Research Article
BibTex RIS Cite

Yapay Zekâ’da Güncel Yaklaşımlar: Bir Tasarım Aracı Olarak Veri Görselleştirme Teknikleri

Year 2024, Issue: Sanatta Dijitalizm Özel Sayısı, 171 - 182, 28.11.2024
https://doi.org/10.17484/yedi.1483618

Abstract

Tasarım, çevrenin insanlar tarafından şekillendirilme, insan ihtiyaçlarına cevap verme ve hayatı anlamlandırma özellikleriyle insana özgü bir yetenek olarak tanımlanmaktadır. Teknolojinin ilerlemesiyle birlikte, görsel tasarım süreçlerinde geleneksel yöntemlerin evrim geçirmesi, tasarımcıların ve ilgili kişilerin izlediği yolu dönüştürmektedir. Algoritmalar, kod sistemleri ve yeni teknolojilerin sunduğu uygulama biçimleri, tasarımın etkilediği her alanda belirgin hale gelmektedir. Araştırmanın amacı, teknolojinin ilerlemesiyle ortaya çıkan yeni görsel üretim tekniklerini incelemek ve kullanım kapsamlarını anlamaktır. Yeni üretim tekniklerinin kavranması, yapay zekânın tasarım içerisindeki rolünün belirlenmesi, kullanım amacı ve gelişim sürecine hâkim olunması açısından önemlidir. Yapay zekâ temelli görsel üretim tekniklerinin ve algoritmalarının karmaşık yapısının, görsel üretimle uğraşan kişiler tarafından anlaşılması, gelecekteki teknolojik evrimin tahmin edilmesi açısından önemlidir. Bu temel kavramlara hâkim olmak, daha nitelikli görsel çıktıların alınmasına ve gelişim sürecine uyum sağlanmasına yardımcı olacak ve tasarım sürecinde tasarımcılara avantaj sağlayacak şekilde kullanılabilecektir. Araştırmada daha önce yapılmış olan araştırmalardan farklı olarak yapay zekânın görsel üretim teknikleri açısından tasarıma hangi rollerde hizmet edebileceği araştırılmıştır. Araştırma kapsamında farklı üretim modellerine sahip yapay zekâ uygulamalarının işleyiş modelleri incelenmiş, yapılan uygulamada istemler yapay zekâ modeline yazdırılmış ve görselleştirme yine yapay zekâ uygulamalarına yaptırılarak sürecin tamamında yeni teknolojilerden faydalanılmıştır. Bu şekilde tasarım alanında yapay zekâ uygulamalarının görsel üretim teknikleri açısından yeri irdelenmiştir.

References

  • Bozkurt, A. ve Sharma, R. C. (2023). Generative AI and prompt engineering: The art of whispering to let the genie out of the algorithmic world. Asian Journal of Distance Education, 18(2), s. 1-7. https://doi.org/10.5281/zenodo.8174941
  • Copeland, B. J. (2002). Accelerating turing machines. Minds and Machines, 12, s. 281-300.
  • Durgadevi, M. (2021). Generative Adversarial Network (GAN): A general review on different variants of GAN and applications. In 2021 6th International Conference on Communication and Electronics Systems (ICCES), s. 1-8. https://doi.org/10.1109/ICCES51350.2021.9489160
  • Fu, A. ve Hou, Y. (2017). Text-to-Image Generation Using Multi-Instance StackGan. Semantic Scholar, 225-231.
  • Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative adversarial nets. Advances in neural information processing systems, 3(11), s. 27.
  • Gray, J. (2016). Let us Calculate. Leibniz, Llull, and the Computational Imagination. The Public Domain Review.
  • Heskett, J. (2013). Tasarım (E. Uzun, Çev.). Dost Kitabevi Yayınları.
  • Hurwitz, J. ve Kirsch, D. (2018). Machine Learning for Dummies, John Wiley and Sons.
  • Ma, L. ve Qu, S. (2023). Application Of Conditional Generative Adversarial Network to Multi-step Car-following Modeling. Frontiers in Neurorobotics, (17). https://doi.org/10.3389/fnbot.2023.1148892
  • Mueller, J. P. & Massaron, L. (2019). Deep Learning for Dummies, John Wiley & Sons.
  • Park, W., J. ve Park, B., J. (2019). History and application of artificial neural networks in dentistry. European Journal of Dentistry, 12(4), 594-601.
  • Parkinson, J. S. (2022). The History of the Enigma Machine, History Publications, 415.
  • Reed, S., Akata, Z., Yan,X., Logeswaran, L., Schiele, B. & Lee, H. (2016). Generative Adversarial Text to Image Synthesis, In International conference on machine learning, s. 1060-1069.
  • Salvagno, M., Taccone, F. S. ve Gerli, A. G. (2023). Can Artificial Intelligence Help for Scientific Writing? Critical Care, 27(1), s.1-5.
  • Schultz, D. P. ve Ellen-Schultz, S. (2007). Modern psikoloji tarihi (Y. Aslay, Çev.). Kaknüs Yayınları.
  • Simon, H. A. & Newell, A. (1971). Human problem solving: The state of the theory in 1970. American psychologist, 26(2), 145.
  • Souza, D., M., Wehrmann, J. ve Ruiz, D., D. (2020). Efficient Neural Architecture for Text-to-Image Synthesis. In 2020 International Joint Conference on Neural Networks (IJCNN), s. 1-8.
  • Tsang, S. H. (2023, Ağustos 2). Brief Review- GAN-CLS-INT: Generative Adversarial Text to Image Synthesis. Medium. https://sh-tsang.medium.com/brief-review-gan-cls-int-generative-adversarial-text-to-image-synthesis-28de6518180b
  • Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X. & Metaxas, D. (2017). StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(8). https://doi.org/10.1109/TPAMI.2018.2856256

