Yazar "Batur, O.Z." seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    A 2.4 GHz High Efficiency Digital IR-UWB Transmitter with Linear Spectrum Control
    (Institute of Electrical and Electronics Engineers Inc., 2022) Alshuwayhidi, A.J.H.; Batur, O.Z.
    This paper presents a low power and a high efficiency Impulse Radio Ultra-Wideband (IR-UWB) transmitter with configurable pulse shape and spectrum features using configurable linear delay lines. The proposed transmitter employs on-of keying (OOK) modulator, configurable current starved and shunt capacitor delay lines, pulse generator, and pulse shaping output stage with a pulse shaping capacitor which is matched to bond wire inductance for the desired 2.4 GHz operation frequency. The delay lines are used for spectrum and pulse shape control by setting the widths and the positions of the generated Gaussian mono-pulses. The transmitter is designed in 130 nm UMC CMOS technology with nominal 1.2 Volts supply and simulated for process corner variations. The proposed design achieves around 2.4 GHz operation frequency, 1.15 Volts output swing and 9.09 pJ energy per pulse (EPP) with 11.22 % efficiency figure. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    A Comparative Study of Deep Learning Methods on Food Classification Problem
    (Institute of Electrical and Electronics Engineers Inc., 2020) Memis, S.; Arslan, B.; Batur, O.Z.; Sonmez, E.B.
    This paper gives a comparative study on the performances of several deep learning methods for the food images recognition challenge. The experiments were conducted on the UEC Food-100 dataset using ResNet-18, Inception-V3, Resnet-50, Densenet-121, Wide Resnet-50 and ResNext-50 with images of size 320x320 and 299x299. The limited size of the database required the transfer learning approach; that is, all models were trained with pretrained ImageNet weights. The best classification result was obtained using ResNext-50 with 87.7 % accuracy. © 2020 IEEE.
  • Küçük Resim Yok
    Öğe
    Fine-Grained Food Classification Methods on the UEC FOOD-100 Database
    (Institute of Electrical and Electronics Engineers Inc., 2022) Arslan, B.; Memis, S.; Sonmez, E.B.; Batur, O.Z.
    The development of an automatic food recognition system has severalinteresting applications ranging from waste food management, to advertisement, to calorie estimation, and daily diet monitoring. Despite the importance of this subject, the number of related studies is still limited. Moreover, the comparison in the literature was currently done over the best-shot performance without considering the most common method of averaging over several trials. This article surveys the most common deep learning methods used for food classification, it presents the publicly available databases of food, it releases benchmark results for the food classification experiment averaged over five-trials, and it beats the current best-shot performance experiment reaching the state-of-the-art accuracy of 90.02% on the UEC Food-100 database. The best results have been achieved by the ensemble method averaging the predictions of ResNeXt and DenseNet models. All the experiments are run on the UEC Food-100 database because it is one of the most used databases, and it is challenging due to the presence of multifood images, which need to be cropped before processing. This article aims to contribute to automatic food recognition by presenting the most common algorithms used for food classification, introducing the main databases of food items currently available, and reaching the state-of-the-art performance in the best-shot classification experiment of the UEC Food-100 database. That is, this article improves the current best-shot performance by 0.44 percentage points, and fixes it to 90.02%. Furthermore, with the best of our knowledge, this is the first article to introduce to the research community comparison of performances of the classification experiment on the UEC Food-100 database averaged over five-trails. As expected, performance averaged is slightly lower thanthe best-shot one. © 2020 IEEE.
  • Küçük Resim Yok
    Öğe
    High data rate and energy efficient configurable IR-UWB transmitter with an integrated balun
    (Elsevier GmbH, 2024) Albayrak, M.; Dündar, G.; Batur, O.Z.
    This paper presents a novel, digitally configurable, switching oscillator-based impulse radio ultra-wideband (IR-UWB) transmitter that is robust to process variations. The pulse width and pulse position properties of the output waveform are configurable to ensure operation for the desired bandwidth and output pulse energy values. The architecture is based on a cross-coupled LC voltage-controlled oscillator (LC VCO) implemented with a custom-designed on-chip balun at a center frequency of 2.4 GHz. With the usage of this on-chip balun, the need for an extra buffer stage is eliminated, and the highest possible efficiency is achieved with the proper turns ratio selected. The generated digital control pulse signals are also used to ensure fast start-up and UWB operation while maintaining low power consumption with an implemented on/off tail switching scheme. The presented IR-UWB transmitter that occupies a total area of 0.35 mm2 is fabricated in the United Microelectronics Corporation (UMC) 180-nm mixed-mode/radio frequency (RF) CMOS process. The measured output voltage swing of the fabricated transmitter is 0.812 V on a 50-? load for the 200 Mb/s data rate, and the bandwidth is measured as 902 MHz. The achieved frequency tuning range is 1 GHz and the fabricated transmitter can drive 50 ?, 75 ? and 100 ? loads with measured efficiency values 4.16%, 5.76%, and 4.05%, respectively. Compared to other works in the literature, this design achieves a higher output pulse energy at a higher data rate while maintaining low power consumption and, thus, high efficiency. © 2024 Elsevier GmbH