Plant disease recognition using residual convolutional enlightened Swin transformer networks

Plant disease recognition using residual convolutional enlightened Swin transformer networks Ponugoti Kalpana R. Anandan Abdelazim G. Hussien Hazem Migdady Laith Abualigah Abstract

Agriculture plays a pivotal role in the economic development of a nation, but, growth of agriculture is affected badly by the many factors one such is plant diseases. Early stage prediction of these disease is crucial role for global health and even for game changers the farmer’s life. Recently, adoption of modern technologies, such as the Internet of Things (IoT) and deep learning concepts has given the brighter light of inventing the intelligent machines to predict the plant diseases before it is deep-rooted in the farmlands. But, precise prediction of plant diseases is a complex job due to the presence of noise, changes in the intensities, similar resemblance between healthy and diseased plants and finally dimension of plant leaves. To tackle this problem, high-accurate and intelligently tuned deep learning algorithms are mandatorily needed. In this research article, novel ensemble of Swin transformers and residual convolutional networks are proposed. Swin transformers (ST) are hierarchical structures with linearly scalable computing complexity that offer performance and flexibility at various scales. In order to extract the best deep key-point features, the Swin transformers and residual networks has been combined, followed by Feed forward networks for better prediction. Extended experimentation is conducted using Plant Village Kaggle datasets, and performance metrics, including accuracy, precision, recall, specificity, and F1-rating, are evaluated and analysed. Existing structure along with FCN-8s, CED-Net, SegNet, DeepLabv3, Dense nets, and Central nets are used to demonstrate the superiority of the suggested version. The experimental results show that in terms of accuracy, precision, recall, and F1-rating, the introduced version shown better performances than the other state-of-art hybrid learning models.
04 15 2024 8660 56393 1 10.1007/springer_crossmark_policy link.springer.com false 5 September 2023 6 March 2024 15 April 2024 The authors declare no competing interests. Linköping University 501100003945 https://creativecommons.org/licenses/by/4.0 https://creativecommons.org/licenses/by/4.0 10.1038/s41598-024-56393-8 20240415120206973 https://www.nature.com/articles/s41598-024-56393-8 https://www.nature.com/articles/s41598-024-56393-8.pdf https://www.nature.com/articles/s41598-024-56393-8.pdf https://www.nature.com/articles/s41598-024-56393-8 Electronics JA Pandian 11 1266 2022 10.3390/electronics11081266 Pandian, J. A. et al. A five convolutional layer deep convolutional neural network for plant leaf disease detection. Electronics 11, 1266 (2022). M Brahimi 93 2018 Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent 10.1007/978-3-319-90403-0_6 Brahimi, M. et al. Deep learning for plant diseases: Detection and saliency map visualisation. In Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent (eds Zhou, J. & Chen, F.) 93–117 (Springer, 2018). Comput. Electr. Eng. G Geetharamani 76 323 2019 10.1016/j.compeleceng.2019.04.011 Geetharamani, G. & Pandian, A. Identification of plant leaf diseases using a nine-layer deep convolutional neural network. Comput. Electr. Eng. 76, 323–338 (2019). Comput. Electron. Agric. T Rumpf 74 91 2010 10.1016/j.compag.2010.06.009 Rumpf, T. et al. Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance. Comput. Electron. Agric. 74, 91–99 (2010). Electronics H-C Chen 11 951 2022 10.3390/electronics11060951 Chen, H.