Citation :

Payal, Munishwar Rai, "Swin-BNN-RF: Hierarchical Attention-Based Probabilistic Framework for Mustard Leaf Disease Detection Using Swin Transformer Bayesian Neural Networks and Ensemble Learning," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 7, pp. 55-68, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I7P105

Abstract

Brassica juncea (Mustard) is one of the most economic seed vegetable crops of the world, playing a major role in the production of world edible oil and the agricultural economy. The third-largest producer is India, which had an area under cultivation of about 8.6 million hectares of Mustard in 2021 22, and annual revenue of over USD 5 billion in 2021 22. Nevertheless, the presence of diseases like Alternaria Leaf Spot, White Rust, Powdery Mildew, and Septoria Leaf Spot threatens yield and quality by up to an estimated 2070% loss every year, based on the severity of the disease, and thus economic losses are estimated at over USD 1.5 billion per year in India alone. Traditional diagnostic systems are based on a manual examination of an agronomist trained to look at the sample and make a judgment, which is time-consuming, subjective, and subject to human error. Current deep learning methods of automated disease detection, promising as they are, are prone to inaccuracies on complex disease patterns, poor uncertainty estimation that is essential in real-world implementation, and poor generalizability to different field conditions. In response to these drawbacks, Swin-BNN-RF, a hybrid framework that combines Swin Transformer as a hierarchical attention-based feature extractor, Bayesian Neural Network (BNN) with symmetrized posterior as a probabilistic learner, and a Random Forest (RF) as an ensemble classifier, is proposed in this study. The Swin Transformer also harnesses local and global spatial biases with its shifted window self-attention network, and it is able to extract better features on leaf images of high-resolution. The uncertainty estimates of the BNN component are trusted, and unambiguous predictions are highlighted to get the opinion of the human expert. Random Forest classifier uses the bagging and boosting ensemble methods to improve stability and the robustness of the classification. A large dataset was experimented with; it consisted of more than 10,000 samples per category of disease in four diseases. In the case of binary classification, the proposed model was 98.32% accurate, 98.52% precise, 98.70% recall, and 98.36% F1. On multi-class classification, it obtained 97.50, 97.82, 98.51, and 97.46 accuracy, precision, recall, and F1 score, respectively, which showed consistent performance in comparison with state-of-the-art models such as EfficientNet, MobileNet, and Residual Networks. The contribution of each component is verified by the Ablation studies and statistical analysis of significance (p < 0.001). The suggested framework is a major achievement of scaling up real-time disease diagnosis in mustard crops, with possibilities of mobile and edge implementation in precision agriculture systems.

Keywords

Mustard leaf disease, Swin Transformer, Bayesian Neural Network, Random Forest, Ensemble Learning, Deep Learning, Precision Agriculture, Uncertainty Estimation.

References

[1] ADDA247 Current Affairs, Largest Mustard Producing Indian State, 2024. [Online]. Available: https://currentaffairs.adda247.com/largest-mustard-producing-indian-state/

[2] Agricultural Marketing Resource Center, Mustard, AG MRC, 2025. [Online]. Available: https://www.agmrc.org/commodities-products/grains-oilseeds/mustard

[3] V. Chapara, A. Chirumamilla, and R. Chapara, Mustard, Viral Diseases of Field and Horticultural Crops, Academic Press, pp. 157-161, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Honglong Chu et al., “First Report of Pectobacterium Aroidearum Causing Soft Rot on Leaf Mustard in China,” Plant Disease, vol. 108, no. 2, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Rashidul Hasan Hridoy, Arindra Dey Arni, and Md Ariful Hassan, “Recognition of Mustard Plant Diseases based on Improved Deep Convolutional Neural Networks,” 2022 IEEE Region 10 Symposium (TENSYMP), Mumbai, India, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Amanpreet Singh Sran et al., White Rust of Indian Mustard Caused by Albugo Candida: Current Status, Symptomatology and Management Strategies, The PLANTA Research Book Series, vol. 5, no. 2, pp. 1667-1674, 2024.
[Google Scholar]

[7] Karunesh K. Shukla et al., “Detection of Alternaria Blight Disease Severity in Mustard Crops using Ground-based Hyperspectral Remote Sensing,” Current Science, vol. 125, no. 10, pp. 1099-1108, 2023.
[CrossRef] [Google Scholar]

[8] Plant Village, Mustard, Plant Village. [Online]. Available: https://plantvillage.psu.edu/topics/mustard/infos

