Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps
An important function of the construction of the Brain-Computer Interface (BCI) device is the development of a model that is able to recognize emotions from electroencephalogram (EEG) signals. Research in this area is very challenging because the EEG signal is non-stationary, non-linear, and contain...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/9/3248 |
_version_ | 1797502938834272256 |
---|---|
author | Ante Topic Mladen Russo Maja Stella Matko Saric |
author_facet | Ante Topic Mladen Russo Maja Stella Matko Saric |
author_sort | Ante Topic |
collection | DOAJ |
description | An important function of the construction of the Brain-Computer Interface (BCI) device is the development of a model that is able to recognize emotions from electroencephalogram (EEG) signals. Research in this area is very challenging because the EEG signal is non-stationary, non-linear, and contains a lot of noise due to artifacts caused by muscle activity and poor electrode contact. EEG signals are recorded with non-invasive wearable devices using a large number of electrodes, which increase the dimensionality and, thereby, also the computational complexity of EEG data. It also reduces the level of comfort of the subjects. This paper implements our holographic features, investigates electrode selection, and uses the most relevant channels to maximize model accuracy. The ReliefF and Neighborhood Component Analysis (NCA) methods were used to select the optimal electrodes. Verification was performed on four publicly available datasets. Our holographic feature maps were constructed using computer-generated holography (CGH) based on the values of signal characteristics displayed in space. The resulting 2D maps are the input to the Convolutional Neural Network (CNN), which serves as a feature extraction method. This methodology uses a reduced set of electrodes, which are different between men and women, and obtains state-of-the-art results in a three-dimensional emotional space. The experimental results show that the channel selection methods improve emotion recognition rates significantly with an accuracy of 90.76% for valence, 92.92% for arousal, and 92.97% for dominance. |
first_indexed | 2024-03-10T03:42:19Z |
format | Article |
id | doaj.art-c26af6ae71334bbb986e7c3b9668827a |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-10T03:42:19Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-c26af6ae71334bbb986e7c3b9668827a2023-11-23T09:15:39ZengMDPI AGSensors1424-82202022-04-01229324810.3390/s22093248Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature MapsAnte Topic0Mladen Russo1Maja Stella2Matko Saric3Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 21000 Split, CroatiaFaculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 21000 Split, CroatiaFaculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 21000 Split, CroatiaFaculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, 21000 Split, CroatiaAn important function of the construction of the Brain-Computer Interface (BCI) device is the development of a model that is able to recognize emotions from electroencephalogram (EEG) signals. Research in this area is very challenging because the EEG signal is non-stationary, non-linear, and contains a lot of noise due to artifacts caused by muscle activity and poor electrode contact. EEG signals are recorded with non-invasive wearable devices using a large number of electrodes, which increase the dimensionality and, thereby, also the computational complexity of EEG data. It also reduces the level of comfort of the subjects. This paper implements our holographic features, investigates electrode selection, and uses the most relevant channels to maximize model accuracy. The ReliefF and Neighborhood Component Analysis (NCA) methods were used to select the optimal electrodes. Verification was performed on four publicly available datasets. Our holographic feature maps were constructed using computer-generated holography (CGH) based on the values of signal characteristics displayed in space. The resulting 2D maps are the input to the Convolutional Neural Network (CNN), which serves as a feature extraction method. This methodology uses a reduced set of electrodes, which are different between men and women, and obtains state-of-the-art results in a three-dimensional emotional space. The experimental results show that the channel selection methods improve emotion recognition rates significantly with an accuracy of 90.76% for valence, 92.92% for arousal, and 92.97% for dominance.https://www.mdpi.com/1424-8220/22/9/3248electroencephalogramBrain-Computer InterfaceReliefFNeighborhood Component Analysisdeep learningcomputer-generated holography |
spellingShingle | Ante Topic Mladen Russo Maja Stella Matko Saric Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps Sensors electroencephalogram Brain-Computer Interface ReliefF Neighborhood Component Analysis deep learning computer-generated holography |
title | Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps |
title_full | Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps |
title_fullStr | Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps |
title_full_unstemmed | Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps |
title_short | Emotion Recognition Using a Reduced Set of EEG Channels Based on Holographic Feature Maps |
title_sort | emotion recognition using a reduced set of eeg channels based on holographic feature maps |
topic | electroencephalogram Brain-Computer Interface ReliefF Neighborhood Component Analysis deep learning computer-generated holography |
url | https://www.mdpi.com/1424-8220/22/9/3248 |
work_keys_str_mv | AT antetopic emotionrecognitionusingareducedsetofeegchannelsbasedonholographicfeaturemaps AT mladenrusso emotionrecognitionusingareducedsetofeegchannelsbasedonholographicfeaturemaps AT majastella emotionrecognitionusingareducedsetofeegchannelsbasedonholographicfeaturemaps AT matkosaric emotionrecognitionusingareducedsetofeegchannelsbasedonholographicfeaturemaps |