Yazar "Koca, Murat" seçeneğine göre listele
Listeleniyor 1 - 10 / 10
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Blockchain for cybersecurity: architectures and challenges(CRC Press, 2024-01-01) Avci, Isa; Koca, MuratBlockchain technology is a sophisticated database technique that facilitates the transparent exchange of information among a network of businesses. The blockchain database is designed to store data by organizing it into blocks that are interconnected in a chain-like structure. A blockchain may be defined as a cryptographic and digitally recorded register or list that securely stores data. In the context of blockchain technology, data is kept in a series of interconnected blocks arranged sequentially, like a chain. Each block has a timestamp identifying the moment of recording, along with the data that is to be registered in the registry. The data is documented in a manner that ensures accessibility and verifiability for all individuals, with the ability for anyone to get a duplicate of the register. The use of blockchain technology guarantees the transparent and safe storage of documents, eliminating the need for a centralized authority. This report provides a comprehensive analysis of the blockchain architecture. This study focuses on the analysis of the security mechanisms used in the blockchain system, with particular emphasis on the comparative evaluation of the four primary blockchain designs. The study focused on the analysis of blockchain applications concerning their implications for cybersecurity and then identified and evaluated their advantages and constraints. Furthermore, a comprehensive analysis has been conducted on the primary cybersecurity dangers that may arise inside these apps.Öğe Classification of malicious urls using naive bayes and genetic algorithm(2023) Koca, Murat; Avcı, İsa; Al-Hayanı, Mohammed Abdulkareem ShakirThe financial losses of vulnerable and insecure websites are increasing day by day. The proposed system in this research presents a strategy based on factor analysis of website categories and accurate identification of unknown information to classify safe and dangerous websites and protect users from the previous one. Probability calculations based on Naive Bayes and other powerful approaches are used throughout the website classification procedure to evaluate and train the website classification model. According to our study, the Naive Bayes approach was benign and showed successful results compared to other tests. This strategy is best optimized to solve the problem of distinguishing secure websites from unsafe ones. The vulnerability data categorization training model included in this datasheet had a better degree of precision. In this study, the best accuracy probability of 96% was achieved in Naive Bayes' NSL-KDD data set categorizationÖğe Cybersecurity Attack Detection Model, Using Machine Learning Techniques(Budapest Tech, 2023) Avci, Isa; Koca, MuratMillions of people use the web every day, in this age of technology and the internet. Protecting the privacy and security of these users is a significant challenge for cybersecurity developers. With tremendous technological advancements, there is a noticeable improvement in the cyber-attackers' capabilities. At the same time, traditional Intrusion Detection Systems (IDS) are no longer effective at detecting intrusions. After the tremendous competences achieved by Artificial Intelligence (AI) techniques in all fields, great interest has developed in its use in the field of cybersecurity. There have been many studies that use Machine Learning (ML)-based intrusion detection systems. Despite the strong performance of ML techniques in detecting malicious activities, some challenges still reduce accuracy of performance. Knowing the proper technique, as well as knowing the features, is essential for effective intrusion detection. Therefore, this study proposes an effective network intrusion detection system based on ML and feature selection techniques. The performance of four ML techniques, the Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and the Decision Tree (DT) systems for intrusion detection are explored. In addition, feature selection techniques are employed for the selection of important features. Among the techniques used, the RF technique achieved the best performance, outperforming other techniques, with an accuracy of 99.72%. This study elaborates on the detection of malicious and benign cyber-attacks, with a new-level, high accuracy.