Перегляд за Автор "Hrypynska, Nadiia"

Зараз показуємо 1 - 5 з 5
  • Ескіз
    Документ
    A framework for exploring and modeling neural architecture search methods
    (CEUR-WS, 2020-05-14) Radiuk, Pavlo; Hrypynska, Nadiia
    For the past years, many researchers and engineers have been developing and optimising deep neural networks (DNN). The process of neural architecture design and tuning its hyperparameters remains monotonous, timeconsuming, and do not always ensure optimal results. In his regard, the automatic design of machine learning (AutoML) has been widely utilised, and neural architecture search (NAS) has been actively developing in recent years. Despite meaningful advances in the field of NAS, a unified, systematic approach to explore and compare search methods has not been established yet. In this paper, we aim to close this knowledge gap by summarising search decisions and strategies and propose a schematic framework. It applies quantitative and qualitative metrics for prototyping, comparing, and benchmarking the NAS methods. Moreover, our framework enables categorising critical areas to search for better neural architectures.
  • Ескіз
    Документ
    A Framework for Exploring and Modelling Neural Architecture Search Methods
    (2020) Radiuk, Pavlo; Hrypynska, Nadiia
    For the past years, many researchers and engineers have been developing and optimising deep neural networks (DNN). The process of neural architecture design and tuning its hyperparameters remains monotonous, timeconsuming, and do not always ensure optimal results. In his regard, the automatic design of machine learning (AutoML) has been widely utilised, and neural architecture search (NAS) has been actively developing in recent years. Despite meaningful advances in the field of NAS, a unified, systematic approach to explore and compare search methods has not been established yet. In this paper, we aim to close this knowledge gap by summarising search decisions and strategies and propose a schematic framework. It applies quantitative and qualitative metrics for prototyping, comparing, and benchmarking the NAS methods. Moreover, our framework enables categorising critical areas to search for better neural architectures.
  • Ескіз
    Документ
    An ensemble machine learning approach for Twitter sentiment analysis
    (CEUR-WS, 2022-07-17) Radiuk, Pavlo; Pavlova, Olga; Hrypynska, Nadiia
    The presented study addresses the issue of classifying emotional expressions based on small texts (tweets) extracted from the social network Twitter. In this paper, we propose a novel approach to preprocessing tweets to fit them more effectively into the classification model. Moreover, we suggest utilizing two types of features, namely unigrams and bigrams, to expand the feature vector. The classification task of emotional expressions was performed according to several machine learning algorithms: raw random forest, gradient boosting random forest, support vector machine, multilayer perceptron, recurrent neural network, and convolutional neural network. The feature vector elements are presented as sparse and dense subvectors. As a result of computational experiments, it was found that the “appearance” in the reflection of the sparse vector provided higher performance than the “regularity.” The experiments also showed that deep learning approaches performed better than traditional machine learning techniques. Consequently, the best recurrent neural network achieved an accuracy of 83.0% on the test dataset, while the best convolutional neural network reached 83.34%. At the same time, it was discovered that the convolutional model with the support vector machine classifier showed better performance than the single convolutional neural network. Overall, the proposed ensemble method based on receiving the most votes according to the five best models’ predictions has reached an absolute accuracy of 85.71%, proving its practical usefulness.
  • Ескіз
    Документ
    Integrated technology of cadmium phytoextraction for soils of urban ecosystems.
    (Polskie Towarzystwo Inżynierii Ekologicznej (PTIE), 2026-03-08) Yakovyshyna, Tetiana; Nester, Anatoliy; Salamon, Ivan; Dzhumelia, Elvira; Hrypynska, Nadiia; Seleznov, Dmytro
    The paper seeks to develop an integrated mechanism for designing a technology of heavy metal phytoextraction from soils to enhance the environmental safety of urban ecosystems affected by anthropogenic impact. Drawing from an analysis of existing remediation methods for soils contaminated with heavy metals, a scheme has been proposed as a multipurpose framework for creating an integrated phytoextraction technology. It incorporates various components aimed at increasing the mobility of heavy metals in soil and their translocation into plants.
  • Ескіз
    Документ
    Optimization of the production plan by three-criterion modeling
    (2019) Dykha, Mariia; Hrypynska, Nadiia; Tsehelyk, Hryhorii; Marko, Mariia
    The object of research is the processes of optimizing the production plan according to certain criteria by modeling. One of the most problematic places is the complexity of coordination and taking into account the influence of criteria on the optimal production plan. From the point of view of mathematics, the search for the optimal result can be obtained with different criteria laid down, but from an economic point of view it is important to choose those that are of decisive importance. That is, their weight is important for the consumer in deciding on a purchase and for the manufacturer – in terms of the production capabilities of certain types of products and performance (production efficiency). This problem was solved by solving the three-criterion problem of planning production. The search for a compromise alternative was achieved through a step-by-step solution of the proposed mathematical model for optimizing the production plan according to the most important criteria for the producer and consumer: profit, quality and demand for products of each type, taking into account the known number of units of each resource.