EEG-Based BCI Emotion Recognition: A Survey

CATM: A Multi-Feature-Based Cross-Scale Attentional Convolutional EEG Emotion Recognition Model

Aiming at the problem that existing emotion recognition methods fail to make full use of the information in the time, frequency, and spatial domains in the EEG signals, which leads to the low accuracy of EEG emotion classification, this paper proposes a multi-feature, multi-frequency band-based cross-scale attention convolutional model (CATM). The model is mainly composed of a cross-scale attention module, a frequency-space attention module, a feature transition module, a temporal feature extraction module, and a depth classification module. First, the cross-scale attentional convolution module extracts spatial features at different scales for the preprocessed EEG signals; then, the frequency-space attention module assigns higher weights to important channels and spatial locations; next, the temporal feature extraction module extracts temporal features of the EEG signals; and, finally, the depth classification module categorizes the EEG signals into emotions. We evaluated the proposed method on the DEAP dataset with accuracies of 99.70% and 99.74% in the valence and arousal binary classification experiments, respectively; the accuracy in the valence-arousal four-classification experiment was 97.27%. In addition, considering the application of fewer channels, we also conducted 5-channel experiments, and the binary classification accuracies of valence and arousal were 97.96% and 98.11%, respectively. The valence-arousal four-classification accuracy was 92.86%. The experimental results show that the method proposed in this paper exhibits better results compared to other recent methods, and also achieves better results in few-channel experiments.

Insights from EEG analysis of evoked memory recalls using deep learning for emotion charting

Affect recognition in a real-world, less constrained environment is the principal prerequisite of the industrial-level usefulness of this technology. Monitoring the psychological profile using smart, wearable electroencephalogram (EEG) sensors during daily activities without external stimuli, such as memory-induced emotions, is a challenging research gap in emotion recognition. This paper proposed a deep learning framework for improved memory-induced emotion recognition leveraging a combination of 1D-CNN and LSTM as feature extractors integrated with an Extreme Learning Machine (ELM) classifier. The proposed deep learning architecture, combined with the EEG preprocessing, such as the removal of the average baseline signal from each sample and extraction of EEG rhythms (delta, theta, alpha, beta, and gamma), aims to capture repetitive and continuous patterns for memory-induced emotion recognition, underexplored with deep learning techniques. This work has analyzed EEG signals using a wearable, ultra-mobile sports cap while recalling autobiographical emotional memories evoked by affect-denoting words, with self-annotation on the scale of valence and arousal. With extensive experimentation using the same dataset, the proposed framework empirically outperforms existing techniques for the emerging area of memory-induced emotion recognition with an accuracy of 65.6%. The EEG rhythms analysis, such as delta, theta, alpha, beta, and gamma, achieved 65.5%, 52.1%, 65.1%, 64.6%, and 65.0% accuracies for classification with four quadrants of valence and arousal. These results underscore the significant advancement achieved by our proposed method for the real-world environment of memory-induced emotion recognition.

Deep learning classification of EEG-based BCI monitoring of the attempted arm and hand movements

OBJECTIVES

The primary objective of this research is to improve the average classification performance for specific movements in patients with cervical spinal cord injury (SCI).

METHODS

The study utilizes a low-frequency multi-class electroencephalography (EEG) dataset from Graz University of Technology. The research combines convolutional neural network (CNN) and long-short-term memory (LSTM) architectures to uncover neural correlations between temporal and spatial aspects of the EEG signals associated with attempted arm and hand movements. To achieve this, three different methods are used to select relevant features, and the proposed model's robustness against variations in the data is validated using 10-fold cross-validation (CV). The research also investigates subject-specific adaptation in an online paradigm, extending movement classification proof-of-concept.

RESULTS

The combined CNN-LSTM model, enhanced by three feature selection methods, demonstrates robustness with a mean accuracy of 75.75 % and low standard deviation (+/- 0.74 %) in 10-fold cross-validation, confirming its reliability.

CONCLUSIONS

In summary, this research aims to make valuable contributions to the field of neuro-technology by developing EEG-controlled assistive devices using a generalized brain-computer interface (BCI) and deep learning (DL) framework. The focus is on capturing high-level spatiotemporal features and latent dependencies to enhance the performance and usability of EEG-based assistive technologies.

