Communications, Series A2-A3: Physical Sciences and Engineering

Permanent URI for this community

https://dspace.ankara.edu.tr/handle/20.500.12575/40673

Browse

Browsing Communications, Series A2-A3: Physical Sciences and Engineering by Author "Aydın, Ayhan"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Modern Learnıng Technıques And Plant Image Classıfıcatıon
    (Ankara Üniversitesi Fen Fakültesi, 2020-07-01) Ünal, Metehan; Bostancı, Erhan; Güzel, Mehmet Serdar; Aydın, Ayhan; Bilgisayar Mühendisliği; Mühendislik Fakültesi
    The intelligent machines concept is born in sci-fi scenarios. Today it seems to be we are much closer to realizing this idea than ever before. By imitating the human nervous system, machines can learn many things. This paper explains modern learning techniques like artificial neural networks, transfer learning. Later purposes an experiment to classify plant seedling images to test the transfer learning with two different CNN architectures. Although the architects were not actually created for this task, result were quite accurate for a different classification task.
  • No Thumbnail Available
    Item
    RF Antenna Desıgn For Button-Type Beam Posıtıon Monıtors Usıng Bıo-Inspıred Optımızatıon Methods
    (Ankara Üniversitesi Fen Fakültesi, 2020-06-30) Aydın, Ayhan; Bostancı, Gazi Erhan; Bilgisayar Mühendisliği; Mühendislik Fakültesi
    Accelerator based facilities are in a leading position for crafting many scientific and technical innovations for a wide range of application from aviation to medicine. Beam Position Monitors (BPMs) are critical diagnostics tools for such facilities. This study presents bio-inspired methods known as Particle Swarm Optimization and Evolutionary Algorithms in order to design RF antennas for button-type BPMs. Our results show that the antenna parameters obtained using this multiple objective approaches present suitable SNR and linearity values for signal processing. It is found that using an antenna radius of 5.5 mm and beam-pipe radius of 17.5 mm, we can obtain SNR values around 40 dB which can be electronically processed.