Improvement of EEG signal-based emotion recognition based on feature learning methods

机译：基于特征学习方法的脑电信号情感识别的改进

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Emotion is inevitable in human life. Today's knowledge is looking for new ways to recognize emotions, without considering of facial expression. One of the new methods for detecting emotions is the use of electroencephalogram signals (EEG). Using signal processing techniques and feature learning methods and with the help of decision tree on EEG signals to improve emotion recognition, a new method for improving emotion recognition is presented in this paper. The proposed method focuses on reducing the number of electrodes used in signal recording and the use of brain alpha waves, and extraction and characterization of characteristics based on received signals, and attempts to improve emotion recognition. Signals are classified using DT decision tree classification after recording, processing and extraction of the property by the two methods of PCA and PSD with. The proposed algorithm has been recorded on 10 people watching 2 videos and 8 happy and sad images. The results obtained from the three pairs of electrodes provide an acceptable improvement percentage. Given a decrease in the number of electrodes and a reduction in processes, an 88.73% improvement is shown in the recognition of emotions of happiness and 86.31% of improvement in detecting emotions of sadness.

机译：情感在人类生活中是不可避免的。当今的知识正在寻找无需考虑面部表情即可识别情绪的新方法。检测情绪的新方法之一是使用脑电图信号（EEG）。利用信号处理技术和特征学习方法，并借助脑电信号的决策树来提高情感识别能力，提出了一种新的情感识别方法。提出的方法着重于减少信号记录中使用的电极数量和脑阿尔法波的使用，以及基于接收到的信号的特征提取和表征，并尝试改善情感识别。在通过PCA和PSD两种方法记录，处理和提取属性后，使用DT决策树分类对信号进行分类。该算法被记录在10个人观看2个视频和8张快乐和悲伤的图像上。从三对电极获得的结果提供了可接受的改进百分比。考虑到电极数量的减少和工艺的减少，幸福情绪的识别率提高了88.73％，而悲伤情绪的检测率提高了86.31％。

著录项

来源
《Conference on Artificial Intelligence and Robotics;Asia-Pacific International Symposium》|2018年|14-18|共5页
会议地点 Kish Island(IR)
作者
Malihe Mohamadi; Amir Masoud Ekhtekhari Moghadam;
展开▼
作者单位

Faculty of Computer and Information Technology Engineering Qazvin Branch Islamic Azad University Qazvin Iran;

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Electroencephalography; Feature extraction; Decision trees; Electrodes; Emotion recognition; Principal component analysis; Brain modeling;

机译：脑电图；特征提取;决策树；电极;情绪识别；主成分分析；脑模型;

相似文献

外文文献
中文文献
专利

1. Learning CNN features from DE features for EEG-based emotion recognition [J] . Hwang Sunhee, Hong Kibeom, Son Guiyoung, Pattern Analysis and Applications . 2020,第3期

机译：从基于脑电图的情感识别学习CNN功能
2. Development of a Real-Time Emotion Recognition System Using Facial Expressions and EEG based on machine learning and deep neural network methods [J] . Aya Hassouneh, A.M. Mutawa, M. Murugappan Informatics in Medicine Unlocked . 2020,第3期

机译：基于机器学习和深神经网络方法，使用面部表情和脑电图的实时情感识别系统的开发
3. Dynamical recursive feature elimination technique for neurophysiological signal-based emotion recognition [J] . Zhong Yin, Lei Liu, Li Liu, Cognition, Technology & Work . 2017,第4期

机译：基于神经生理信号的情感识别动态递归特征消除技术
4. Improvement of EEG signal-based emotion recognition based on feature learning methods [C] . Malihe Mohamadi, Amir Masoud Ekhtekhari Moghadam Conference on Artificial Intelligence and Robotics . 2018

机译：基于特征学习方法的基于EEG信号的情感识别的改进
5. 3D Face Recognition Using Local Feature Based Methods [D] . Soltanpour, Sima. 2018

机译：使用基于局部特征的方法进行3D人脸识别
6. Multi-method Fusion of Cross-Subject Emotion Recognition Based on High-Dimensional EEG Features [O] . Fu Yang, Xingcong Zhao, Wenge Jiang, 1968

机译：基于高维脑电特征的跨学科情感识别的多方法融合
7. A comparative analysis of machine learning methods for emotion recognition using EEG and peripheral physiological signals [O] . Vikrant Doma, Matin Pirouz 2020

机译：脑电图和外周生理信号的情感识别机器学习方法的比较分析

Improvement of EEG signal-based emotion recognition based on feature learning methods

摘要

著录项

相似文献

相关主题

期刊订阅