Performance analysis of emotion detection using machine learning algorithms

This project’s goal is not just to identify emotions, but also to develop methods for training and evaluating how well various machine learning models recognize emotions. This study investigates how different facial emotions (happy, fear, neutral, sad, angry, astonished) may be recognized using feat...

Full description

Saved in:
Bibliographic Details
Published inAIP conference proceedings Vol. 3075; no. 1
Main Authors Jatin, Raj, Kundan, Vidhya, R.
Format Journal Article Conference Proceeding
LanguageEnglish
Published Melville American Institute of Physics 29.07.2024
Subjects
Algorithms
Artificial neural networks
Decision trees
Emotion recognition
Emotions
Feature recognition
Machine learning
Regression models
Online AccessGet full text
ISSN0094-243X
1551-7616
DOI10.1063/5.0217097

Cover

More Information
Summary:This project’s goal is not just to identify emotions, but also to develop methods for training and evaluating how well various machine learning models recognize emotions. This study investigates how different facial emotions (happy, fear, neutral, sad, angry, astonished) may be recognized using feature extraction from face expressions in conjunction with a neural network combination. Convolutional neural networks, decision trees, logistic regression, and K-Nearest Neighbors will be among the several models investigated. The trial results shown that the recommended model is more accurate than 80% at identifying emotions.
Bibliography:ObjectType-Conference Proceeding-1
SourceType-Conference Papers & Proceedings-1
content type line 21
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0217097