Optimized Light-Weight Deep Learning Model for Rice Disease Identification
Keywords:
Data augmentation, pruning, deep learning, compression, fine-tuningAbstract
From past decade, deep learning models have gained the Convolutional neural network models have made substantial progression in the agricultural sector. But the utilization of the deep learning models is restricted confined because of enormous supernumerary and imperative parameters. In this article , the magnitude based pruning and dynamic range quantization have been employed to optimize the CNN model so as to be deployed on edge devices for the identification of four classes of rice leave i.e. brown spot, hispa, leaf blast and healthy. Experimental results show that classification accuracy achieved by baseline CNN Model for brownspot -97.15%, hispa- 97.03%, leaf blast- 96.94% and the healthy-96.9%.Overall test accuracy using baseline CNN model is 98.11%, using magnitude base pruning is 97.39% and using dynamic range quantization and pruning is 96.02%.The initial model size of the cnn model without pruning is 78.24 MB, model size with pruning is 25.743 MB, and with quantization model size achieved is 21.88 MB. The proposed work can deploy the models on edge devices that would be light weight with less memory consumption.
Downloads
References
Dhiman, P. (2014, September). Empirical validation of website quality using statistical and machine learning methods. In 2014 5th International Conference-Confluence The Next Generation Information Technology Summit (Confluence) (pp. 286-291). IEEE.
Arumuga Arun, R., & Umamaheswari, S. (2023). Effective multi-crop disease detection using pruned complete concatenated deep learning model.
Zhang, S., Wu, G., Gu, J., & Han, J. (2020). Pruning convolutional neural networks with an attention mechanism for remote sensing image classification. Electronics, 9(8), 1209.
Joshi, P., Das, D., Udutalapally, V., Pradhan, M. K., & Misra, S. (2022). Ricebios: Identification of biotic stress in rice crops using edge-as-a-service. IEEE Sensors Journal, 22(5), 4616-4624.
Chen, R., Qi, H., Liang, Y., & Yang, M. (2022). Identification of plant leaf diseases by deep learning based on channel attention and channel pruning. Frontiers in Plant Science, 13.
Arumuga Arun, R., & Umamaheswari, S. (2023). Effective multi-crop disease detection using pruned complete concatenated deep learning model.
Sowmiya, B., Saminathan, K., & Devi, M. C. Classification of paddy leaf diseases with extended huber loss function using convolutional neural networks.
Laut, S., Poapolathep, S., Piasai, O., Sommai, S., Boonyuen, N., Giorgi, M., ... & Poapolathep, A. (2023). Storage Fungi and Mycotoxins Associated with Rice Samples Commercialized in Thailand. Foods, 12(3), 487.
Dhiman, P., Kukreja, V., & Kaur, A. (2021, September). Citrus Fruits Classification and Evaluation using Deep Convolution Neural Networks: An Input Layer Resizing Approach. In 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO) (pp. 1-4). IEEE.
Geng, Z., Xu, Y., Wang, B. N., Yu, X., Zhu, D. Y., & Zhang, G. (2023). Target Recognition in SAR Images by Deep Learning with Training Data Augmentation. Sensors, 23(2), 941.
Dhiman, P., Kaur, A., Hamid, Y., Alabdulkreem, E., Elmannai, H., & Ababneh, N. (2023). Smart Disease Detection System for Citrus Fruits Using Deep Learning with Edge Computing. Sustainability, 15(5), 4576.
Ghimire, D., & Kim, S. H. (2023). Magnitude and Similarity Based Variable Rate Filter Pruning for Efficient Convolution Neural Networks. Applied Sciences, 13(1), 316.
Dhiman, P., Poongodi, M., Lilhore, U. K., AlQahtani, S. A., Kaur, A., Iwendi, C., & Raahemifar, K. (2023). PFDI: A Precise Fruit disease Identification Model based on Context Data Fusion with Faster-CNN in Edge Computing Environment.
Alsubai, S., Dutta, A. K., Alkhayyat, A. H., Jaber, M. M., Abbas, A. H., & Kumar, A. (2023). Hybrid deep learning with improved Salp swarm optimization based multi-class grape disease classification model. Computers and Electrical Engineering, 108, 108733.
P. Seelwal and A. Sharma, "Machine Vision Systems for Rice Diseases Detection: A Review," 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), Greater Noida, India, 2022, pp. 1686-1689, doi: 10.1109/ICACITE53722.2022.9823713.
Prema, K. ., & J, V. . (2023). A Novel Marine Predators Optimization based Deep Neural Network for Quality and Shelf-Life Prediction of Shrimp. International Journal on Recent and Innovation Trends in Computing and Communication, 11(3s), 65–72. https://doi.org/10.17762/ijritcc.v11i3s.6156
Raj, R., & Sahoo, D. S. S. . (2021). Detection of Botnet Using Deep Learning Architecture Using Chrome 23 Pattern with IOT. Research Journal of Computer Systems and Engineering, 2(2), 38:44. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/31
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.