- Advanced Malware Detection Techniques
- Network Security and Intrusion Detection
- Educational Methods and Analysis
- Image and Object Detection Techniques
- Industrial Vision Systems and Defect Detection
- Radiomics and Machine Learning in Medical Imaging
- Anomaly Detection Techniques and Applications
- Education Practices and Challenges
- Cultural and Sociopolitical Studies
- Music Education and Analysis
- Lung Cancer Diagnosis and Treatment
- AI in cancer detection
- Linguistics and Cultural Studies
- Natural Language Processing Techniques
- Spam and Phishing Detection
- Video Analysis and Summarization
- High-Velocity Impact and Material Behavior
- Image Retrieval and Classification Techniques
- Emotion and Mood Recognition
- Advanced Neural Network Applications
- Face recognition and analysis
- Speech and Audio Processing
- Image Enhancement Techniques
- Quality Function Deployment in Product Design
- Scientific and Engineering Research Topics
Marmara University
2015-2025
Altınbaş University
2017
Turkish Society of Hypertension and Renal Diseases
2017
Istanbul University
2015-2017
Pamukkale University
2017
Yıldız Technical University
2015
TU Dortmund University
2008-2009
In recent years, due to the extensive use of Internet, number networked computers has been increasing in our daily lives. Weaknesses servers enable hackers intrude on by using not only known but also new attack-types, which are more sophisticated and harder detect. To protect from them, Intrusion Detection System (IDS), is trained with some machine learning techniques a pre-collected dataset, one most preferred protection mechanisms. The used datasets were collected during limited period...
In recent years, due to the emergence of boundless communication paradigm and increased number networked digital devices, there is a growing concern about cybersecurity which tries preserve either information or technology system. Intruders discover new attack types day by day, therefore prevent these attacks firstly they need be identified correctly used intrusion detection systems (IDSs), then proper responses should given. IDSs, play very crucial role for security network, consist three...
Phishing websites are malicious sites which impersonate as legitimate web pages and they aim to reveal users important information such user id, password, credit card information. Detection of these phishing is a very challenging problem because mainly semantics-based attack, especially abuses human vulnerabilities, however not network or system vulnerabilities. As software detection scheme, two main approaches widely used: blacklists/whitelists machine learning approaches. Machine solutions...
In this study, a computer-aided detection (CAD) system was developed for the of lung nodules in computed tomography images. The CAD consists four phases, including two-dimensional and three-dimensional preprocessing phases.
Super-resolution techniques are employed to enhance the quality of digital images. Color spaces developed model colors in various environments. In literature, several studies suggest that applying color space transformations and subsequently employing super-resolution on transformed im-ages improve image quality. This study analyzes impact trans-formations applications. The analysis is conducted by performing process entirely RGB space, followed converting obtained result into a different...
Gerçek zamanlı çalışan sistemlerde görüntü işleme uygulamaları yapmak son zamanlarda oldukça popüler olan bir konu haline gelmiştir. Yapay zekâ alanının alt dallarından biri derin öğrenme yöntemleri ve görüntülerden nesne tespiti yapma alanında kullanılan algoritmaları birlikte kullanılarak, otonom otomobiller, insansız hava araçları, yardımcı robot teknolojileri, engelli yaşlı bireyler için asistan teknolojileri gibi birçok alanda uygulamalar geliştirilmektedir. Yapılan çalışmada, görme...
Intrusion detection systems (IDSs) analyze internet activities and traffic to detect potential attacks, thereby safeguarding computer systems. In this study, researchers focused on developing an advanced IDS that achieves high accuracy through the application of feature selection ensemble learning methods. The utilization CIC-CSE-IDS2018 dataset for training testing purposes adds relevance study. study comprised two key stages, each contributing its significance. first stage, reduced...
In recent years, almost all the real-world operations are transferred to cyber world and these market computers connect with each other via Internet. As a result of this, there is an increasing number security breaches networks, whose admins cannot protect their networks from types attacks. Although most attacks can be prevented use firewalls, encryption mechanisms, access controls some password protections mechanisms; due emergence new type attacks, dynamic intrusion detection mechanism...
ÖzThis paper presents a computer aided detection (CAD) system which uses wiener filter based approach for of defects in poplin fabric.The defective fabric images are taken with the help digital camera.The developed consists three phases, including preprocessing, segmentation and defect.In preprocessing phase, RGB to gray level conversion image enhancement operations were applied camera images.In background segmented using morphologic operations.Then, was converted binary facilitate defect...
One of the best methods learning in programming courses depends on practical exercises. But preparing, collecting and grading homework manually takes time. When number students increases given reduces. This reduces effectiveness whole course. way to solve this problem is distributing through an automatic system getting back fast feedback. paper describes such a that grades automatically. using test driven software development technologies are being used by those methods. tested with 8 course...
Abstract Social networking sites (SNSs) are a popular Internet‐based means for users to communicate and interact with each other. Although they have caught the attention of many researchers already being used as educational tools, very few studies investigated effects using an SNS in engineering education. This study, therefore, aims analyze Edmodo platform teaching learning support tool on students’ academic practical performance Introduction Information Technology Algorithms course, well...
Solid waste management, which includes collection, transportation, disposal and recycling, is a critical environmental issue increasing in severity due to industrialization, urban population growth consumption. In this study, we present vehicle routing approach based on the ant colony optimization algorithm. We work real-world data of Maltepe Municipality, Istanbul, Turkey. The experimental results show that estimate shortest route path with 13% efficiency compared existing route. believe...
Unmanned Aerial Vehicle (UAV) technology is being used increasingly for military and civilian purposes. The primary reason this increase that UAVs eliminate the risk to human life in difficult dangerous missions, are cost effective, easily deployed. Developments UAV decreasing costs have increased usage. However, when multiple deployed, inter communication becomes complicated. For reason, multi-UAV systems most important problem needs be solved. To enable among without infrastructure...
Blockchain is an emerging technology whose extraordinary advantages make it popular. applications are not limited to cryptocurrencies; can be used in many areas, including smart ownership. Blockchain-based land registry systems have great potential thanks their of high-level security and no intermediary transactions. Although the requirements vary by country, common all them eye-catching conveniences that a blockchain-based system brings. We examined process Turkey, which consists eight...
The latest version and the use of video streaming platforms is increasing day by day, adding new ones. Competition also in development for expanding film TV series. purpose replicating these to achieve more, better quality on some platforms, keep them one platform even better. Before that, series artificial intelligence algorithms. In this study, aim create more attractive cover photos user finding suitable frames from a movie or converting into cover/thumbnail images platform. It based...
In recent years, despite of the increasing use design experiments (DoE) in development drug product formulation, it has still not been sufficient. It known that using DoE is very useful particularly formulation solid and semi-solid dosage forms including many components process parameters with unknown effect on outputs. Proper selection also important at least as instead old approaches such trial error. Non-correctly selected type or inappropriately applied measurements results only wasted...
This article consists of a collection slides from the author's conference presentation. No English translation this document was provided by author or organizers.
The use of video broadcasting platforms is increasing day by day. competition for developing the and sharing movies TV series increasing. purpose reproducing these to increase quality trace them on a single platform. Film artificial intelligence algorithms shares. aim this study create more attractive cover photos users finding suitable frames from movie or series. First, that were transformed into covers/small pictures platform obtained. Unnecessary which consist closed eyes, blurry frames,...