Перегляд за Автор "Matveiev, Oleksandr"
Зараз показуємо 1 - 2 з 2
Результатів на сторінці
Налаштування сортування
Документ Multi-Agent Modeling of Project Management Processes in Distributed Teams(2021) Cherednichenko, Olga; Matveiev, Oleksandr; Yanholenko, Olha; Maneva, RositsaChanges in the business environment, the innovative nature of projects, lack of necessary skills of project team members lead to increased uncertainty and inability to plan with a given degree of accuracy. Such projects use adaptive project and program management methodologies. In the field of information technology, the use of multi-agent systems is of particular interest. In the context of the use of multi-agent systems for the design of intelligent systems for various purposes, the development and study of a model and software implementation of a prototype of an agent platform are relevant. The aim of this work is to develop and research an agent platform that can be implemented in the work of the distributed team in order to improve the assignment of tasks. The paper presents the formal agent architecture as a basis of multi-agent model. The task assignment is a case study to implement and test multi-agent model prototype. The agent platform is developed based on Kotlin programming language. A prototype of the agent platform based on the FIPA specification allows to increase the productivity, scalability and interoperability of multiagent system.Документ Towards Classifying HTML-embedded Product Data Based On Machine Learning Approach(2021) Matveiev, Oleksandr; Zubenko, Anastasiia; Yevtushenko, Dmitry; Cherednichenko, OlgaIn this paper we explored machine learning approaches using descriptions and titles to classify footwear by brand. The provided data were taken from many different online stores. In particular, we have created a pipeline that automatically classifies product brands based on the provided data. The dataset is provided in JSON format and contains more than 40,000 rows. The categorization component was implemented using K-Nearest Neighbour (K-NN) and Support Vector Machine (SVM) algorithms. The results of the pipeline construction were evaluated basing on the classification report, especially the Precision weighted average value was considered during the calculation, which reached 79.0% for SVM and 72.0% for K-NN.