Implementasi Convolutional Neural Network untuk Klasifikasi Kualitas Sarang Burung Walet Menggunakan MobileNetV2 dan EfficientNet-B3
DOI:
https://doi.org/10.47065/bulletincsr.v6i6.1394Keywords:
Convolutional Neural Network; EfficientNet-B3; MobileNetV2; Swiftlet Nests; Transfer LearningAbstract
The quality of swiftlet nests is a main factor affecting their selling price, given its high economic value. Quality assessment still performed visually and manually is prone to subjectivity and inconsistency. Therefore, a system that can classify swiftlet nest quality automatically and objectively is needed. This study develops a Convolutional Neural Network (CNN)-based classification system by comparing MobileNetV2 and EfficientNet-B3 through transfer learning with a two-phase training strategy. The dataset consists of 1,200 swiftlet nest images in three quality categories, namely high, medium, and low (400 images per category), all primary data except the high category, which comprises 300 primary and 100 secondary images. The data were split into 70% training, 15% validation, and 15% test sets, after which augmentation was applied only to the training data for both architectures, so the validation and test sets contain only original images with no shared parent images across subsets. The system is implemented as a website, Qualet, that lets users upload nest images and obtain classification results. MobileNetV2 achieved a test accuracy of 78.89% with a loss of 0.6767, while EfficientNet-B3 achieved 80.56% with a loss of 0.6954. Misclassifications in both models occurred mainly in the medium category, presumably because it is a transitional class with less distinct visual boundaries and a limited number of original images. Both architectures showed comparable performance, with an accuracy difference of 1.67 percentage points, equivalent to 3 of the 180 test images. This study contributes a comparison of two CNN architectures and the Qualet website.
Downloads
References
F. Agus, E. Sulfika, and G. M. Putra, “Analisis Kualitas Sarang Burung Walet Menggunakan Metode Fuzzy Tsukamoto,” J. Teknol. Inf. dan Ilmu Komput., vol. 12, no. 2, pp. 391–398, 2025, doi: https://doi.org/10.25126/jtiik.2025129441.
P. Pojanalai, P. Akkajit, and A. Sukkuea, “Explainable deep learning for grading of Edible Bird ’s Nest( EBN),” J. Agric. Food Res., vol. 27, p. 102815, 2026, doi: https://doi.org/10.1016/j.jafr.2026.102815.
N. N. Zulkefle et al., “A Review on the Edible Bird’s Nest Quality and Manufacturing Standards of the Three Largest Exporting Countries in the World,” J. Food Qual., vol. 2024, p. 5608357, 2024, doi: https://doi.org/10.1155/2024/5608357.
B.-H. Yeo, Y. Rukayadi, S.-F. Wong, C.-P. Tan, and O.-M. Lai, “Physicochemical Properties of Raw Cleaned Edible Bird ’s Nest after Different Primary Processing Including a New Cleaning Method,” Sains Malaysiana, vol. 52, no. 12, pp. 3421–3435, 2023, doi: https://doi.org/10.17576/jsm-2023-5212-06.
R. A. Saemani, D. Manongga, and Hendry, “Pendekatan Multi-Hirarki untuk Grading Sarang Burung Walet Berdasarkan Deteksi Bentuk dan Klasifikasi Warna,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 6, no. 2, pp. 462–474, 2026, doi: https://doi.org/10.57152/malcom.v6i2.2594.
S. Ahmad and Supatman, “Analisis Cnn Untuk Klasifikasi Kebersihan Sarang Burung Walet,” J. Inform. dan Tek. Elektro Terap., vol. 13, no. 3, p. 8, 2025, doi: https://doi.org/10.23960/jitet.v13i3.6685.
H. Arini Parhusip, S. Trihandaru, K. D. Hartomo, K. Bianca Lewerissa, L. Ariany Mahastanti, and D. Hartanto, “Management of Traditional Business into Modern: from Microsoft Excel to Deep Learning for prototyping classification Swiftlet’s nests,” Int. J. Community Serv., vol. 4, no. 2, pp. 123–132, 2024, doi: https://doi.org/10.51601/ijcs.v4i2.268.
D. Indrajaya, H. A. Parhusip, S. Trihandaru, and D. Hartanto, “MobileNetV2-D and multiple cameras for swiftlet nest classification based on feather intensity,” Indones. J. Electr. Eng. Comput. Sci., vol. 34, no. 2, pp. 1144–1158, 2024, doi: 10.11591/ijeecs.v34.i2.pp1144-1158.