Working memory load recognition with deep learning time series classification

Working memory load (WML) is one of the widely applied signals in the areas of human-machine interaction. The precise evaluation of the WML is crucial for this kind of application. This study aims to propose a deep learning (DL) time series classification (TSC) model for inter-subject WML decoding. We used fNIRS to record the hemodynamic signals of 27 participants during visual working memory tasks. Traditional machine learning and deep time series classification algorithms were respectively used for intra-subject and inter-subject WML decoding from the collected blood oxygen signals. The intra-subject classification accuracy of LDA and SVM were 94.6% and 79.1%. Our proposed TAResnet-BiLSTM model had the highest inter-subject WML decoding accuracy, reaching 92.4%. This study provides a new idea and method for the brain-computer interface application of fNIRS in real-time WML detection.

Neural correlates of recalled sadness, joy, and fear states: a source reconstruction EEG study

Introduction

The capacity to understand the others' emotional states, particularly if negative (e.g. sadness or fear), underpins the empathic and social brain. Patients who cannot express their emotional states experience social isolation and loneliness, exacerbating distress. We investigated the feasibility of detecting non-invasive scalp-recorded electrophysiological signals that correspond to recalled emotional states of sadness, fear, and joy for potential classification.

Methods

The neural activation patterns of 20 healthy and right-handed participants were studied using an electrophysiological technique. Analyses were focused on the N400 component of Event-related potentials (ERPs) recorded during silent recall of subjective emotional states; Standardized weighted Low-resolution Electro-magnetic Tomography (swLORETA) was employed for source reconstruction. The study classified individual patterns of brain activation linked to the recollection of three distinct emotional states into seven regions of interest (ROIs).

Results

Statistical analysis (ANOVA) of the individual magnitude values revealed the existence of a common emotional circuit, as well as distinct brain areas that were specifically active during recalled sad, happy and fearful states. In particular, the right temporal and left superior frontal areas were more active for sadness, the left limbic region for fear, and the right orbitofrontal cortex for happy affective states.

Discussion

In conclusion, this study successfully demonstrated the feasibility of detecting scalp-recorded electrophysiological signals corresponding to internal and subjective affective states. These findings contribute to our understanding of the emotional brain, and have potential applications for future BCI classification and identification of emotional states in LIS patients who may be unable to express their emotions, thus helping to alleviate social isolation and sense of loneliness.

EEG-based emotion recognition using a temporal-difference minimizing neural network

Electroencephalogram (EEG) emotion recognition plays an important role in human-computer interaction. An increasing number of algorithms for emotion recognition have been proposed recently. However, it is still challenging to make efficient use of emotional activity knowledge. In this paper, based on prior knowledge that emotion varies slowly across time, we propose a temporal-difference minimizing neural network (TDMNN) for EEG emotion recognition. We use maximum mean discrepancy (MMD) technology to evaluate the difference in EEG features across time and minimize the difference by a multibranch convolutional recurrent network. State-of-the-art performances are achieved using the proposed method on the SEED, SEED-IV, DEAP and DREAMER datasets, demonstrating the effectiveness of including prior knowledge in EEG emotion recognition.

EEG multi-domain feature transfer based on sparse regularized Tucker decomposition

Tensor analysis of electroencephalogram (EEG) can extract the activity information and the potential interaction between different brain regions. However, EEG data varies between subjects, and the existing tensor decomposition algorithms cannot guarantee that the features across subjects are distributed in the same domain, which leads to the non-objectivity of the classification result and analysis, In addition, traditional Tucker decomposition is prone to the explosion of feature dimensions. To solve these problems, combined with the idea of feature transfer, a novel EEG tensor transfer algorithm, Tensor Subspace Learning based on Sparse Regularized Tucker Decomposition (TSL-SRT), is proposed in this paper. In TSL-SRT, new EEG samples are considered as the target domain and original samples as the source domain. The target features can be obtained by projecting the target tensor to the source feature space to ensure that all features are in the same domain. Furthermore, to solve the problem of dimension explosion caused by TSL-SRT, a redundant EEG features screening algorithm is adopted to eliminate the redundant features, and achieves 77.8%, 73.2% and 75.3% accuracy on three BCI datasets. By visualizing the spatial basic matrix of the feature space, it can be seen that TSL-SRT is effective in extracting the features of active brain regions in the BCI task and it can extract the multi-domain features of different subjects in the same domain simultaneously, which provides a new method for the tensor analysis of EEG.

