Survey of emotion recognition methods using EEG information

Yu, Chaofei; Wang, Mei

doi:10.1016/j.cogr.2022.06.001

Cited by 21 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 5 demonstrates the comparison of the accuracy of emotion classifiers with the accuracy of the SAETM. KNN (K-nearest neighbour classifier), BN (naive Bayesian classifier), and SVM (support vector machines) are selected for the reason that these classifiers are known as widely used classifiers in emotion recognition field using EEG information [ 23 ].…”

Section: Resultsmentioning

confidence: 99%

“…Mean, standard deviation, and zero-crossing rate are examined as statistical features [ 6 ] and signal complexity is measured by entropy [ 1 ]. The fractal dimension is used for measuring the complexity and irregularity of the signal [ 23 ]. The correlation dimension shows the relationship between the signal and itself, which extracts repetitive and periodic patterns of the signal [ 24 ] that these features were extracted from the filtered signal.…”

Section: Methodsmentioning

confidence: 99%

“…The extracted features were normalized to the baseline signal in the range of zero and one. Table 1 lists the features extracted in this study based on previous studies [ 23 ].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Extracting a Novel Emotional EEG Topographic Map Based on a Stacked Autoencoder Network

Vafaei

Rahatabad

Setarehdan

et al. 2023

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Emotion recognition based on brain signals has increasingly become attractive to evaluate human’s internal emotional states. Conventional emotion recognition studies focus on developing machine learning and classifiers. However, most of these methods do not provide information on the involvement of different areas of the brain in emotions. Brain mapping is considered as one of the most distinguishing methods of showing the involvement of different areas of the brain in performing an activity. Most mapping techniques rely on projection and visualization of only one of the electroencephalogram (EEG) subband features onto brain regions. The present study aims to develop a new EEG-based brain mapping, which combines several features to provide more complete and useful information on a single map instead of common maps. In this study, the optimal combination of EEG features for each channel was extracted using a stacked autoencoder (SAE) network and visualizing a topographic map. Based on the research hypothesis, autoencoders can extract optimal features for quantitative EEG (QEEG) brain mapping. The DEAP EEG database was employed to extract topographic maps. The accuracy of image classifiers using the convolutional neural network (CNN) was used as a criterion for evaluating the distinction of the obtained maps from a stacked autoencoder topographic map (SAETM) method for different emotions. The average classification accuracy was obtained 0.8173 and 0.8037 in the valence and arousal dimensions, respectively. The extracted maps were also ranked by a team of experts compared to common maps. The results of quantitative and qualitative evaluation showed that the obtained map by SAETM has more information than conventional maps.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Extracting a Novel Emotional EEG Topographic Map Based on a Stacked Autoencoder Network

Vafaei

Rahatabad

Setarehdan

et al. 2023

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Brainwaves are an internal scientific indicator of mood changes [ 49 ]; α waves are called ‘relaxing waves’ and ‘creative waves’ and are related to the active activity of the brain [ 50 ]; when the energy released by α waves is strong, this represents the brain being in a heightened state of learning and thinking. β waves are associated with concentration; when beta waves emit higher energy, they represent a positive increase in attention [ 51 ].…”

Section: Methodsmentioning

confidence: 99%

Physiological Effects of a Garden Plant Smellscape from the Perspective of Perceptual Interaction

