STRUCTURAL AND FUNCTIONAL MODEL OF A CONVOLUTIONAL NEURAL NETWORK FOR PROCESSING, ANALYSING AND CLASSIFYING IMAGES OF VARYING COMPLEXITY
DOI:
https://doi.org/10.26906/SUNZ.2025.4.103Keywords:
convolutional neural network, image processing, classification, feature analysis, structural-functional model, deep learningAbstract
The article presents presents a structural and functional model of a convolutional neural network (CNN) designed for processing, analysing and classifying images of varying complexity. The model is based on a multi-level architecture using convolutional, residual and parallel computing blocks, which ensure high adaptability to different types of input data. The input tensor is normalised by the mean and standard deviation of the sample, which reduces data variability and stabilises the learning process. The first convolutional layer performs the initial extraction of image features with ELU activation, which ensures continuity of gradients and eliminates the problem of ‘dead neurons.’ The implementation of skip connections ensures the consistency of information flows and increases the stability of training. The results demonstrate increased classification accuracy and noise resistance compared to basic CNN architectures.Downloads
References
1. Hussain, S., Lu, L. Mubeen, M., Nasim, W., Karuppannan, S., Fahad, S., Tariq, A., Mousa, B. G., Mumtaz, F. & Aslam, M. Spatiotemporal variation in land use land cover in the response to local climate change using multispectral remote sensing data. Land, 2022, vol. 11, no. 5, article no. 595. DOI: https://doi.org/10.3390/land11050595
2. Yaloveha, V., Hlavcheva, D., Podorozhniak, A. & Kuchuk, H. Fire hazard research of forest areas based on the use of convolutional and capsule neural networks. 2019 IEEE 2nd Ukraine Conference on Electrical and Computer Engineering (UKRCON), 2019, pp. 828-832. DOI: https://doi.org/10.1109/UKRCON.2019.8879867
3. Radočaj, D., Jurišić, M. & Gašparović, M. The Role of Remote Sensing Data and Methods in a Modern Approach to Fertilization in Precision Agriculture. Remote Sensing, 2022, vol. 14, no. 3, DOI: https://doi.org/10.3390/rs14030778
4. Munawar, H. S., Hammad, A. W. A. & Waller, S. T. Remote Sensing Methods for Flood Prediction: A Review. Sensors, 2022, vol. 22, no. 3, article no. 960. DOI: https://doi.org/10.3390/s22030960
5. Barabash, O., Bandurka, O., Svynchuk, O. & Tverdenko, H. Method of identification of tree species composition of forests on the basis of geographic information database. Advanced Information Systems, 2022, vol. 6, no. 4, pp 5-10. DOI: https://doi.org/10.20998/2522-9052.2022.4.01
6. Svyrydov, A., Kuchuk, H. and Tsiapa, O. (2018), “Improving efficienty of image recognition process: Approach and case study”, Proceedings of 2018 IEEE 9th International Conference on Dependable Systems, Services and Technologies, DESSERT 2018, pp. 593–597, doi: https://doi.org/10.1109/DESSERT.2018.8409201
7. Alganci, U., Soydas, M. & Sertel, E. Comparative research on deep learning approaches for airplane detection from very highresolution satellite images. Remote Sensing, 2020, vol. 12, no. 3, article no. 458. DOI: https://doi.org/10.3390/rs12030458
8. Kuchuk, H. and Malokhvii, E. (2024), “Integration of IOT with Cloud, Fog, and Edge Computing: A Review”, Advanced Information Systems, vol. 8(2), pp. 65–78, doi: https://doi.org/10.20998/2522-9052.2024.2.08
9. Weiss, K., Khoshgoftaar, T. M. & Wang, D. D. A survey of transfer learning. Journal of Big data, 2016, vol. 3, article no. 9. DOI: https://doi.org/10.1186/s40537-016-0043-6
10. Hlavcheva, D., Yaloveha, V., Podorozhniak, A. & Kuchuk, H. Tumor nuclei detection in histopathology images using R – CNN. CEUR Workshop Proceedings, 2020. vol. 2740, pp. 63-74. Available at: https://ceur-ws.org/Vol-2740/20200063.pdf
11. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770-778. DOI: https://doi.org/10.1109/CVPR.2016.90
12. Yaloveha, V., Podorozhniak, A. & Kuchuk, H. CNN hyperparameter optimization applied to land cover classification. Radioelectronic and computer systems, 2022, no. 1 (101), pp. 115-128. DOI: https://doi.org/10.32620/reks.2022.1.09
13. Hlavcheva, D., Yaloveha, V., Podorozhniak, A. & Kuchuk, H. Comparison of CNNs for Lung Biopsy Images Classification. 2021 IEEE 3rd Ukraine Conference on Electrical and Computer Engineering, UKRCON 2021 – Proceedings, 2021, pp. 1–5. DOI: https://doi.org/10.1109/UKRCON53503.2021.9575305
14. Tan, M. & Le, Q. V. Efficientnetv2: Smaller models and faster training. ArXiv (Cornell University), Preprint arXiv:2104.00298, 2021. DOI: https://doi.org/10.48550/arXiv.2104.00298
15. Carneiro, T., Da Nóbrega, R. V. M., Nepomuceno, T., Bian, G.-B., De Albuquerque, V. H. C. & Filho, P. P. R. Performance analysis of google colaboratory as a tool for accelerating deep learning applications. IEEE Access, 2018, vol. 6, pp. 61677- 61685. DOI: https://doi.org/10.1109/ACCESS.2018.2874767
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Oleksandr Mozhaiev , Heorhii Kuchuk , Renat Safarov , Maksym Lavrovskyi , Kostiantyn Moroz
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
