Selection of appropriate architecture and parameters of neural network for images recognition and classification

Описание

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: International Scientific Conference on Applied Physics, Information Technologies and Engineering (APITECH) / 2-nd International Scientific and Practical Conference on Borisov's Readings; Siberian Fed Univ, Polytechn Inst, Krasnoyarsk, RUSSIA; Siberian Fed Univ, Polytechn Inst, Krasnoyarsk, RUSSIA

Год издания: 2019

Идентификатор DOI: 10.1088/1742-6596/1399/3/033105

Аннотация: In this article the image recognition and classification problem is considered. Further, there will be suggestion of the new way of using a convolutional neural network to solve the considering problem in an example of a particular task, such as the recognition of ischemic stroke on magnetic resonance images. Moreover, it is considПоказать полностьюering reasons of choosing the image classification and making arguments obtained by a literary analysis of studies affecting the task. Authors have investigated different neural networks architectures and the accuracy depending on training speed, numbers of layers, numbers of epochs and mini sample size. Experiments result is presented in the table form. During the studying, magnetic resonance images of different diseases having same signals with a considering pathology in diffusion-weighted images format has been selected for the training of the convolutional neural network and for getting the most favourable result. In the result, a suitable architecture with defined parameters has been selected to get the highest accuracy. © Published under licence by IOP Publishing Ltd.

Ссылки на полный текст

Издание

Журнал: Journal of Physics: Conference Series

Выпуск журнала: Vol. 1399, Is. 3

Номера страниц: 33105

ISSN журнала: 17426588

Издатель: Institute of Physics Publishing

Персоны

  • Kukartsev V.V. (Siberian Fed Univ, 79 Svobodny Pr, Krasnoyarsk 660041, Russia; Reshetnev Siberian State Univ Sci & Technol, 31 Krasnoyarsky Rabochy Av, Krasnoyarsk 660037, Russia)
  • Mikhalev A.S. (Siberian Fed Univ, 79 Svobodny Pr, Krasnoyarsk 660041, Russia)
  • Tarasevich A.V (Siberian Fed Univ, 79 Svobodny Pr, Krasnoyarsk 660041, Russia)
  • Tynchenko V.S. (Siberian Fed Univ, 79 Svobodny Pr, Krasnoyarsk 660041, Russia; Reshetnev Siberian State Univ Sci & Technol, 31 Krasnoyarsky Rabochy Av, Krasnoyarsk 660037, Russia)
  • Ogol A.R. (Reshetnev Siberian State Univ Sci & Technol, 31 Krasnoyarsky Rabochy Av, Krasnoyarsk 660037, Russia)
  • Khramkov V.V. (Siberian Fed Univ, 79 Svobodny Pr, Krasnoyarsk 660041, Russia)