Convolutional neural network model for early detection of meatballs containing borax

Aryo Michael (Universitas Kristen Indonesia Toraja, Indonesia)
Juprianus Rusman (Universitas Kristen Indonesia Toraja, Indonesia)

Jurnal Mantik
Vol. 7 No. 3 (2023): November: Manajemen, Teknologi Informatika dan Komunikasi (Mantik)

The use of borax in meatballs to improve the texture and durability of meatballs is still rampant. Borax is very dangerous for consumers. Currently, monitoring of meatballs containing borax is done by experts in the laboratory. The public needs to know this information quickly. Therefore, a system is needed that can detect meatballs containing borax in real time. In this study we built a lightweight Convolutional Neutal Network (CNN) model and searched for optimal hyperparameters for the classification of meatballs containing borax. The results show that the proposed model outperforms other models in classifying meatballs containing borax with an accuracy value of 90%.