Gökçay, Erhan

Profile Picture
Profile URL
https://hdl.handle.net/20.500.14411/7011
Name Variants
Gokcay, E
E.,Gökçay
Gökçay,E.
E., Gökçay
G.,Erhan
Gokcay E.
Goekcay, Erhan
Gokcay, Erhan
Erhan, Gokcay
Gökçay, Erhan
E., Gokcay
GOKCAY, E
Erhan, Gökçay
Gokcay,E.
Gökçay E.
G., Erhan
E.,Gokcay
Job Title
Doktor Öğretim Üyesi
Email Address
erhan.gokcay@atilim.edu.tr
Main Affiliation
Software Engineering
Status
Website
ORCID ID
0000-0002-4220-199X
Scopus Author ID
7004217859
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
JOK-0734-2023

Sustainable Development Goals

NO POVERTY1
NO POVERTY
0
Research Products
ZERO HUNGER2
ZERO HUNGER
0
Research Products
GOOD HEALTH AND WELL-BEING3
GOOD HEALTH AND WELL-BEING
1
Research Products
QUALITY EDUCATION4
QUALITY EDUCATION
0
Research Products
GENDER EQUALITY5
GENDER EQUALITY
0
Research Products
CLEAN WATER AND SANITATION6
CLEAN WATER AND SANITATION
0
Research Products
AFFORDABLE AND CLEAN ENERGY7
AFFORDABLE AND CLEAN ENERGY
0
Research Products
DECENT WORK AND ECONOMIC GROWTH8
DECENT WORK AND ECONOMIC GROWTH
0
Research Products
INDUSTRY, INNOVATION AND INFRASTRUCTURE9
INDUSTRY, INNOVATION AND INFRASTRUCTURE
1
Research Products
REDUCED INEQUALITIES10
REDUCED INEQUALITIES
0
Research Products
SUSTAINABLE CITIES AND COMMUNITIES11
SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
RESPONSIBLE CONSUMPTION AND PRODUCTION12
RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
CLIMATE ACTION13
CLIMATE ACTION
0
Research Products
LIFE BELOW WATER14
LIFE BELOW WATER
0
Research Products
LIFE ON LAND15
LIFE ON LAND
0
Research Products
PEACE, JUSTICE AND STRONG INSTITUTIONS16
PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
PARTNERSHIPS FOR THE GOALS17
PARTNERSHIPS FOR THE GOALS
0
Research Products
Documents

16

Citations

400

h-index

7

Go to Scopus profile
Documents

15

Citations

293

Go to WoS profile
Scholarly Output

21

Articles

6

Views / Downloads

28/70

Supervised MSc Theses

6

Supervised PhD Theses

2

WoS Citation Count

36

Scopus Citation Count

55

Patents

0

Projects

0

WoS Citations per Publication

1.71

Scopus Citations per Publication

2.62

Open Access Source

4

Supervised Theses

8

JournalCount
Multimedia Tools and Applications3
2017 IEEE 1st Ukraine Conference on Electrical and Computer Engineering, UKRCON 2017 - Proceedings -- 1st IEEE Ukraine Conference on Electrical and Computer Engineering, UKRCON 2017 -- 29 May 2017 through 2 June 2017 -- Kyiv -- 1317631
24th IEEE International Conference on Electronics, Circuits and Systems (ICECS) -- DEC 05-08, 2017 -- Batumi, GEORGIA1
7th International Conference on Cloud Computing and Services Science (CLOSER) -- APR 24-26, 2017 -- Porto, PORTUGAL1
8th International Conference on Cloud Computing and Services Science (CLOSER) -- MAR 19-21, 2018 -- Funchal, PORTUGAL1
Current Page: 1 / 3

