scholarly journals The Design of CNN Architectures for Optimal Six Basic Emotion Classification Using Multiple Physiological Signals

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 866 ◽  
Author(s):  
SeungJun Oh ◽  
Jun-Young Lee ◽  
Dong Keun Kim
Keyword(s):  
Emotion Recognition ◽  
Identification Accuracy ◽  
Physiological Signals ◽  
Dominant Factor ◽  
Basic Emotion ◽  
Emotion Classification ◽  
Physiological Signal ◽  
Proposed Model ◽  
Respiration Sensor ◽  
Signal Combination

This study aimed to design an optimal emotion recognition method using multiple physiological signal parameters acquired by bio-signal sensors for improving the accuracy of classifying individual emotional responses. Multiple physiological signals such as respiration (RSP) and heart rate variability (HRV) were acquired in an experiment from 53 participants when six basic emotion states were induced. Two RSP parameters were acquired from a chest-band respiration sensor, and five HRV parameters were acquired from a finger-clip blood volume pulse (BVP) sensor. A newly designed deep-learning model based on a convolutional neural network (CNN) was adopted for detecting the identification accuracy of individual emotions. Additionally, the signal combination of the acquired parameters was proposed to obtain high classification accuracy. Furthermore, a dominant factor influencing the accuracy was found by comparing the relativeness of the parameters, providing a basis for supporting the results of emotion classification. The users of this proposed model will soon be able to improve the emotion recognition model further based on CNN using multimodal physiological signals and their sensors.

scholarly journals EEG-based human emotion recognition using entropy as a feature extraction measure

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Pragati Patel ◽  
Raghunandan R ◽  
Ramesh Naidu Annavarapu
Keyword(s):  
Emotion Recognition ◽  
Emotional State ◽  
Computer Interface ◽  
Eeg Signal ◽  
Emotion Classification ◽  
Emotion Identification ◽  
Physiological Signal ◽  
Wide Range ◽  
Electrical Activities ◽  
The Brain

AbstractMany studies on brain–computer interface (BCI) have sought to understand the emotional state of the user to provide a reliable link between humans and machines. Advanced neuroimaging methods like electroencephalography (EEG) have enabled us to replicate and understand a wide range of human emotions more precisely. This physiological signal, i.e., EEG-based method is in stark comparison to traditional non-physiological signal-based methods and has been shown to perform better. EEG closely measures the electrical activities of the brain (a nonlinear system) and hence entropy proves to be an efficient feature in extracting meaningful information from raw brain waves. This review aims to give a brief summary of various entropy-based methods used for emotion classification hence providing insights into EEG-based emotion recognition. This study also reviews the current and future trends and discusses how emotion identification using entropy as a measure to extract features, can accomplish enhanced identification when using EEG signal.

scholarly journals An Emotion Recognition Based on Physiological Signals

2019 ◽  
Vol 8 (9S) ◽  
pp. 335-341
Keyword(s):  
Emotion Recognition ◽  
Pulse Signal ◽  
Physiological Signals ◽  
Computer Interface ◽  
Human Computer Interface ◽  
Emotion Detection ◽  
Extraction Techniques ◽  
Emotion Elicitation ◽  
Physiological Signal ◽  
Plausible Mechanism

Emotion recognition is alluring considerable interest among the researchers. Emotions are discovered by facial, speech, gesture, posture and physiological signals. Physiological signals are a plausible mechanism to recognize emotion using human-computer interaction. The objective of this paper is to put forth the recognition of emotions using physiological signals. Various emotion elicitation protocols, feature extraction techniques, classification methods that aim at recognizing emotions from physiological signals are discussed here. Wrist Pulse Signal is also discussed to fill the lacunae of the other physiological signal for emotion detection. Working on basic as well as non-basic human emotion and human-computer interface will make the system robust.

Emotion Recognition Based on Chaos Characteristics of Physiological Signals

2013 ◽  
Vol 380-384 ◽  
pp. 3750-3753 ◽  
Author(s):  
Chun Yan Nie ◽  
Rui Li ◽  
Ju Wang
Keyword(s):  
Nonlinear Dynamics ◽  
Emotion Recognition ◽  
Classical Theory ◽  
Chaos Theory ◽  
Biomedical Engineering ◽  
Recognition System ◽  
Physiological Signals ◽  
Signal Recognition ◽  
Physiological Signal ◽  
Linear Signal

Changes of physiological signals are affected by human emotions, but also the emotional fluctuations are reflected by the body's variation of physiological signal's feature. Physiological signal is a non-linear signal ,nonlinear dynamics and biomedical engineering ,which based on chaos theory, providing us a new method for studying on the parameters of these complex physiological signals which can hardly described by the classical theory. This paper shows physiological emotion signal recognition system based on the chaotic characteristics, and than describes some current applications of chaotic characteristics for multiple physiological signals on emotional recognition.

