Comparative Analysis of Decision-Level Ensemble Voting Strategies for Tomato Leaf Disease Classification Using EfficientNet-B0 and MobileNetV2
DOI:
https://doi.org/10.15294/rji.v4i2.61961Keywords:
Tomato Leaf Disease, Decision-Level Voting, Ensemble Learning, EfficientNet-B0, MobileNetV2Abstract
Abstract. Tomato leaf diseases are a major threat to agricultural productivity, making accurate and timely disease classification essential for supporting precision agriculture. Recent advances in convolutional neural networks have significantly improved automated plant disease recognition, while ensemble learning has further enhanced classification performance by combining predictions from multiple models. Among various ensemble approaches, decision-level voting strategies, including hard voting, soft voting, and weighted soft voting, are widely adopted because of their simplicity and effectiveness. However, systematic comparisons of these voting strategies, particularly when combining lightweight CNN architectures for tomato leaf disease classification, remain limited. Therefore, this study investigates the comparative performance of different decision-level voting strategies to provide empirical evidence for selecting the most appropriate ensemble approach.
Purpose: This study aims to systematically compare hard voting, soft voting, and weighted soft voting for combining EfficientNet-B0 and MobileNetV2 to identify the most effective decision-level ensemble strategy for tomato leaf disease classification.
Methods/Study design/approach: EfficientNet-B0 and MobileNetV2 were trained independently and combined using hard voting with confidence-based tie breaking, soft voting, and weighted soft voting, with voting weights optimized through grid search. Performance was evaluated using accuracy, macro-F1 score, confusion matrices, and McNemar's test.
Result/Findings: EfficientNet-B0 outperformed MobileNetV2 as the best single model (94.05% accuracy, 0.9266 macro-F1 vs. 90.64% accuracy, 0.8781 macro-F1). All three ensemble strategies further improved classification performance, with weighted soft voting achieving the highest performance (95.15% accuracy, 0.9417 macro-F1). McNemar's test showed that only soft voting and weighted soft voting significantly outperformed the best single model, whereas hard voting did not. No statistically significant differences were observed among the three ensemble voting strategies.
Novelty: This study systematically compares hard voting, soft voting, and weighted soft voting for decision-level ensemble using EfficientNet-B0 and MobileNetV2 in tomato leaf disease classification. In addition to evaluating predictive performance, the study incorporates McNemar's statistical test to determine whether the observed performance differences among the ensemble strategies are statistically significant, providing empirical guidance for selecting appropriate voting strategies.
References
[1] I. N. Yulita, N. A. Amri, and A. Hidayat, “Mobile Application for Tomato Plant Leaf Disease Detection Using a Dense Convolutional Network Architecture,” Computation, vol. 11, no. 2, Feb. 2023, doi: 10.3390/computation11020020.
[2] D. Peng, W. Li, H. Zhao, G. Zhou, and C. Cai, “Recognition of Tomato Leaf Diseases Based on DIMPCNET,” Agronomy, vol. 13, no. 7, Jul. 2023, doi: 10.3390/agronomy13071812.
[3] M. Bouni, B. Hssina, K. Douzi, and S. Douzi, “Synergistic use of handcrafted and deep learning features for tomato leaf disease classification,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-71225-5.
[4] M. S. A. M. Al-gaashani, F. Shang, M. S. A. Muthanna, M. Khayyat, and A. A. Abd El-Latif, “Tomato leaf disease classification by exploiting transfer learning and feature concatenation,” IET Image Process., vol. 16, no. 3, pp. 913–925, Feb. 2022, doi: 10.1049/ipr2.12397.
[5] W. Shafik, A. Tufail, C. De Silva Liyanage, and R. A. A. H. M. Apong, “Using transfer learning-based plant disease classification and detection for sustainable agriculture,” BMC Plant Biol., vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12870-024-04825-y.
[6] J. Sharma et al., “Deep learning based ensemble model for accurate tomato leaf disease classification by leveraging ResNet50 and MobileNetV2 architectures,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-98015-x.
[7] N. Ullah et al., “A Lightweight Deep Learning-Based Model for Tomato Leaf Disease Classification,” Computers, Materials and Continua, vol. 77, no. 3, pp. 3969–3992, 2023, doi: 10.32604/cmc.2023.041819.
[8] H. Ulutaş and V. Aslantaş, “Design of Efficient Methods for the Detection of Tomato Leaf Disease Utilizing Proposed Ensemble CNN Model,” Electronics (Switzerland), vol. 12, no. 4, Feb. 2023, doi: 10.3390/electronics12040827.
[9] A. H. Ali, A. Youssef, M. Abdelal, and M. A. Raja, “An ensemble of deep learning architectures for accurate plant disease classification,” Ecol. Inform., vol. 81, Jul. 2024, doi: 10.1016/j.ecoinf.2024.102618.
[10] S. M. Javidan, A. Banakar, K. A. Vakilian, and Y. Ampatzidis, “Tomato leaf diseases classification using image processing and weighted ensemble learning,” Agron. J., vol. 116, no. 3, pp. 1029–1049, May 2024, doi: 10.1002/agj2.21293.
[11] S. M. Javidan, Y. Ampatzidis, A. Banakar, K. A. Vakilian, and K. Rahnama, “An Intelligent Group Learning Framework for Detecting Common Tomato Diseases Using Simple and Weighted Majority Voting with Deep Learning Models,” AgriEngineering, vol. 7, no. 2, Feb. 2025, doi: 10.3390/agriengineering7020031.
[12] H. Raval and J. Chaki, “Ensemble transfer learning meets explainable AI: A deep learning approach for leaf disease detection,” Ecol. Inform., vol. 84, Dec. 2024, doi: 10.1016/j.ecoinf.2024.102925.
[13] J. M. Johnson and T. M. Khoshgoftaar, “Survey on deep learning with class imbalance,” J. Big Data, vol. 6, no. 1, Dec. 2019, doi: 10.1186/s40537-019-0192-5.
[14] M. Buda, A. Maki, and M. A. Mazurowski, “A systematic study of the class imbalance problem in convolutional neural networks,” Neural Networks, vol. 106, pp. 249–259, Oct. 2018, doi: 10.1016/j.neunet.2018.07.011.
[15] M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” in International Conference on Machine Learning, 2019, pp. 6105–6114. Accessed: Jul. 11, 2026. [Online]. Available: https://proceedings.mlr.press/v97/tan19a.html
[16] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474.
[17] G. Geetharamani and A. P. J., “Identification of plant leaf diseases using a nine-layer deep convolutional neural network,” Computers and Electrical Engineering, vol. 76, pp. 323–338, Jun. 2019, doi: 10.1016/j.compeleceng.2019.04.011.
[18] J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Jun. 2009, pp. 248–255. doi: 10.1109/CVPR.2009.5206848.
[19] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Jan. 2017, [Online]. Available: http://arxiv.org/abs/1412.6980
[20] M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” May 2016, [Online]. Available: http://arxiv.org/abs/1605.08695
[21] M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, Jul. 2009, doi: 10.1016/j.ipm.2009.03.002.
