Cassava Diseases Classification using EfficientNet Model with Imbalance Data Handling

Authors

  • Stephany Octaviani Ngesthi Department of Computer Science, Binus University Jakarta, Indonesia
  • Lili Ayu Wulandhari Department of Computer Science, Binus University Jakarta, Indonesia

DOI:

https://doi.org/10.15575/join.v9i2.1300

Keywords:

Basic augmentation, Cassava diseases classification, EfficientNet, Imbalance data handling, Neural style transfer, SMOTE

Abstract

This research highlights the urgent need for classifying cassava diseases into five classes, such as Cassava Bacterial Blight (CBB), Cassava Brown Streak Disease (CBSD), Cassava Green Mottle (CGM), and Cassava Mosaic Disease (CMD), and Healthy. The study proposes the utilization of the EfficientNet model, a lightweight deep learning architecture, for classifying cassava diseases based on leaf images. However, the datasets available for this classification task are all unbalanced, made it difficult for researchers to perform. To tackle this imbalance issue, the authors compared several imbalance data handling methods commonly used for image classification, including SMOTE (Synthetic Minority Oversampling Technique), basic augmentation, and neural style transfer, to be applied before fed into EfficientNet. Initially, EfficientNet model without addressing dataset imbalances, the F1-Score stands at 78%, with most images misclassified into the majority class. Integration with SMOTE notably boosts the F1-Score to 82%, showcasing the efficacy of oversampling methods in enhancing model performance. Conversely, employing data augmentation, both basic and deep learning-based, lowers the F1-Score to 74% and 65% respectively, yet it results in a more balanced distribution of true positives across disease classes. The findings suggest that SMOTE surpasses the other methods in handling imbalanced data.

References

[1] Okwuonu et al., “Opportunities and challenges for biofortification of cassava to address iron and zinc deficiency in Nigeria,” Global Food Security, vol.28, 2021

[2] C. Fauquet, “Cassava Stories CMD Outbreak in Mainland SEA,” Global Cassava Partnership 21. [Online]. Available: https:// gcp21.org/. [Accessed: 25-Sep-2023].

[3] E. Mwebaze, T. Gebru, A. Frome, S. Nsumba, J. Tusubira, “iCassava 2019Fine-Grained Visual Categorization Challenge,” arXiv preprint arXiv:1908.02900, 2019.

[4] Makerere University AI Lab, “Cassava Leaf Disease Classification”, Kaggle. [Online]. Available: https://www.kaggle.com /competitions/cassava-disease/data/. [Accessed: 25-Sep-2023].

[5] H. Ayu, A. Surtono, D. Apriyanto, “Deep learning for detection cassava leaf disease”. Journal of Physics: Conference Series, vol. 1751, 2021.

[6] I. Sangbumrung, P. Praneetpholkrang, S. Kanjanawattana, “A Novel Automatic Method for Cassava Disease Classification Using Deep Learning. Journal of Advances in Information Technology,” Journal of Advances in Information Technology, vol. 11, no. 4, pp. 241–248, 2020.

[7] A. Maryum et al., “Cassava Leaf Disease Classification using Deep Neural Networks,” in IEEE 18th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET), 2021, pp. 32–37.

[8] Y. Zhong, B. Huang, C. Tang, “Classification of Cassava Leaf Disease Based on a Non-Balanced Dataset Using Transformer-Embedded ResNet,” Agriculture, vol. 12, no. 9, p. 1260, Sep. 2022.

[9] M. Liu, H. Liang, M. Hou, “Research on cassava disease classification using the multi-scale fusion model based on EfficientNet and attention mechanism,” Journal of Frontiers in Plant Science, vol. 13, Dec. 2022.

[10] J. N. Nabende et al., “Improving In-field Cassava Whitefly Pest Surveillance with Machine Learning,” Journal of Frontiers in Plant Science, vol. 41, Feb. 2022.

[11] F. Gao, J. Sa, Z. Wang, Z. Zhao, “Cassava disease detection method based on EfficientNet,” in 2021 7th International Conference on Systems and Informatics (ICSAI), Chongqing, China, 2021, pp. 1–6.

[12] S. Aravind, S. Harini, Varun kumar K A, “Cassava leaf disease classification using Deep Learning,” Natural Volatiles and Essential Oils (NVEO) Journal, vol. 8, no. 5, pp. 9375–9389, 2021.

[13] H. Shahriar, P.S. Shuvo, Md.S.H. Fahim, Md.S. Sordar, Md.E. Haque, “Cassava leaf disease classification using deep learning and convolutional neural network ensemble,” Brac University, Bangladesh, 2022.

[14] G. Sambasivam, G. D. Opiyo, “A predictive machine learning application in agriculture: Cassava disease detection and classification with imbalanced dataset using convolutional neural networks,” Egyptian Informatics Journal, vol. 22, no. 1, pp. 27–34, 2021.

[15] U.K. Lilhore et al., “Enhanced Convolutional Neural Network Model for Cassava Leaf Disease Identification and Classification,” Mathematics, MDPI, vol. 10, no. 4, pp. 1–19, Feb. 2022.

[16] N. Chawla, K. Bowyer, L. Hall, W. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique”. Journal of Artificial. Intelligence Research (JAIR), vol. 16, no. 1, pp.321-357, 2022.

[17] Shorten, Connor and Taghi M. Khoshgoftaar. “A survey on Image Data Augmentation for Deep Learning.” Journal of Big Data 6 (2019): 1-48.

[18] Q. Cai et al, " Image neural style transfer: A review", Journal of Computers and Electrical Engineering (2023), vol. 10.

[19] L. Perez & J. Wang, “The Effectiveness of Data Augmentation in Image Classification using Deep Learning.” ArXiv abs/1712.04621 (2017).

[20] X. Zheng et al., “Stada: Style transfer as data augmentation”, arXiv preprint arXiv:1909.01056 (2019).

[21] Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., & Shlens, J. (2017). Exploring the structure of a real-time, arbitrary neural artistic stylization network. ArXiv, abs/1705.06830.

[22] Papers with Code. [Online] Available: https://paperswithcode.com/datasets?task=style-transfer/. [Accessed: 23-Jan-2024]

[23] M. Tan, Q.V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks”, in 36th International Conference on Machine Learning (ICML) 2019, Long Beach, 9-15 June 2019, pp. 6105-6114.

[24] J. Lederer, “Activation functions in artificial neural networks: A systematic overview”. arXiv preprint arXiv:2101.09957 (2021).

Downloads

Published

2024-08-24

Issue

Section

Article

Citation Check