PERFORMANCE EVALUATION OF LIGHTWEIGHT DEEP LEARNING MODELS FOR BORAX-CONTAMINATED MEATBALL IMAGE CLASSIFICATION
DOI:
https://doi.org/10.33480/jitk.v11i3.7462Keywords:
Deep Learning, Food Safety, Image Classification, Lightweight ModelAbstract
Food safety, particularly concerning the use of illegal additives such as borax in processed meat products like meatballs, remains a critical issue in Indonesia. This study analyzes the performance of several lightweight deep learning models based on Convolutional Neural Networks (CNN) and Transformers to classify images of meatballs containing borax, enabling their deployment on resource-constrained devices such as smartphones. Data collection involved capturing 1,429 images of meatballs with and without borax using a smartphone camera under varying lighting conditions and shooting angles. The five main architectures evaluated were ConvNeXt-Nano, Swin-Tiny, ViT-Tiny, MobileViT-XS, and EfficientNet-B0. Hyperparameter optimization was conducted using Optuna, followed by training with a 5-fold cross-validation scheme. Model evaluation metrics included accuracy, precision, recall, F1 score, and inference speed. The results show that MobileViT-XS was the best-performing architecture, achieving 65.93% accuracy, 0.703 precision, 0.706 recall, 0.659 F1 score, and efficient memory consumption (45.94 MB). These findings indicate that a hybrid approach combining the strengths of CNNs and Transformers can achieve an optimal balance between detection accuracy and computational efficiency. Therefore, such models have the potential to be applied as food safety detection systems on devices with limited resources
Downloads
References
[1] B. Patwardhan and B. S. Paranthaman, “Nutrition, food and global health,” Oct. 01, 2021, Elsevier B.V. doi: 10.1016/j.jaim.2021.11.003.
[2] B. Patwardhan and B. S. Paranthaman, “Nutrition, food and global health,” Oct. 01, 2021, Elsevier B.V. doi: 10.1016/j.jaim.2021.11.003.
[3] L. S. Jakobsen, M. Al Huthiel, F. Al Natour, and A. Agudo, “Health consequences of harmful chemicals in foods: insights from the WHO Global Burden of Foodborne Disease Study,” Eur J Public Health, vol. 34, no. Supplement_3, p. ckae144.633, Nov. 2024, doi: 10.1093/eurpub/ckae144.633.
[4] M. M. Sarhan, S. E. Alotaibi, N. A. Alharbi, S. A. Aljohani, Y. A. Alnazzawi, and M. A. M. Alwadi, “Exploring the contributing factors of fast food consumption in daily life: a qualitative study of Saudi university students,” BMC Public Health, vol. 25, no. 1, p. 2402, Jul. 2025, doi: 10.1186/s12889-025-23624-0.
[5] D. Rahardiyan, “Fortifying bakso (Restructured meat product) with potential encapsulated functional strategies – A mini review,” Feb. 01, 2021, Rynnye Lyan Resources. doi: 10.26656/fr.2017.5(1).277.
[6] L. Shao, S. Chen, H. Wang, J. Zhang, X. Xu, and H. Wang, “Advances in understanding the predominance, phenotypes, and mechanisms of bacteria related to meat spoilage,” Trends Food Sci Technol, vol. 118, pp. 822–832, Dec. 2021, doi: 10.1016/j.tifs.2021.11.007.
[7] S. P. Mohanty et al., “The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images,” Front Nutr, vol. 9, no. May, pp. 1–13, 2022, doi: 10.3389/fnut.2022.875143.
[8] S. Kaushal, D. K. Tammineni, P. Rana, M. Sharma, K. Sridhar, and H.-H. Chen, “Computer vision and deep learning-based approaches for detection of food nutrients/nutrition: New insights and advances,” Trends Food Sci Technol, vol. 146, p. 104408, 2024, doi: https://doi.org/10.1016/j.tifs.2024.104408.
[9] A. A. S. Pradhana et al., “Sensor Array System Based on Electronic Nose to Detect Borax in Meatballs with Artificial Neural Network,” Journal of Electrical and Computer Engineering, vol. 2023, pp. 1–10, Sep. 2023, doi: 10.1155/2023/8847929.
