Eduard Manziuk

Prof. Dr. Eduard Manziuk

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 February 2020 in Computational Intelligence
Verified
Journal Article
Closed access
PDF file
IKIurii Krak
Iurii Krak
OBOlexander Barmak
Olexander Barmak
Eduard ManziukEduard Manziuk
Eduard Manziuk

27 October 2019
Verified
Book Chapter
Closed access
PDF file
IKIurii Krak
Iurii Krak
OBOlexander Barmak
Olexander Barmak
Eduard ManziukEduard Manziuk
Eduard Manziuk
AKAnatolii Kulias
Anatolii Kulias

29 March 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
Pavlo RadiukPavlo Radiuk
Pavlo Radiuk
OBOleksandr Barmak
Oleksandr Barmak
Eduard ManziukEduard Manziuk
Eduard Manziuk
IKIurii Krak
Iurii Krak
The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F1m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems.

1 January 2019 in Journal of Long-Term Effects of Medical Implants
Verified
Journal Article
Closed access
PDF file
OBOleksandr Barmak
Oleksandr Barmak
YKYuriy V. Krak
Yuriy V. Krak
Eduard ManziukEduard Manziuk
Eduard Manziuk
VKVeda S. Kasianiuk
Veda S. Kasianiuk
Information technology allowing one to implement the tasks of classification, clustering, studying the topology of the data of the information component is proposed. The multidimensional feature space is reduced to the visual presentation space to determine the information content of the data. Optimized reduction of the space dimension to two-dimensional one applying multidimensional scaling methods is used. Visual definition of grouping data allows separating areas to form. The next stage is visual limitation of categories of classes using graphic separators. To enable flexibility of nonlinear areas limitation a combination of linear ones is used, thereby forming a piecewise linear set with necessary degree of sampling. Using piecewise linear constraints allows us to implement projecting into original multidimensional feature space. Visual construction of restrictive separators makes it possible to consider tolerance fields of changing of features parameters, separation measure of classes, nonlinearity of data grouping. This is followed by reverse expansion of space with the projection of the separators into n -dimensional space with the separating hyperspace synthesis. Thus the limitative areas of hyperspace for the necessary categories of classes are formed. At the same time the visualization of classification process in a hyperspace is provided. The information technology base is the multidimensional space projection into visual (two-dimensional) space construction piecewise linear limiters of studied areas, subsequent limiters projecting into multidimensional space. Thus the information technology enables us to synthesize separating hyperplanes limiting categories of classes in multidimensional space. The technology application successive stages are described.

1 January 2018 in Journal of Long-Term Effects of Medical Implants
Verified
Journal Article
Closed access
PDF file
Eduard ManziukEduard Manziuk
Eduard Manziuk
OBOleksandr Barmak
Oleksandr Barmak
YKYuriy V. Krak
Yuriy V. Krak
VKVeda S. Kasianiuk
Veda S. Kasianiuk
The analysis of the classifiers assessments based on the definition of informational value of classification attributes is carried out. The stages of the preprocessing of documents and the classification of documents based on modern approaches are considered. The classification is performed using both individual classifiers and the component approach of the assembly of classifiers. Assembly of classifiers uses composition to change the training sample and combine the classifiers of different nature. The introduced approach allows us to identify the classification elements that are of informational value and have properties of generalization by evaluating the similarity measure between them based on classification results.

1 January 2018 in PROBLEMS IN PROGRAMMING
Verified
Journal Article
Closed access
PDF file
OBO.V. Barmak
O.V. Barmak
IKIurii Krak
Iurii Krak
Eduard ManziukEduard Manziuk
Eduard Manziuk
Characteristics for choice of models in the ansables classification