Butterfly Classification Accuracy Analysis Using EfficientNet with Adam and AdamW Optimizer
Article Sidebar
Abstract:
Background: Accurate butterfly species classification plays an important role in biodiversity monitoring and environmental conservation. However, image-based classification remains challenging due to similarities in wing color patterns and shapes among species.
Aims: This study aims to evaluate the performance of butterfly image classification using transfer learning based on the EfficientNet architecture with different optimization strategies.
Methods: EfficientNet-B2 and EfficientNet-B3 were implemented as the main models. Image preprocessing techniques, including resizing, normalization, and data augmentation, were applied to improve model performance. The models were optimized using Adam and AdamW optimizers with different learning rates. Performance evaluation was conducted using accuracy, precision, recall, and F1-score.
Results: The results show that EfficientNet-B2 optimized with the Adam optimizer (learning rate 5 × 10⁻⁴) achieved the best performance, with a validation accuracy of 92.62% and an F1-score of 92.61%. In comparison, EfficientNet-B3 optimized using AdamW (learning rate 6 × 10⁻⁴) produced slightly lower performance, indicating the influence of optimizer selection and learning rate configuration on model convergence and generalization.
Conclusion: EfficientNet-B2 combined with the Adam optimizer provides a stable and effective approach for butterfly species classification. These findings highlight the importance of optimization strategies in improving model performance and support the development of automated systems for biodiversity monitoring.
Keywords: Adam Optimizer, AdamW Optimizer, Butterfly Species , EfficientNet-B2, Image Classification
Copyright (c) 2026 Amanda Mutiara Bunga, Risma, Fauzan Ulyadda Putra
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Anggrela, V., Arini, D., Hasibuan, W. A., Maysarah, M., & Masdar, E. (2023). Identifikasi Spesies Kupu- Kupu (Lepidoptera) di Kawasan Hutan Lindung Kota Langsa. Jurnal Jeumpa, 10(2), 359–368. https://doi.org/10.33059/jj.v10i2.8793
Ardiansyah, H., & Desyani, T. (2025). Transfer Learning Menggunakan Model VGG16 untuk Klasifikasi Citra Hewan. Jurnal Pustaka AI, 5(2), 441–448. https://doi.org/10.55382/jurnalpustakaai.v5i2.1174
Azahra, S. D. (2021). POTENSI JENIS KUPU-KUPU SEBAGAI BIOINDIKATOR KONDISI LINGKUNGAN KAWASAN PERKOTAAN. Gunung Djati Conference Series, 6, 2021. https://conference.uinsgd.ac.id/index.php/
Azis, A. R. (2025). Analisis Komparasi Algoritma Machine Learning dalam Prediksi Performa Akademik Mahasiswa: Literature Review. Jurnal Ilmu Komputer dan Informatika, 4(2), 143–148. https://doi.org/10.54082/jiki.212
Bibas, E., Kurnia, F., Raynaldo, A., Marista, E., Wahyuni, M. Y. D., & Linda, R. (2025). Butterfly Species Richness in Different Habitats of Pontianak City, West Kalimantan. Jurnal Biologi Tropis, 25(2), 1251–1261. https://doi.org/10.29303/jbt.v25i2.8715
Castro, M. D. B., & Tumibay, G. M. (2021). A literature review: efficacy of online learning courses for higher education institution using meta-analysis. Education and Information Technologies, 26(2), 1367–1385. https://doi.org/10.1007/s10639-019-10027-z
Dalimunthe, A. A. (2025). Klasifikasi Arthropoda Dengan Pendekatan Convolutional Neural Network (CNN). Data Sciences Indonesia (DSI), 5(1), 119–125. https://doi.org/10.47709/dsi.v5i1.6324
Efendi, I., Karmana, I. W., Adawiyah, S. R., & Arifin, A. A. (2024). Keragaman Spesies Kupu-Kupu (Lepidoptera) Sebagai Objek Pengembangan Ekowisata TWA Suranadi Dan Upaya Penyusunan E-Modul Ekologi Hewan. Bioscientist : Jurnal Ilmiah Biologi, 12(2), 2245. https://doi.org/10.33394/bioscientist.v12i2.12921
