Analysis of EMG Based Emotion Recognition for Multiple People and Emotions

Mithbavkar, Shraddha A.; Shah, Meet

doi:10.1109/ecbios51820.2021.9510858

Cited by 12 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically integrated with virtual reality training, it allows users to receive real-time feedback on muscle activity, contributing to assisted therapy and muscle training [7]. Moreover, EMG has been employed for gesture and facial expression recognition [8], [9]. It detects subtle muscle changes associated with gestures or emotional states, providing a novel perspective and depth to user experience design and interface control.…”

Section: Electromyography and Electrical Stimulationmentioning

confidence: 99%

Electromyography Acquisition and Intervention in Healthcare for Older Adults: A HCI Scoping Review

Dai,

Wang,

Yao

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

As age advances, the decline in bodily functions and the rise in age-related diseases pose various challenges to the daily lives of the older population. This scoping review discusses the potential of Electromyography and Electrical Stimulation technologies in addressing aging health issues. This review aims to discover potential design opportunities for EMG and ES technologies in promoting healthy aging by searching for answers from the diverse research purposes, target groups and human-computer interactions involved in the 42 selected articles. Through the thematic analysis, we discovered six categories of applications and four core design themes. Based on our findings, a map has been illustrated to provide visual guidelines for future research and design practice. To enhance the overall health and quality of life for older adults, it would be beneficial to concentrate on three interdependent aspects: independent at home, active outdoors, and mental well-being.

show abstract

Section: Electromyography and Electrical Stimulationmentioning

confidence: 99%

Electromyography Acquisition and Intervention in Healthcare for Older Adults: A HCI Scoping Review

Dai,

Wang,

Yao

et al. 2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…For example, Kim et al [ 64 ] explored the use of facial EMG and EEG signals for the classification of the emotions of happiness, surprise, fear, anger, sadness, and disgust. Mithbavkar et al [ 65 ] developed a dataset for emotion recognition based on data collected through electromyograms using dance to stimulate emotional responses such as astonishment, awe, humor, and tranquility. While Wioleta [ 66 ] proposed feature extraction from EMG, blood pressure, and GSR measurements for the detection of the emotional stages of happiness, sadness, anger, hatred, and respect.…”

Section: Emotion Recognitionmentioning

confidence: 99%

Applying Self-Supervised Representation Learning for Emotion Recognition Using Physiological Signals

Quispe

Utyiama

Santos

et al. 2022

Sensors

View full text Add to dashboard Cite

The use of machine learning (ML) techniques in affective computing applications focuses on improving the user experience in emotion recognition. The collection of input data (e.g., physiological signals), together with expert annotations are part of the established standard supervised learning methodology used to train human emotion recognition models. However, these models generally require large amounts of labeled data, which is expensive and impractical in the healthcare context, in which data annotation requires even more expert knowledge. To address this problem, this paper explores the use of the self-supervised learning (SSL) paradigm in the development of emotion recognition methods. This approach makes it possible to learn representations directly from unlabeled signals and subsequently use them to classify affective states. This paper presents the key concepts of emotions and how SSL methods can be applied to recognize affective states. We experimentally analyze and compare self-supervised and fully supervised training of a convolutional neural network designed to recognize emotions. The experimental results using three emotion datasets demonstrate that self-supervised representations can learn widely useful features that improve data efficiency, are widely transferable, are competitive when compared to their fully supervised counterparts, and do not require the data to be labeled for learning.

show abstract

“…Research by using facial EMG has shown that the number of subjects influences the emotion recognition accuracy [ 31 , 32 , 33 ]. In [ 34 ], long short-term memory (LSTM) network has shown not to be influenced by the number of subjects achieving an accuracy from 92.28% for 9 emotions up to 99.09% for 2 emotions.…”

Section: Related Workmentioning

confidence: 99%

Graph Theoretical Analysis of EEG Functional Connectivity Patterns and Fusion with Physiological Signals for Emotion Recognition

Xefteris

Tsanousa

Georgakopoulou

et al. 2022

Sensors

View full text Add to dashboard Cite

Emotion recognition is a key attribute for realizing advances in human–computer interaction, especially when using non-intrusive physiological sensors, such as electroencephalograph (EEG) and electrocardiograph. Although functional connectivity of EEG has been utilized for emotion recognition, the graph theory analysis of EEG connectivity patterns has not been adequately explored. The exploitation of brain network characteristics could provide valuable information regarding emotions, while the combination of EEG and peripheral physiological signals can reveal correlation patterns of human internal state. In this work, a graph theoretical analysis of EEG functional connectivity patterns along with fusion between EEG and peripheral physiological signals for emotion recognition has been proposed. After extracting functional connectivity from EEG signals, both global and local graph theory features are extracted. Those features are concatenated with statistical features from peripheral physiological signals and fed to different classifiers and a Convolutional Neural Network (CNN) for emotion recognition. The average accuracy on the DEAP dataset using CNN was 55.62% and 57.38% for subject-independent valence and arousal classification, respectively, and 83.94% and 83.87% for subject-dependent classification. Those scores went up to 75.44% and 78.77% for subject-independent classification and 88.27% and 90.84% for subject-dependent classification using a feature selection algorithm, exceeding the current state-of-the-art results.

show abstract

Analysis of EMG Based Emotion Recognition for Multiple People and Emotions

Cited by 12 publications

References 10 publications

Electromyography Acquisition and Intervention in Healthcare for Older Adults: A HCI Scoping Review

Electromyography Acquisition and Intervention in Healthcare for Older Adults: A HCI Scoping Review

Applying Self-Supervised Representation Learning for Emotion Recognition Using Physiological Signals

Graph Theoretical Analysis of EEG Functional Connectivity Patterns and Fusion with Physiological Signals for Emotion Recognition

Contact Info

Product

Resources

About