Master Degree / Yüksek Lisans Tezleri

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

Browse

Filters

Settings

Author: search.filters.author.Ayav, Tolga

Search Results

Now showing 1 - 10 of 25
  • Master Thesis
    Çoklu Etmen Büyük Dil Modelleri ile Doğal Dilin Niteliksel SQL Arama Sorgularına Dönüştürülmesi
    (2025) Sönmez, Simge; Ayav, Tolga
    Doğal dilden SQL'e dönüşüm (NL2SQL), kullanıcı tarafından doğal dilde ifade edilen sorguların, aynı anlamı taşıyan yapısal SQL ifadelerine çevrilmesi sürecidir. Bu işlem, uzmanlık seviyesinde SQL bilgisi gerektirir, veri bilimciler ya da iş analistleri tarafından manuel olarak gerçekleştirildiğinde zaman alıcı olabilir. Bu süreci hızlandırmak ve kolaylaştırmak için araştırmacılar, veritabanlarıyla doğal dil üzerinden iletişimi mümkün kılacak yöntemler üzerine çalışmış; kullanıcılarla veri sistemleri arasında etkili bir arayüz oluşturmayı hedeflemişlerdir. Yaklaşık otuz yıllık bir süreçte, bu alandaki yaklaşımlar, kural tabanlı gramer sistemlerinden, veritabanı bilgisinin kodlandığı (database-aware encoding) seq2seq modellere evrilmiştir. Ancak, büyük dil modellerinin (LLM'ler) ortaya çıkmasıyla birlikte bu alanda kaydedilen ilerleme önemli ölçüde hızlanmış ve daha önce ulaşılamayan bir seviyeye erişmiştir. Bu çalışmada, NL2SQL görevi, GPT gibi büyük ölçekli modellere güvenmek yerine, orta ölçekli açık kaynak dil modellerinin etkin akıl yürütme gücünden ve işbirliğinden yararlanılarak ele alınmaya çalışılmıştır. Çalışmanın amacı, çok daha az kaynak gerektiren modellerle rekabetçi bir performansın elde edilip edilemeyeceğini araştırmaktır. Bu araştırma kapsamında, üç orta ölçekli açık kaynak model — Gemma3-IT (Google), Qwen2.5 Instruct (Alibaba) ve Mistral Nemo (Mistral AI) — kullanıldı. Hem modellerin iş birliğinden ve hem de bağlamsal veritabanı içeriğinden yararlanılarak, Spider geliştirme değerlendirme setinde %81,3 yürütme doğruluğuna ulaşıldı. Bu sonuç, her bir modelin bireysel performansının üzerinde olup, C3-SQL'e kıyasla yalnızca %0,6 ve DIN-SQL'e kıyasla %1,5 daha düşüktür. Sonuçlar, çalışmanın ortaya koyduğu yaklaşımın etkinliğini göstermektedir.
  • Master Thesis
    Estrus Detection in Cows With Deep Learning Techniques
    (01. Izmir Institute of Technology, 2024) Arıkan, İbrahim; Ayav, Tolga; Soygazi, Fatih
    Accurately predicting the estrus period is essential for enhancing the efficiency and lowering the costs of artificial insemination in livestock, a crucial sector for global food production. Precisely identifying the estrus period is critical to avoid economic losses such as decreased milk production, delayed calf births, and loss of eligibility for government subsidies. Since the most obvious movement that needs to be detected during the fertilization period is mounting, it is important to detect this movement. Since manual detection of this movement is difficult and costly, automated methods were needed. Therefore, it is thought that deep learning-based methods can be applied to detect the mounting moment. The proposed method detects the estrus period using deep learning and XAI (Explainable Artificial Intelligence) techniques. Deep learning-based mounting detection is performed using CNN, ResNet, VGG-19 and YOLO-v5 models. The ResNet model in this proposed study detects mounting movement with 99% accuracy. Explainability of deep learning models describes features that aid in decision-making in detecting mounting motion. Grad-CAM and Gradient Inputs models, which are XAI techniques, are used for the black box behind the proposed models. The developed deep learning models reveal that they focus on the udder and back area of the cows during the decision-making phase. In addition, how successfully the Grad-CAM and Gradient Inputs models, which are the XAI models used for the explainability of the deep learning models trained in this study, performed the explanation process was measured by calculating the 'faithfulness', 'maximum sensitivity' and 'complexity' metrics.
  • Master Thesis
    Testing Microservice Applications
    (2023) Öztürk, Özgür; Ayav, Tolga; Demirörs, Onur
    This thesis contributes to the testing processes of microservice architecture. Microservices provide a scalable, reliable and cloud-based environment that is frequently preferred in today's technology applications. It consists of small, loosely coupled, isolated applications that work in harmony. In this study, microservice application is modeled using timed automata and model checker-based testing methods are exploited to generate test cases automatically. To this end, UPPAAL model checker tool is utilized. The model of the microservice application is mutated with respect to a set of fault hypotheses and these mutant models are verified against certain properties defined by system or application specifications. The returned counterexamples from the model checker are used to constitute the test cases. The entire process is automated and experimentally run for an example application. The generated test cases are also shown to be efficiently detect the errors. The proposed testing methodology has the benefits like a faster test generation process and achieving test cases with better fault detection capability
