Learning Rate Tuning of Transfer Learning Models for Fresh and Spoiled Beef Image Classification

Tri Mulya Dharma; Mukhsin Nuzula; Aviv Fitria  Yulia; Dwi  Feriyanto; Ningsiah

Authors

Tri Mulya Dharma Universitas Jabal Ghafur Author
Mukhsin Nuzula Universitas Jabal Ghafur Author
Aviv Fitria Yulia Universitas Aisyah Pringsewu Author
Dwi Feriyanto Universitas Aisyah Pringsewu Author
Ningsiah Universitas Aisyah Pringsewu Author

Keywords:

Beef Quality, CNN, Deep Learning, VGG16, Learning Rate

Abstract

Beef freshness assessment is a critical aspect of the food industry, where conventional methods relying on visual inspection and olfaction are subjective and prone to human error. This study aims to develop an automated beef freshness classification system utilizing deep learning to enhance the accuracy and objectivity of quality assessments. A total of 2.800 beef images were sourced from an open research data repository, divided equally into fresh and spoiled classes. Three Convolutional Neural Networks (CNN) architectures with transfer learning VGG16, ResNet50-V2, and Inception-V3 were evaluated. The models were systematically tested using learning rate tuning at 0.01, 0.001, and 0.0001 to optimize training convergence. Evaluation results showed that VGG16 outperformed other models in classifying beef freshness. VGG16 achieved a peak testing accuracy of 99.46% at a learning rate of 0.001. The main contribution of this study is the systematic evaluation of transfer learning architectures to establish an optimal baseline for beef quality assessment. By deploying the best performing model into a web based application, this approach offers a practical, objective, and accessible alternative to conventional manual inspection, enabling rapid early detection of beef freshness to improve food safety.

References

[1] M. A. Wali et al., “Nutritional and chemical characterization of cow, camel, and goat meat from Kebridehar, Ethiopia: a comparative analysis and statistical approaches,” RSC Adv., vol. 15, no. 10, pp. 7617–7629, 2025, doi: 10.1039/D4RA07096H.

[2] Badan Pusat Statistik Indonesia, “Produksi Daging Sapi menurut Provinsi, 2025,” Badan Pusat Statistik. Accessed: Dec. 17, 2025. [Online]. Available: https://www.bps.go.id/id/statistics-table/2/NDgwIzI=/produksi-daging-sapi-menurut-provinsi.html

[3] Reza Umamah, Vikko Hilmi Pradana, Nesya Zuhrah, Heikelindra Kurniawan, and Silva Syalikha, “Analisis Faktor yang Mempengaruhi Konsumsi Daging di Pulau Jawa,” Diversity: Jurnal Ilmiah Pascasarjana, vol. 4, no. 2, pp. 173–183, Aug. 2024, doi: 10.32832/djip-uika.v14i2.17035.

[4] T. M. Dharma, R. Adriman, K. Saddami, and R. Ramadhana, “BeefFreshNet: A New Benchmarking Dataset and Pre-trained Model for Beef Freshness Classification,” in 2025 Tenth International Conference on Informatics and Computing (ICIC), IEEE, Oct. 2025, pp. 1–6. doi: 10.1109/ICIC68054.2025.11309417.

[5] T. Yulianti, A. Yudamson, H. D. Septama, S. R. Sulistiyanti, F. X. A. Setiawan, and M. Telaumbanua, “Meat quality classification based on color intensity measurement method,” in 2016 International Symposium on Electronics and Smart Devices (ISESD), 2016, pp. 248–252. doi: 10.1109/ISESD.2016.7886727.

[6] Guo, Lingling, et al. "Portable food‐freshness prediction platform based on colorimetric barcode combinatorics and deep convolutional neural networks." Advanced Materials 32.45 (2020): 2004805.

[7] A. Taheri-Garavand, S. Fatahi, M. Omid, and Y. Makino, “Meat quality evaluation based on computer vision technique: A review,” Oct. 01, 2019, Elsevier Ltd. doi: 10.1016/j.meatsci.2019.06.002.