[9] Government of India, Mustard: Diseases and Symptoms, Government of India, 2019. [Online]. Available: https://agriculture.vikaspedia.in/

[10] M.K. Dharani et al., “Leaf Disease Detection using Deep Learning Models,” 2022 2^nd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, pp. 646-650, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Akshit Sood et al., “AI-Driven Mustard Disease Identification: A Multiclass and Binary Classification Approach for Advanced Crop Health Monitoring,” 2023 3^rd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan, pp. 256-261, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Mustafa Guzel et al., “How to Affect the Number of Images on the Success Rate for Detection of Weeds with Deep Learning,” Turkish Journal of Agriculture-Food Science and Technology, vol. 10, no. 8, pp. 1441-1446, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Hana Dibekulu Tafese et al., “Detection and Classification of Ethiopian Kale Leaf Disease using Deep Learning,” 2024 International Conference on Information and Communication Technology for Development for Africa (ICT4DA), Bahir Dar, Ethiopia, pp. 19-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Prashant Kumar Mishra, Jagrati Singh, and Prateek Raj Gautam, Mustard and Wheat Mildew Disease Classification using Deep Learning, 1^st ed., CRC Press, 2024.
[Google Scholar] [Publisher Link]

[15] Sakshi et al., “Green Intelligence: A Sequential CNN Odyssey in Mustard Leaf Disease Detection,” 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), Manama, Bahrain, pp. 877-882, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Raghav Jain et al., “Hybrid CNN-RNN Modelling for Precisely Classifying the Seriousness of Mustard White Rust Disease at Five Levels,” 2024 5^th International Conference for Emerging Technology (INCET), Belgaum, India, pp. 1-5, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Saumitra Chattopadhyay et al., “Leveraging Deep Learning's Potential: A CNN and LSTM Network-based Severity Classification of Mustard Downy Mildew,” 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), Greater Noida, India, pp. 791-795, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Vinay Kukreja, Rishabh Sharma, and Satvik Vats, “Early Detection and Prevention of Mustard Downy Mildew Disease using a Hybrid CNN-LSTM Model,” 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), Jalandhar, India, pp. 246-251, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Arshleen Kaur et al., “Mitigating Mustard Downy Mildew Disease: Early Detection and Prevention through a Hybrid CNN-SVM Model,” 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI), Gwalior, India, pp. 1-4, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20]  Alok Sahu et al., “A Novel Deep Learning Framework for Mustard Crop Disease Identification using Leaf Images,” National Academy Science Letters, pp. 1-4, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[21] MD Tausif Mallick et al., “Mustard and Mung Bean Diseases and Pest Detection and Classification using Deep Learning Techniques,” International Conference on Systems and Technologies for Smart Agriculture: ICSTA, Springer, Singapore, pp. 363-382, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[22] MD Tausif Mallick et al., “Deep Learning based Automated Disease Detection and Pest Classification in Indian Mung Bean,” Multimedia Tools and Applications, vol. 82, no. 8, pp. 12017-12041, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Sharada P. Mohanty, David P. Hughes, and Marcel Salathé, “Using Deep Learning for Image-based Plant Disease Detection,” Frontiers in Plant Science, vol. 7, pp. 1-10, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Konstantinos P. Ferentinos, “Deep Learning Models for Plant Disease Detection and Diagnosis,” Computers and Electronics in Agriculture, vol. 145, pp. 311-318, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[25] S.K. Mahmudul Hassan et al., “Identification of Plant-Leaf Diseases using CNN and Transfer-Learning Approach,” Electronics, vol. 10, no. 12, pp. 1-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Antonio Guerrero-Ibañez, and Angelica Reyes-Muñoz, “Monitoring Tomato Leaf Disease through Convolutional Neural Networks,” Electronics, vol. 12, no. 1, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Rakhee Sharma et al., “Detection of Plant Leaf Disease using Advanced Deep Learning Architectures,” International Journal of Information Technology, vol. 16, no. 6, pp. 3475-3492, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Lili Li, Shujuan Zhang, and Bin Wang, “Plant Disease Detection and Classification by Deep Learning -A Review,” IEEE Access, vol. 9, pp. 56683-56698, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[29] Habiba N. Ngugi et al., “Revolutionizing Crop Disease Detection with Computational Deep Learning: A Comprehensive Review,” Environmental Monitoring and Assessment, vol. 196, no. 3, pp. 1-35, 2024.
[CrossRef] [Google Scholar] [Publisher Link]