A novel deep-learning based framework for multi-subject emotion recognition

Qiao, Rui; Qing, Chunmei; Zhang, Tong; Xing, Xiaofen; Xu, Xiangmin

doi:10.1109/iccss.2017.8091408

Cited by 38 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Martinez et al trained an efficient deep convolution neural network (CNN) to classify four cognitive states (relaxation, anxiety, excitement and fun) using skin conductance and blood volume pulse signals [ 119 ]. As mentioned in EEG, the authors of [ 23 ] used the Convolutional Neural Network (CNN) for feature abstraction ( Figure 14 b). In the work of [ 120 ], several statistical features were extracted and sent to the CNN and DNN, where the achieved accuracy of 85.83% surpassed those achieved in other papers using DEAP.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Emotion Recognition Using Physiological Signals

Shu

Xie

Yang

et al. 2018

Sensors

Self Cite

651

352

View full text Add to dashboard Cite

Emotion recognition based on physiological signals has been a hot topic and applied in many areas such as safe driving, health care and social security. In this paper, we present a comprehensive review on physiological signal-based emotion recognition, including emotion models, emotion elicitation methods, the published emotional physiological datasets, features, classifiers, and the whole framework for emotion recognition based on the physiological signals. A summary and comparation among the recent studies has been conducted, which reveals the current existing problems and the future work has been discussed.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In the work of [ 23 ], the author proposed a novel model for multi-subject emotion classification. The basic idea is to extract the high-level features through the deep learning model and transform traditional subject-independent recognition tasks into multi-subject recognition tasks.…”

Section: Emotional Relevant Features Of Physiological Signalsmentioning

confidence: 99%

A Review of Emotion Recognition Using Physiological Signals

Shu

Xie

Yang

et al. 2018

Sensors

Self Cite

651

352

View full text Add to dashboard Cite

show abstract

“…V ranged from unpleasant to pleasant, and A ranged from inactive to active. A threshold of 5 is a common choice in this type of analysis and has been used in similar studies previously [ 22 , 23 ]. Therefore, based on A and V, we selected a rating of 5 as the threshold to divided the emotions into four categories: high valence (HAHV), low arousal high valence (LAHV), low arousal low valence (LALV) and high arousal low valence (HALV), as shown in Figure 1 .…”

Section: Methodsmentioning

confidence: 99%

Hemispheric Asymmetry of Functional Brain Networks under Different Emotions Using EEG Data

Cao

Shi

Wang

et al. 2020

Entropy

View full text Add to dashboard Cite

Despite many studies reporting hemispheric asymmetry in the representation and processing of emotions, the essence of the asymmetry remains controversial. Brain network analysis based on electroencephalography (EEG) is a useful biological method to study brain function. Here, EEG data were recorded while participants watched different emotional videos. According to the videos’ emotional categories, the data were divided into four categories: high arousal high valence (HAHV), low arousal high valence (LAHV), low arousal low valence (LALV) and high arousal low valence (HALV). The phase lag index as a connectivity index was calculated in theta (4–7 Hz), alpha (8–13 Hz), beta (14–30 Hz) and gamma (31–45 Hz) bands. Hemispheric networks were constructed for each trial, and graph theory was applied to quantify the hemispheric networks’ topological properties. Statistical analyses showed significant topological differences in the gamma band. The left hemispheric network showed significantly higher clustering coefficient (Cp), global efficiency (Eg) and local efficiency (Eloc) and lower characteristic path length (Lp) under HAHV emotion. The right hemispheric network showed significantly higher Cp and Eloc and lower Lp under HALV emotion. The results showed that the left hemisphere was dominant for HAHV emotion, while the right hemisphere was dominant for HALV emotion. The research revealed the relationship between emotion and hemispheric asymmetry from the perspective of brain networks.

show abstract

“…EDA and blood volume pulse data was used to train a one dimensional CNN (1D CNN) to classify relaxation, anxiety excitement [25] achieving accuracies between 70-75%. Additionally, EEG data was used to train a CNN to infer valence and arousal using channel selection strategy, where the strongest correlated channels generate the training set, achieving 87.27% accuracy, an increase of nearly 20% [26]. Furthermore, 1D CNNs have been used with a transfer learning approach to increase affective model personalisation, achieving 93.9% accuracy when tested with 3 users [27].…”

Section: B Mental Wellbeing Inferencementioning

confidence: 99%

iFidgetCube: Tangible Fidgeting Interfaces (TFIs) to Monitor and Improve Mental Wellbeing

Woodward

Kanjo

2021

IEEE Sensors J.

View full text Add to dashboard Cite

The ability to unobtrusively measure mental wellbeing states using non-invasive sensors has the potential to greatly improve mental wellbeing by alleviating the effects of high stress levels. Multiple sensors, such as electrodermal activity, heart rate and accelerometers, embedded within tangible devices pave the way to continuously and non-invasively monitor wellbeing in real-world environments. On the other hand, fidgeting tools enable repetitive interaction methods that may help to tap into individual's psychological need to feel occupied and engaged; hence potentially reducing stress. In this paper, we present the design, implementation, and deployment of Tangible Fidgeting Interfaces (TFIs) in the form of computerised iFidgetCubes. iFidgetCubes embed non-invasive sensors along with fidgeting mechanisms to aid relaxation and ease restlessness. We take advantage of our labeling techniques at the point of collection to implement multiple subject-independent deep learning classifiers to infer wellbeing. The obtained performance demonstrates that these new forms of tangible interfaces combined with deep learning classifiers have the potential to accurately infer wellbeing in addition to providing fidgeting tools.

show abstract

A novel deep-learning based framework for multi-subject emotion recognition

Cited by 38 publications

References 9 publications

A Review of Emotion Recognition Using Physiological Signals

A Review of Emotion Recognition Using Physiological Signals

Hemispheric Asymmetry of Functional Brain Networks under Different Emotions Using EEG Data

iFidgetCube: Tangible Fidgeting Interfaces (TFIs) to Monitor and Improve Mental Wellbeing

Contact Info

Product

Resources

About