Current Approaches in Artificial Intelligence: Data Visualisation Techniques as a Design Tool

Year 2024, Issue: Sanatta Dijitalizm Özel Sayısı, 171 - 182, 28.11.2024
https://doi.org/10.17484/yedi.1483618

Abstract

Design is defined as a human ability to shape the environment, respond to human needs and make sense of life. With the advancement of technology, traditional methods in visual design processes are evolving, transforming the pathways followed by designers and related to people. Algorithms, code systems and the application forms introduced by new technologies are becoming evident in every field affected by design. The aim of the research is to examine the new visual production techniques that have emerged with technological advancements and to understand their scope of use. Understanding new production techniques is important in terms of the correct use of this technology and mastering the development process. Comprehending the complex structure of AI-based visual production techniques and algorithms is essential for those involved in visual production as it allows them to anticipate future technological evolution. Mastering these basic concepts will help to obtain more qualified visual outputs and adapt to the development process and can be used to the advantage of designers in the design processThis researchdiffers from previous studies in its focus on the roles that artificial intelligence can play in visual production techniques within the realm of design. In this research, unlike previous studies, the roles in which artificial intelligence can serve design in terms of visual production techniques were investigated. Within the scope of the research, the functioning models of artificial intelligence applications with different production models were examined, the prompts were printed to the artificial intelligence model and the visualization was done by artificial intelligence applications and new technologies were used in the whole process. By doing so,the research analyzes the role of artificial intelligence applications in the design field particularly visual production techniques.

References

  • Bozkurt, A. ve Sharma, R. C. (2023). Generative AI and prompt engineering: The art of whispering to let the genie out of the algorithmic world. Asian Journal of Distance Education, 18(2), s. 1-7. https://doi.org/10.5281/zenodo.8174941
  • Copeland, B. J. (2002). Accelerating turing machines. Minds and Machines, 12, s. 281-300.
  • Durgadevi, M. (2021). Generative Adversarial Network (GAN): A general review on different variants of GAN and applications. In 2021 6th International Conference on Communication and Electronics Systems (ICCES), s. 1-8. https://doi.org/10.1109/ICCES51350.2021.9489160
  • Fu, A. ve Hou, Y. (2017). Text-to-Image Generation Using Multi-Instance StackGan. Semantic Scholar, 225-231.
  • Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. & Bengio, Y. (2014). Generative adversarial nets. Advances in neural information processing systems, 3(11), s. 27.
  • Gray, J. (2016). Let us Calculate. Leibniz, Llull, and the Computational Imagination. The Public Domain Review.
  • Heskett, J. (2013). Tasarım (E. Uzun, Çev.). Dost Kitabevi Yayınları.
  • Hurwitz, J. ve Kirsch, D. (2018). Machine Learning for Dummies, John Wiley and Sons.
  • Ma, L. ve Qu, S. (2023). Application Of Conditional Generative Adversarial Network to Multi-step Car-following Modeling. Frontiers in Neurorobotics, (17). https://doi.org/10.3389/fnbot.2023.1148892
  • Mueller, J. P. & Massaron, L. (2019). Deep Learning for Dummies, John Wiley & Sons.
  • Park, W., J. ve Park, B., J. (2019). History and application of artificial neural networks in dentistry. European Journal of Dentistry, 12(4), 594-601.
  • Parkinson, J. S. (2022). The History of the Enigma Machine, History Publications, 415.
  • Reed, S., Akata, Z., Yan,X., Logeswaran, L., Schiele, B. & Lee, H. (2016). Generative Adversarial Text to Image Synthesis, In International conference on machine learning, s. 1060-1069.
  • Salvagno, M., Taccone, F. S. ve Gerli, A. G. (2023). Can Artificial Intelligence Help for Scientific Writing? Critical Care, 27(1), s.1-5.
  • Schultz, D. P. ve Ellen-Schultz, S. (2007). Modern psikoloji tarihi (Y. Aslay, Çev.). Kaknüs Yayınları.
  • Simon, H. A. & Newell, A. (1971). Human problem solving: The state of the theory in 1970. American psychologist, 26(2), 145.
  • Souza, D., M., Wehrmann, J. ve Ruiz, D., D. (2020). Efficient Neural Architecture for Text-to-Image Synthesis. In 2020 International Joint Conference on Neural Networks (IJCNN), s. 1-8.
  • Tsang, S. H. (2023, Ağustos 2). Brief Review- GAN-CLS-INT: Generative Adversarial Text to Image Synthesis. Medium. https://sh-tsang.medium.com/brief-review-gan-cls-int-generative-adversarial-text-to-image-synthesis-28de6518180b
  • Zhang, H., Xu, T., Li, H., Zhang, S., Wang, X., Huang, X. & Metaxas, D. (2017). StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(8). https://doi.org/10.1109/TPAMI.2018.2856256
There are 19 citations in total.

Details

Primary Language Turkish
Subjects Graphic Design, Visual Communication Design (Other)
Journal Section Araştırma Makaleler
Authors

İlter Alkan 0000-0002-3889-587X

Semih Oduncu 0000-0001-9220-0461

Early Pub Date October 18, 2024
Publication Date November 28, 2024
Submission Date May 14, 2024
Acceptance Date September 16, 2024
Published in Issue Year 2024 Issue: Sanatta Dijitalizm Özel Sayısı

Cite

APA Alkan, İ., & Oduncu, S. (2024). Yapay Zekâ’da Güncel Yaklaşımlar: Bir Tasarım Aracı Olarak Veri Görselleştirme Teknikleri. Yedi(Sanatta Dijitalizm Özel Sayısı), 171-182. https://doi.org/10.17484/yedi.1483618

18409

This work is licensed under a Creative Commons Attribution 4.0 International License.