Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Sains dan Ilmu Terapan
Rifaldi Rifaldi
Unknown Affiliation
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Aplikasi Pengenalan Kue Tradisional Bugis Menggunakan Metode Convolutional Neural Network (CNN) Berbasis Android Rifaldi Rifaldi; Ade Hastuty; Ahmad Selao; Untung Suwardoyo; Masnur Masnur
Jurnal Sains dan Ilmu Terapan Vol. 8 No. 2 (2025): Jurnal Sains dan Ilmu Terapan
Publisher : Politeknik Kampar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59061/jsit.v8i2.1151

Abstract

Traditional Bugis cakes are an important and distinctive part of Indonesian culinary culture, yet their existence is starting to erode due to globalization and a lack of proper digital documentation. The visual similarities between the cakes make manual identification difficult, especially for the younger generation who are more exposed to modern, global food trends. This study aims to develop an Android application for the automatic classification of traditional Bugis cakes using a Convolutional Neural Network (CNN). The experimental method was conducted by collecting a comprehensive dataset of cake images, training a CNN model, and evaluating its performance using a black box testing approach. This method was chosen because it yielded a validation accuracy of 97.00% and a final accuracy of 92.40%. The application can recognize cakes in real-time through a mobile phone camera, with optimal results achieved at a distance of 15–30 cm and under adequate lighting conditions. However, its performance decreases when the distance increases, objects are cut off, or lighting is poor. 
Co-Authors Ade Hastuty ahmad selao Masnur Masnur Untung Suwardoyo