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...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tomsk Polytechnic University
2023-03-01
|
| Series: | Известия Томского политехнического университета: Промышленная кибернетика |
| Subjects: | |
| Online Access: | https://indcyb.ru/journal/article/view/13/12 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849472780945326080 |
|---|---|
| author | Nikita V. Laptev Olga M. Gerget Vladislav V. Laptev Dmitriy Yu. Kolpashchikov |
| author_facet | Nikita V. Laptev Olga M. Gerget Vladislav V. Laptev Dmitriy Yu. Kolpashchikov |
| author_sort | Nikita V. Laptev |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-768d3d18ce724db8a14558bb1e05f21f |
| institution | Kabale University |
| issn | 2949-5407 |
| language | English |
| publishDate | 2023-03-01 |
| publisher | Tomsk Polytechnic University |
| record_format | Article |
| series | Известия Томского политехнического университета: Промышленная кибернетика |
| spelling | doaj-art-768d3d18ce724db8a14558bb1e05f21f2025-08-20T03:24:26ZengTomsk Polytechnic UniversityИзвестия Томского политехнического университета: Промышленная кибернетика2949-54072023-03-0111444910.18799/29495407/2023/1/13INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURESNikita V. Laptev0Olga M. Gerget1Vladislav V. Laptev2Dmitriy Yu. Kolpashchikov3National Research Tomsk Polytechnic University, RussiaInstitute of Control Sciences of Russian Academy of Sciences, RussiaNational Research Tomsk Polytechnic University, RussiaNational Research Tomsk Polytechnic University, RussiaImage 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.https://indcyb.ru/journal/article/view/13/12neural networkstraditional machine learningclassificationimagedetection of fire hazards |
| spellingShingle | Nikita V. Laptev Olga M. Gerget Vladislav V. Laptev Dmitriy Yu. Kolpashchikov INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES Известия Томского политехнического университета: Промышленная кибернетика neural networks traditional machine learning classification image detection of fire hazards |
| title | INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES |
| title_full | INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES |
| title_fullStr | INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES |
| title_full_unstemmed | INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES |
| title_short | INVESTIGATION OF THE CAPABILITIES OF ARTIFICIAL NEURAL NETWORKS WHEN CLASSIFYING OBJECTS DYNAMIC FEATURES |
| title_sort | investigation of the capabilities of artificial neural networks when classifying objects dynamic features |
| topic | neural networks traditional machine learning classification image detection of fire hazards |
| url | https://indcyb.ru/journal/article/view/13/12 |
| work_keys_str_mv | AT nikitavlaptev investigationofthecapabilitiesofartificialneuralnetworkswhenclassifyingobjectsdynamicfeatures AT olgamgerget investigationofthecapabilitiesofartificialneuralnetworkswhenclassifyingobjectsdynamicfeatures AT vladislavvlaptev investigationofthecapabilitiesofartificialneuralnetworkswhenclassifyingobjectsdynamicfeatures AT dmitriyyukolpashchikov investigationofthecapabilitiesofartificialneuralnetworkswhenclassifyingobjectsdynamicfeatures |