Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Mufidatun Nuha
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Klasifikasi Emosi Berdasarkan Ekspresi Wajah Menggunakan Metode Extreme Learning Machine dan Algoritme Genetika Untuk Seleksi Fitur Mufidatun Nuha; Fitra Abdurrachman Bachtiar
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 13 (2021): Publikasi Khusus Tahun 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Emotion is a feeling of a person's feelings that can influence a person's decision to act and behave. The most recognizable and identifiable expressions of a person's emotions are facial expressions. Research related to emotion recognition based facial expressions is relatively new research and its application is comprehensive in various fields such as academia, industry, and government. Emotion recognition requires a classification method capable of recognizing the type of emotion of each facial expression and a feature selection method to select optimal features. Therefore, this study will classify emotions based on facial expressions by implementing the Extreme Learning Machine (ELM) method as a classification method and Genetic Algorithm (GA) to select the most optimal features. Based on implementation and analysis, the average accuracy by the ELM and Genetic Algorithm is 82,87879% with the number of generations = 22, population size = 70, crossover rate = 0,8, mutation rate = 0,2, and the number of hidden neurons = 40. These results were compared with the ELM method without Genetic Algorithm which implies an average accuracy of 72,12121%. The accuracy results obtained from the two methods show that the feature selection using Genetic Algorithm has succeeded in increasing the average accuracy generated by ELM by 10,75758%. Genetic Algorithm is moreover succeeded in selecting features with an average of 63 selected features from a total of 136 features.
Co-Authors Fitra Abdurrachman Bachtiar