Enhancing Weighted Averaging for CNN Model Ensemble in Plant Diseases Image Classification
Abstract
Deep learning, especially convolutional neural networks (CNN), has gained traction in the field of image classification. In the specific case of plant disease classification, improving the accuracy and reliability of image classification is paramount. This paper delves into the ensemble prediction technique using a weighted soft-voting method. Instead of assigning a generalized weight to each CNN model, our approach emphasizes giving weights to each label's prediction within every individual model. We employed three respected CNN architectures for our experiments: DenseNet201, InceptionV3, and Xception focus on classifying various diseases that affect grapes. By harnessing transfer learning coupled with end-to-end fine-tuning, we achieved a streamlined and efficient training process. In particular, the f1-score for each grape disease class was used as a parameter for weight determination and as a metric for the final evaluation. In our study, the newly proposed method was tested across various datasets and ensemble scenarios, demonstrating its effectiveness by not only outperforming the conventional soft-voting and prevalent weighted soft-voting methods, which achieved best scores of 95.68% and 95.81% respectively, but also by achieving a remarkable accuracy of 96.56%. The efficacy of this method is enhanced when the ensemble models exhibit distinct characteristics; the more varied the model characteristics, the more enhanced the ensemble results.
Downloads
References
L. Li, S. Zhang, and B. Wang, “Plant Disease Detection and Classification by Deep Learning—A Review,” IEEE Access, vol. 9, pp. 56683–56698, 2021, doi: 10.1109/ACCESS.2021.3069646.
I. Ul Haq and S. Ijaz, “History and Recent Trends in Plant Disease Control: An Overview,” 2020, pp. 1–13. doi: 10.1007/978-3-030-35955-3_1.
Charu C. Aggarwal, Neural Networks and Deep Learning: A Textbook, 2nd editon. Cham, Switzerland: Springer International Publishing, 2023.
M. Albahar, “A Survey on Deep Learning and Its Impact on Agriculture: Challenges and Opportunities,” Agriculture, vol. 13, no. 3, p. 540, Feb. 2023, doi: 10.3390/agriculture13030540.
X. Zhang, Y. Qiao, F. Meng, C. Fan, and M. Zhang, “Identification of Maize Leaf Diseases Using Improved Deep Convolutional Neural Networks,” IEEE Access, vol. 6, pp. 30370–30377, 2018, doi: 10.1109/ACCESS.2018.2844405.
U. P. Singh, S. S. Chouhan, S. Jain, and S. Jain, “Multilayer Convolution Neural Network for the Classification of Mango Leaves Infected by Anthracnose Disease,” IEEE Access, vol. 7, pp. 43721–43729, 2019, doi: 10.1109/ACCESS.2019.2907383.
S. Ghosal and K. Sarkar, “Rice Leaf Diseases Classification Using CNN With Transfer Learning,” in 2020 IEEE Calcutta Conference (CALCON), IEEE, Feb. 2020, pp. 230–236. doi: 10.1109/CALCON49167.2020.9106423.
S. Van Ho, H. G. Vuong, B. Q. Nguyen, Q.-H. Trinh, and M.-T. Tran, “Ensemble of Deep Neural Networks for Rice Leaf Disease Classification,” in 2022 RIVF International Conference on Computing and Communication Technologies (RIVF), IEEE, Dec. 2022, pp. 238–243. doi: 10.1109/RIVF55975.2022.10013858.
S. Yuvalatha, J. Keerthika, S. Prabhavathy, M. Banupriya, and R. Priyadharshini, “Automated Plant Leaf Classification using Ensemble Transfer Learning in CNN model,” in 2022 IEEE North Karnataka Subsection Flagship International Conference (NKCon), IEEE, Nov. 2022, pp. 1–5. doi: 10.1109/NKCon56289.2022.10126722.
S. Chaudhary and Y. Qiang, “Ensemble deep learning method for Covid-19 detection via chest X-rays,” in 2021 Ethics and Explainability for Responsible Data Science (EE-RDS), IEEE, Oct. 2021, pp. 1–3. doi: 10.1109/EE-RDS53766.2021.9708581.
M. Patel, A. Das, V. K. Pant, and J. M, “Detection of Tuberculosis in Radiographs using Deep Learning-based Ensemble Methods,” in 2021 Smart Technologies, Communication and Robotics (STCR), IEEE, Oct. 2021, pp. 1–7. doi: 10.1109/STCR51658.2021.9588936.
F. A. Noor, I. Munzerin, A. M. A. Iqbal, T. Islam, and E. Hossain, “An ensemble learning based approach to autonomous COVID19 detection using transfer learning with the help of pre-trained Deep Neural Network models,” in 2021 24th International Conference on Computer and Information Technology (ICCIT), IEEE, Dec. 2021, pp. 1–6. doi: 10.1109/ICCIT54785.2021.9689825.
S. Cyriac, N. Raju, and Y.-W. Kim, “Pneumonia Detection using Ensemble Transfer Learning,” in 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), IEEE, Oct. 2022, pp. 479–484. doi: 10.1109/ICTC55196.2022.9952532.
H. Zhao, Q. Liu, and Y. Yang, “Transfer Learning with Ensemble of Multiple Feature Representations,” in 2018 IEEE 16th International Conference on Software Engineering Research, Management and Applications (SERA), IEEE, Jun. 2018, pp. 54–61. doi: 10.1109/SERA.2018.8477189.
A. Acharya, A. Muvvala, S. Gawali, R. Dhopavkar, R. Kadam, and A. Harsola, “Plant Disease detection for paddy crop using Ensemble of CNNs,” in 2020 IEEE International Conference for Innovation in Technology (INOCON), IEEE, Nov. 2020, pp. 1–6. doi: 10.1109/INOCON50539.2020.9298295.
