Ihor Sliusar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ihor Sliusar has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Vadym Slyusar
Institute of Artificial Intelligence Problems, Ukraine
10 shared publications - Sergey Sheleg
ENIT, Inc.,Scottsdale,USA
4 shared publications - Olena Kopishynska
Educational Research Institute of Economics, Management, Law and Information Technologies, Poltava State Agrarian University
3 shared publications Sergiy Voloshko
Department of Computer Engineering, Poltava National Technical University Named after Y. Kondratyuk, Poltava, Ukraine
3 shared publicationsViktor Smolyar
Department of Computer Engineering, Poltava National Technical University Named after Y. Kondratyuk, Poltava, Ukraine
2 shared publications- Viktor Smolyar
Department of Computer Engineering, Poltava National Technical Y. Kondratyuk University, Ukraine
2 shared publications
Latest Publications
- Open Access
- 1 August 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (8) , 085008
Evaluating machine learning and baseline methods for crop yield forecasting using small datasets
Accurate crop-yield forecasting is difficult when only small official-statistics datasets are available. This study evaluates a reproducible pre-season regional forecasting workflow for wheat, maize, and sunflower in Poltava region, Ukraine, using harmonised AgroStats records for 2010–2024. The analysis is based on one annual regional time series per crop; it is therefore a benchmark of temporal forecasting from official statistics rather than a gridded yield-prediction or spatial-mapping study. Forecast accuracy is assessed with mean absolute error (MAE), root mean squared error, and mean absolute percentage error. To avoid information leakage, feature transformations, imputations, scaling, and hyperparameter choices are performed only within the corresponding historical training window under a forward temporal design: training set 2010–2018, validation set 2019–2021, and held-out test set 2022–2024. In addition to ElasticNet, XGBoost, and LightGBM, the study compares transparent baseline forecasting methods: Naive, FORECAST.LINEAR, LINEST, and autoregressive integrated moving averag. Under the conservative lag-only scenario, the best 2022–2024 test results are obtained for maize (LightGBM, MAE 0.69 t ha −1 ) and sunflower (LightGBM, MAE 0.04 t ha −1 ), whereas for wheat the linear-trend baseline remains slightly better (MAE 0.49 t ha −1 versus 0.54 t ha −1 for ElasticNet). Supplementary analyses show that extended lag structures can improve selected crops and that seasonal NASA Prediction of Worldwide Energy Resources climate aggregates improve maize forecasts (MAE 0.52 t ha −1 ) but not wheat or sunflower. SHapley Additive exPlanations are used descriptively to examine whether the selected models rely on agronomically plausible predictors. The findings should be interpreted as crop-specific evidence under a small annual dataset: machine learning does not guarantee superiority over simple baselines, but it can provide a reproducible comparison framework and useful gains for selected regional forecasting tasks.
- 1 August 2026
- Published by IOP Publishing in Environmental Research Communications
- Vol. 8 (8) , 085008
Open AccessEvaluating machine learning and baseline methods for crop yield forecasting using small datasets
Accurate crop-yield forecasting is difficult when only small official-statistics datasets are available. This study evaluates a reproducible pre-season regional forecasting workflow for wheat, maize, and sunflower in Poltava region, Ukraine, using harmonised AgroStats records for 2010–2024. The analysis is based on one annual regional time series per crop; it is therefore a benchmark of temporal forecasting from official statistics rather than a gridded yield-prediction or spatial-mapping study. Forecast accuracy is assessed with mean absolute error (MAE), root mean squared error, and mean absolute percentage error. To avoid information leakage, feature transformations, imputations, scaling, and hyperparameter choices are performed only within the corresponding historical training window under a forward temporal design: training set 2010–2018, validation set 2019–2021, and held-out test set 2022–2024. In addition to ElasticNet, XGBoost, and LightGBM, the study compares transparent baseline forecasting methods: Naive, FORECAST.LINEAR, LINEST, and autoregressive integrated moving averag. Under the conservative lag-only scenario, the best 2022–2024 test results are obtained for maize (LightGBM, MAE 0.69 t ha −1 ) and sunflower (LightGBM, MAE 0.04 t ha −1 ), whereas for wheat the linear-trend baseline remains slightly better (MAE 0.49 t ha −1 versus 0.54 t ha −1 for ElasticNet). Supplementary analyses show that extended lag structures can improve selected crops and that seasonal NASA Prediction of Worldwide Energy Resources climate aggregates improve maize forecasts (MAE 0.52 t ha −1 ) but not wheat or sunflower. SHapley Additive exPlanations are used descriptively to examine whether the selected models rely on agronomically plausible predictors. The findings should be interpreted as crop-specific evidence under a small annual dataset: machine learning does not guarantee superiority over simple baselines, but it can provide a reproducible comparison framework and useful gains for selected regional forecasting tasks.
