Emotion recognition using effective connectivity and pre-trained convolutional neural networks in EEG signals

Bagherzadeh, Sara; Maghooli, Keivan; Shalbaf, Ahmad; Maghsoudi, Arash

doi:10.1007/s11571-021-09756-0

Cited by 30 publications

(16 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modified from DTF, dDTF estimates the direct causal relationship only between the given pair of channels, and dDTF makes no assumptions about the underlying neural mechanism (Korzeniewska et al, 2003). dDTF has been used for effective connectivity estimation in many neural and cognitive studies (Bagherzadeh et al, 2022; Ghahari et al, 2020; Talebi & Motie Nasrabadi, 2022).…”

Section: Discussionmentioning

confidence: 99%

Enhanced electroencephalography effective connectivity in frontal low‐gamma band correlates of emotional regulation after mindfulness training

Huang

et al. 2023

J of Neuroscience Research

View full text Add to dashboard Cite

Practicing mindfulness, focusing attention on the internal and external experiences occurring in the present moment with open and nonjudgement stance, can lead to the development of emotional regulation skills. Yet, the effective connectivity of brain regions during mindfulness has been largely unexplored. Studies have shown that mindfulness practice promotes functional connectivity in practitioners, potentially due to improved emotional regulation abilities and increased connectivity in the lateral prefrontal areas. To examine the changes in effective connectivity due to mindfulness training, we analyzed electroencephalogram (EEG) signals taken before and after mindfulness training, focusing on training‐related effective connectivity changes in the frontal area. The mindfulness training group participated in an 8‐week mindfulness‐based stress reduction (MBSR) program. The control group did not take part. Regardless of the specific mindfulness practice used, low‐gamma band effective connectivity increased globally after the mindfulness training. High‐beta band effective connectivity increased globally only during Breathing. Moreover, relatively higher outgoing effective connectivity strength was seen during Resting and Breathing and Body‐scan. By analyzing the changes in outgoing and incoming connectivity edges, both F7 and F8 exhibited strong parietal connectivity during Resting and Breathing. Multiple regression analysis revealed that the changes in effective connectivity of the right lateral prefrontal area predicted mindfulness and emotional regulation abilities. These results partially support the theory that the lateral prefrontal areas have top‐down modulatory control, as these areas have high outflow effective connectivity, implying that mindfulness training cultivates better emotional regulation.

show abstract

Section: Discussionmentioning

confidence: 99%

Enhanced electroencephalography effective connectivity in frontal low‐gamma band correlates of emotional regulation after mindfulness training

Huang

et al. 2023

J of Neuroscience Research

View full text Add to dashboard Cite

show abstract

“…This can be particularly useful in studying cognitive processes that are associated with specific frequency ranges. In addition, dDTF has proven efficacy in neuroscience investigations 31 , 32 37 , 38 .…”

Section: Methodsmentioning

confidence: 99%

“…However, there is still no single robust method that can accurately assess the MWL. To tackle this issue, we are exploring a brain connectivity-based approach that has shown promising results in various domains 31 – 33 . So, we will use neural activity flow based on the direct directed transfer function (dDTF) to explore different regions and networks that distinguish between different levels of MWL.…”

Section: Introductionmentioning

confidence: 99%

Classification of mental workload using brain connectivity and machine learning on electroencephalogram data

Safari,

Shalbaf,

Bagherzadeh

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Mental workload refers to the cognitive effort required to perform tasks, and it is an important factor in various fields, including system design, clinical medicine, and industrial applications. In this paper, we propose innovative methods to assess mental workload from EEG data that use effective brain connectivity for the purpose of extracting features, a hierarchical feature selection algorithm to select the most significant features, and finally machine learning models. We have used the Simultaneous Task EEG Workload (STEW) dataset, an open-access collection of raw EEG data from 48 subjects. We extracted brain-effective connectivities by the direct directed transfer function and then selected the top 30 connectivities for each standard frequency band. Then we applied three feature selection algorithms (forward feature selection, Relief-F, and minimum-redundancy-maximum-relevance) on the top 150 features from all frequencies. Finally, we applied sevenfold cross-validation on four machine learning models (support vector machine (SVM), linear discriminant analysis, random forest, and decision tree). The results revealed that SVM as the machine learning model and forward feature selection as the feature selection method work better than others and could classify the mental workload levels with accuracy equal to 89.53% (± 1.36).

show abstract

“…A common practice in these few EEG studies is to apply an extra feature engineering step before the ResNet model. For example, the direct Directed Transfer Function (dDTF) method was used to represent EEG as images before the ResNet model [23]. In another EEG study, short-time Fourier transform (STFT) was applied to EEG data first to yield the 3D input for the ResNet model.…”

Section: B Application Of Resnet On Time Series Datamentioning

confidence: 99%

Deep Learning With Convolutional Neural Networks for Motor Brain-Computer Interfaces Based on Stereo-Electroencephalography (SEEG)

Jiang

et al. 2023

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Deep learning based on convolutional neural networks (CNN) has achieved success in brain-computer interfaces (BCIs) using scalp electroencephalography (EEG). However, the interpretation of the so-called 'black box' method and its application in stereo-electroencephalography (SEEG)-based BCIs remain largely unknown. Therefore, in this paper, an evaluation is performed on the decoding performance of deep learning methods on SEEG signals. Methods: Thirty epilepsy patients were recruited, and a paradigm including five hand and forearm motion types was designed. Six methods, including filter bank common spatial pattern (FBCSP) and five deep learning methods (EEGNet, shallow and deep CNN, ResNet, and a deep CNN variant named STSCNN), were used to classify the SEEG data. Various experiments were conducted to investigate the effect of windowing, model structure, and the decoding process of ResNet and STSCNN. Results: The average classification accuracy for EEGNet, FBCSP, shallow CNN, deep CNN, STSCNN, and ResNet were 35 ± 6.1%, 38 ± 4.9%, 60 ± 3.9%, 60 ± 3.3%, 61 ± 3.2%, and 63 ± 3.1% respectively. Further analysis of the proposed method demonstrated clear separability between different classes in the spectral domain. Conclusion: ResNet and STSCNN achieved the first-and second-highest decoding accuracy, respectively. The STSCNN demonstrated that an extra spatial convolution layer was beneficial, and the decoding process can be partially interpreted from spatial and spectral perspectives. Significance: This study is the first to investigate the performance of deep learning on SEEG signals.In addition, this paper demonstrated that the so-called 'black-box' method can be partially interpreted.Index Terms-stereo-electroencephalography (SEEG), brain-computer interface (BCI), forearm and hand motion, deep learning, convolutional neural networks (CNN)

show abstract

Emotion recognition using effective connectivity and pre-trained convolutional neural networks in EEG signals

Cited by 30 publications

References 65 publications

Enhanced electroencephalography effective connectivity in frontal low‐gamma band correlates of emotional regulation after mindfulness training

Enhanced electroencephalography effective connectivity in frontal low‐gamma band correlates of emotional regulation after mindfulness training

Classification of mental workload using brain connectivity and machine learning on electroencephalogram data

Deep Learning With Convolutional Neural Networks for Motor Brain-Computer Interfaces Based on Stereo-Electroencephalography (SEEG)

Contact Info

Product

Resources

About