Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Building of Informatics, Technology and Science
Uwar, Tarissa Rizky Salsabiila
Unknown Affiliation
Computer Science & IT

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

Found 1 Documents
Search
Journal : Building of Informatics, Technology and Science

 1 
Implementasi Transfer Learning pada Convolutional Neural Network dengan Arsitektur VGG dalam Klasifikasi Down Syndrome di Asia Uwar, Tarissa Rizky Salsabiila; Aditya, Christian Sri Kusuma
Building of Informatics, Technology and Science (BITS) Vol 7 No 1 (2025): June (2025)
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i1.7150

Abstract

Early detection of Down syndrome is crucial for enabling early intervention and providing healthcare education for children. Down syndrome is associated with specific facial features, such as distinct characteristics of the eyes, nose, lips, face shape, hair, and skin color, which can be analyzed using computer vision techniques. This study aims to classify Down syndrome, especially in the Asian Region, which includes countries with medium/low SDI. The study proposed a CNN based on the VGG16 and VGG19 architectures by implementing transfer learning and augmentation. Augmentation is performed to balance the number of images between classes, while transfer learning is used to train the model first on ImageNet data. The dataset used consists of two categories, Down syndrome and Healthy. The results indicate that the VGG16 model has higher sensitivity and is able to classify more cases of Down syndrome, but has a fairly large prediction error. However, VGG19 model has a better specificity value and has a smaller potential for prediction error. The best model in this study was selected based on the highest validation accuracy value, where VGG19 achieved an accuracy of 93% in its best iteration, and VGG16 achieved an accuracy of 91%. These findings suggest that the proposed models, particularly VGG19, exhibit optimal performance in classifying Down syndrome, especially in the Asian region, with a lower prediction error rate.
Co-Authors Christian Sri kusuma Aditya, Christian Sri kusuma