Scopus Quartile Distribution

Competency Cloud

GCRIS Competency Cloud

Filters

2017 - 2019102020 - 202511
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 10 of 21
  • Thumbnail Image
    Master Thesis
    Videoda Nesne Takibi için Hibrit Metot Geliştirmesi
    (2019) Taşan, Hakan; Gökçay, Erhan
    Videodaki nesnenin algılanması ve takibi, bilgisayarla görü ve görüntü işlemede önemli bir araştırma alanı olarak ortaya çıkmıştır. Nesne takibi için birçok algoritma geliştirilmiştir ve her algoritmanın başarılı veya başarısız olduğu bazı koşullar vardır. Bu tezde, videoda nesne takibi amacıyla üç nesne tespiti ve takibi algoritmasından oluşan güçlü bir karma sistem önerilmiştir. Bunlar şablon eşleştirme, renk histogramı ve özellik çıkarımına dayalı SURF algoritmalarıdır. Bu algoritmaları hibrit sistemde uygulamak için OpenCV kütüphanesi kullanılmıştır. Algoritmalar uygulanırken; gaussian blur, renk uzayı dönüşümleri, Otsu eşiklemesi, kayan pencere yaklaşımı, özellik çıkarımı ve betimlemesi, ve uzaklık hesaplamaları gibi farklı teknikler uygulanmıştır. Videodaki herhangi bir nesne seçilebilir ve seçilen nesne videonun geri kalanında takip edilebilir. Nesnenin tıkanmasını önlemek ve sahnenin ani hareketinin etkilerini en aza indirmek için, videonun her beşinci karesinde seçilen nesnenin yenilenmesi yaklaşımı kullanılır. Hibrit sistemin amacı, video karelerindeki takip edilecek nesnenin tespit oranını iyileştirmektir. Tüm performans testleri NTU-VOI 2018, Visual Tracker Benchmark 2013, NfS 2017 ve Davis 2017 veri setleri üzerinde gerçekleştirilmiştir. Önerilen hibrit sistemin test sonuçları, üç ayrı tespit ve takip algoritmasının sonuçlarıyla karşılaştırılmıştır. Sonuçlar, hibrit sistemin video nesne takibi için işlem süresi dışında en iyi performansı verdiğini göstermektedir.
  • Thumbnail Image
    Article
    Entropy Based Streaming Big-Data Reduction With Adjustable Compression Ratio
    (Springer, 2023) Gokcay, Erhan
    The Internet of Things is a novel concept in which numerous physical devices are linked to the internet to collect, generate, and distribute data for processing. Data storage and processing become more challenging as the number of devices increases. One solution to the problem is to reduce the amount of stored data in such a way that processing accuracy does not suffer significantly. The reduction can be lossy or lossless, depending on the type of data. The article presents a novel lossy algorithm for reducing the amount of data stored in the system. The reduction process aims to reduce the volume of data while maintaining classification accuracy and properly adjusting the reduction ratio. A nonlinear cluster distance measure is used to create subgroups so that samples can be assigned to the correct clusters even though the cluster shape is nonlinear. Each sample is assumed to arrive one at a time during the reduction. As a result of this approach, the algorithm is suitable for streaming data. The user can adjust the degree of reduction, and the reduction algorithm strives to minimize classification error. The algorithm is not dependent on any particular classification technique. Subclusters are formed and readjusted after each sample during the calculation. To summarize the data from the subclusters, representative points are calculated. The data summary that is created can be saved and used for future processing. The accuracy difference between regular and reduced datasets is used to measure the effectiveness of the proposed method. Different classifiers are used to measure the accuracy difference. The results show that the nonlinear information-theoretic cluster distance measure improves the reduction rates with higher accuracy values compared to existing studies. At the same time, the reduction rate can be adjusted as desired, which is a lacking feature in the current methods. The characteristics are discussed, and the results are compared to previously published algorithms.
  • Thumbnail Image
    Article
    Citation - WoS: 13
    Citation - Scopus: 16
    A Novel Data Encryption Method Using an Interlaced Chaotic Transform
    (Pergamon-elsevier Science Ltd, 2024) Gokcay, Erhan; Tora, Hakan