Öğe Gerçek zamanlı görüntü oluşumu için kullanılan gölgeleme algoritmalarının cuda kütüphanesi ile geliştirilmesi(Karabük Üniversitesi, 2014) Koca, Murat; Çavuşoğlu, AbdullahGerçek zamanlı gölge oluşturma: bilgisayar grafiğinde hızlı ve hatasız görüntü elde etmek adına önemli bir kavramdır. Son zamanlarda bu konu üzerine birçok çalışma yapılmıştır. Ancak bu çalışmalar yapılırken bir takım zorluklar ile karşılaşılmıştır. Bu zorluklardan en önemlisi performans artırmak ve kaliteli gölge oluşturmaktır. Temel olarak bu konuda daha önce oluşturulmuş geometri tabanlı gölge eşleme algoritmaları kullanılmıştır. Günümüzde grafik işlem birimi gücünden yararlanılarak gölge eşleme algoritmasında paralel hesaplama mimarisine sahip CUDA kütüphanesi kullanılarak performans ve kalite artışı sağlamaya çalışılmıştır. Üç boyutlu görüntü oluşturmada izlenilen görüntülerde gerçekçilik düzeyini ve performansı artırma üzerine yoğunlaşıp; saniye başına milyon sayıda üçgen gölgesi oluşturmaya çalışılmıştır.Öğe Intelligent Transportation System Technologies, Challenges and Security(Mdpi, 2024) Avci, Isa; Koca, MuratIntelligent Transportation Systems (ITS) first appeared in 1868 with traffic lights. With developing technology, the need to bring a smart approach to transportation applications within the scope of speed and environmental protection has emerged. Protecting ITS infrastructure against cyber attacks has become a matter of reputation for states. It is essential to provide the necessary technological infrastructure for the integrated operation of the systems used in ITS, especially geographical location, communication, and mapping. These technological developments bring cyber attacks, risks, and many dangers that should be avoided, especially on the systems used. This study examines ITS architecture, applications, communication technologies, and new trend technologies in detail. This study includes contributing to studies in the field of ITS and preventing attacks and incidents that may occur in terms of cyber security. The most important cyber attacks that may occur in ITS applications are included. In addition, the minimum security requirements that can be taken in ITS applications and infrastructures against these attacks are included.Öğe A Novel Security Risk Analysis Using the AHP Method in Smart Railway Systems(Mdpi, 2024) Avci, Isa; Koca, MuratTransportation has an essential place in societies and importance to people in terms of its social and economic aspects. Innovative rail systems need to be integrated with developing technologies for transportation. Systemic failures, personnel errors, sabotage, and cyber-attacks in the techniques used will cause a damaged corporate reputation and revenue losses. In this study, cybersecurity attack methods in smart rail systems were determined, and cyber events occurring worldwide through these technologies were analyzed. Risk analysis in terms of transportation safety in smart rail systems was determined by considering the opinions of 10 different experts along with the Analytic Hierarchical Process (AHP) performance criteria. Informatics experts were selected from a group of people with at least 5-15 years of experience. According to these risk analysis calculations, cybersecurity stood out as the most critical security risk at 27.74%. Other risky areas included physical security, calculated at 14.59%, operator errors at 16.20%, and environmental security at 10.93%.Öğe Optimization planning techniques with meta-heuristic algorithms in iot: performance and qos evaluation(2024) Koca, Murat; Avcı, İsaBig data analysis used by Internet of Things (IoT) objects is one of the most difficult issues to deal with today due to the data increase rate. Container technology is one of the many technologies available to address this problem. Because of its adaptability, portability, and scalability, it is particularly useful in IoT micro-services. The most promising lightweight virtualization method for providing cloud services has emerged owing to the variety of workloads and cloud resources. The scheduler component is critical in cloud container services for optimizing performance and lowering costs. Even though containers have gained enormous traction in cloud computing, very few thorough publications address container scheduling strategies. This work organizes its most innovative contribution around optimization scheduling techniques, which are based on three meta-heuristic algorithms. These algorithms include the particle swarm algorithm, the genetic algorithm, and the ant colony algorithm. We examine the main advantages, drawbacks, and significant difficulties of the existing approaches based on performance indicators. In addition, we made a fair comparison of the employed algorithms by evaluating their performance through Quality of Service (QoS) while each algorithm proposed a contribution. Finally, it reveals a plethora of potential future research areas for maximizing the use of emergent container technology.