Yazar "Dalyan, T." seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Detection of Change in the Senses of AI in Popular Discourse
    (Springer Science and Business Media Deutschland GmbH, 2023) Suerdem, A.; Dalyan, T.; Yıldırım, S.
    As chatbots, driverless cars and other robot-like applications become a part of everyday life, we are witnessing an increase in the popularization of Artificial Intelligence (AI) by the mass media. While this has some potential in terms of informing the public about technological development, it also makes the term a buzzword not pointing to any actual object with no agreed-upon meaning. AI is usually deployed as an umbrella term for sealing a variety of analytical tools such as intelligent decision support systems, deep learning, and computational linguistics disregarding their actual denotations. As the popular discourse and media represent its mundane features to connote miracles or apocalypses, AI gains a mythical status that can have different significations according to different cultural contexts. Our aim in this paper is to study the semantic shifts in the meaning of AI in different contexts by examining the mapping of the words to different semantic vector spaces over time. © 2023, Springer Nature Switzerland AG.
  • Küçük Resim Yok
    Öğe
    Facial Expression Recognition in the Wild with Application in Robotics
    (Institute of Electrical and Electronics Engineers Inc., 2021) Han, H.; Karadeniz, O.; Sönmez, E.B.; Dalyan, T.; Sanoğlu, B.
    One of the major problems with robot companions is their lack of credibility. Since emotions play a key role in human behaviour their implementation in virtual agents is a conditio sine-qua-non for realistic models. That is, correct classification of facial expressions in the wild is a necessary preprocessing step for implementing artificial empathy. The aim of this work is to implement a robust Facial Expression Recognition (FER) module into a robot. Considering the results of an empirical comparison among the most successful deep learning algorithms used for FER, this study fixes the state-ofthe-art performance of 75% on the FER2013 database with the ensemble method. With a single model, the best performance of 70.8% has been reached using the VGG16 architecture. Finally, the VGG16-based FER module has been been implemented into a robot and reached a performance of 70% when tested with wild expressive faces. © 2021 IEEE
  • Küçük Resim Yok
    Öğe
    From Image to Simulation: An ANN-based Automatic Circuit Netlist Generator (Img2Sim)
    (Institute of Electrical and Electronics Engineers Inc., 2022) Sertdemir, A.E.; Besenk, M.; Dalyan, T.; Gokdel, Y.D.; Afacan, E.
    This study proposes an Artificial Neural Network (ANN) based netlist generator: Img2Sim. The tool acquires an image of an electronic circuit, classifies the existing circuit elements, including active components (MOSFET, BJT, Op-Amp, etc.), with at least 98% accuracy, and decides the circuit topology and the connections with over 90% accuracy through a rule-based algorithm. Finally, it automatically yields a simulation-ready netlist for the circuit of concern. It is worth noting that some CAD tools have been developed before; however, they have mostly focused on recognizing the circuit elements only and, to our best knowledge, Img2Sim is the first CAD tool that creates the entire netlist for a given circuit in image format. © 2022 IEEE.
  • Küçük Resim Yok
    Öğe
    Img2Sim-V2: A CAD Tool for User-Independent Simulation of Circuits in Image Format
    (Institute of Electrical and Electronics Engineers Inc., 2023) Gurbuz, H.B.; Balta, A.; Dalyan, T.; Gokdel, Y.D.; Afacan, E.
    Composition of the simulation-ready representations of circuits may be laborius and also vulnerable to human-induced errors, which results in wasted effort before the design process. Artificial intelligence (AI)-aided approaches are used in various applications to minimize the human error, and automatize the Netlist generation process. In literature, presented studies are mostly focused on the recognition of circuit components. In the previous version of Img2Sim, both active and passive components can be detected with 90% accuracy while the netlist for a given circuit can be generated automatically. In this study, we propose Img2Sim-V2, which is an AI assisted mobile application that provides high detection accuracy for hand or computer-drawn electrical circuits, generates related circuit netlist and produces a circuit schematic. Additionally, proposed system performs basic electrical analyses (DC, AC, and Transient) through Python packages. © 2023 IEEE.