Classification of Sunflowers by the Means of Convolutional- Capsular Model of Neural Network CNN-Capsnet
DOI:
https://doi.org/10.31649/1997-9266-2024-176-5-63-70Keywords:
classification, sunflower, convolution-capsule model, neural network, accuracyAbstract
Sunflower classification using convolutional- capsular model of neural network CNN-CapsNet of improved architecture, which combines the convolutional neural network CNN and the capsular neural network CapsNet and enables to use the advantages of these two architectures is suggested in the paper. The conducted review of the literature sources allows to conclude that the advantage of convolutional neural network CNN is a shorter training time and the advantages of capsular neural network CapsNet include greater precision, reliability and the ability to work effectively with the complex tasks. Combination of convolutional neural network CNN and capsular neural network CapsNet as well as improvement of CNN-CapsNet architecture were conducted by means of making changes to CapsNet. These changes are that in dynamic routing, the feedback process adds support for the capsule that most closely matches the original signal. Activation functions are also applied to approximate nonlinear connections in deep networks. They are implemented as basic mathematical functions, usually for scalar quantities. Convolutional layers are used to get initial feature maps, which are then loaded into the CapsNet model to perform the final classification. Based on this approach , two separate model have been developed. One model provides classification, based on two classes: "unripe sunflower" and "ripe sunflower". The second model provides classification based on three classes: "unripe sunflower", "ripe sunflower" and "sick sunflower". Main indicators of the effectiveness of the CNN-CapsNet neural network were selected such characteristics as accuracy, sensitivity and F-score based on type I and II errors. To analyze these indicators, error matrices and graphs of accuracy and errors of these models were constructed. The comparison of the proposed models of the CNN-CapsNet neural network with similar ones was made, the highest accuracy was demonstrated by the proposed models.
References
Названо топ-3 культури, посівні площі під якими змінилися найбільше. [Електронний ресурс]. Режим доступу: https://agroportal.ua/news/eksklyuzivy/nazvano-top-3-kulturi-posivni-ploshchi-pid-yakimi-zminilisya-naybilshe . Дата звернення 09.07.2024.
Що вигідно вирощувати фермеру в Україні? [Електронний ресурс]. Режим доступу: https://veles-agro.com/news/chto-vygodno-vyrashhivat-fermeru-v-ukraine. Дата звернення 09.07.2024.
Найбільш популярні сільськогосподарські культури в Україні [Електронний ресурс]. Режим доступу: https://ropa.in.ua/news/najbilsh-populjarni-silskogospodarski-kulturi-v-ukraini. Дата звернення 09.07.2024.
А. Б. Ачасов, А. О. Седов, і А. О. Ачасова, «Оцінка забур’яненості посівів соняшника за допомогою безпілотних літальних апаратів,» Людина та довкілля. Проблеми неоекології, № 3-4 (26), с. 69-74, 2016.
B. Knysh, and Y. Kulyk, “Development of an image segmentation model based on a convolutional neural network,” Eastern-European Journal of Enterprise Technologies, no. 2 (110), pp. 6-15, 2021. https://doi.org/10.15587/1729-4061.2021.228644 .
B. Knysh, and Y. Kulyk, “Improving a model of object recognition in images based on a convolutional neural network,” Eastern-European Journal of Enterprise Technologies, no. 3 (111), pp. 40-50, 2021. https://doi.org/10.15587/1729-4061.2021.233786 .
Y. Unal, and M. N. Dudak, “Deep Learning Approaches for Sunflower Disease Classification: A Study of Convolutional Neural Networks with Squeeze and Excitation Attention Blocks,” Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, vol 13 (1), pp. 247-258, 2024. https://doi.org/10.17798/bitlisfen.1380995 .
A. Sirohi, and A. Malik, “A Hybrid Model for the Classification of Sunflower Diseases Using Deep Learning,” in 2nd International Conference on Intelligent Engineering and Management (ICIEM), 2021, no. 2, pp. 58-62. https://doi.org/10.1109/ICIEM51511.2021.9445342 .
G. E. Hinton, A. Krizhevsky, and S. D. Wang, “Transforming autoencoders,” in International Conference on Artificial Neural Networks, 2011, pp. 44-51.
J. Xuefeng, W. Yikun, L. Wenbo, L. Shuying, and L. Junrui, “CapsNet, CNN, FCN: Comparative Performance Evaluation for Image Classification,” International Journal of Machine Learning and Computing, vol. 9, no. 6, pp. 840-848, 2019. https://doi.org/10.18178/ijmlc.2019.9.6.881 .
R. Mukhometzianov, and J. Carrillo, “CapsNet comparative performance evaluation for image classification,” Computer Vision and Pattern Recognition, vol. 1, pp. 1-14, 2018. https://arxiv.org/ftp/arxiv/papers/1805/1805.11195.pdf .
D. Rodica, and D. Ciprian, “ResNet interpretation methods applied to the classification of foliar diseases in sunflower,” Journal of Agriculture and Food Research, vol. 9, no. 100323, pp. 1-12, 2022. https://doi.org/10.1016/j.jafr.2022.100323 .
M. Bakr, S. Abdel-Gaber, M. Nasr, and M. Hazman, “DenseNet Based Model for Plant Diseases Diagnosis,” European Journal of Electrical Engineering and Computer Science, vol. 6, pp. 1-9, 2022. https://doi.org/10.24018/ejece.2022.6.5.458 .
Gh. Promila, A. K. Mondal, S. Chatterjee, M. Masud, H. Meshref, and A. K. Bairagi, “Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI,” Mathematics, vol. 11, no. 10, pp. 1-24, 2023. https://doi.org/10.3390/math11102241 .
M. U. Haq, M. A. J. Sethi, and A. U. Rehman, “Capsule Network with Its Limitation, Modification, and Applications – A Survey,” Machine Learning and Knowledge Extraction, vol. 5(3), pp. 891-921, 2023. https://doi.org/10.3390/make5030047 .
B. Juba, and H. S. Le, “Precision-recall versus accuracy and the role of large data sets,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2019, vol. 33, pp. 4039-4048.
Sun Flower Fruits and Leaves dataset for Sunflower Disease Classification through Machine Learning and Deep Learning. [Electronic resource]. Available: https://data.mendeley.com/datasets/b83hmrzth8/1 . Accessed: 09.07.2024.
Sunflower_detection Computer Vision Project [Electronic resource]. Available: https://universe.roboflow.com/khaing/sunflower_detection . Accessed: 09.07.2024.
G. Rana, R. Singh, A. Pal, and R. Gupta, “Enhancing Sunflower Disease Identification with CNN-SVM Integration,” in 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), 2023, pp. 1-6. https://doi.org/10.1109/SMARTGENCON60755.2023.10442779 .
M. Peker, “Multi-channel capsule network ensemble for plant disease detection,” SN Applied Sciences, vol. 3, pp. 1-10, 2021. https://doi.org/10.1007/s42452-021-04694-2 .
282 Sunflower labeled image dataset [Electronic resource]. Available: https://images.cv/download/sunflower/282 . Accessed 09.07.2024.
Downloads
-
pdf (Українська)
Downloads: 4
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
