Automatic ECG-Based Emotion Recognition in Music Listening

Hsu, Yu-Liang; Wang, Jeen-Shing; Chiang, Wei-Chun; Hung, Chien-Han

doi:10.1109/taffc.2017.2781732

Cited by 148 publications

(91 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of brain activity, signals from the central nervous system are recorded using electroencephalography (EEG) [ 12 , 14 , 15 ], as well as medical magnetic resonance imaging (fMRI) [ 18 ]. Other physiological signals used include: electrocardiography (ECG) [ 19 – 21 ], electromyography (EMG) [ 22 ], electrodermal activity (EDA) [ 19 , 20 , 23 ], heart rate [ 24 – 26 ], respiration rate and depth [ 24 , 27 ], and arterial pressure [ 24 ]. Eye-tracking [ 28 – 32 ] and pupil width [ 33 – 36 ] are also used to recognize emotions.…”

Section: Introductionmentioning

confidence: 99%

Eye-Tracking Analysis for Emotion Recognition

Tarnowski

Kołodziej

Majkowski

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

This article reports the results of the study related to emotion recognition by using eye-tracking. Emotions were evoked by presenting a dynamic movie material in the form of 21 video fragments. Eye-tracking signals recorded from 30 participants were used to calculate 18 features associated with eye movements (fixations and saccades) and pupil diameter. To ensure that the features were related to emotions, we investigated the influence of luminance and the dynamics of the presented movies. Three classes of emotions were considered: high arousal and low valence, low arousal and moderate valence, and high arousal and high valence. A maximum of 80% classification accuracy was obtained using the support vector machine (SVM) classifier and leave-one-subject-out validation method.

show abstract

Section: Introductionmentioning

confidence: 99%

Eye-Tracking Analysis for Emotion Recognition

Tarnowski

Kołodziej

Majkowski

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Various feature extraction and selection optimization approaches, classification algorithms, and evaluation methods are currently been used for the emotion recognition from psychophysiological data in recent years [5,6,7]. To adapt to the fast-changing technologies and recent applications, automatic recognition algorithms have been also applied to different psychophysiological signals in order to efficiently compute and classify human's affective states [8,9].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Various Emotion Classification Approaches from Physiological Signals

Hazer-Rau¹,

Zhang²,

Traue³

2018

IJAIA

View full text Add to dashboard Cite

This paper aims at evaluating the performance of various emotion classification approaches from psychophysiological signals. The goal is to identify the combinations of approaches that are most relevant for assessing human affective states. A classification analysis of various combinations of feature selection techniques, classification algorithms and evaluation methods is presented. The emotion recognition is conducted based on four physiological signals: two electromyograms, skin conductivity and respiration sensors. Affective states are classified into three different emotion classes: 2-categoryclass (Arousal), 3-category-class (Valence) and 5-category-class (Valence/Arousal). The performance of the various combinations of approaches is evaluated by comparing the resulting recognition rates. For all the category-classes, the best results are obtained when considering skin conductivity combined with the respiration signals. Highest rates when fusing all physiological channels resulted when applying the SFS feature selection, the LDA classifier and the normal split evaluation approach, showing a robust combination of approaches leading to good performance.

show abstract

“…Therefore, we consider that ECG has rich emotion-relevant features, which can clearly reflect changes in human emotions. Many researchers have used ECG for emotion recognition [ 11 , 49 , 50 ]. We can also see that the classification performance of the comprehensive nonlinear processing model (KPCA & GBDT) on multichannel physiological signals is better than that on single signal.…”

Section: Methodsmentioning

confidence: 99%

Emotion Recognition Based on Multichannel Physiological Signals with Comprehensive Nonlinear Processing

Zhang

Xue

et al. 2018

Sensors

View full text Add to dashboard Cite

Multichannel physiological datasets are usually nonlinear and separable in the field of emotion recognition. Many researchers have applied linear or partial nonlinear processing in feature reduction and classification, but these applications did not work well. Therefore, this paper proposed a comprehensive nonlinear method to solve this problem. On the one hand, as traditional feature reduction may cause the loss of significant amounts of feature information, Kernel Principal Component Analysis (KPCA) based on radial basis function (RBF) was introduced to map the data into a high-dimensional space, extract the nonlinear information of the features, and then reduce the dimension. This method can provide many features carrying information about the structure in the physiological dataset. On the other hand, considering its advantages of predictive power and feature selection from a large number of features, Gradient Boosting Decision Tree (GBDT) was used as a nonlinear ensemble classifier to improve the recognition accuracy. The comprehensive nonlinear processing method had a great performance on our physiological dataset. Classification accuracy of four emotions in 29 participants achieved 93.42%.

show abstract

Automatic ECG-Based Emotion Recognition in Music Listening

Cited by 148 publications

References 42 publications

Eye-Tracking Analysis for Emotion Recognition

Eye-Tracking Analysis for Emotion Recognition

Performance Evaluation of Various Emotion Classification Approaches from Physiological Signals

Emotion Recognition Based on Multichannel Physiological Signals with Comprehensive Nonlinear Processing

Contact Info

Product

Resources

About