- 2 January 2026
- Published by Springer Nature
- p. 347-357
Expansion of Customer Relationship Management Functionality Using Recurrent LSTM Networks for Automation Demand Forecasting
- 2 January 2026
- Published by Springer Nature
- p. 347-357
Expansion of Customer Relationship Management Functionality Using Recurrent LSTM Networks for Automation Demand Forecasting
- 1 July 2024
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 67 (7) , 354-368
Properties of 2- and 4-Cell Metamaterial Modules Based on Double Moebius Strips
The article continues the study of a new type of metamaterial cells based on double Moebius strips, which are mathematical constructs with unique propertie
- 1 July 2024
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 67 (7) , 354-368
Properties of 2- and 4-Cell Metamaterial Modules Based on Double Moebius Strips
The article continues the study of a new type of metamaterial cells based on double Moebius strips, which are mathematical constructs with unique propertie
- 15 September 2023
- Published by Springer Nature
- p. 675-692
A Two-Tape Design of Metamaterial Based on a Quasi-fractal Approach
- 15 September 2023
- Published by Springer Nature
- p. 675-692
A Two-Tape Design of Metamaterial Based on a Quasi-fractal Approach
- Open Access
- 24 July 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 40 (1) , 22
Innovative Projects in the Industry 4.0 Sphere of Poltava State Agrarian University
The activity of the “Industry 4
- 24 July 2023
- Published by MDPI AG in Engineering Proceedings
- Vol. 40 (1) , 22
Open AccessInnovative Projects in the Industry 4.0 Sphere of Poltava State Agrarian University
The activity of the “Industry 4
- 1 May 2023
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 66 (5) , 251-262
Patch Antennas Based on Micro QR Codes
The article proposes a new type of broadband patch antennas based on micro QR codes with integrated metamaterial cell as a marker. In this research, severa
- 1 May 2023
- Published by Allerton Press in Radioelectronics and Communications Systems
- Vol. 66 (5) , 251-262
Patch Antennas Based on Micro QR Codes
The article proposes a new type of broadband patch antennas based on micro QR codes with integrated metamaterial cell as a marker. In this research, severa
- Open Access
- 1 March 2023
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 22 (1) , 121-139
Double Negative Metamaterial Based on Moebius Strip
- 1 March 2023
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 22 (1) , 121-139
Open AccessDouble Negative Metamaterial Based on Moebius Strip
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 614-618
Improved PSP and U-Net Architectures for Forest Segmentation in Remote Sensing Pictures
Various PSP and U-Net architectures for forest segmentation in remote sensing pictures have been proposed and investigated. The main improvements of the proposed architectures are based on using the BathNormalization layers, replacing MaxPool2D layers with A veragePooling2D, changing Conv2DTranspose to UpSampling2D blocks, etc. For the training of neural networks was used modified dataset of 128x128 pictures based on the dataset from Kaggle. As a result of improving architecture was given the maximum segmentation accuracy of 80.8 % on the validation set of pictures.
- 14 November 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 614-618
Improved PSP and U-Net Architectures for Forest Segmentation in Remote Sensing Pictures
Various PSP and U-Net architectures for forest segmentation in remote sensing pictures have been proposed and investigated. The main improvements of the proposed architectures are based on using the BathNormalization layers, replacing MaxPool2D layers with A veragePooling2D, changing Conv2DTranspose to UpSampling2D blocks, etc. For the training of neural networks was used modified dataset of 128x128 pictures based on the dataset from Kaggle. As a result of improving architecture was given the maximum segmentation accuracy of 80.8 % on the validation set of pictures.
- Open Access
- 1 June 2022
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 21 (2) , 220-241
Broadband Antennas Based on the Double Moebius Strip
- 1 June 2022
- Published by FapUNIFESP (SciELO) in Journal of Microwaves, Optoelectronics and Electromagnetic Applications
- Vol. 21 (2) , 220-241
Open AccessBroadband Antennas Based on the Double Moebius Strip
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 404-410
Main Aspects of the Creation of Managing Information System at the Implementation of Precision Farming
The paper presents the results of the research of the leading role of integrative information systems of management and accounting of agricultural production in the re-engineering of precision farming systems in agrarian enterprises. The authors determined the necessity, consistency, complexity and content of the main stages of the implementation of precision farming systems, analyzed the main problems and limitations of the implementation process, as well as the expediency of using a single software platform. The practical value of the work is to define the integration role of the management information system in the processing of data of various origins and generation of solution options for the effective management of the agrarian enterprise.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 404-410
Main Aspects of the Creation of Managing Information System at the Implementation of Precision Farming
The paper presents the results of the research of the leading role of integrative information systems of management and accounting of agricultural production in the re-engineering of precision farming systems in agrarian enterprises. The authors determined the necessity, consistency, complexity and content of the main stages of the implementation of precision farming systems, analyzed the main problems and limitations of the implementation process, as well as the expediency of using a single software platform. The practical value of the work is to define the integration role of the management information system in the processing of data of various origins and generation of solution options for the effective management of the agrarian enterprise.