A Hybrid Transformer-Based Approach for Arecanut Disease Prediction

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 6

Year of Publication : 2025

Authors : Sangeetha Shibu, Jinu Raj R, Divya G S, Jincy Jesudasan

10.14445/23488549/IJECE-V12I6P128

How to Cite?

Sangeetha Shibu, Jinu Raj R, Divya G S, Jincy Jesudasan, "A Hybrid Transformer-Based Approach for Arecanut Disease Prediction," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 6, pp. 352-363, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I6P128

Abstract:

Crop development is affected by several variables, such as climatic conditions, soil quality, and diseases, which significantly affect yield and productivity. Arecanut, or betel nut, is a tropical crop susceptible to various diseases affecting different parts of the plant, from root to fruit. Accurate and timely disease recognition is essential for maintaining crop health and enhancing agricultural productivity. Conventional disease identification techniques depend on manual examination, which consumes time and is susceptible to inaccuracies. Existing models often face challenges in extracting long range dependencies and global feature interactions, limiting the classification accuracies. This study presented a hybrid deep learning (DL) framework combining ResNet-50 and Swin transformer for better disease identification. The ResNet-50 model extracts hierarchical spatial features, while the Swin Transformer with shifted window self-attention captures global dependencies, enhancing classification by emphasising specific disease patterns. The framework is trained and examined using a dataset of Arecanut disease sourced from Kaggle with 11,063 images across nine disease categories. Findings demonstrated that the suggested framework attains a classification accuracy of 98.42%, outperforming conventional methods. The study highlights the effectiveness of incorporating transformer-based attention mechanisms in agricultural disease detection.

Keywords:

Arecanut disease, Deep learning, Self-attention mechanism, ResNet-50, Swim transformer, Convolutional Neural Networks.

References:

[1] Shabari Shedthi Billadi et al., “Classification of Arecanut using Machine Learning Techniques,” International Journal of Electrical and Computer Engineering, vol. 13, no. 2, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Shuhan Lei et al., “Remote Sensing Detecting of Yellow Leaf Disease of Arecanut based on UAV Multisource Sensors,” Remote Sensing, vol. 13, no. 22, pp. 1-22, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] M.G. Anilkumar et al., “Detection of Diseases in Areca Nut using Convolutional Neural Networks,” International Research Journal of Engineering and Technology, vol. 8, no. 5, pp. 4282-4286, 2021.
[Google Scholar] [Publisher Link]
[4] Dhanush Ghate et al., “Enhancing Arecanut Quality Grading: A Comparison of Custom CNNs and Transfer Learning Models,” Researchsquare, pp. 1-27, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] M. Pavan et al., “Areca Nut Disease Detection using Deep Learning,” Journal of Computer Science, vol. 18, no. 1, pp. 1-7, 2025.
[Google Scholar] [Publisher Link]
[6] S. Anupama Kumar et al., “An Automated Deep Learning Model to Classify Diseases in Arecanut Plant,” Indian Journal of Computer Science and Engineering, vol. 15, no. 1, pp. 43-53, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Praveen M. Naik, and Bhawana Rudra, “Quantum‐Inspired Arecanut X‐Ray Image Classification using Transfer Learning,” IET Quantum Communication, vol. 5, no. 4, pp. 303-309, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Khairunnisa, and Ferdy Riza, “Android-Based Areca Plant Disease Detection Using Convolutional Neural Network (CNN) Algorithm,” Install: Computer Journal, vol. 16, no. 3, pp. 277-288, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Anitha Arekattedoddi Chikkalingaiah et al., “Segmentation and Yield Count of an Arecanut Bunch Using Deep Learning Techniques,” IAES International Journal of Artificial Intelligence, vol. 13, no. 1, pp. 542-553, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Rajashree Krishna, and K.V. Prema, “Constructing and Optimizing RNN Models to Predict Fruit Rot Disease Incidence in Areca Nut Crop based on Weather Parameters,” IEEE Access, vol. 11, pp. 110582-110595, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Sameer Patil, Aparajita Naik, and Jivan Parab, “Efficient Deep Learning Model for De-Husked Areca Nut Classification,” Applied and Natural Science, vol. 15, no. 4, pp. 1529-1540, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ajit Hegde et al., “Identification and Categorization of Diseases in Arecanut: A Machine Learning Approach,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 31, no. 3, pp. 1803-1810, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Praveen M. Naik, and Bhawana Rudra, “Classification of Arecanut X-Ray Images for Quality Assessment using Adaptive Genetic Algorithm and Deep Learning,” IEEE Access, vol. 11, pp. 127619-127636, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Namra Mahveen et al., “Enhancing Areca Nut Plant Wellness: Innovative Disease Detection using Deep Learning Algorithms,” 3rd Indian International Conference on Industrial Engineering and Operations Management, New Delhi, India, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] P. Pallavi, K. Sowmya Nag, and S.V. Veenadevi, Arecanut Disease Classification using CNN, Advances in Intelligent Systems and Technologies, pp. 19-24, 2023.
[CrossRef] [Publisher Link]
[16] Sameer Patil et al., “Optimizing Dehusked Arecanut Quality Segregation: CNN-based Approach with Contrast Enhancement and Data Augmentation,” International Symposium on Smart Cities, Challenges, Technologies and Trends, pp. 1-10, 2023.
[Google Scholar] [Publisher Link]
[17] Dong Xu et al., “Areca Yellow Leaf Disease Severity Monitoring using UAV-based Multispectral and Thermal Infrared Imagery,” Remote Sensing, vol. 15, no. 12, pp. 1-19, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Patil Balanagouda et al., “Timing of Oomycete-Specific Fungicide Application Impacts the Efficacy against Fruit Rot Disease in Arecanut,” Frontiers in Plant Science, vol. 14, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] T. Paviraj, Arecanut Dataset, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/tejpaviraj/arecanut/data
[20] Bishwas Mandal, Adaeze Okeukwu, and Yihong Theis, “Masked Face Recognition using ResNet-50,” arXiv, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 9992-10022, 2021.
[CrossRef] [Google Scholar] [Publisher Link]