The Effect of Data Augmentation on the Accuracy of CNN Model Training for Fish Type Classification
Article Sidebar
Main Article Content
Abstract
Sustainability of marine resources and management of aquatic ecosystems depend on accurate fish classification. CNNs have proven successful in image classification tasks; however, they often face the problem of limited data variation. The purpose of this study was to examine how data augmentation affects the training accuracy of CNN models for fish species classification. Two scenarios were studied: the first scenario involved training without data augmentation, and the second scenario involved training with data augmentation. In both scenarios, a custom CNN architecture for ten epochs was used. Experimental results showed that using data augmentation with the configuration used actually caused the model performance to deteriorate. Loss values on both datasets increased, with training accuracy dropping from 76.08% to 63.81%, and validation accuracy also dropping from 91.13% to 84.55%. Overly aggressive augmentation parameters or insufficient training time for the introduced data variation could have caused this decline. Interestingly, validation accuracy was consistently higher than training accuracy in both situations, indicating that certain datasets have specific features. This study emphasizes the importance of carefully optimizing augmentation parameters and training duration to maximize the benefits of data augmentation in image classification.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
[2] N. Abdurrahman, B. Rahmat, and A. N. Sihananto, “Perbandingan Performa Klasifikasi Citra Ikan Menggunakan Metode K-Nearest Neighbor (K-NN) Dan Convolutional Neural Network (CNN),” J. Sist. Inf. dan Inform., vol. 2, no. 2, pp. 84–93, 2023, doi: 10.33379/jusifor.v2i2.3728.
[3] A. Azis, “Identifikasi Jenis Ikan Menggunakan Model Hybrid Deep Learning Dan Algoritma Klasifikasi,” Sebatik, vol. 24, no. 2, pp. 201–206, 2020, doi: 10.46984/sebatik.v24i2.1057.
[4] S. S. Asmoro, M. F. Amrulloh, M. A. Toybah, and M. A. Saputra, “Rancang Bangun Aplikasi Mobile Untuk Klasifikasi Jenis Ikan Koi Menggunakan Algoritma Convolutional Neural Network,” Semin. Nas. Teknol. Sains, vol. 3, no. 1, pp. 270–277, 2024, doi: 10.29407/stains.v3i1.4312.
[5] L. Vanneschi and M. Castelli, Multilayer perceptrons, vol. 1–3. 2018. doi: 10.1016/B978-0-12-809633-8.20339-7.
[6] M. Hashemi, “Enlarging smaller images before inputting into convolutional neural network: zero-padding vs. interpolation,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0263-7.
[7] A. Performance, E. Alshdaifat, D. Alshdaifat, A. Alsarhan, F. Hussein, and S. Moh, “The Effect of Preprocessing Techniques , Applied to Numeric,” Data, vol. 6, no. 11, 2021.
[8] M. F. Gunardi, “Implementasi Augmentasi Citra pada Suatu Dataset,” J. Inform., vol. 9, no. 1, pp. 1–5, 2023.
[9] S. Calderon-ramirez et al., “Correcting data imbalance for semi-supervised COVID-19 detection using X-ray chest images,” no. January, 2020.
[10] A. H. Khan, X. Cao, S. Li, V. N. Katsikis, and L. Liao, “BAS-ADAM: An ADAM based approach to improve the performance of beetle antennae search optimizer,” IEEE/CAA J. Autom. Sin., vol. 7, no. 2, pp. 461–471, 2020, doi: 10.1109/JAS.2020.1003048.
[11] Y. Shao et al., “An Improvement of Adam Based on a Cyclic Exponential Decay Learning Rate and Gradient Norm Constraints,” Electron., vol. 13, no. 9, 2024, doi: 10.3390/electronics13091778.
[12] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.
[13] L. Perez and J. Wang, “The Effectiveness of Data Augmentation in Image Classification using Deep Learning,” 2017, [Online]. Available: http://arxiv.org/abs/1712.04621
[14] M. Elgendi et al., “The Effectiveness of Image Augmentation in Deep Learning Networks for Detecting COVID-19: A Geometric Transformation Perspective,” Front. Med., vol. 8, no. March, pp. 1–12, 2021, doi: 10.3389/fmed.2021.629134
[15] Hidra Amnur, A. K. Vadreas, and M. Ridwan, “Aplikasi Pendeteksi Kematangan Tanaman Menggunakan Metode Transformasi Ruang Warna HSI (Hue, Saturation, Intensity) dan K-NN (K- Nearest Neighbor)”, jitsi, vol. 5, no. 4, pp. 161 -167, Dec. 2024.
[16] C. Lei, B. Hu, D. Wang, S. Zhang, and Z. Chen, “A preliminary study on data augmentation of deep learning for image classification,” ACM Int. Conf. Proceeding Ser., pp. 7–10, 2019, doi: 10.1145/3361242.3361259.