-C. et al. AlexNet convolutional neural network for disease detection and classification of tomato leaf. Electronics 11, 951 (2022). 10.1109/ICIP.2015.7350839 Lee, S. H., Chan, C. S., Wilkin, P., & Remagnino, P. Deep-plant: Plant identification with convolutional neural networks. In Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada, 27–30 September 2015, 452–456. Front. Plant Sci. SH Lee 2002 10.3389/fpls.2020.601250 Lee, S. H., Goëau, H., Bonnet, P. & Joly, A. Attention-based recurrent neural network for plant disease classification. Front. Plant Sci. https://doi.org/10.3389/fpls.2020.601250 (2002). Comput. Intell. Neurosci. S Sladojevic 2016 3289801 2016 10.1155/2016/3289801 Sladojevic, S., Arsenovic, M., Anderla, A., Culibrk, D. & Stefanovic, D. Deep neural networks based recognition of plant diseases by leaf image classification. Comput. Intell. Neurosci. 2016, 3289801 (2016). Comput. Electron. Agric. KP Ferentinos 145 311 2018 10.1016/j.compag.2018.01.009 Ferentinos, K. P. Deep learning models for plant disease detection and diagnosis. Comput. Electron. Agric. 145, 311–318 (2018). Arun Pandian, J., & Geetharamani, G. Data for: Identification of plant leaf diseases using a 9-layer deep convolutional neural network. Mendeley Data. 2019. https://data.mendeley.com/datasets/tywbtsjrjv/1. Accessed 29 Mar 2020. Sensors A Almadhor 21 3830 2021 10.3390/s21113830 Almadhor, A. et al. AI-driven framework for recognition of guava plant diseases through machine learning from DSLR camera sensor based high resolution imagery. Sensors 21, 3830 (2021). 10.1109/iSES47678.2019.00024 Kumar, S., Chowdhary, G., Udutalapally, V., Das, D. & Mohanty, S. P. "gCrop: Internet-of-Leaf-Things (IoLT) for monitoring of the growth of crops in smart agriculture. In 2019 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), 2019, 53–56. https://doi.org/10.1109/iSES47678.2019.00024. ACM Trans. Asian Low-Resour. Lang. Inf. Process. N Praveena 20 20 2023 10.1145/3618110 Praveena, N. et al. Deep learning based multilingual speech synthesis using multi feature fusion methods. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 20, 20. https://doi.org/10.1145/3618110 (2023). Plant Methods J Liu 17 22 2021 10.1186/s13007-021-00722-9 Liu, J. & Wang, X. Plant diseases and pests detection based on deep learning: A review. Plant Methods 17, 22. https://doi.org/10.1186/s13007-021-00722-9 (2021). Eng. Proc. P Alagumariappan 2020 10.3390/ecsa-7-08160 Alagumariappan, P. et al. Intelligent plant disease identification system using machine learning. Eng. Proc. https://doi.org/10.3390/ecsa-7-08160 (2020). Int. J. Eng. Res. Technol. R Ramya 8 12 2020 2020 Ramya, R., Kiran, M., Marimuthu, E., Naveen Kumar, B. & Pavithra, G. Plant monitoring and leaf disease detection with classification using machine learning-MATLAB. Int. J. Eng. Res. Technol. 8(12), 2020 (2020). AgriEngineering MEH Chowdhury 3 294 2021 10.3390/agriengineering3020020 Chowdhury, M. E. H. et al. Automatic and reliable leaf disease detection using deep learning techniques. AgriEngineering 3, 294–312. https://doi.org/10.3390/agriengineering3020020 (2021). PLoS One A Khan 15 12 2020 10.1371/journal.pone.0243243 Khan, A., Nawaz, U., Ulhaq, A. & Robinson, R. W. Real-time plant health assessment via implementing cloud-based scalable transfer learning on AWS DeepLens. PLoS One 15, 12. https://doi.org/10.1371/journal.pone.0243243 (2020). 