Researcher:
Yüksel, Buket

Profile Picture
ORCID

Job Title

Teaching Faculty

First Name

Buket

Last Name

Yüksel

Name

Name Variants

Yüksel, Buket

Email Address

Birth Date

Filters

2014 - 20173

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.75382b74-5a89-4bc1-8223-0050584ecf8c

Search Results

Now showing 1 - 3 of 3
  • Placeholder
    PublicationMetadata only
    RGB-D object recognition using deep convolutional neural networks
    (Ieee, 2017) N/A; Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Zia, Saman; Yüksel, Buket; Yüret, Deniz; Yemez, Yücel; Master Student; Teaching Faculty; Faculty Member; Faculty Member; Department of Computer Engineering; Graduate School of Sciences and Engineering; College of Engineering; College of Engineering; College of Engineering; N/A; 326941; 179996; 107907
    We address the problem of object recognition from RGB-D images using deep convolutional neural networks (CNNs). We advocate the use of 3D CNNs to fully exploit the 3D spatial information in depth images as well as the use of pretrained 2D CNNs to learn features from RGB-D images. There exists currently no large scale dataset available comprising depth information as compared to those for RGB data. Hence transfer learning from 2D source data is key to be able to train deep 3D CNNs. To this end, we propose a hybrid 2D/3D convolutional neural network that can be initialized with pretrained 2D CNNs and can then be trained over a relatively small RGB-D dataset. We conduct experiments on the Washington dataset involving RGB-D images of small household objects. Our experiments show that the features learnt from this hybrid structure, when fused with the features learnt from depth-only and RGB-only architectures, outperform the state of the art on RGB-D category recognition.
  • Placeholder
    PublicationMetadata only
    Research issues for privacy and security of electronic health services
    (Elsevier, 2017) Department of Computer Engineering; Department of Computer Engineering; Department of Computer Engineering; Yüksel, Buket; Küpçü, Alptekin; Özkasap, Öznur; Teaching Faculty; Faculty Member; Faculty Member; Department of Computer Engineering; College of Engineering; College of Engineering; College of Engineering; 326941; 168060; 113507
    With the prevalence of information and communication technologies, Electronic Health Services (EHS) are commonly used by patients, doctors, and other healthcare professionals to decrease healthcare costs and provide efficient healthcare processes. However, using EHS increases the concerns regarding security, privacy, and integrity of healthcare data. Several solutions have been proposed to address these issues in EHS. In this survey, we categorize and evaluate state-of-the-art electronic health system research based on their architecture, as well as services including access control, emergency access, sharing, searching, and anonymity methods by considering their cryptographic approaches. Our survey differs from previous EHS related surveys in being method-based such that the proposed services are classified based on their methods and compared with other solutions. We provide performance comparisons and state commonly used methods for each category. We also identify relevant open problems and provide future research directions.
  • Placeholder
    PublicationMetadata only
    Control network programming development environments
    (World Scientific and Engineering Academy and Society, 2014) Kratchanov, Kostadin; Golemanov, Tzanko; Golemanova, Emilia; Department of Computer Engineering; Yüksel, Buket; Teaching Faculty; Department of Computer Engineering; College of Engineering; 326941
    In this paper we discuss the unusual distinctive features of Control Network Programming as a hybrid programming paradigm. We postulate the maxim "Primitives + Control Network = Control Network Program", and use this observation in the design of programming environments for developing Control Network Programming projects. The various possible approaches to building such environments are the main focus of the paper, together with a relatively detailed presentation of the currently most powerful locally run SpiderCNP environment with graphical editing and tracing, as well as two light-weight and ready-to-use cloud-based environments. An extended survey of cloud compilers and IDEs is also included.