An emotion recognition method based on EWT-3D-CNN-BiLSTM-GRU-AT model

This has become a significant study area in recent years because of its use in brain-machine interaction (BMI). The robustness problem of emotion classification is one of the most basic approaches for improving the quality of emotion recognition systems. One of the two main branches of these approaches deals with the problem by extracting the features using manual engineering and the other is the famous artificial intelligence approach, which infers features of EEG data. This study proposes a novel method that considers the characteristic behavior of EEG recordings and based on the artificial intelligence method. The EEG signal is a noisy signal with a non-stationary and non-linear form. Using the Empirical Wavelet Transform (EWT) signal decomposition method, the signal's frequency components are obtained. Then, frequency-based features, linear and non-linear features are extracted. The resulting frequency-based, linear, and nonlinear features are mapped to the 2-D axis according to the positions of the EEG electrodes. By merging this 2-D images, 3-D images are constructed. In this way, the multichannel brain frequency of EEG recordings, spatial and temporal relationship are combined. Lastly, 3-D deep learning framework was constructed, which was combined with convolutional neural network (CNN), bidirectional long-short term memory (BiLSTM) and gated recurrent unit (GRU) with self-attention (AT). This model is named EWT-3D-CNN-BiLSTM-GRU-AT. As a result, we have created framework comprising handcrafted features generated and cascaded from state-of-the-art deep learning models. The framework is evaluated on the DEAP recordings based on the person-independent approach. The experimental findings demonstrate that the developed model can achieve classification accuracies of 90.57 % and 90.59 % for valence and arousal axes, respectively, for the DEAP database. Compared with existing cutting-edge emotion classification models, the proposed framework exhibits superior results for classifying human emotions.

Encoding of multi-modal emotional information via personalized skin-integrated wireless facial interface

Human affects such as emotions, moods, feelings are increasingly being considered as key parameter to enhance the interaction of human with diverse machines and systems. However, their intrinsically abstract and ambiguous nature make it challenging to accurately extract and exploit the emotional information. Here, we develop a multi-modal human emotion recognition system which can efficiently utilize comprehensive emotional information by combining verbal and non-verbal expression data. This system is composed of personalized skin-integrated facial interface (PSiFI) system that is self-powered, facile, stretchable, transparent, featuring a first bidirectional triboelectric strain and vibration sensor enabling us to sense and combine the verbal and non-verbal expression data for the first time. It is fully integrated with a data processing circuit for wireless data transfer allowing real-time emotion recognition to be performed. With the help of machine learning, various human emotion recognition tasks are done accurately in real time even while wearing mask and demonstrated digital concierge application in VR environment.

[Research progress of brain-computer interface application paradigms based on rapid serial visual presentation]

Rapid serial visual presentation (RSVP) is a type of psychological visual stimulation experimental paradigm that requires participants to identify target stimuli presented continuously in a stream of stimuli composed of numbers, letters, words, images, and so on at the same spatial location, allowing them to discern a large amount of information in a short period of time. The RSVP-based brain-computer interface (BCI) can not only be widely used in scenarios such as assistive interaction and information reading, but also has the advantages of stability and high efficiency, which has become one of the common techniques for human-machine intelligence fusion. In recent years, brain-controlled spellers, image recognition and mind games are the most popular fields of RSVP-BCI research. Therefore, aiming to provide reference and new ideas for RSVP-BCI related research, this paper reviewed the paradigm design and system performance optimization of RSVP-BCI in these three fields. It also looks ahead to its potential applications in cutting-edge fields such as entertainment, clinical medicine, and special military operations.

S-LSTM-ATT: a hybrid deep learning approach with optimized features for emotion recognition in electroencephalogram

Purpose

Human emotion recognition using electroencephalograms (EEG) is a critical area of research in human-machine interfaces. Furthermore, EEG data are convoluted and diverse; thus, acquiring consistent results from these signals remains challenging. As such, the authors felt compelled to investigate EEG signals to identify different emotions.

Methods

A novel deep learning (DL) model stacked long short-term memory with attention (S-LSTM-ATT) model is proposed for emotion recognition (ER) in EEG signals. Long Short-Term Memory (LSTM) and attention networks effectively handle time-series EEG data and recognise intrinsic connections and patterns. Therefore, the model combined the strengths of the LSTM model and incorporated an attention network to enhance its effectiveness. Optimal features were extracted from the metaheuristic-based firefly optimisation algorithm (FFOA) to identify different emotions efficiently.