Emotion recognition from physiological signals and video games to detect personality traits

2020 ◽  
pp. 1-9
Author(s):  
M. Callejas-Cuervo ◽  
L.A. Martínez-Tejada ◽  
A.C. Alarcón-Aldana
Keyword(s):  
Emotion Recognition ◽  
Galvanic Skin Response ◽  
Skin Conductance Response ◽  
Statistical Data ◽  
Inverse Correlation ◽  
Physiological Signals ◽  
Physiological Signal ◽  
First Approximation ◽  
Skin Response ◽  
Electrocardiogram Ecg

This paper presents a system that allows for the identification of two values: arousal and valence, which represent the degree of stimulation in a subject, using Russell’s model of affect as a reference. To identify emotions, a step-by-step structure is used, which, based on statistical data from physiological signal metrics, generates the representative arousal value (direct correlation); from the PANAS questionnaire, the system generates the valence value (inverse correlation), as a first approximation to the techniques of emotion recognition without the use of artificial intelligence. The system gathers information concerning arousal activity from a subject using the following metrics: beats per minute (BPM), heart rate variability (HRV), the number of galvanic skin response (GSR) peaks in the skin conductance response (SCR) and forearm contraction time, using three physiological signals (Electrocardiogram - ECG, Galvanic Skin Response - GSR, Electromyography - EMG).

Application of Chaos Characteristics about Physiological Signals in Emotion Recognition Based on Approximate Entropy

2014 ◽  
Vol 543-547 ◽  
pp. 2539-2542
Author(s):  
Chun Yan Nie ◽  
Hai Xin Sun ◽  
Ju Wang
Keyword(s):  
Emotion Recognition ◽  
Frequency Domain ◽  
Affective Computing ◽  
System Modeling ◽  
Approximate Entropy ◽  
Physiological Signals ◽  
Ecg Signal ◽  
Human Beings ◽  
Physiological Signal ◽  
Study Results

Emotion recognition is an important part in affective computing. It is the basis of building a harmonious man-machine environment. Respiratory (RSP) signal and electrocardiogram (ECG) signal are one of the main study objects in the emotion recognition based on physiological signal. The variations of the RSP signal and the ECG signal is one of the true performances of the human emotions. Through the analyses of the RSP signal and the ECG signal, we can recognize the inner emotion variations of human beings. This lays the foundation for the system modeling of emotion recognition. In this paper, we study the approximate entropy extraction of the physiological signals and analyze the chaotic characteristics and frequency domain characteristics of the approximate entropy under different emotions. The study results show that the different emotion status is corresponding to different approximate entropy and different variations in the frequency domain.

scholarly journals AdCOFE: Advanced Contextual Feature Extraction in conversations for emotion classification

2021 ◽  
Vol 7 ◽  
pp. e786
Author(s):  
Vaibhav Bhat ◽  
Anita Yadav ◽  
Sonal Yadav ◽  
Dhivya Chandrasekaran ◽  
Vijay Mago
Keyword(s):  
Feature Extraction ◽  
Emotion Recognition ◽  
Unique Feature ◽  
Contextual Information ◽  
Online Support ◽  
Emotion Classification ◽  
Emotional Information ◽  
Proposed Model ◽  
Contextual Feature ◽  
Knowledge Graphs

Emotion recognition in conversations is an important step in various virtual chatbots which require opinion-based feedback, like in social media threads, online support, and many more applications. Current emotion recognition in conversations models face issues like: (a) loss of contextual information in between two dialogues of a conversation, (b) failure to give appropriate importance to significant tokens in each utterance, (c) inability to pass on the emotional information from previous utterances. The proposed model of Advanced Contextual Feature Extraction (AdCOFE) addresses these issues by performing unique feature extraction using knowledge graphs, sentiment lexicons and phrases of natural language at all levels (word and position embedding) of the utterances. Experiments on emotion recognition in conversations datasets show that AdCOFE is beneficial in capturing emotions in conversations.

