Merdan Ozkahraman

Mr. Merdan Ozkahraman

Department of Mechatronics Engineering, Isparta University of Applied Sciences
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 December 2021 in Düzce Üniversitesi Bilim ve Teknoloji Dergisi
Verified
Journal Article
Closed access
PDF file
HBHilmi Cenk Bayrakçi
Hilmi Cenk Bayrakçi
RÇRabia Sultan Çi̇çEkdemi̇r
Rabia Sultan Çi̇çEkdemi̇r
MOMerdan Ozkahraman
Merdan Ozkahraman
Ülkemizde ve dünyada en önemli problemlerden birisi de su problemidir. Su tüketiminin en çok olduğu alanlar arasında tarım sektörü gelmektedir. Tarımda sulamada kullanılan önemli yöntemlerden birisi de damla sulama yöntemidir. Damlama sulama sisteminde bitkilerin köküne su vererek büyümesi sağlanarak daha az su tüketilmesi sağlanmaktadır. Ayrıca önemli noktalardan birisi de her bitkinin su ihtiyacının farklı olmasıdır. Çalışmada örnek bölgelerden ve açık erişimli internet sitelerinden toplanan İl, ilçe, bitkinin türü gibi veriler ışığında tespit edilen su harcama miktarına göre veri seti oluşturulmuştur. Elde edilen veri seti üzerinde farklı yapay zekâ algoritmaları kullanılarak harcanan su miktarı tahmin edilmeye çalışılmıştır. En doğru sonucu veren yapay zekâ modeli için ara yüz programı hazırlanarak kullanıcının ara yüz programından girmiş olduğu değerlere göre en doğru su harcama miktarını veren ve sonucu ekranda görüntüleyen bir sistem oluşturulmuştur.

15 October 2022 in Tehnicki vjesnik - Technical Gazette
Verified
Journal Article
Closed access
PDF file
MOMerdan Ozkahraman
Merdan Ozkahraman
HLHaydar Livatyali
Haydar Livatyali
Production systems using robotic manipulators have become common in the last few decades, and the trend is towards fenceless cells that save from space. Thus, the safety and flexibility of these systems have become more critical. The safety systems a...

9 December 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
MOMerdan Ozkahraman
Merdan Ozkahraman
CYCuneyt Yilmaz
Cuneyt Yilmaz
HLHaydar Livatyali
Haydar Livatyali
A two-dimensional (2-D) camera system with a real-time image processing-based safety technology is a cost-effective alternative that needs optimization of the cell layout, the number of cameras, and the camera’s locations and orientations. A design optimization study was performed using the multi-criteria linear fractional programming method and considering the number of cameras, the resolution, as well as camera positions and orientations. A table-top experimental setup was designed and built to test the effectiveness of the optimized design using two cameras. The designs at optimal and nonoptimal parameters were compared using a deep learning algorithm, ResNet-152. To eliminate blind spots, a simple but novel 2-D image merging technique was proposed as an alternative to commonly employed stereo imaging methods. Verification experiments were conducted by using two camera resolutions with two graphic processors under varying illuminance. It was validated that high-speed entrances to the safety system were detected reliably and with a 0.1 s response time. Moreover, the system was proven to work effectively at a minimum illuminance of 120 lux, while commercial systems cannot be operated under 400 lux. After determining the most appropriate 2-D camera type, positions, and angles within the international standards, the most cost-effective solution set with a performance-to-price ratio up to 15 times higher than high-cost 3-D camera systems was proposed and validated.