  • Master Thesis
    A Blockchain Application for Payment and Traffic Management in Smart Vehicles
    (Izmir Institute of Technology, 2022) Yiğitbaşı, Boğaçhan; Ayav, Tolga; Ayav, Tolga
    The proposed solution offers an alternative way to our current retail shopping of fuel fees. It can be applied to any retail shopping process but this phase of the project is considered an initiation of upcoming. The next phases of the project, include full integration with smart cars in order to handle all procedures automatically. In the traditional way, when you buy some gas from a station with your credit card, the station owner pays some fee to his bank and it has to wait for some time to be able to get that money. You as an individual have to expose your identity so they can track your shopping habits and follow your expenses. Sometimes they may offer some loyalty discounts or gifts but with really ridiculous rates. Our system offers a digital payment system based on the Ethereum blockchain. It has its own token called TRANT (Transport Token) and by this token, any client with a digital wallet (Metamask) is able to pay their gas fees without exposing their real identity -only their wallet address-, and get some rewards in terms of TRANT for their loyalties and using our DEX (Decentralized Exchange) exchange them into the ether which can be converted into real fiat money easily. On the other hand, the proposed solution also has some advantages for the other party in this equation such as gas station owners, they immediately get their money at that very first moment without any remittance.
  • Master Thesis
    Blackhole Attacks in Iot Networks
    (01. Izmir Institute of Technology, 2020) Sokat, Barış; Ayav, Tolga; Erten, Yusuf Murat
    IoT technologies are very popular today, and they are used in almost every field. Therefore, the number of IoT devices used is increasing day by day. Like every field in computer networks, security is quite important in IoT networks. However, the resource-constrained nature of IoT devices makes the study of security measures for IoT networks very challenging. In the literature research conducted before this thesis study, it was seen that it can perform a wide variety of RPL-based attacks on IoT networks. One of these attacks is the blackhole attack. Although the black hole attack is functionally simple, the damage it causes in the network can be extremely destructive. As far as it is known, in addition to the limited number of studies in this field of attack, the black hole attack used in the studies in this field has also basic features. The basic feature mentioned here is that the attacker node that will perform a black hole attack drops all the packets that come to it. When the attacker node drops all incoming packets, it causes the topology to change in the network, the number of control messages to increase and the attacker node to be isolated from the network in a short time. However, blackhole attack can be combined with different attacks. Therefore, in this thesis, the node that will perform the black hole attack is designed to allow control messages to pass, while dropping all other packets. Here, it is aimed that the attacker node remains on the network for a longer time. As a result, as long as the attacker node is active, it will be able to drop more packets and the number of control messages in the network will be controlled since the topology does not change. With the black hole attack developed as a result of the simulation tests, the number of control messages released in the network was taken under control and it was observed that the attacker node could remain in the network throughout the simulation period. Thus, the effect of different types of black hole attacks on the network that can be developed has been revealed.
  • Master Thesis
    Predictive Maintenance for Smart Industry
    (01. Izmir Institute of Technology, 2020) Asadzade, Asad; Ayav, Tolga
    After the internet of things developed rapidly, it started to be used in many several industrial areas. Thanks to IoT, data that affect the health of any equipment or other important systems are collected. When these data are processed correctly, important information about the production process is obtained. For example, thanks to this data, systems based on machine learning are created to predict when various components will fail. Thus, maintenance operations are carried out before the component's breakdown, and replacement operations are performed if necessary. This strategy, called predictive maintenance, provides industries with advantages such as maximizing the life of components, reducing extra costs, and time saving. In this study, we applied ARF method, which is based on stream learning, on Turbofan Engine Degradation Simulation Datasets which are provided by NASA to estimate the remaining useful lifetime of jet engines. As a result, we mentioned about the advantages of streaming learning over batch learning and compared our results with other batch learning based studies which are applied on the same datasets.