    We present a novel data encryption approach that utilizes a cascaded chaotic map application. The chaotic map used in both permutation and diffusion is Arnold's Cat Map (ACM), where the transformation is periodic and the encrypted data can be recovered. The original format of ACM is a two-dimensional mapping, and therefore it is suitable to randomize the pixel locations in an image. Since the values of pixels stay intact during the transformation, the process cannot encrypt an image, and known-text attacks can be used to get back the transformation matrix. The proposed approach uses ACM to shuffle the positions and values of two-dimensional data in an interlaced and nested process. This combination extends the period of the transformation, which is significantly longer than the period of the initial transformation. Furthermore, the nested process's possible combinations vastly expand the key space. At the same time, the interlaced pixel and value transformation makes the encryption highly resistant to any known-text attacks. The encrypted data passes all random-data tests proposed by the National Institute of Standards and Technology. Any type of data, including ASCII text, can be encrypted so long as it can be rearranged into a two-dimensional format.
  • Thumbnail Image
    Conference Object
    Citation - WoS: 1
    Citation - Scopus: 2
    An on Demand Virtual CPU Arhitecture based on Cloud Infrastructure
    (Scitepress, 2017) Gokcay, Erhan
    Cloud technology provides different computational models like, including but not limited to, infrastructure, platform and software as a service. The motivation of a cloud system is based on sharing resources in an optimal and cost effective way by creating virtualized resources that can be distributed easily but the distribution is not necessarily parallel. Another disadvantage is that small computational units like smart devices and less powerful computers, are excluded from resource sharing. Also different systems may have interoperability problems, since the operating system and CPU design differs from each other. In this paper, an on demand dynamically created computational architecture, inspired from the CPU design and called Cloud CPU, is described that can use any type of resource including all smart devices. The computational and data transfer requirements from each unit are minimized. Because of this, the service can be created on demand, each time with a different functionality. The distribution of the calculation over not-so-fast internet connections is compensated by a massively parallel operation. The minimized computational requirements will also reduce the interoperability problems and it will increase fault tolerance because of increased number of units in the system.
  • Thumbnail Image
    Master Thesis
    Frekans Alanında Görüntü Sınıflandırma İçin Konvolüsyonel Sinir Ağlarının Uygulanması
    (2024) Dağı, Göktuğ Erdem; Gökçay, Erhan; Tora, Hakan
    Bu tezde, Evrişimsel Sinir Ağları (CNN'ler) son yıllarda çeşitli görüntü işleme ve bilgisayarlı görme görevlerinde dikkate değer başarılar elde etmiştir. Geleneksel CNN'ler doğrudan uzaysal alan görüntüleri üzerinde çalışır. Bununla birlikte, Hızlı Fourier Dönüşümü (FFT) yoluyla elde edilen görüntülerin frekans alanı gösterimi, piksel değerlerinin ilişkisizleştirilmesi ve hesaplama karmaşıklığında potansiyel azalma gibi benzersiz avantajlar sunar. Bu tez, görüntü sınıflandırmasını ve tanıma doğruluğunu artırmak için FFT ile dönüştürülmüş görüntülerin CNN algoritmalarına girdi olarak kullanılmasının etkilerini araştırmayı amaçlamaktadır. Araştırma, FFT'nin teorik temellerinin ve özelliklerinin kapsamlı bir incelemesiyle başlıyor. Daha sonra CNN'ler için ön işleme ardışık düzenlerinde FFT'nin entegrasyonunu araştırıyor. Giriş görüntülerini uzamsal alandan frekans alanına dönüştürerek, CNN'lerin en önemli frekans bileşenlerine odaklanarak daha verimli öğrenebileceğini, dolayısıyla yakınsama oranlarını ve genel performansı potansiyel olarak iyileştirebileceğini varsayıyoruz. Bunun etkinliğini değerlendirmek için CIFAR-10 (Kanada İleri Araştırma Enstitüsü), MNIST (Modifiye Ulusal Standartlar ve Teknoloji Enstitüsü)-Digits ve MNIST-Fashion dahil olmak üzere çeşitli kıyaslama veri setleri kullanılarak deneyler gerçekleştirildi. yaklaşmak. FFT ile dönüştürülmüş görüntüler çeşitli CNN mimarilerine beslendi ve sonuçlar, geleneksel uzaysal alan girdileri kullanılarak elde edilenlerle karşılaştırıldı. Sınıflandırma doğruluğu, eğitim süresi ve hesaplamalı kaynak kullanımı gibi ölçümler titizlikle analiz edildi. Sonuçlar, FFT tabanlı ön işlemenin, özellikle veri kümelerinin yüksek frekanslı gürültü veya gereksiz bilgi içerdiği senaryolarda, sınıflandırma doğruluğunda iyileştirmelere yol açabileceğini göstermektedir. Ancak faydaların farklı veri kümeleri ve ağ mimarileri arasında farklılık göstermesi, FFT ön işlemenin etkililiğinin bağlama bağlı olabileceğini düşündürmektedir. Sonuç olarak bu tez, FFT ön işlemesinin CNN iş akışlarına dahil edilmesinin görüntü işleme görevlerini geliştirme konusunda umut vaat ettiğini göstermektedir. Bulgular, hem uzaysal hem de frekans alanı bilgisinden yararlanan hibrit modellerin geliştirilmesi ve FFT tabanlı tekniklerin diğer sinir ağı türlerine ve makine öğrenimi algoritmalarına uygulanması da dahil olmak üzere gelecekteki araştırmalar için yollar önermektedir. Bu çalışma, bilgisayarlı görme alanını geliştirmek için frekans alanı analizinin derin öğrenme metodolojileriyle nasıl sinerjik olarak entegre edilebileceğinin daha geniş bir şekilde anlaşılmasına katkıda bulunmaktadır.
  • Thumbnail Image
    Article
    Citation - WoS: 1
    Citation - Scopus: 1
    A New Multi-Target Compiler Architecture for Edge-Devices and Cloud Management
    (Gazi Univ, 2022) Gokcay, Erhan
    Edge computing is the concept where the computation is handled at edge-devices. The transfer of the computation from servers to edge-devices will decrease the massive amount of data transfer generated by edge-devices. There are several efficient management tools for setup and connection purposes, but these management tools cannot provide a unified programming system from a single source code/project. Even though it is possible to control each device efficiently, a global view of the computation is missing in a programming project that includes several edge-devices for computation and data analysis purposes, and the devices need to be programmed individually. A generic workflow engine might automate part of the problem using standard interfaces and predefined objects miming on edge-devices. Nevertheless, the approach fails in fine-tuning each edge-device since the computation cannot be moved easily among devices. This paper introduces a new compiler architecture to control and program edge-devices from a single source code. The source code can be distributed to multiple edge-devices using simple compiler directives, and the transfer and communication of the source code with multiple devices are handled transparently. Fine-tuning the source code and code movement between devices becomes very efficient in editing and time. The proposed architecture is a lightweight system with fine-tuned computation and distribution among devices.
  • Thumbnail Image
    Article
    Citation - WoS: 3
    Citation - Scopus: 3
    An Information-Theoretic Instance-Based Classifier
    (Elsevier Science inc, 2020) Gokcay, Erhan
    Classification algorithms are used in many areas to determine new class labels given a training set. Many classification algorithms, linear or not, require a training phase to determine model parameters by using an iterative optimization of the cost function for that particular model or algorithm. The training phase can adjust and fine-tune the boundary line between classes. However, the process may get stuck in a local optimum, which may or may not be close to the desired solution. Another disadvantage of training processes is that upon arrival of a new sample, a retraining of the model is necessary. This work presents a new information-theoretic approach to an instance-based supervised classification. The boundary line between classes is calculated only by the data points without any external parameters or weights, and it is given in closed-form. The separation between classes is nonlinear and smooth, which reduces memorization problems. Since the method does not require a training phase, classified samples can be incorporated in the training set directly, simplifying a streaming classification operation. The boundary line can be replaced with an approximation or regression model for parametric calculations. Features and performance of the proposed method are discussed and compared with similar algorithms. (C) 2020 Elsevier Inc. All rights reserved.
