Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Gudiato, Chandra
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 1 Documents
Search

 1 
Deteksi Ekspresi Wajah Manusia Menggunakan Metode Convolutional Neural Network Cahyaningtyas, Christian; Mira; Gudiato, Chandra; Sari, Maya
JURNAL FASILKOM Vol. 15 No. 1 (2025): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v15i1.9119

Abstract

Detecting emotions based on human facial expressions has long been a focus of research in the field of psychology that identifies the relationship between expressions and a person's emotional state. Deep learning has the ability to learn data representations with a high level of abstraction, allowing models to make predictions or decisions based on big data without human intervention and deep learning can also understand and classify an object. One of the main breakthroughs in the field of deep learning is the convolutional neural network, its advantage is that it has very good performance results in various tasks in image processing. In this study, research will be conducted on detecting human facial expressions using the convolutional neural network method by conducting several experiments. Image data will be processed using the python programming language and the dataset used is data sourced from the official kaggle.com website, namely FER2013. Based on the results of training the convolutional neural network model for facial expression recognition, the highest accuracy reached 60% at the 60th epoch with batch sizes of 64 and 128. When viewed based on the graph produced, the best model training was carried out with a batch size of 128 epoch 60. While the confusion matrix produced by batch size 64 epoch 60, the resulting model is more balanced in detecting expressions. And the classification report produced has no significant difference
Co-Authors Cahyaningtyas, Christian Maya Sari Mira