[10] A. Michael, S. Palelleng, I. Devi Damayanti, and J. Rusman, “Kombinasi Pretrained Model dan Random Forest Pada Klasifikasi Bakso Mengandung Boraks dan Non-Boraks Berbasis Citra,” Teknika, vol. 12, no. 1, pp. 27–32, Feb. 2023, doi: 10.34148/teknika.v12i1.591.
[11] L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of image classification algorithms based on convolutional neural networks,” Remote Sens (Basel), vol. 13, no. 22, pp. 1–51, 2021, doi: 10.3390/rs13224712.
[12] Maurício, I. Domingues, and J. Bernardino, “Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review,” May 01, 2023, MDPI. doi: 10.3390/app13095521.
[13] X. Meng, J. Ma, F. Liu, Z. Chen, and T. Zhang, “An Interpretable Breast Ultrasound Image Classification Algorithm Based on Convolutional Neural Network and Transformer,” Mathematics, vol. 12, no. 15, Aug. 2024, doi: 10.3390/math12152354.
[14] A. Agarwal, A. Dash, G. Galbale, and S. P. Singh, “Analyzing Impact of Data Augmentation Techniques in Computer Vision,” in 2025 2nd International Conference on Computational Intelligence, Communication Technology and Networking (CICTN), IEEE, Feb. 2025, pp. 733–737. doi: 10.1109/CICTN64563.2025.10932445.
[15] R. Poojary, R. Raina, and A. Kumar Mondal, “Effect of data-augmentation on fine-tuned CNN model performance,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 10, no. 1, p. 84, Mar. 2021, doi: 10.11591/ijai.v10.i1.pp84-92.
[16] Z. Liu, H. Mao, C. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11966–11976, 2022, doi: 10.1109/CVPR52688.2022.01167.
[17] S. Woo et al., “ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders,” in 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 16133–16142. doi: 10.1109/CVPR52729.2023.01548.
[18] H. Li, H. Hu, Z. Jin, Y. Xu, and X. Liu, “The Image Recognition and Classification Model Based on ConvNeXt for Intelligent Arms,” in 2025 IEEE 5th International Conference on Electronic Technology, Communication and Information (ICETCI), 2025, pp. 1436–1441. doi: 10.1109/ICETCI64844.2025.11084094.
[19] Z. Liu et al., “Swin Transformer: Hierarchical Vision Transformer using Shifted Windows,” Aug. 2021, [Online]. Available: http://arxiv.org/abs/2103.14030
[20] S. H. Lee, S. Lee, and B. C. Song, “Vision Transformer for Small-Size Datasets,” Dec. 2021, [Online]. Available: http://arxiv.org/abs/2112.13492
[21] A. Dosovitskiy et al., “AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE,” [Online]. Available: https://github.com/
[22] S. Mehta and M. Rastegari, “MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2110.02178
[23] H. Ali, N. Shifa, R. Benlamri, A. A. Farooque, and R. Yaqub, “A fine tuned EfficientNet-B0 convolutional neural network for accurate and efficient classification of apple leaf diseases,” Sci Rep, vol. 15, no. 1, p. 25732, Jul. 2025, doi: 10.1038/s41598-025-04479-2.
[24] S. Tripathy, R. Singh, and M. Ray, “Automation of Brain Tumor Identification using EfficientNet on Magnetic Resonance Images,” Procedia Comput Sci, vol. 218, pp. 1551–1560, 2023, doi: https://doi.org/10.1016/j.procs.2023.01.133.
[25] J. Pardede and A. S. Purohita, “Hyperparameter Search for CT-Scan Classification Using Hyperparameter Tuning in Pre-Trained Model CNN With MLP,” in 2022 IEEE International Conference of Computer Science and Information Technology (ICOSNIKOM), 2022, pp. 1–8. doi: 10.1109/ICOSNIKOM56551.2022.10034878.
[26] Ștefana Duță and A. E. Sultana, “Optimizing Depression Classification Using Combined Datasets and Hyperparameter Tuning with Optuna,” Sensors, vol. 25, no. 7, p. 2083, Mar. 2025, doi: 10.3390/s25072083
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Aryo Michael, Ireve Devi Damayanti
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
