From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification

By Johannes Wagner, Jonghwa Kim, Elisabeth André. IEEE International Conference on Multimedia and Expo, 2005

551 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, Social Psychology

View Paper: https://www.semanticscholar.org/paper/6fe7117a6bc1bf3ee103e74df5de0f387a10cc1d

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 Social Psychology

Citations in the corpus

Recognising realistic emotions and affect in speech: State of the art and lessons learnt from the first challenge (2011, background): “…dealing with analysis of biosignals, such as heart rate, skin conductivity, or brain-waves are found (e.g., de Gelder et al., 1999; de Gelder and Vroomen, 2000; Picard et al., 2001; Kim et al., 2004, 2005; Nasoz et al., 2004; Takahashi, 2004; Wagner et al., 2005), also in combination with speech.”
EEG-based classification of positive and negative affective states (2014, methodology): “Interestingly, these two studies used continuous stimuli such as music [28] and movies [36] to elicit”
Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011 (2012, methodology): “15 %, 6 emotions (unknown dataset) Wang et al. (2008) ∼63 % in a corpus that includes deceptive and non-deceptive speech Graciarena et al.”
DREAMER: A Database for Emotion Recognition Through EEG and ECG Signals From Wireless Low-cost Off-the-Shelf Devices (2018, background): “signals as baseline signals have been proven to allow the removal of daily dependencies when recording physiological data [12], [26].”
Emotional speech recognition: Resources, features, and methods (2006, background): “There is a direct evidence that the aforementioned signals are related more to the arousal information of speech than to the valence of the emotion, i.e. the positive or negative character of the emotions (Wagner et al., 2005).”
Short-term emotion assessment in a recall paradigm (2009, background): “Thanks to the works of Wagner et al. (2005) and Picard et al. (2001), it is possible to compare results on valence-arousal classes to those obtained on basic emotions classes in an intra-study framework.”
Continuous Prediction of Spontaneous Affect from Multiple Cues and Modalities in Valence-Arousal Space (2011, background): “For instance, Wagner et al. [62] analyzes four emotions, each belonging to one quadrant of the V-A emotion space: high arousal positive valence (joy), high arousal negative valence (anger), low arousal positive valence (relief), and low arousal negative valence (sadness).”
Affect Detection: An Interdisciplinary Review of Models, Methods, and Their Applications (2010, methodology): “This approach is more commonly used in multimodal HCI and has been used in affective computing, for example, in the Augsburg Biosignal Toolbox [113].”
Human Emotion Recognition: Review of Sensors and Methods (2020, methodology): “Present fully implemented emotion recognition system including data analysis and classification Joy, anger, pleasure, sadness EMG, ECG, GSR, respiration rate Four-channel EMG, ECG, GSR, respiration rate bio sensor [155]”
Emotional state classification from EEG data using machine learning approach (2014, unknown): “…EEGデータセットの実験結果から，我々はパワースペクトルの特徴は他の 2種類より優れていることを示す．また，線形動的システムに基づく特徴平滑化方法は感情分類精度を大きく向上させることを示し，感情変化の軌跡はマニホールド学習の学習対象に依存しない特徴量を低下させることで，可視化を可能とした． 5 キーワード Emotion classification, Electroencephalograph, Brain?computer interface, Feature reduction, Support vector machine, Manifold learning 6 参考文献”