Büyükkaya, Eliya

Profile Picture
Name Variants
Büyükkaya, Eliya
E.,Büyükkaya
E. Büyükkaya
Eliya, Büyükkaya
Buyukkaya, Eliya
E.,Buyukkaya
E. Buyukkaya
Eliya, Buyukkaya
Job Title
Dr. Öğr. Üyesi
Email Address
Elıya.buyukkaya@khas.edu.tr
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Scholarly Output

4

Articles

2

Citation Count

0

Supervised Theses

1

Filters

2017 - 201932020 - 20211
Reset filters

Settings

Scholarly Output Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    Master Thesis
    Vehicle Classification Using Magnetic Sensor Data
    (Kadir Has Üniversitesi, 2019) Uçar, Mustafa Said; Büyükkaya, Eliya; Büyükkaya, Eliya
    Bilgisayarların hesaplama gücündeki artış her gecen gün daha zor problemlerin çözümünü kolaylaştırmaktadır. Özellikle numerik sensör verileri düşünüldüğünde insan ile kıyaslanıldığında, bilgisayarlar tartışmasız daha fazla veri işleme kapasitesine sahip. Bilgisayar tabanlı sistemler, uygun modeller ve veri setleri kullanıldığında, günlük hayattaki problemlerimizi çözmektedirler. Otomatize edilmiş araç sınıflandırma sistemleri hem Şehirlerin çevre düzenlemelerinde, yol planlamalarında önemli bir rol oynamaktadır. Çeşitli sensörler ve kamera sistemleri kullanılarak devam eden çalışmalar halen yapılmakta. Bu çalışmada, araçların manyetik alan verisi toplanıldı, işaretlendi ve 2 farklı veri seti oluşturuldu. Her iki veri seti, çeşitli Makine Öğrenmesi ve Sinir Ağları modelleriyle eğitildi ve sonuçları kıyaslandı. Bu çalışmada yapılan katkı, ileriki çalışmalarda da kullanılmak üzere veri seti oluşturulmasıdır. Advancements in computational power allow us to create more complex systems to solve various complicated problems. Considering numerical sensor values, computers are able to process more and more data compared to humans. Computer-based systems provide useful statistics, and predictions for problems and helps us to solve our problems in daily life. Automated vehicle classification plays an important role in City Environmental Planning and will play an even more important role when the Self-Driving Vehicles increased in traffic. Experiments on several different sensor and camera systems are ongoing. In this study, we collect magnetic field sensor data of passing vehicles and created two datasets. Multi-class classification algorithms using Neural Networks developed and key parameters are compared. Also, popular Machine Learning algorithms also trained and evaluated. The main contribution of this research is data collection; the creation of a dataset for further research and development.
  • Thumbnail Image
    Article
    Vcc-Bps: Vertical Collaborative Clustering Using Bit Plane Slicing
    (PUBLIC LIBRARY SCIENCE, 2021-01) Ishaq, Waqar; Büyükkaya, Eliya; Büyükkaya, Eliya; Ali, Mushtaq; Khan, Zakir
    The vertical collaborative clustering aims to unravel the hidden structure of data (similarity) among different sites, which will help data owners to make a smart decision without sharing actual data. For example, various hospitals located in different regions want to investigate the structure of common disease among people of different populations to identify latent causes without sharing actual data with other hospitals. Similarly, a chain of regional educational institutions wants to evaluate their students' performance belonging to different regions based on common latent constructs. The available methods used for finding hidden structures are complicated and biased to perform collaboration in measuring similarity among multiple sites. This study proposes vertical collaborative clustering using a bit plane slicing approach (VCC-BPS), which is simple and unique with improved accuracy, manages collaboration among various data sites. The VCC-BPS transforms data from input space to code space, capturing maximum similarity locally and collaboratively at a particular bit plane. The findings of this study highlight the significance of those particular bits which fit the model in correctly classifying class labels locally and collaboratively. Thenceforth, the data owner appraises local and collaborative results to reach a better decision. The VCC-BPS is validated by Geyser, Skin and Iris datasets and its results are compared with the composite dataset. It is found that the VCC-BPS outperforms existing solutions with improved accuracy in term of purity and Davies-Boulding index to manage collaboration among different data sites. It also performs data compression by representing a large number of observations with a small number of data symbols.
  • Thumbnail Image
    Article
    Peer-To Live Video Streaming With Rateless Codes for Massively Multiplayer Online Games
    (Springer, 2018) Ahmad, Shakeel; Büyükkaya, Eliya; Bouras, Christos; Büyükkaya, Eliya; Dawood, Muneeb; Hamzaoui, Raouf; Kapoulas, Vaggelis; Papazois, Andreas; Simon, Gwendal
    We present a multi-level multi-overlay hybrid peer-to-peer live video system that enables players of Massively Multiplayer Online Games to simultaneously stream the video of their game and watch the game videos of other players. Each live video bitstream is encoded with rateless codes and multiple trees are used to transmit the encoded symbols. Trees are constructed dynamically with the aim to minimize the transmission rate at the source while maximizing the number of served peers and guaranteeing on-time delivery and reliability. ns-2 simulations and real measurements on the Internet show competitive performance in terms of start-up delay playback lag rejection rate used bandwidth continuity index and video quality.
  • Thumbnail Image
    Conference Object
    Dark Patches in Clustering
    (IEEE, 2017) Ishaq, Waqar; Büyükkaya, Eliya; Büyükkaya, Eliya
    This survey highlights issues in clustering which hinder in achieving optimal solution or generates inconsistent outputs. We called such malignancies as dark patches. We focus on the issues relating to clustering rather than concepts and techniques of clustering. For better insight into the issues of clustering we categorize dark patches into three classes and then compare various clustering methods to analyze distributed datasets with respect to classes of dark patches rather than conventional way of comparison by performance and accuracy criteria because performance and accuracy may provide misleading conclusions due to lack of labeled data in unsupervised learning. To the best of our knowledge this prime feature makes our survey paper unique from other clustering survey papers.