INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES

INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES

Image classification is a classic machine learning task. Deep neural networks are widely used in the field of object classification. However, the problem of analyzing objects with dynamically changing features remains relevant. To solve this problem, the authors propose using a long short-term memor...

Full description

Saved in:
Bibliographic Details
Main Authors: Nikita V. Laptev, Olga M. Gerget, Vladislav V. Laptev, Dmitriy Yu. Kolpashchikov
Format: Article
Language:English
Published: Tomsk Polytechnic University 2023-03-01
Series:Известия Томского политехнического университета: Промышленная кибернетика
Subjects:
neural networks
traditional machine learning
classification
image
detection of fire hazards
Online Access:https://indcyb.ru/journal/article/view/13/12
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Image classification is a classic machine learning task. Deep neural networks are widely used in the field of object classification. However, the problem of analyzing objects with dynamically changing features remains relevant. To solve this problem, the authors propose using a long short-term memory networks. Unlike classical convolutional neural networks, the proposed network uses information about the sequence of images, thereby providing a higher classification accuracy of detected objects with dynamic features. In the study, the authors analyze the classification accuracy of smoke cloud detection in a forest using various machine learning methods.
ISSN:2949-5407

Similar Items