  • Thumbnail Image
    Article
    Citation - WoS: 13
    Citation - Scopus: 21
    A Generalized Arnold's Cat Map Transformation for Image Scrambling
    (Springer, 2022) Tora, Hakan; Gokcay, Erhan; Turan, Mehmet; Buker, Mohamed
    This study presents a new approach to generate the transformation matrix for Arnold's Cat Map (ACM). Matrices of standard and modified ACM are well known by many users. Since the structure of the possible matrices is known, one can easily select one of them and use it to recover the image with several trials. However, the proposed method generates a larger set of transform matrices. Thus, one will have difficulty in estimating the transform matrix used for scrambling. There is no fixed structure for our matrix as in standard or modified ACM, making it much harder for the transform matrix to be discovered. It is possible to use different type, order and number of operations to generate the transform matrix. The quality of the shuffling process and the strength against brute-force attacks of the proposed method is tested on several benchmark images.
  • Thumbnail Image
    Conference Object
    Citation - Scopus: 1
    Effect of Secret Image Transformation on the Steganography Process
    (Institute of Electrical and Electronics Engineers Inc., 2017) Buke,M.; Tora,H.; Gokcay,E.
    Steganography is the art of hiding information in something else. It is favorable over encryption because encryption only hides the meaning of the information; whereas steganography hides the existence of the information. The existence of a hidden image decreases Peak Signal to Noise Ratio (PSNR) and increases Mean Square Error (MSE) values of the stego image. We propose an approach to improve PSNR and MSE values in stego images. In this method a transformation is applied to the secret image, concealed within another image, before embedding into the cover image. The effect of the transformation is tested with Least Significant Bit (LSB) insertion and Discrete Cosine Transformation (DCT) techniques. MSE and PSNR are calculated for both techniques with and without transformation. Results show a better MSE and PSNR values when a transformation is applied for LSB technique but no significant difference was shown in DCT technique. © 2017 IEEE.
  • Thumbnail Image
    Master Thesis
    Akciğer Kanseri Histopatolojik Görüntü Sınıflandırmasının K-kat Çapraz Doğrulama ve Vahanade Tabanlı Dijital Görüntü İşleme Hattı Kullanılarak Geliştirilmesi
    (2025) Vesek, Mehmet Çağlar; Gökçay, Erhan
    Küresel kanser ölümlerinin önde gelen nedeni olan akciğer kanseri, kesin ve etkili tanı çözümleri gerektirir. Bu çalışma, LC25000 veri setinden yinelenenleri kaldırarak, üç sınıfta 14195 dengeli görüntüye (4727/4744/4724) düşüren yeni bir ön işleme adımı sunar; bu daha önce belgelenmemiş bir iyileştirmedir. 5 katlı çapraz doğrulama (5 epoch) altında InceptionResNetV2 ve ConViT-Small kullanılarak yapılan ilk sınıflandırma, hiperparametre ayarlaması olmadan benzeri görülmemiş bir maliyet etkinliği göstererek neredeyse mükemmel doğruluk (≤6 hata) elde etti. Daha düşük hesaplama gereksinimi nedeniyle seçilen ConViT-Small, TIFF dönüştürme ve renk normalizasyonu yoluyla daha da optimize edildi. Test edilen yöntemler arasında, Vahanade'nin dönüşümü Reinhard ve hibrit tekniklerden (örn. DCT-DWT, CLAHE) daha iyi performans göstererek, mükkemel doğruluk (0 hata), Kappa ve MCC puanları elde etti. Veri seti iyileştirme, hafif derin öğrenme ve sağlam görüntü işlemeyi entegre ederek, bu çalışma yüksek doğruluklu akciğer kanseri sınıflandırmasını ilerletiyor ve tıbbi görüntüleme için ölçeklenebilir çözümler sunuyor.