scholarly journals EEG data augmentation for emotion recognition with a multiple generator conditional Wasserstein GAN

2021 ◽  
Author(s):  
Aiming Zhang ◽  
Lei Su ◽  
Yin Zhang ◽  
Yunfa Fu ◽  
Liping Wu ◽  
...  
Keyword(s):  
Emotion Recognition ◽  
Data Augmentation ◽  
Real Data ◽  
Training Data ◽  
Quality Data ◽  
Emotion Classification ◽  
High Quality ◽  
Proposed Model ◽  
Eeg Data ◽  
Substantial Progress

AbstractEEG-based emotion recognition has attracted substantial attention from researchers due to its extensive application prospects, and substantial progress has been made in feature extraction and classification modelling from EEG data. However, insufficient high-quality training data are available for building EEG-based emotion recognition models via machine learning or deep learning methods. The artificial generation of high-quality data is an effective approach for overcoming this problem. In this paper, a multi-generator conditional Wasserstein GAN method is proposed for the generation of high-quality artificial that covers a more comprehensive distribution of real data through the use of various generators. Experimental results demonstrate that the artificial data that are generated by the proposed model can effectively improve the performance of emotion classification models that are based on EEG.

scholarly journals Emotion Recognition Based on Weighted Fusion Strategy of Multichannel Physiological Signals

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Wei Wei ◽  
Qingxuan Jia ◽  
Yongli Feng ◽  
Gang Chen
Keyword(s):  
Emotion Recognition ◽  
Recognition Rate ◽  
Recognition System ◽  
Physiological Signals ◽  
Support Vector ◽  
Svm Classifier ◽  
Fusion Strategy ◽  
Pattern Recognition Problem ◽  
Physiological Signal ◽  
Decision Level

Emotion recognition is an important pattern recognition problem that has inspired researchers for several areas. Various data from humans for emotion recognition have been developed, including visual, audio, and physiological signals data. This paper proposes a decision-level weight fusion strategy for emotion recognition in multichannel physiological signals. Firstly, we selected four kinds of physiological signals, including Electroencephalography (EEG), Electrocardiogram (ECG), Respiration Amplitude (RA), and Galvanic Skin Response (GSR). And various analysis domains have been used in physiological emotion features extraction. Secondly, we adopt feedback strategy for weight definition, according to recognition rate of each emotion of each physiological signal based on Support Vector Machine (SVM) classifier independently. Finally, we introduce weight in decision level by linear fusing weight matrix with classification result of each SVM classifier. The experiments on the MAHNOB-HCI database show the highest accuracy. The results also provide evidence and suggest a way for further developing a more specialized emotion recognition system based on multichannel data using weight fusion strategy.

scholarly journals Emotion recognition techniques using physiological signals and video games –Systematic review–

2017 ◽  
Vol 26 (46) ◽  
Author(s):  
Mauro Callejas-Cuervo ◽  
Laura Alejandra Martínez-Tejada ◽  
Andrea Catherine Alarcón-Aldana
Keyword(s):  
Systematic Review ◽  
Video Games ◽  
Emotion Recognition ◽  
Emotional Reactions ◽  
Physiological Signals ◽  
Multimedia Tools ◽  
Physiological Signal ◽  
Important Approach ◽  
The Individual ◽  
Education Psychology

Emotion recognition systems from physiological signals are innovative techniques that allow studying the behavior and reaction of an individual when exposed to information that may evoke emotional reactions through multimedia tools, for example, video games. This type of approach is used to identify the behavior of an individual in different fields, such as medicine, education, psychology, etc., in order to assess the effect that the content has on the individual that is interacting with it. This article shows a systematic review of articles that report studies on emotion recognition with physiological signals and video games, between January 2010 and April 2016. We searched in eight databases, and found 15 articles that met the selection criteria. With this systematic review, we found that the use of video games as emotion stimulation tools has become an innovative field of study, due to their potential to involve stories and multimedia tools that can interact directly with the person in fields like rehabilitation. We detected clear examples where video games and physiological signal measurement became an important approach in rehabilitation processes, for example, in Posttraumatic Stress Disorder (PTSD) treatments.

Sign in / Sign up

Export Citation Format

Share Document