Work

Architecture of the intelligent system for risk management and recognition of mushroom species

Year: 2024

Type: article

Abstract: The article presents the development of an intelligent system for recognising mushroom species that provides high accuracy and ease of use. To train the model, a large dataset ‘Mushrooms classification’ from the Kaggle platform was used, which provided the necessary diversity of images and achieved a classification accuracy of 85%. Data pre-processing included image quality checks, standardisation, and division into training, validation, and test samples, which contributed to efficient model training. The recognition algorithm is based on the ResNet convolutional neural network, which has demonstrated an accuracy advantage over other architectures.

Source: Optoelectronic Information-Power Technologies

DOI: 10.31649/1681-7893-2024-48-2-114-127

Authors: D.I. Uhryn, Yu.O. Ushenko, V.V. Dvorzhak, T.V. Terletskyi, O.L. Kaidyk

Institutions: Yuriy Fedkovych Chernivtsi National University, Lutsk National Technical University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4404496934

FWCI:

Cites:

Cited by:

Related to: 10