Emotion recognition based on physiological changes in music listening

By Jonghwa Kim, Elisabeth André. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

1,079 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0e32ff526eac54a048aca75d08c750a37c8fc491

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

DEAP: A Database for Emotion Analysis ;Using Physiological Signals (2012, background): “There has been a large number of published works in the domain of emotion recognition from physiological signals [16], [20], [21], [22], [23], [24].”
Comparing Recognition Performance and Robustness of Multimodal Deep Learning Models for Multimodal Emotion Recognition (2021, background): “Moreover, other physiological signals, such as electromyogram, electrocardiogram (ECG), skin conductivity, respiration, and eye movement signals, are also used to recognize emotions [18], [19].”
Identifying Stable Patterns over Time for Emotion Recognition from EEG (2016, background): “In addition, we cannot obtain the ‘ground truth’ behind human emotions in theory, that is, the true label for an EEG corresponding to different emotional states, because emotion is considered as a function of time, context, space, language, culture, and races [5].”
Categorical and dimensional affect analysis in continuous input: Current trends and future directions (2013, methodology): “In accordance with this, Kim and André proposed a novel scheme of emotionspecific multilevel dichotomous classification (EMDC) using the property of the dichotomous categorization in the 2D emotion model and the fact that arousal classification yields a higher correct classification ratio than valen”
Multi-source domain adaptation and its application to early detection of fatigue (2011, methodology): “There was some classification work dealing with physiological signals using neural networks [17] and linear discriminant analysis [15]; they achieved moderate generalization performance across subjects.”
Multimodal fusion framework: A multiresolution approach for emotion classification and recognition from physiological signals (2014, background): “Kim and Andre (2008) reported GSR a very reliable physiological measure of human arousal.”
AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups (2017, methodology): “GSR: Following the method of Kim [57], the skin conductance (SC) was calculated from the GSR and then the SC signal was normalized.”
Emotion in Human-Computer Interaction (2012, neutral): “[18-20]).”
A Two-Stage Weighting Framework for Multi-Source Domain Adaptation (2011, positive): “As a part of the future work we plan to extend the proposed multi-source framework to applications involving other types of physiological signals for developing generalized models across subjects for emotion and health monitoring [27, 28].”
EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities (2020, methodology): “…tree, Bayesian networks, support vector machines (SVM) [133, 135], canonical correlation analysis (CCA) [136], artiﬁcial neural network (ANN) [137], linear discriminant analysis (LDA) [138], and Marquardt back-propagation (MBP) [139] were used by researchers to classify the diﬀerent emotions.”
Classification of human emotion from EEG using discrete wavelet transform (2010, background): “Emotions can be induced by one of the following ways: 1) visual (images/pictures) [12]; 2) audio-visual (film clips/video clips) [13,16]; 3) recalling of past emotional events [8]; 4) audio (songs/sounds) [17].”
Physiological Signals-based Emotion Recognition via High-order Correlation Learning (2019, methodology): “…SVM, CNN, and DNN. Electromyogram, electrocardiogram, skin conductivity, and respiration changes are adopted as physiological signals in Reference [17], and features including time/frequency, entropy, geometric analysis, subband spectra, and multiscale entropy were extracted to investigate the…”
Introducing WESAD, a Multimodal Dataset for Wearable Stress and Affect Detection (2018, methodology): “In order to detect emotions in response to music, Kim et al. [10] used ECG, RESP, EDA, and electromyogram (EMG) data.”
Emotion recognition using wireless signals (2016, methodology): “Existing approaches for inferring a person’s emotions either rely on audiovisual cues, such as images and audio clips [64, 30, 54], or require the person to wear physiological sensors like an ECG monitor [28, 48, 34, 8].”
Continuous inference of psychological stress from sensory measurements collected in the natural environment (2011, background): “Some recent work has tried to address between-person differences in physiology using a personalized classifier of emotion for use in controlled environments [40, 25].”
A Multimodal Database for Affect Recognition and Implicit Tagging (2012, methodology): “In total, 102 features were extracted from peripheral physiological responses based on the proposed features in the literature [34], [33], [30].”
ASCERTAIN: Emotion and Personality Recognition Using Commercial Sensors (2018, methodology): “We also extracted power spectral density (PSD) in low frequency bands as in [11], [24].”
Emotion representation, analysis and synthesis in continuous space: A survey (2011, methodology): “…of emotion-specific multilevel dichotomous classification (EMDC) using the property of the dichotomous categorization in the 2D emotion model and the fact that arousal classification yields a higher correct classification ratio than valence classification (or direct multiclass classification) [55].”
EEG-Based Emotion Recognition in Music Listening (2010, background): “As compared with audio- and/or visual-based methods, the responses of biosignals tend to provide more detailed and complex information as an indicator for estimating emotional states [3].”