V. C. Osamor and A. F. Okezie, “Enhancing the weighted voting ensemble algorithm for tuberculosis predictive diagnosis,” Sci Rep, vol. 11, no. 1, p. 14806, Jul. 2021, doi: 10.1038/s41598-021-94347-6.
Md. S. H. Talukder and A. K. Sarkar, “Nutrients deficiency diagnosis of rice crop by weighted average ensemble learning,” Smart Agricultural Technology, vol. 4, p. 100155, Aug. 2023, doi: 10.1016/j.atech.2022.100155.
S. Misra, D. Kim, J. Kim, W. Shin, and C. Kim, “A voting-based ensemble feature network for semiconductor wafer defect classification,” Sci Rep, vol. 12, no. 1, p. 16254, Sep. 2022, doi: 10.1038/s41598-022-20630-9.
K. Chauhan, Kashish, K. Dagar, and R. K. Yadav, “Cataract detection from eye fundus image using an ensemble of transfer learning models,” in 2022 2nd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE), IEEE, Apr. 2022, pp. 2194–2198. doi: 10.1109/ICACITE53722.2022.9823638.
V. C. Osamor and A. F. Okezie, “Enhancing the weighted voting ensemble algorithm for tuberculosis predictive diagnosis,” Sci Rep, vol. 11, no. 1, p. 14806, Jul. 2021, doi: 10.1038/s41598-021-94347-6.
H. K. Kondaveeti, K. G. Ujini, B. V. V. Pavankumar, B. S. Tarun, and S. C. Gopi, “Plant Disease Detection Using Ensemble Learning,” in 2023 2nd International Conference on Computational Systems and Communication (ICCSC), IEEE, Mar. 2023, pp. 1–6. doi: 10.1109/ICCSC56913.2023.10142982.
H. Wang, Y. Yang, H. Wang, and D. Chen, “Soft-Voting Clustering Ensemble,” 2013, pp. 307–318. doi: 10.1007/978-3-642-38067-9_27.
Z.-H. Zhou, Ensemble Methods: Foundations and Algorithms, 1st ed. Chapman & Hall/CRC, 2012.
E. Ayan, H. Erbay, and F. Varçın, “Crop pest classification with a genetic algorithm-based weighted ensemble of deep convolutional neural networks,” Comput Electron Agric, vol. 179, p. 105809, Dec. 2020, doi: 10.1016/j.compag.2020.105809.
A. M．P． and P. Reddy, “Ensemble of CNN models for classification of groundnut plant leaf disease detection,” Smart Agricultural Technology, vol. 6, p. 100362, Dec. 2023, doi: 10.1016/j.atech.2023.100362.
A. Ghosh, A. Sufian, F. Sultana, A. Chakrabarti, and D. De, “Fundamental Concepts of Convolutional Neural Network,” 2020, pp. 519–567. doi: 10.1007/978-3-030-32644-9_36.
S.-H. Wang and Y.-D. Zhang, “DenseNet-201-Based Deep Neural Network with Composite Learning Factor and Precomputation for Multiple Sclerosis Classification,” ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 16, no. 2s, pp. 1–19, Apr. 2020, doi: 10.1145/3341095.
M. K. Bohmrah and H. Kaur, “Classification of Covid-19 patients using efficient fine-tuned deep learning DenseNet model,” Global Transitions Proceedings, vol. 2, no. 2, pp. 476–483, Nov. 2021, doi: 10.1016/j.gltp.2021.08.003.
A. Shabani, L. Dhamo, and O. Zavalani, “Modelling Building Energy Systems using Electric Circuit Analogy,” European Journal of Electrical Engineering and Computer Science, vol. 7, no. 1, pp. 56–61, Jan. 2023, doi: 10.24018/ejece.2023.7.1.491.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the Inception Architecture for Computer Vision,” Dec. 2015.
C. Wang et al., “Pulmonary Image Classification Based on Inception-v3 Transfer Learning Model,” IEEE Access, vol. 7, pp. 146533–146541, 2019, doi: 10.1109/ACCESS.2019.2946000.
Y. Qian et al., “Fresh Tea Leaves Classification Using Inception-V3,” in 2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP), IEEE, Sep. 2019, pp. 415–419. doi: 10.1109/ICICSP48821.2019.8958529.
F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions,” Oct. 2016.
N. An, “Xception Network for Weather Image Recognition Based on Transfer Learning,” in 2022 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE), IEEE, Aug. 2022, pp. 330–333. doi: 10.1109/MLISE57402.2022.00072.
V. Menon, V. Ashwin, and R. K. Deepa, “Plant Disease Detection using CNN and Transfer Learning,” in 2021 International Conference on Communication, Control and Information Sciences (ICCISc), IEEE, Jun. 2021, pp. 1–6. doi: 10.1109/ICCISc52257.2021.9484957.
D. P. Hughes and M. Salathé, “An open access repository of images on plant health to enable the development of mobile disease diagnostics through machine learning and crowdsourcing,” CoRR, vol. abs/1511.08060, 2015, [Online]. Available: http://arxiv.org/abs/1511.08060
G. G. and A. P. J., “Identification of plant leaf diseases using a nine-layer deep convolutional neural network,” Computers & Electrical Engineering, vol. 76, pp. 323–338, Jun. 2019, doi: 10.1016/j.compeleceng.2019.04.011.
M. Khan, “Healthy and Disease affected Leaves of Grape Plant,” Jan. 2020, doi: 10.6084/m9.figshare.13083890.v1.
Copyright (c) 2024 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
