Andrii Oliinyk

Andrii Oliinyk

Auto-generated profile, based on publicly available information

Andrii Oliinyk

Department of Software Tools National University ‘’Zaporizhzhia Polytechnic’’, Zaporizhzhia, Ukraine

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
7 October 2024 in IEEE Access
Verified
Journal Article
Open access
VSVadym Shkarupylo
Vadym Shkarupylo
JAJamil Alsayaydeh
Jamil Alsayaydeh
MYMOHD FAIZAL YUSOF
MOHD FAIZAL YUSOF
AOAndrii Oliinyk
Andrii Oliinyk
Volodymyr O ArtemchukVolodymyr O Artemchuk
Volodymyr O Artemchuk
SHSafarudin Gazali Herawan
Safarudin Gazali Herawan
The Industry 5.0 revolution has launched a new age of intelligent manufacturing equipment, which is crucial to our society and economy. Industry 5.0 aims to enhance human potential by integrating cutting-edge IT technology, Artificial Intelligence (AI), the Internet of Things (IoT), robots, and augmented reality into everyday living, especially in smart industrial settings, to maximize human potential. Smart Production Processes (SP2), accessible standards, and resource sharing on the web have increased network vulnerabilities as enterprises adopt them. These vulnerabilities primarily target industry IoT systems, threatening private data. Existing system issues include network vulnerabilities, production capability, and data management. Traditional applications struggle with industrial data’s bulk and complexity, causing data analysis, security, and privacy challenges. Modern industrial systems use AI and ML for big data analysis and data processing to overcome these issues. Optimizing human-machine synergy minimizes costs and equipment maintenance and boosts efficiency. An ML-assisted Smart Production Process (ML-SP2) and Intrusion Detection System (ML-IDS) have been proposed to assess and address Industrial 5.0 concerns. Data capture, predictive maintenance and optimization, transparent decision-making, and proactive maintenance are integrated into the manufacturing process with the ML-SP2. The ML-IDS detects network vulnerabilities using ensemble methods and manages distribution efficiently. The ML-IDS uses the variety of ML techniques such as random forest, decision tree and support vector machines that identifies the intruder with maximum prediction accuracy. In addition, the intruder activities are observed with the help of the convolution networks that improve the overall intruder activities recognition. The smart industrial production phase’s effectiveness is measured by the RPL (0.9), maintenance cost (2500$), production performance (1.0), VDR (97.6%), FAR, accuracy (99%), precision (94%)-recall (96%), and f1-measure (98%) compared to the existing methods such as ML-RF-FLID, NRDD-DBSCAN, and OC-SVM.

1 April 2014 in Optical Memory and Neural Networks
Verified
Journal Article
Closed access
PDF file
AOA. Oliinyk
A. Oliinyk
TZT. Zaiko
T. Zaiko
Sergei A. SubbotinSergei A. Subbotin
Sergei A. Subbotin
The problem of reduction of training samples for synthesizing diagnostic models has been solved in the paper. The method of dimension reduction of training sample based on association rules has been proposed. It includes the implementation of stages of reduction of instances, features and superfluous terms, uses information on extracted association rules for evaluation of informativeness of features. The proposed method allows to create a partition of feature space with a fewer number of instances compared to the original sample, which in turn makes the synthesis of easier and more convenient for perception diagnostic models possible. The developed method has been implemented in the developed software and was used for the practical problem solving of reduction of training sample for the synthesis of a diagnostic model of confectionery products quality.

1 January 2015 in Optical Memory and Neural Networks
Verified
Journal Article
Closed access
PDF file
AOA. A. Oliinyk
A. A. Oliinyk
Sergei A. SubbotinSergei A. Subbotin
Sergei A. Subbotin
The problem of mathematical support development for automation of the decision tree construction for the neuro-fuzzy network synthesis based on the training data samples is solved. The method of...

24 April 2019 in Eastern-European Journal of Enterprise Technologies
Verified
Journal Article
Open access
PDF file
IFIevgen Fedorchenko
Ievgen Fedorchenko
AOAndrii Oliinyk
Andrii Oliinyk
ASAlexander Stepanenko
Alexander Stepanenko
TZTetiana Zaiko
Tetiana Zaiko
SSSerhii Shylo
Serhii Shylo
ASAnton Svyrydenko
Anton Svyrydenko
Development of the modified methods to train a neural network to solve the task on recognition of road users

1 January 2015 in Automatic Control and Computer Sciences
Verified
Journal Article
Closed access
PDF file
AOA. O. Oliinyk
A. O. Oliinyk
SSS. Yu. Skrupsky
S. Yu. Skrupsky
Sergei A. SubbotinSergei A. Subbotin
Sergei A. Subbotin
The problem of training neuro-fuzzy networks is discussed. The computational complexity of the method for training neuro-fuzzy networks on the basis of parallel random search is analyzed. Theoretical...

1 April 2016 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
AOA. A. Oliinyk
A. A. Oliinyk
Sergei A. SubbotinSergei A. Subbotin
Sergei A. Subbotin