Yazar "Koruk, Talha" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Optimized YOLOv8 (YOLO-Prime), M-CNN, and Dynamic Linear Regression for Real-Time Aerial Vehicle Detection in Embedded Systems
    (Ieee, 2025) Caliskan, Halil Huseyin; Koruk, Talha
    This paper introduces a modified architecture of YOLOv8, called YOLO-Prime, to detect aerial vehicles. By employing YOLO-Prime to embedded systems such as Nvidia Jetson Xavier Nx and Rockchip 3588, we reduced the inference time by 130% compared to the YOLOv8m model and by 158% compared to the YOLOv8l model. In addition to YOLO-Prime, we present a Morphological CNN (M-CNN) to classify regions detected by YOLO-Prime. With the integration of M-CNN, we achieved an increase in detection accuracy by 20% in the detection of aerial vehicles. Furthermore, we introduce a dynamic linear regression model to predict the future coordinates of aerial vehicles. As a result of the integration of dynamic linear regression models to embedded systems, GPU utilization of deep learning models decreased by approximately 66%. In summary, the combination of YOLO-Prime, M-CNN, and the dynamic linear regression model contributes to detecting aerial vehicles in embedded systems where energy consumption, inference time, and accuracy are crucial for real-time applications.
  • Küçük Resim Yok
    Öğe
    Unveiling trends: a comprehensive analysis of state funded projects of Türkiye through content analysis and text mining
    (Murat Yakar, 2025) Koruk, Talha; Bilgin, Turgay Tugay
    This paper presents a comprehensive analysis of 12,724 projects approved by TUBITAK (The Scientific and Technological Research Council of Türkiye) between 2008 and 2022. The research employs advanced text mining techniques, including N-gram-based text categorization, TF-IDF, and PMI scores, to uncover trends in research and development activities in Türkiye. The analysis begins by examining the distribution of projects across years and regions, then focuses on five leading sectors: Information Technologies, Automotive, Machinery Manufacturing, Electrical-Electronics, and Defense Industry. The study identifies prominent themes and their evolution over time for each sector, thereby illuminating the dynamics of Türkiye's innovation ecosystem. The results highlight sector-specific trends as well as cross-sector common themes such as artificial intelligence, mobile applications, and sustainable technologies. This research provides valuable insights for policymakers, researchers, and industry stakeholders in shaping Türkiye's scientific and technological development. By leveraging text mining techniques on a large corpus of project data, the study offers a data-driven perspective on the changing landscape of innovation in Türkiye, contributing to a better understanding of national research priorities and emerging technological focus areas. © Author(s) 2024.