P. Medina and E. Rahayu, “Implementasi Algoritma SVM (Support Vector Machine) Dalam Memprediksi Hasil Produksi Sarang Burung Walet,” Explore, vol. 16, no. 1, pp. 40–49, 2026, doi: https://doi.org/10.35200/sd.v16i1.188.
Ilmiati, S. Mutmainah, and Khairunnas, “Classification of Swiftlet Nest Quality Based on SNI 8998:2021 Using Deep Learning,” Build. Informatics, Technol. Sci., vol. 8, no. 1, pp. 308–317, 2026, doi: https://doi.org/10.47065/bits.v8i1.9901.
F. Chollet, Deep Learning with Python, 2nd ed. Shelter Island, NY, USA: Manning Publications, 2021.
X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif. Intell. Rev., vol. 57, no. 4, pp. 1–43, 2024, doi: 10.1007/s10462-024-10721-6.
A. Zhang, Z. C. Lipton, M. Li, and A. J. Smola, Dive into Deep Learning. Cambridge, U.K.: Cambridge University Press, 2023.
M. Iman, H. R. Arabnia, and K. Rasheed, “A Review of Deep Transfer Learning and Recent Advancements,” Technologies, vol. 11, no. 2, pp. 1–14, 2023, doi: https://doi.org/10.3390/technologies11020040.
M. Isnan, A. A. Hidayat, and B. Pardamean, “Indonesian Agricultural-crops Classification Using Transfer Learning Model,” Procedia Comput. Sci., vol. 227, pp. 128–136, 2023, doi: https://doi.org/10.1016/j.procs.2023.10.510.
K. Halloum and H. E. Zahraouy, “Enhancing Medical Image Classification through Transfer Learning and CLAHE Optimization,” Curr. Med. Imaging, vol. 21, no. 1, p. e15734056342623, 2025, doi: https://doi.org/10.2174/0115734056342623241119061744.
V. Zárate and D. C. Hernández, “Simplified Deep Learning for Accessible Fruit Quality Assessment in Small Agricultural Operations,” Appl. Sci., vol. 14, no. 18, 2024, doi: https://doi.org/10.3390/app14188243.
H. Chen, G. Zhou, W. He, X. Duan, and H. Jiang, “Classification and identification of agricultural products based on improved MobileNetV2,” Sci. Rep., vol. 14, no. 1, p. 14, 2024, doi: https://doi.org/10.1038/s41598-024-53349-w.
Y. P. Vera et al., “Deep Learning Models for Defect Identification in Oryza sativa Rice Grains: A Comparative Study,” AgriEngineering, vol. 8, no. 6, p. 28, 2026, doi: 10.3390/agriengineering8060252.
E. Dewi, S. Mulyani, T. Mufizar, D. Rohpandi, A. Djuliani, and E. Rahmatulloh, “Classification of Cihateup duck egg fertility using convolutional neural network EfficientNet-B3,” IAES Int. J. Artif. Intell., vol. 15, no. 1, pp. 798–809, 2026, doi: https://doi.org/10.11591/ijai.v15.i1.pp798-809.
K. A. Tamayasa and L. J. E. Dewi, “Analisis Perbandingan Model Arsitektur MobileNetV2 dan EfficientNetB3 dalam Klasifikasi Penyakit Daun Jagung,” J. Inform. dan Tek. Elektro Terap., vol. 14, no. 1, p. 12, 2026, doi: https://doi.org/10.23960/jitet.v14i1.8624.
F. Nan et al., “A novel method for maize leaf disease classification using the image data,” Front. Plant Sci., vol. 14, p. 14, 2023, doi: https://doi.org/10.3389/fpls.2023.1268015.
Y. Puspitasari, J. J. Siang, and A. G. Prabawati, “Comparison of Convolutional Neural Network Architectures EfficientNet-B4 and MobileNetV2 in Cataract Disease Detection,” JITK (Jurnal Ilmu Pengetah. dan Teknol. Komputer), vol. 11, no. 4, pp. 1020–1027, 2026, doi: https://doi.org/10.33480/jitk.v11i4.7502.
IOT Lab Sensor, “Swiftlet’s Nest Shape (3 Classes),” 2022, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/iotlabsensor/bentuk-sarang-bulu-burung-wallet-3-kelas
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Implementasi Convolutional Neural Network untuk Klasifikasi Kualitas Sarang Burung Walet Menggunakan MobileNetV2 dan EfficientNet-B3
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 I Komang Aditya, Muhammad Fachrie
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
