Penerapan Model EfficientNetV2-B0 pada Benchmark IP102 Dataset untuk Menyelesaikan Masalah Klasifikasi Hama Serangga
Abstract
Hama serangga merupakan masalah yang sering di hadapi oleh petani. Karena ukurannya yang kecil dan jenis spesiesnya banyak. tak jarang petanipun kesulitan untuk menjaga tanaman mereka dari ancaman hama serangga karena penanganannya tidak memakai satu obat, melainkan dengan mencocokan spesies serangga. Sehingga karena banyaknya obat pembasmi, petanipun bingung obat mana yang tepat. Di dalam penelitian ini, telah di coba penggunaan metode deep learning arsitektur model EfficientNetV2 B0 pada dataset IP102 yang berkarakteristik imbalance dan ada jenis serangga yang identik antara satu dengan yang lain. Penelitian ini bertujuan untuk mengeksplorasi kemungkinan model kecil yang dapat di
implementasikan di smartphone atau IOT yang mudah di bawa ke ladang pertanian tanpa tergantung pada internet. Model terbaik yang berhasil dibuat memperoleh akurasi 51% dengan F1-Score 50.14%
References
“FAO - News Article: Climate change fans spread of pests and threatens plants and crops, new FAO study.” https://www.fao.org/news/story/en/item/1402920/icode (accessed Dec. 04, 2022).
X. Wu, C. Zhan, Y.-K. Lai, M.-M. Cheng, and J. Yang, “IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognition.” pp. 8787–8796, 2019. Accessed: Dec. 04, 2022. [Online]. Available: https://github.com/
G. Mittal, C. Liu, N. Karianakis, V. Fragoso, M. Chen, and Y. Fu, “HyperSTAR: Task-Aware Hyperparameters for Deep Networks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 8733–8742, May 2020, doi: 10.48550/arxiv.2005.10524.
L. Xu and Y. Wang, “XCloud: Design and Implementation of AI Cloud Platform with RESTful API Service,” Dec. 2019, doi: 10.48550/arxiv.1912.10344.
F. Ren, W. Liu, and G. Wu, “Feature reuse residual networks for insect pest recognition,” IEEE Access, vol. 7, pp. 122758–122768, 2019, doi: 10.1109/ACCESS.2019.2938194.
L. Nanni, G. Maguolo, and F. Pancino, “Insect pest image detection and recognition based on bio- inspired methods,” Ecol Inform, vol. 57, p. 101089, May 2020, doi: 10.1016/J.ECOINF.2020.101089.
E. Bollis, H. Pedrini, and S. Avila, “Weakly Supervised Learning Guided by Activation Mapping Applied to a Novel Citrus Pest Benchmark,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2020-June, pp. 310–319, Apr. 2020, doi: 10.48550/arxiv.2004.11252.
E. Bollis, H. Maia, H. Pedrini, and S. Avila, “Weakly supervised attention-based models using activation maps for citrus mite and insect pest classification,” Comput Electron Agric, vol. 195, p. 106839, Apr. 2022, doi: 10.1016/J.COMPAG.2022.106839.
L. Nanni, A. Manfè, G. Maguolo, A. Lumini, and S. Brahnam, “High performing ensemble of convolutional neural networks for insect pest image detection,” Ecol Inform, vol. 67, p. 101515, Mar. 2022, doi: 10.1016/J.ECOINF.2021.101515.
J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” pp. 248–255, Mar. 2010, doi: 10.1109/CVPR.2009.5206848.
L. Perez and J. Wang, “The Effectiveness of Data Augmentation in Image Classification using Deep Learning,” Dec. 2017, doi: 10.48550/arxiv.1712.04621.
C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data, vol. 6, no. 1, pp. 1–48, Dec. 2019, doi: 10.1186/S40537-019-0197-0/FIGURES/33.
M. Tan and Q. v. Le, “EfficientNetV2: Smaller Models and Faster Training,” Apr. 2021, doi: 10.48550/arxiv.2104.00298.
M. Tan and Q. v. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” 36th International Conference on Machine Learning, ICML 2019, vol. 2019-June, pp. 10691–10700, May 2019, doi: 10.48550/arxiv.1905.11946.
J. Jin, A. Dundar, and E. Culurciello, “Flattened Convolutional Neural Networks for Feedforward Acceleration,” 3rd International Conference on Learning Representations, ICLR 2015 - Workshop Track Proceedings, Dec. 2014, doi: 10.48550/arxiv.1412.5474.
H. Gholamalinezhad and H. Khosravi, “Pooling Methods in Deep Neural Networks, a Review,” Sep. 2020, doi: 10.48550/arxiv.2009.07485.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 56, pp. 1929–1958, 2014, Accessed: Dec. 09, 2022. [Online]. Available: http://jmlr.org/papers/v15/srivastava14a.html
S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift,” 32nd International Conference on Machine Learning, ICML 2015, vol. 1, pp. 448–456, Feb. 2015, doi: 10.48550/arxiv.1502.03167.
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely Connected Convolutional Networks,” Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 2261–2269, Aug. 2016, doi: 10.48550/arxiv.1608.06993.
D. P. Kingma and J. L. Ba, “Adam: A Method for Stochastic Optimization,” 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, Dec. 2014, doi: 10.48550/arxiv.1412.6980.
M. Feurer and F. Hutter, “Hyperparameter Optimization,” pp. 3–33, 2019, doi: 10.1007/978-3- 030-05318-5_1.
M. v. Valueva, N. N. Nagornov, P. A. Lyakhov, G. v. Valuev, and N. I. Chervyakov, “Application of the residue number system to reduce hardware costs of the convolutional neural network implementation,” Math Comput Simul, vol. 177, pp. 232–243, Nov. 2020, doi: 10.1016/J.MATCOM.2020.04.031.
K. Itoh, W. Zhang, Y. Ichioka, and J. Tanida, “Parallel distributed processing model with local space-invariant interconnections and its optical architecture,” Applied Optics, Vol. 29, Issue 32, pp. 4790-4797, vol. 29, no. 32, pp. 4790–4797, Nov. 1990, doi: 10.1364/AO.29.004790
Copyright (c) 2023 Jurnal Repositor
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All material contained in this journal is protected by law. It is prohibited to quote part or all of the contents of this journal for commercial purposes without the approval of the editorial board of the Repositor Journal. If you find one or more articles contained in the Repositor Journal that violate or have the potential to violate your copyright, please report it to us via email at repositor@umm.ac.id. The formal legal aspect of access to any information and articles contained in this journal refers to the terms of the Creative Commons Attribution 4.0 license. All information contained in the Repositor Journal is academic in nature. Repositor Journal is not responsible for losses that occur due to misuse of information from this journal.