Results

The proposed approach recognised emotions in two publicly available standard datasets: SEED and EEG Brainwave. An outstanding accuracy of 97.83% in the SEED and 98.36% in the EEG Brainwave datasets were obtained for three emotion indices: positive, neutral and negative. Aside from accuracy, a comprehensive comparison of the proposed model's precision, recall, F1 score and kappa score was performed to determine the model's applicability. When applied to the SEED and EEG Brainwave datasets, the proposed S-LSTM-ATT achieved superior results to baseline models such as Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU) and LSTM.

Conclusion

Combining an FFOA-based feature selection (FS) and an S-LSTM-ATT-based classification model demonstrated promising results with high accuracy. Other metrics like precision, recall, F1 score and kappa score proved the suitability of the proposed model for ER in EEG signals.

Classifying human emotions in HRI: applying global optimization model to EEG brain signals

Significant efforts have been made in the past decade to humanize both the form and function of social robots to increase their acceptance among humans. To this end, social robots have recently been combined with brain-computer interface (BCI) systems in an attempt to give them an understanding of human mental states, particularly emotions. However, emotion recognition using BCIs poses several challenges, such as subjectivity of emotions, contextual dependency, and a lack of reliable neuro-metrics for real-time processing of emotions. Furthermore, the use of BCI systems introduces its own set of limitations, such as the bias-variance trade-off, dimensionality, and noise in the input data space. In this study, we sought to address some of these challenges by detecting human emotional states from EEG brain activity during human-robot interaction (HRI). EEG signals were collected from 10 participants who interacted with a Pepper robot that demonstrated either a positive or negative personality. Using emotion valence and arousal measures derived from frontal brain asymmetry (FBA), several machine learning models were trained to classify human's mental states in response to the robot personality. To improve classification accuracy, all proposed classifiers were subjected to a Global Optimization Model (GOM) based on feature selection and hyperparameter optimization techniques. The results showed that it is possible to classify a user's emotional responses to the robot's behavior from the EEG signals with an accuracy of up to 92%. The outcome of the current study contributes to the first level of the Theory of Mind (ToM) in Human-Robot Interaction, enabling robots to comprehend users' emotional responses and attribute mental states to them. Our work advances the field of social and assistive robotics by paving the way for the development of more empathetic and responsive HRI in the future.

EEG-based emotion recognition using dual tree complex wavelet transform and random subspace ensemble classifier

Emotions are strongly admitted as a main source to establish meaningful interactions between humans and computers. Thanks to the advancements in electroencephalography (EEG), especially in the usage of portable and cheap wearable EEG devices, the demand for identifying emotions has extremely increased. However, the overall scientific knowledge and works concerning EEG-based emotion recognition is still limited. To cover this issue, we introduce an EEG-based emotion recognition framework in this study. The proposed framework involves the following stages: preprocessing, feature extraction, feature selection and classification. For the preprocessing stage, multi scale principle component analysis and sysmlets-4 filter are used. A version of discrete wavelet transform (DWT), namely dual tree complex wavelet transform (DTCWT) is utilized for the feature extraction stage. To reduce the feature dimension size, a variety of statistical criteria are employed. For the final stage, we adopt ensemble classifiers due to their promising performance in classification problems. The proposed framework achieves nearly 96.8% accuracy by using random subspace ensemble classifier. It can therefore be resulted that the proposed EEG-based framework performs well in terms of identifying emotions.

BrainWave-Scattering Net: a lightweight network for EEG-based motor imagery recognition

Objective.Brain-computer interfaces (BCIs) enable a direct communication of the brain with the external world, using one's neural activity, measured by electroencephalography (EEG) signals. In recent years, convolutional neural networks (CNNs) have been widely used to perform automatic feature extraction and classification in various EEG-based tasks. However, their undeniable benefits are counterbalanced by the lack of interpretability properties as well as the inability to perform sufficiently when only limited amount of training data is available.Approach.In this work, we introduce a novel, lightweight, fully-learnable neural network architecture that relies on Gabor filters to delocalize EEG signal information into scattering decomposition paths along frequency and slow-varying temporal modulations.Main results.We utilize our network in two distinct modeling settings, for building either a generic (training across subjects) or a personalized (training within a subject) classifier.Significance.In both cases, using two different publicly available datasets and one in-house collected dataset, we demonstrate high performance for our model with considerably less number of trainable parameters as well as shorter training time compared to other state-of-the-art deep architectures. Moreover, our network demonstrates enhanced interpretability properties emerging at the level of the temporal filtering operation and enables us to train efficient personalized BCI models with limited amount of training data.

