Abstrak
This study aims to compare the performance of two Convolutional Neural Network (CNN) architectures, EfficientNetB0 and EfficientNetV2-S, in classifying guava (Psidium guajava L.) conditions based on digital images. The dataset consists of three classes: anthracnose, fruit fly infestation, and healthy fruits. Class imbalance was addressed using an undersampling technique, while both models were developed using a transfer learning approach with ImageNet pre-trained weights and trained for 30 epochs. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results showed that EfficientNetB0 achieved a validation accuracy of 99.49% with a loss of 0.0124, whereas EfficientNetV2-S achieved a validation accuracy of 94.17% with a loss of 0.2153. The classification report further showed that EfficientNetB0 achieved F1-scores ranging from 0.99 to 1.00 across the three classes, while EfficientNetV2-S achieved F1-scores ranging from 0.92 to 0.96. Based on these results, EfficientNetB0 demonstrated higher classification performance than EfficientNetV2-S on the dataset and training configuration used in this study.
Referensi
Amin, M. Al, Mahmud, M. I., Rahman, A. Bin, Parvin, M. A., & Mamun, M. A. Al. (2024). Guava fruit disease dataset [Data set]. Mendeley Data. https://data.mendeley.com/datasets/bkdkc4n835
Apriliansyah, R., Handayanto, A., & Saputro, N. D. (2025). Penerapan arsitektur EfficientNetB0 pada model convolutional neural network untuk deteksi dini mata katarak. Journal of Computer Engineering, System and Science, 10(2), 435–446. https://doi.org/10.24114/cess.v10i2.66913
Hanik, N. R., Hidayati, S. N., Fitriani, R. D. A., Cahyanti, F. A., Oktavianingtyas, D., & Wahyuni, T. (2023). Identification of pests and diseases crystal guava (Psidium guajava L.) in Ngargoyoso District, Karanganyar Regency. Jurnal Biologi Tropis, 23(3), 127–135. https://doi.org/10.29303/jbt.v23i3.5021
Hasibuan, R., Taufik, I., Al Idrus, S. I., & Indra, Z. (2025). Implementasi convolutional neural network dalam mendeteksi tingkat kematangan buah kakao. JATI (Jurnal Mahasiswa Teknik Informatika), 9(4), 6479–6487. https://doi.org/10.36040/jati.v9i4.14116
Huang, Z., Jiang, X., Huang, S., Qin, S., & Yang, S. (2023). An efficient convolutional neural network-based diagnosis system for citrus fruit diseases. Frontiers in Genetics, 14, Article 1253934. https://doi.org/10.3389/fgene.2023.1253934
Maylianti, N. P., Wijayakusuma, I. G. N. L., & Wiguna, I. P. C. A. (2025). Comparison of EfficientNet-B0 and ResNet-50 for detecting diseases in cocoa fruit. Journal of Applied Informatics and Computing, 9(1), 115–120. https://doi.org/10.30871/jaic.v9i1.8868
Pitaloka, D. (2020). Hortikultura: Potensi, pengembangan dan tantangan. Jurnal Teknologi Terapan: G-Tech, 1(1), 1–4. https://doi.org/10.33379/gtech.v1i1.260
Raihan, J., Mahmud, Z., Ridita, S. A., & Bhattacharya, A. (2023). PhytoCare: A hybrid approach for identifying rice, potato and corn diseases [Bachelor's thesis, University of Liberal Arts Bangladesh].
Raup, A., Ridwan, W., Khoeriyah, Y., Supiana, S., & Zaqiah, Q. Y. (2022). Deep learning dan penerapannya dalam pembelajaran. JIIP - Jurnal Ilmiah Ilmu Pendidikan, 5(9), 3258–3267. https://doi.org/10.54371/jiip.v5i9.805
Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller models and faster training. In Proceedings of the 38th International Conference on Machine Learning (Vol. 139, pp. 10096–10106). PMLR.
Ye, Y., Zhou, H., Yu, H., Hu, H., Zhang, G., Hu, J., & He, T. (2022). An improved EfficientNetV2 model based on visual attention mechanism: Application to identification of cassava disease. Computational Intelligence and Neuroscience, 2022, Article 1569911. https://doi.org/10.1155/2022/1569911
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
Hak Cipta (c) 2026 Rahman Wahabi Hasibuan, Muhammad Amin Rais, Mutiara Akbar Nasution