Zhang

Guo

Zhang

et al. 2023

IJERPH

View full text Add to dashboard Cite

The purpose of this study was to investigate the physiological recovery effects of olfactory, visual and olfactory–visual stimuli associated with garden plants. In a randomized controlled study design, ninety-five Chinese university students were randomly selected to be exposed to stimulus materials, namely the odor of Osmanthus fragrans and a corresponding panoramic image of a landscape featuring the plant. Physiological indexes were measured by the VISHEEW multiparameter biofeedback instrument and a NeuroSky EEG tester in a virtual simulation laboratory. The results showed the following: (1) In the olfactory stimulation group, from before to during exposure to the stimuli, the subjects’ diastolic blood pressure (DBP) (ΔDBP = 4.37 ± 1.69 mmHg, p < 0.05) and pulse pressure (PP) values increased (ΔPP = −4.56 ± 1.24 mmHg, p < 0.05), while their pulse (p) values decreased (ΔP = −2.34 ± 1.16 bmp, p < 0.05) significantly. When compared to the control group, only the amplitudes of α and β brainwaves increased significantly (Δα = 0.37 ± 2.09 µV, Δβ = 0.34 ± 1.01 µV, p < 0.05). (2) In the visual stimulation group, the amplitudes of skin conductance (SC) (ΔSC = 0.19 ± 0.01 µΩ, p < 0.05), α brainwaves (Δα = 6.2 ± 2.26 µV, p < 0.05) and β brainwaves (Δβ = 5.51 ± 1.7 µV, p < 0.05) all increased significantly relative to the control group. (3) In the olfactory–visual stimulus group, DBP (ΔDBP = 3.26 ± 0.45 mmHg, p < 0.05) values increased, and PP values decreased (ΔPP = −3.48 ± 0.33 bmp, p < 0.05) significantly from before to during exposure to the stimuli. The amplitudes of SC (ΔSC = 0.45 ± 0.34 µΩ, p < 0.05), α brainwaves (Δα = 2.28 ± 1.74 µV, p < 0.05) and β brainwaves (Δβ = 1.4 ± 0.52 µV, p < 0.05) all increased significantly relative to the control group. The results of this study show that the interaction of olfactory and visual stimuli associated with a garden plant odor landscape was able to relax and refresh the body to a certain extent, and this physiological health effect was greater with regards to the integrated response of the autonomic nervous system and central nervous system than the effect of only smelling or viewing the stimuli. In the planning and designing of plant smellscapes in garden green space, it should be ensured that plant odors and corresponding landscapes are present at the same time in order to ensure the best health effect.

show abstract

“…Although emotions are often conveyed through facial expressions, vocal tones, and body language, a more intricate layer of emo-tional manifestation lies embedded within the neural activity of the brain. EEG, a non-invasive methodology for tracking neural electrical activity, pro-vides a distinctive lens into this concealed realm of emotions [3]. In actuality, the neurological underpinning of emotion consists of intricate and dynamic brain activity patterns that are challenging to interpret using just standard behavioural analysis [4].…”

Section: Introductionmentioning

confidence: 99%

Integrated Modeling for In-Depth EEG Based Emotional State Analysis via Convolutional-Transformer Fusion

Ali,

Kang,

Himral

2023

Preprint

View full text Add to dashboard Cite

This study introduces a hybrid model designed for the predic- tion of emotional states derived from electroencephalogram (EEG) data, employing an amalgamation of convolutional and trans- former layers. The architectural framework of the model is metic- ulously structured to facilitate concurrent assimilation of local pat- terns and long-range dependencies inherent in EEG data, thereby augmenting its discernment of nuanced emotional experiences. The investigation presented herein undertakes a comprehensive explo- ration of the fusion technique, with a primary focus on dis- cerning three elemental emotional dimensions: Arousal, Valence, and Dominance, in addition to their concurrent combinations. The research methodology encompasses an in-depth evaluation of the model’s performance across these diverse emotional states, encompassing the intricate task of simultaneous Valence-Arousal (VA) prediction. Furthermore, the study extends its purview to encompass the intricate Valence-Arousal-Dominance (VAD) space, thereby providing a thorough analysis of the model’s efficacy. To articulate the model’s discriminative efficacy, this study meticu- lously presents the detailed F1 scores corresponding to each emotional state classification: Arousal (96.8), Valence (97.3), Valence-Arousal (VA) simultaneously (95.6), and Valence-Arousal-Dominance simultaneously (94.9). These scores serve as a testament to the model’s robust per- formance across diverse emotional dimensions. Importantly, to fortify the credibility of our findings, rigorous experimentation has been con- ducted on the DEAP dataset, unveiling noteworthy results even in scenarios involving simultaneous recognition of multiple emotional states.

show abstract

Survey of emotion recognition methods using EEG information

Cited by 21 publications

References 50 publications

Extracting a Novel Emotional EEG Topographic Map Based on a Stacked Autoencoder Network

Extracting a Novel Emotional EEG Topographic Map Based on a Stacked Autoencoder Network

Physiological Effects of a Garden Plant Smellscape from the Perspective of Perceptual Interaction

Integrated Modeling for In-Depth EEG Based Emotional State Analysis via Convolutional-Transformer Fusion

Contact Info

Product

Resources

About