[8] M. K. Rinaldi, E. Ernawati, D. Andreswari, and J. P. Sari, “Application of Two-Stream Late Fusion on EfficientNetV2 based on Transfer Learning to classify AI-generated paintings,” sinkron, vol. 10, no. 2, pp. 976–990, Apr. 2026, doi: 10.33395/sinkron.v10i2.15814.

[9] G. F. Rizqullah, P. Eosina, and A. E. K. Pramuko, “Enhanced Performance Evaluation of VGG16 and ResNet50 for Deepfake Detection Using Local Ternary Pattern,” Sinkron, vol. 10, no. 1, pp. 701–712, Jan. 2026, doi: 10.33395/sinkron.v10i1.15582.

[10] M. I. Ramdani, H. H. Handayani, Y. E. Wicaksana, and T. Al-Mudzakir, “Pengujian Model Klasifikasi Kesegaran Daging Sapi Berbasis GLCM (Gray Level Co-occurrence Matrix) dan Algoritma Machine Learning,” MIND Journal, vol. 10, no. 1, pp. 73–88, Jun. 2025, doi: 10.26760/mindjournal.v10i1.73-88.

[11] S. E. Abdallah, W. M. Elmessery, M. Y. Shams, N. S. A. Al-Sattary, A. A. Abohany, and M. Thabet, “Deep Learning Model Based on ResNet-50 for Beef Quality Classification,” Information Sciences Letters, vol. 12, no. 1, pp. 289–297, Jan. 2023, doi: 10.18576/isl/120124.

[12] Calvin, G. B. Putra, and E. Prakasa, “Classification of Chicken Meat Freshness using Convolutional Neural Network Algorithms,” in 2020 International Conference on Innovation and Intelligence for Informatics, Computing and Technologies, 3ICT 2020, Institute of Electrical and Electronics Engineers Inc., Dec. 2020. doi: 10.1109/3ICT51146.2020.9312018.

[13] W. B. Zulfikar, A. Angelyna, M. Irfan, A. R. Atmadja, and J. Jumadi, “A Deep Learning Approach Using VGG16 to Classify Beef and Pork Images,” JOIV : International Journal on Informatics Visualization, vol. 9, no. 2, p. 568, Mar. 2025, doi: 10.62527/joiv.9.2.2848.

[14] Kade Bramasta Vikana Putra, I Putu Agung Bayupati, and Dewa Made Sri Arsa, “Klasifikasi Citra Daging Menggunakan Deep Learning dengan Optimisasi Hard Voting,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 5, no. 4, pp. 656–662, Aug. 2021, doi: 10.29207/resti.v5i4.3247.

[15] Adhi Kusnadi et al., “Beef Freshness Classification Using CNN with DCT and GLCM Feature Extraction,” Journal of Soft Computing and Data Mining, vol. 7, no. 1, pp. 11–21, 2026, [Online]. Available: https://publisher.uthm.edu.my/ojs/index.php/jscdm/article/view/23280

[16] Tuan, Hoang Minh, et al. "Fake Beef Detection Using Lightweight Convolutional Neural Networks." International Congress on Information and Communication Technology. Singapore: Springer Nature Singapore, 2025.

[17] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. A. Azim, “Transfer learning: a friendly introduction,” J. Big Data, vol. 9, no. 1, Dec. 2022, doi: 10.1186/s40537-022-00652-w.

[18] C. Igiri, A. Uzoma, and A. Silas, “Effect of Learning Rate on Artificial Neural Network in Machine Learning,” International Journal of Engineering Research, vol. 4, Jun. 2021.

[19] Mustofa, Aufa Ab'dil, and Erwin Budi Setiawan. "Optimizing the Learning Rate Hyperparameter for Hybrid BiLSTM-FFNN Model in a Tourism Recommendation System." Jurnal Teknik Informatika 17.2 (2024): 112-126.

[20] M. W. Ilahi, C. N. Apriyani, A. Desiani, N. Gofar, Y. Andriani, and M. R. Halim, “Classification of Geometric Batik Motif Typical of Indonesian Using Convolutional Neural Network,” Jurnal Teknik Informatika, vol. 15, no. 1, pp. 91–100, Jun. 2022, doi: 10.15408/jti.v15i1.24968.