Öğe Optimization planning techniques with meta-heuristic algorithms in IoT: performance and QoS evaluation(Sakarya University, 2024-08-31) Koca, Murat; Avcı, İsaBig data analysis used by Internet of Things (IoT) objects is one of the most difficult issues to deal with today due to the data increase rate. Container technology is one of the many technologies available to address this problem. Because of its adaptability, portability, and scalability, it is particularly useful in IoT micro-services. The most promising lightweight virtualization method for providing cloud services has emerged owing to the variety of workloads and cloud resources. The scheduler component is critical in cloud container services for optimizing performance and lowering costs. Even though containers have gained enormous traction in cloud computing, very few thorough publications address container scheduling strategies. This work organizes its most innovative contribution around optimization scheduling techniques, which are based on three metaheuristic algorithms. These algorithms include the particle swarm algorithm, the genetic algorithm, and the ant colony algorithm. We examine the main advantages, drawbacks, and significant difficulties of the existing approaches based on performance indicators. In addition, we made a fair comparison of the employed algorithms by evaluating their performance through Quality of Service (QoS) while each algorithm proposed a contribution. Finally, it reveals a plethora of potential future research areas for maximizing the use of emergent container technology.Öğe The Place of Stock Photography as a Digital Commerce in Turkey(Springer International Publishing Ag, 2022) Avci, Isa; Koca, Murat; Uysal, BusraWith the development of technologies, digital commerce is increasing in many sectors today. The concept of digital commerce has gained more importance in recent years due to the pandemic. Stock photography, which is a branch of digital commerce and passive income model, is a sector that has no development in Turkey and benefits from foreign-sourced services. This study aims to find a domestic solution to this issue and make a study that will facilitate the work of digital content producers. In order to carry out these studies, it is necessary to follow and implement the websites and the innovations that come with web 2.0. In addition, the software used forms the basis of every detail that serves its purpose. The fact that the software used in stock photography is flexible and has a structure that meets the needs increases the work's applicability. In the globalizing world, giving importance to such issues has become as important as health and education. The state of development in countries' economies is such an essential issue that it can direct these issues worldwide. Working on this issue will contribute significantly to developing countries and digital commerce in terms of stock photography. Especially in this study, evaluations will be made regarding the place and application areas of stock photography as digital commerce in Turkey.Öğe Predicting DDoS Attacks Using Machine Learning Algorithms in Building Management Systems(Mdpi, 2023) Avci, Isa; Koca, MuratThe rapid growth of the Internet of Things (IoT) in smart buildings necessitates the continuous evaluation of potential threats and their implications. Conventional methods are increasingly inadequate in measuring risk and mitigating associated hazards, necessitating the development of innovative approaches. Cybersecurity systems for IoT are critical not only in Building Management System (BMS) applications but also in various aspects of daily life. Distributed Denial of Service (DDoS) attacks targeting core BMS software, particularly those launched by botnets, pose significant risks to assets and safety. In this paper, we propose a novel algorithm that combines the power of the Slime Mould Optimization Algorithm (SMOA) for feature selection with an Artificial Neural Network (ANN) predictor and the Support Vector Machine (SVM) algorithm. Our enhanced algorithm achieves an outstanding accuracy of 97.44% in estimating DDoS attack risk factors in the context of BMS. Additionally, it showcases a remarkable 99.19% accuracy in predicting DDoS attacks, effectively preventing system disruptions, and managing cyber threats. To further validate our work, we perform a comparative analysis using the K-Nearest Neighbor Classifier (KNN), which yields an accuracy rate of 96.46%. Our model is trained on the Canadian Institute for Cybersecurity (CIC) IoT Dataset 2022, enabling behavioral analysis and vulnerability testing on diverse IoT devices utilizing various protocols, such as IEEE 802.11, Zigbee-based, and Z-Wave.