Irfan, D., Rosnelly, R., Wahyuni, M., Samudra, J. T., & Rangga, A. (2022). PERBANDINGAN OPTIMASI SGD, ADADELTA, DAN ADAM DALAM KLASIFIKASI HYDRANGEA MENGGUNAKAN CNN. In Journal of Science and Social Research (Issue 2). http://jurnal.goretanpena.com/index.php/JSSR
Irsa, A. F. N., Rahadian, R., & Hadi, M. (2022). Struktur komunitas, keragaman tumbuhan inang, dan status konservasi kupu-kupu (Lepidoptera) di Desa Ngesrepbalong Kecamatan Limbangan Kabupaten Kendal. Jurnal Ilmu Lingkungan, 20(4), 777–786. https://doi.org/10.14710/jil.20.4.777-786
Kurniawan, A. A., & Samani, K. A. (2023). Identifikasi Jenis Kupu-kupu (Lepidoptera) di Taman Wisata Alam Baning Kabupaten Sintang. Biocaster : Jurnal Kajian Biologi, 3(2), 72–84. https://doi.org/10.36312/biocaster.v3i2.169
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. International Conference on Learning Representations (ICLR). https://doi.org/10.48550/arXiv.1412.6980
Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. International Conference on Learning Representations (ICLR). https://doi.org/10.48550/arXiv.1711.05101
Nadiyah Hidayati, & Maulidah, M. (2023). EKSTRAKSI FITUR DENGAN COLOR HISTOGRAM DAN CLASSIFIER RANDOM FOREST PADA CITRA KUPU-KUPU. JAMI: Jurnal Ahli Muda Indonesia, 4(2), 148–157. https://doi.org/10.46510/jami.v4i2.172
Norman, E., Pahlawati, E., Ui Bbc, P., Mulia, S., & Bekasi, P. (2024). Peran Artificial Intelligence dalam Rekrutmen dan Seleksi: Meningkatkan Efisiensi dan Akurasi dalam MSDM. In Sci-Tech Journal (Vol. 3). https://doi.org/10.56709/stj.v3i1.320
Ray, R. P. (n.d.). Analisis Pengaruh Fungsi Aktivasi CNN terhadap Performa Klasifikasi Hewan Analysis of the Effect of CNN Activation Function on Animal Classification Performance. http://journal.mahesacenter.org/index.php/incoding
Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural Computation, 29(9), 2352–2449. https://doi.org/10.1162/neco_a_00990
Sonianto, & Hartono. (2025). Penerapan Algoritma K-Means untuk Mengidentifikasi Minat dan Bakat Siswa Sekolah Dasar. https://doi.org/10.47637/sienna.v6i1.1759
Saedan, M. A. H., Kassim, M., & Abd Aziz, A. F. (2024). Biological butterfly characterization with mobile system using convolutional neural network (CNN) classify image. International Journal of Interactive Mobile Technologies, 18(7). https://doi.org/10.3991/ijim.v18i07.46267
Toding, G., Rosyid, A., Sustri, S., Toknok, B., Rukmi, R., & Ihsan, M. (2024). KEANEKARAGAMAN JENIS KUPU-KUPU DI DESA BOMBA KECAMATAN LORE SELATAN KABUPATEN POSO. Jurnal Belantara, 7(2), 287–296. https://doi.org/10.29303/jbl.v7i2.1039
Tresnani, G., Zamroni, Y., & Hadi, I. (2025). PENGENALAN KEANEKARAGAMAN HAYATI SEBAGAI PENUNJANG PEMBELAJARAN IPA BAGI PESERTA DIDIK DI SDN 1 UBUNG, LOMBOK TENGAH. Jurnal Warta Desa (JWD), 7(1), 34–41. https://doi.org/10.29303/jwd.v7i1.314
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning. https://doi.org/10.48550/arXiv.1905.11946
Wang, Y., et al. (2021). Fine-grained image classification for butterflies and moths using deep learning. Ecological Informatics, 61, 101244. https://doi.org/10.1016/j.ecoinf.2021.101244
Xin, D., Chen, Y.-W., & Li, J. (2020). Fine-grained butterfly classification in ecological images using squeeze-and-excitation and spatial attention modules. Applied Sciences, 10(5), 1681. https://doi.org/10.3390/app10051681
Zulaikha, S., & Bahri, S. (2021). Keanekaragaman Jenis Kupu-Kupu (Rhopalocera: Papilionoidea dan Hesperioidea) di Kawasan Cagar Alam Gunung Sigogor Kecamatan Ngebel, Kabupaten Ponorogo. BIO-EDU: Jurnal Pendidikan Biologi, 6(2), 90–101. https://doi.org/10.32938/jbe.v6i2.1189