Implementation of artificial intelligence and machine learning-based methods in brain-computer interaction

Brain-computer interfaces are used for direct two-way communication between the human brain and the computer. Brain signals contain valuable information about the mental state and brain activity of the examined subject. However, due to their non-stationarity and susceptibility to various types of interference, their processing, analysis and interpretation are challenging. For these reasons, the research in the field of brain-computer interfaces is focused on the implementation of artificial intelligence, especially in five main areas: calibration, noise suppression, communication, mental condition estimation, and motor imagery. The use of algorithms based on artificial intelligence and machine learning has proven to be very promising in these application domains, especially due to their ability to predict and learn from previous experience. Therefore, their implementation within medical technologies can contribute to more accurate information about the mental state of subjects, alleviate the consequences of serious diseases or improve the quality of life of disabled patients.

Survey on the research direction of EEG-based signal processing

Electroencephalography (EEG) is increasingly important in Brain-Computer Interface (BCI) systems due to its portability and simplicity. In this paper, we provide a comprehensive review of research on EEG signal processing techniques since 2021, with a focus on preprocessing, feature extraction, and classification methods. We analyzed 61 research articles retrieved from academic search engines, including CNKI, PubMed, Nature, IEEE Xplore, and Science Direct. For preprocessing, we focus on innovatively proposed preprocessing methods, channel selection, and data augmentation. Data augmentation is classified into conventional methods (sliding windows, segmentation and recombination, and noise injection) and deep learning methods [Generative Adversarial Networks (GAN) and Variation AutoEncoder (VAE)]. We also pay attention to the application of deep learning, and multi-method fusion approaches, including both conventional algorithm fusion and fusion between conventional algorithms and deep learning. Our analysis identifies 35 (57.4%), 18 (29.5%), and 37 (60.7%) studies in the directions of preprocessing, feature extraction, and classification, respectively. We find that preprocessing methods have become widely used in EEG classification (96.7% of reviewed papers) and comparative experiments have been conducted in some studies to validate preprocessing. We also discussed the adoption of channel selection and data augmentation and concluded several mentionable matters about data augmentation. Furthermore, deep learning methods have shown great promise in EEG classification, with Convolutional Neural Networks (CNNs) being the main structure of deep neural networks (92.3% of deep learning papers). We summarize and analyze several innovative neural networks, including CNNs and multi-structure fusion. However, we also identified several problems and limitations of current deep learning techniques in EEG classification, including inappropriate input, low cross-subject accuracy, unbalanced between parameters and time costs, and a lack of interpretability. Finally, we highlight the emerging trend of multi-method fusion approaches (49.2% of reviewed papers) and analyze the data and some examples. We also provide insights into some challenges of multi-method fusion. Our review lays a foundation for future studies to improve EEG classification performance.

Influence of Multimodal Emotional Stimulations on Brain Activity: An Electroencephalographic Study

This study aimed to reveal the influence of emotional valence and sensory modality on neural activity in response to multimodal emotional stimuli using scalp EEG. In this study, 20 healthy participants completed the emotional multimodal stimulation experiment for three stimulus modalities (audio, visual, and audio-visual), all of which are from the same video source with two emotional components (pleasure or unpleasure), and EEG data were collected using six experimental conditions and one resting state. We analyzed power spectral density (PSD) and event-related potential (ERP) components in response to multimodal emotional stimuli, for spectral and temporal analysis. PSD results showed that the single modality (audio only/visual only) emotional stimulation PSD differed from multi-modality (audio-visual) in a wide brain and band range due to the changes in modality and not from the changes in emotional degree. The most pronounced N200-to-P300 potential shifts occurred in monomodal rather than multimodal emotional stimulations. This study suggests that emotional saliency and sensory processing efficiency perform a significant role in shaping neural activity during multimodal emotional stimulation, with the sensory modality being more influential in PSD. These findings contribute to our understanding of the neural mechanisms involved in multimodal emotional stimulation.

