in the field of legislation and in the technical field, a solution proposal is also included in this thesis.