Abstract
The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.
Original language | English |
---|---|
Article number | 1383 |
Journal | Sensors (Switzerland) |
Volume | 18 |
Issue number | 5 |
DOIs | |
Publication status | Published - 2018 May 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Analytical Chemistry
- Atomic and Molecular Physics, and Optics
- Biochemistry
- Instrumentation
- Electrical and Electronic Engineering
Cite this
}
Electroencephalography based fusion two-dimensional (2D)-convolution neural networks (CNN) model for emotion recognition system. / Kwon, Yea Hoon; Shin, Sae Byuk; Kim, Shin-Dug.
In: Sensors (Switzerland), Vol. 18, No. 5, 1383, 01.05.2018.Research output: Contribution to journal › Article
TY - JOUR
T1 - Electroencephalography based fusion two-dimensional (2D)-convolution neural networks (CNN) model for emotion recognition system
AU - Kwon, Yea Hoon
AU - Shin, Sae Byuk
AU - Kim, Shin-Dug
PY - 2018/5/1
Y1 - 2018/5/1
N2 - The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.
AB - The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.
UR - http://www.scopus.com/inward/record.url?scp=85046355554&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85046355554&partnerID=8YFLogxK
U2 - 10.3390/s18051383
DO - 10.3390/s18051383
M3 - Article
AN - SCOPUS:85046355554
VL - 18
JO - Sensors
JF - Sensors
SN - 1424-3210
IS - 5
M1 - 1383
ER -