Modification of software tool for human activity classification : доклад, тезисы доклада

Farafonov Maxim; Peresunko Evgeniye; Mymlikov Vladislav

Дополнительные ссылки: eLibrary · Источник статьи

База данных: Каталог библиотеки СФУ

Библиографическое описание: Modification of software tool for human activity classification : доклад, тезисы доклада / M. M. Farafonov, E. E. Peresunko, V. V. Mymlikov. - [S. l. : s. n.], 2025. - Текст : непосредственный // ITM Web of Conferences : III International Workshop / Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-III 2024) (2024 ; 02.12 - 04.12 ; Krasnoyarsk). - Krasnoyarsk, 2025. - P. 4005. - This work was supported by the Ministry of Science and Higher Education of the Russian Federation (Grant № 075-15-2022-1121). - DOI 10.1051/itmconf/20257204005.

Аннотация: The work is devoted to the modification and improvement of a neural network system for classifying human actions by changing the position of points of his skeleton. Within the framework of this paper, the description and results of some experiments on modification of the system developed by the authors several years ago will be presented. The experiments include new methods of augmenting the training data, removing some elements of the network, using a completely different representation of the data as a sequence of pictures rather than a set of points, using memory values and the state of the hidden LSTM cell as the output of the network instead of its direct output, and a variant of the network with the introduction of a new layer of feature encoding at the stage of sending skeletal point data to the recurrent LSTM network. The network with different layer configurations was trained multiple times, and the run data was averaged to remove the influence of randomness. In the end, the best network for the network was the one with pre-coded features.

Год издания: 2025

Авторы: Farafonov Maxim , Peresunko Evgeniye , Mymlikov Vladislav

Издательство: Krasnoyarsk

Источник: ITM Web of Conferences

Номера страниц: 4005

Держатель оригинала документа: Siberian Federal University

Мероприятие: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-III 2024) (Krasnoyarsk, 2024 ; 02.12 - 04.12)

Количество экземпляров:

Твёрдая копия издания отсутствует в фонде библиотеки

Показать дополнительные сведения

Classification of voting algorithms for N-version software

Tsarev R.Yu и др.
2018 год

A modification of Random Forest investment assets selection algorithm

Zinenko Anna и др.
2025 год

Classification of brain activity patterns using machine learning based on EEG data

Murtazina M.S. и др.
2020 год

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

Kukartsev V.V. и др.
2019 год

Comparative analysis of engineering tools for modeling and analysis

Matygov Movsar и др.
2025 год

Machine learning model for the BIM classification in IFC format

Petrochenko M. V. и др.
2024 год

Generative adversarial network for classification of mechanical fault diagnosis model

Guo C. и др.
2025 год

Intellectual technologies and modeling for transformation of engineering tools

Khadueva Yakha и др.
2025 год

Use of available engineering tools for modelling in multiple industries

Khaliev Magomed и др.
2025 год

The Modified Method of Logical Analysis Used for Solving Classification Problems

Kuzmich Roman и др.
2018 год

The software for simulating the operation of the spherical nuclear reactor

Zaronov Danila и др.
2025 год

Research of methods of classification of time series based on various metrics classifiers

Kukartsev V.V. и др.
2021 год

Comparative analysis of the efficiency of classical and neural network approaches for text…

Sherstnev P. A. и др.
2022 год

Classification of non-normative errors in measuring instruments based on data mining

Milov Anton Vladimirovich и др.
2018 год

Methodology for assessing the predicted didactic effects from the use of educational and training…

Zhukov Aleksandr и др.
2024 год

Classification of Microscopy Image Stained by Ziehl–Neelsen Method Using Different Architectures…

Shelomentseva I.G. и др.
2021 год

Библиотечно-издательский комплекс СФУ

Modification of software tool for human activity classification : доклад, тезисы доклада
доклад, тезисы доклада, статья из сборника материалов конференций

Похожие публикации