10.1109/INCET54531.2022.9824653 Varshney, D., Babukhanwala, B., Khan, J., Saxena, D. & Singh, A. K. Plant disease detection using machine learning techniques. In 2022 3rd International Conference for Emerging Technology (INCET), 2022, 1–5. https://doi.org/10.1109/INCET54531.2022.9824653. Plants G Latif 11 2230 2022 10.3390/plants11172230 Latif, G., Abdelhamid, S. E., Mallouhy, R. E., Alghazo, J. & Kazimi, Z. A. Deep learning utilization in agriculture: Detection of rice plant diseases using an improved CNN model. Plants 11, 2230. https://doi.org/10.3390/plants11172230 (2022). Int. Conf. Adv. Technol. D Gosai 2022 1 2022 10.1109/ICONAT53423.2022.9726036 Gosai, D., Kaka, B., Garg, D., Patel, R. & Ganatra, A. Plant disease detection and classification using machine learning algorithm. Int. Conf. Adv. Technol. 2022, 1–6. https://doi.org/10.1109/ICONAT53423.2022.9726036 (2022). Lect. Notes Comput. Sci. T Honkela 6791 25 2011 10.1007/978-3-642-21735-7 Honkela, T., Duch, W., Girolami, M. & Kaski, S. Artificial neural networks and machine learning–icann 2011. Lect. Notes Comput. Sci. 6791, 25. https://doi.org/10.1007/978-3-642-21735-7 (2011). Neurocomputing GB Huang 70 1 489 2006 10.1016/j.neucom.2005.12.126 Huang, G. B., Zhu, Q.-Y. & Siew, C.-K. Extreme learning machine: Theory and applications. Neurocomputing 70(1), 489–501 (2006). Neurocomputing B Wang 149 224 2015 10.1016/j.neucom.2014.03.076 Wang, B. et al. Parallel online sequential extreme learning machine based on MapReduce. Neurocomputing 149, 224–232 (2015). 10.1109/EICT48899.2019.9068805 Mukti, Z., & Biswas, D. Transfer learning based plant diseases detection using ResNet50. In 2019 4th International Conference on Electrical Information and Communication Technology (EICT), 2019, 1–6. https://doi.org/10.1109/EICT48899.2019.9068805. IEEE Access W-J Hu 8 115287 2020 10.1109/ACCESS.2020.3001237 Hu, W.-J. et al. MDFC–ResNet: An agricultural IoT system to accurately recognize crop diseases. IEEE Access 8, 115287–115298. https://doi.org/10.1109/ACCESS.2020.3001237 (2020). 10.1109/TRIBES52498.2021.9751620 Saxena, O., Agrawal, S. & Silakari, S. Disease detection in plant leaves using deep learning models: AlexNet and GoogLeNet. In 2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES), 2021, 1–6. https://doi.org/10.1109/TRIBES52498.2021.9751620. 10.1109/ICSSIT53264.2022.9716233 Jayaprakash, K. & Balamurugan, S. P. Design of optimal multilevel thresholding based segmentation with AlexNet model for plant leaf disease diagnosis. In 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT), 2022, 1473–1479. https://doi.org/10.1109/ICSSIT53264.2022.9716233. IEEE Sens. J. J Chen 22 14 14628 2022 10.1109/JSEN.2022.3182304 Chen, J., Chen, W., Zeb, A., Yang, S. & Zhang, D. Lightweight inception networks for the recognition and detection of rice plant diseases. IEEE Sens. J. 22(14), 14628–14638. https://doi.org/10.1109/JSEN.2022.3182304 (2022). 10.1109/ACMI53878.2021.9528199 Peyal, H. I., Shahriar, S. M., Sultana, A., Jahan, I. & Mondol, M. H. Detection of tomato leaf diseases using transfer learning architectures: A comparative analysis. In 2021 International Conference on Automation, Control and Mechatronics for Industry 4.0 (ACMI), 2021, 1–6. https://doi.org/10.1109/ACMI53878.2021.9528199. IEEE Trans. Geosci. Remote Sens. Y Shi 60 1 2022 10.1109/TGRS.2021.3058782 Shi, Y. et al. A biologically interpretable two-stage deep neural network (BIT-DNN) for vegetation recognition from hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 60, 1–20. https://doi.org/10.1109/TGRS.2021.3058782 (2022). A Bose 2021 Proceedings of International Conference on Computational Intelligence, Data Science and Cloud Computing. Lecture Notes on Data Engineering and Communications Technologies 10.1007/978-981-33-4968-1_17 Bose, A. et al. Capsnet-VGG16 architecture for Cassava plant disease detection. In Proceedings of International Conference on Computational Intelligence, Data Science and Cloud Computing. Lecture Notes on Data Engineering and Communications Technologies (eds Balas, V. E. et al.), Vol. 62 (Springer, 2021). https://doi.org/10.1007/978-981-33-4968-1_17.