Effectiveness of a Mindfulness Meditation App Based on an Electroencephalography-Based Brain-Computer Interface in Radiofrequency Catheter Ablation for Patients With Atrial Fibrillation: Pilot Randomized Controlled Trial

BACKGROUND

Radiofrequency catheter ablation (RFCA) for patients with atrial fibrillation (AF) can generate considerable physical and psychological discomfort under conscious sedation. App-based mindfulness meditation combined with an electroencephalography (EEG)-based brain-computer interface (BCI) shows promise as effective and accessible adjuncts in medical practice.

OBJECTIVE

This study aimed to investigate the effectiveness of a BCI-based mindfulness meditation app in improving the experience of patients with AF during RFCA.

METHODS

This single-center pilot randomized controlled trial involved 84 eligible patients with AF scheduled for RFCA, who were randomized 1:1 to the intervention and control groups. Both groups received a standardized RFCA procedure and a conscious sedative regimen. Patients in the control group were administered conventional care, while those in the intervention group received BCI-based app-delivered mindfulness meditation from a research nurse. The primary outcomes were the changes in the numeric rating scale, State Anxiety Inventory, and Brief Fatigue Inventory scores. Secondary outcomes were the differences in hemodynamic parameters (heart rate, blood pressure, and peripheral oxygen saturation), adverse events, patient-reported pain, and the doses of sedative drugs used in ablation.

RESULTS

BCI-based app-delivered mindfulness meditation, compared to conventional care, resulted in a significantly lower mean numeric rating scale (mean 4.6, SD 1.7 [app-based mindfulness meditation] vs mean 5.7, SD 2.1 [conventional care]; P=.008), State Anxiety Inventory (mean 36.7, SD 5.5 vs mean 42.3, SD 7.2; P<.001), and Brief Fatigue Inventory (mean 3.4, SD 2.3 vs mean 4.7, SD 2.2; P=.01) scores. No significant differences were observed in hemodynamic parameters or the amounts of parecoxib and dexmedetomidine used in RFCA between the 2 groups. The intervention group exhibited a significant decrease in fentanyl use compared to the control group, with a mean dose of 3.96 (SD 1.37) mcg/kg versus 4.85 (SD 1.25) mcg/kg in the control group (P=.003).The incidence of adverse events was lower in the intervention group (5/40) than in the control group (10/40), though this difference was not significant (P=.15).

CONCLUSIONS

BCI-based app-delivered mindfulness meditation effectively relieved physical and psychological discomfort and may reduce the doses of sedative medication used in RFCA for patients with AF.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05306015; https://clinicaltrials.gov/ct2/show/NCT05306015.

Multi-domain feature analysis method of MI-EEG signal based on Sparse Regularity Tensor-Train decomposition

Tensor analysis can comprehensively retain multidomain characteristics, which has been employed in EEG studies. However, existing EEG tensor has large dimension, making it difficult to extract features. Traditional Tucker decomposition and Canonical Polyadic decomposition(CP) decomposition algorithms have problems of low computational efficiency and weak capability to extract features. To solve the above problems, Tensor-Train(TT) decomposition is adopted to analyze the EEG tensor. Meanwhile, sparse regularization term can then be added to TT decomposition, resulting in a sparse regular TT decomposition (SR-TT). The SR-TT algorithm is proposed in this paper, which has higher accuracy and stronger generalization ability than state-of-the-art decomposition methods. The SR-TT algorithm was verified with BCI competition III and BCI competition IV dataset and achieved 86.38% and 85.36% classification accuracies, respectively. Meanwhile, compared with traditional tensor decomposition (Tucker and CP) method, the computational efficiency of the proposed algorithm was improved by 16.49 and 31.08 times in BCI competition III and 20.72 and 29.45 times more efficient in BCI competition IV. Besides, the method can leverage tensor decomposition to extract spatial features, and the analysis is performed by pairs of brain topography visualizations to show the changes of active brain regions under the task condition. In conclusion, the proposed SR-TT algorithm in the paper provides a novel insight for tensor EEG analysis.

The EEG microstate representation of discrete emotions

Understanding how human emotions are represented in our brain is a central question in the field of affective neuroscience. While previous studies have mainly adopted a modular and static perspective on the neural representation of emotions, emerging research suggests that emotions may rely on a distributed and dynamic representation. The present study aimed to explore the EEG microstate representations for nine discrete emotions (Anger, Disgust, Fear, Sadness, Neutral, Amusement, Inspiration, Joy and Tenderness). Seventy-eight participants were recruited to watch emotion eliciting videos with their EEGs recorded. Multivariate analysis revealed that different emotions had distinct EEG microstate features. By using the EEG microstate features in the Neutral condition as the reference, the coverage of C, duration of C and occurrence of B were found to be the top-contributing microstate features for the discrete positive and negative emotions. The emotions of Disgust, Fear and Joy were found to be most effectively represented by EEG microstate. The present study provided the first piece of evidence of EEG microstate representation for discrete emotions, highlighting a whole-brain, dynamical representation of human emotions.