  • Master Thesis
    Evaluation of Scheduling Architectures for Osek/Vdx Compliant Hard Real-Time Operating Systems
    (Izmir Institute of Technology, 2020) Saydam, Berkay; Ayav, Tolga
    Technological advancements are reflected to the vehicles as well, but it brings the challenge of adding new functionalities to vehicles without compromising safety. Tasks are used to provide functionalities which are used in car. These tasks have different characterictics. Safety and performance are two main criteria to determine characterictic of tasks. Characteristics of tasks can be classified according to their safety levels which are known as Automotive Safety Integrity Levels. Designing of hardware and software and also testing them is a long progress in automotive industry. Any changes on the design of hardware is quite costly when an ECU began to be used in field. According to my hypothesis, scheduling algorithms which are used by Central Processing Unit to determine sequences of task executions, should be well known. Besides, designing of hardware and software should be done according to these characteristics and algorithms. If not, tasks will cause serious problem like missing deadline for safety-critical component. In this thesis, the scheduling architectures are evaluated and they are determined which scheduling architectures should be used for which purpose. Besides, the advantages and disadvantages are explained.
  • Master Thesis
    Internet of things simulation using cisco packet tracer
    (01. Izmir Institute of Technology, 2020) Thera, David; Ayav, Tolga; Erten, Yusuf Murat
    Nowadays, the term IoT (internet of things) have become extremely important in our life. This technology is used in many fields such as education, health, industries, agriculture and infrastructures. In order to learn and understand how this technology works, many practical learning tools are used. The aim of the thesis is to introduce a iot simulation tool, where student can simulate or build and manage the systems for better understanding of the philosophy behind iot networks. The tool used is Cisco packet tracer which is a software developed by Cisco that is used to create and simulate a virtual network, basically a wireless network, without the need for any network hardware. The tool is free of charge, and suitable to work with almost all the operating systems. Cisco packet tracer allows users to have a practical networking technology knowledge. In this thesis, "Cisco packet tracer" is used to design an internet-based home automation system or smart home.
  • Master Thesis
    Blockchain Application on Loyalty Card
    (Izmir Institute of Technology, 2020) Sönmeztürk, Osman; Ayav, Tolga; Erten, Yusuf Murat
    Today, traditional loyalty systems are insufficient to meet the needs of users. The users need to stay within the loyalty system for a long time and accumulate points in order to win prizes and besides, the rewards they receive may be out of their interest. In addition, users usually forget the awards they have won in traditional loyalty systems and have difficulty in following up rewards. In addition to that, users usually do not prefer to share their personal information to join loyalty systems due to privacy concerns. Therefore, the number of customers in the loyalty systems is decreasing day by day. The designed loyalty program mentioned in this thesis works with IZTECH Tokens, which works on the Ethereum chain and are created by following ERC20 standards. Thanks to the new generation loyalty system, users can convert their earned tokens to Ethereum on the stock exchange without accumulating them or can receive services or products with the accumulated tokens according to their interests from a market that has been contracted by the manufacturer. Additionally, users in the designed system do not need to carry many cards, it is adequate to have only one Ethereum wallet. Furthermore, users do not need to share any personal data to join the loyalty system. Markets can request Ether from the manufacturer according to the number of tokens they have accumulated. The loyalty system mentioned in this thesis not only aims to establish a win-win relationship between the manufacturer, market, and client but also to find solutions to the customer problems mentioned above.
  • 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.