30 December 2021 in International Journal of 3D Printing Technologies and Digital Industry
Verified
Journal Article
Open access
PDF file
TPTolga Palandiz
Tolga Palandiz
HBHilmi Cenk Bayrakçi
Hilmi Cenk Bayrakçi
MOMerdan Ozkahraman
Merdan Ozkahraman
Günümüzde sürekli olarak ilerlemekte olan teknolojik gelişmeler ile yapay zeka hayatımızın vazgeçilmez bir parçası haline gelmiştir. Yapay sinir ağlarının kullanıldığı çalışma alanlarından birisi de ulaşımdır. Ulaşım alanında olası kazaların azaltılması amacıyla sürücü destek sistemleri uygulamalarında yapay zeka kullanılmaktadır. Bu çalışmada hem trafik işaret levhalarının fotoğraflarının çekilmesiyle bireysel olarak oluşturulan veri seti hem de açık kaynak erişimli internet sitesinden (kaggle.com) elde edilen veri seti olmak üzere toplamda 4000 adet trafik işaret levhası görüntüsüne ait resimlerden oluşan veri seti kullanılmıştır. Veri seti 3200 adet eğitim verisi ve 800 adet test verisi içermektedir. Hazırlanan veri setleri CNN (Evrişimli Sinir Ağları) modeliyle birlikte ResNet50, MobileNetV2 ve NASNetMobile olmak üzere üç farklı derin öğrenme metoduyla eğitilerek eğitim doğruluğu, test doğruluğu, eğitim kaybı ve test kaybı faktörlerine göre performansları değerlendirilmiştir. ResNet50 metoduyla eğitim doğruluğu %97.62, test doğruluğu %78.75, eğitim kaybı %0.1 ve test kaybı %6.28 olmuştur. MobileNetV2 metoduyla eğitim doğruluğu %97.8, test doğruluğu %48.12, eğitim kaybı %0.38 ve test kaybı %38.34 olmuştur. NASNetMobile metoduyla eğitim doğruluğu %98.56, test doğruluğu %41.56, eğitim kaybı %0.1 ve test kaybı %17.28 olmuştur.

31 August 2024 in Sakarya University Journal of Science
Verified
Journal Article
Open access
PDF file
MEMustafa Emre Erbil
Mustafa Emre Erbil
MOMerdan Ozkahraman
Merdan Ozkahraman
HBHilmi Cenk Bayrakçı
Hilmi Cenk Bayrakçı
In the context of the widespread application of robotics technology across numerous industrial sectors, the security of data communication in industrial robot arms emerges as a paramount concern. These robotic arms are instrumental in enhancing productivity and safety in a variety of fields, including but not limited to transportation, agriculture, construction, and mining, by automating tasks and reducing human exposure to hazardous conditions. This paper proposes a novel hybrid encryption strategy to fortify the data security of these industrial robot arms, particularly focusing on preventing data breaches during both wired and wireless communications. The suggested encryption framework combines the strengths of Elliptic Curve Cryptography (ECC) for its efficient asymmetric encryption capabilities, ChaCha20 for its rapid and low-energy symmetric encryption, and Poly1305 for ensuring data integrity through its message authentication code (MAC) algorithm. By leveraging these technologies, the paper outlines the development and application of a secure communication protocol, implemented using Python, that guarantees the confidentiality and integrity of data shared among robot arms and between these arms and their control systems. Additionally, the research conducts a comparative analysis between the ECC-based method and the RSA encryption standard, highlighting the efficiency and effectiveness of the proposed hybrid approach through various tests on different data types and sizes. The findings illustrate a marked improvement in safeguarding against potential data leaks, thereby significantly contributing to the enhancement of industrial robot arms' data security. This study not only addresses the pressing need for robust data protection mechanisms in the face of evolving cyber threats but also sets a benchmark for future research in the field of industrial robotics security.

19 January 2025 in Journal of Applied Polymer Science
Verified
Journal Article
Open access
MOMerdan Ozkahraman
Merdan Ozkahraman
MKmevlüt yunus Kayacan
mevlüt yunus Kayacan
AKAli Nadi Kaplan
Ali Nadi Kaplan
An extensive experimental analysis was conducted to assess the thermal, acoustic, magnetic, and electrical properties of composite materials reinforced with varying ratios of silicon carbide (SiC) and alumina (Al₂O₃) powders, with a focus on enhancing the functionality of robotic arms. This study underscores the innovative potential of these materials for applications in robotics. Mechanical tests showed that composites with 5% SiC and 95% resin achieved a maximum compressive stress of 68 MPa, meeting the structural demands of robotic components. Higher SiC content improved thermal conductivity, reaching 0.25 W/m·K, advantageous for managing heat in robotic joints and actuators. Acoustic testing demonstrated an average sound transmission loss of 20 dB, effectively reducing noise in robotic operations. Additionally, magnetic permeability and electrical permittivity tests revealed that composites with 10% SiC and 90% resin had the highest magnetic energy storage capacity, with a real permeability of 3.5 H/m, providing enhanced electromagnetic shielding. These findings offer valuable insights into optimizing composite materials for robotic arms, demonstrating the importance of experimental validation in developing advanced, multifunctional materials for robotic applications.