EEG-Based Emotion Classification in Financial Trading Using Deep Learning: Effects of Risk Control Measures

Day traders in the financial markets are under constant pressure to make rapid decisions and limit capital losses in response to fluctuating market prices. As such, their emotional state can greatly influence their decision-making, leading to suboptimal outcomes in volatile market conditions. Despite the use of risk control measures such as stop loss and limit orders, it is unclear if these strategies have a substantial impact on the emotional state of traders. In this paper, we aim to determine if the use of limit orders and stop loss has a significant impact on the emotional state of traders compared to when these risk control measures are not applied. The paper provides a technical framework for valence-arousal classification in financial trading using EEG data and deep learning algorithms. We conducted two experiments: the first experiment employed predetermined stop loss and limit orders to lock in profit and risk objectives, while the second experiment did not employ limit orders or stop losses. We also proposed a novel hybrid neural architecture that integrates a Conditional Random Field with a CNN-BiLSTM model and employs Bayesian Optimization to systematically determine the optimal hyperparameters. The best model in the framework obtained classification accuracies of 85.65% and 85.05% in the two experiments, outperforming previous studies. Results indicate that the emotions associated with Low Valence and High Arousal, such as fear and worry, were more prevalent in the second experiment. The emotions associated with High Valence and High Arousal, such as hope, were more prevalent in the first experiment employing limit orders and stop loss. In contrast, High Valence and Low Arousal (calmness) emotions were most prominent in the control group which did not engage in trading activities. Our results demonstrate the efficacy of our proposed framework for emotion classification in financial trading and aid in the risk-related decision-making abilities of day traders. Further, we present the limitations of the current work and directions for future research.

A BCI framework for smart home automation using EEG signal

Since the first recording in 1924, modern developments in technology have enabled human electroencephalogram (EEG) acquisition as a non-invasive process, enabling a multitude of opportunities to learn about human brain dynamics. With the capability to tap into localized brain dynamics, it is possible to correlate event-related potentials such as meditation, concentration, and motor control with localized brain activities, opening up a broad spectrum for exploration and implementation in prosthetic, control, and brain computer interfaces. In this work, an attempt has been made to explore human emotions and other intelligent states that can be interpreted to automate and control electrical appliances for differently abled people. A smart home automation model has been designed and implemented using a Think Gear Application-specific integrated circuit (ASIC) Module (TGAM) EEG sensor module integrated with a Bluetooth module, which serves as the core for control applications. A combination of external triggers and brain states are interpreted and forwarded to gain control of the connected appliances via a local server over the internet. Equipped with internet connectivity and Internet of Things (IoT), the system also facilitates long-distance communication and control, which can be easily translated to industrial control and automation applications. Based on a single-channel analog EEG signal acquisition module, this study details the development of a Brain Computer Interface (BCI) control and monitoring system for smart home automation with blink and attention features. The designed BCI system has a large bandwidth of 400 Hz, an easy setup, Morphological Component Analysis (MCA) based blink detection, monitoring, control of devices, and high accuracy at a low cost. Each subject completed three trials separated by one minute. The smart devices underwent testing in two states, namely on and off. The response time and accuracy of the system were recorded for each trial. The average system response time for the devices was determined to be 17.13 sec for switching ON and 20.66 sec for switching OFF, with an accuracy of 98.73% and 95.75% for ON and OFF states respectively.

Leveraging Multiple Distinct EEG Training Sessions for Improvement of Spectral-Based Biometric Verification Results

Most studies on EEG-based biometry recognition report results based on signal databases, with a limited number of recorded EEG sessions using the same single EEG recording for both training and testing a proposed model. However, the EEG signal is highly vulnerable to interferences, electrode placement, and temporary conditions, which can lead to overestimated assessments of the considered methods. Our study examined how different numbers of distinct recording sessions used as training sessions would affect EEG-based verification. We analyzed the original data from 29 participants with 20 distinct recorded sessions each, as well as 23 additional impostors with only one session each. We applied raw coefficients of power spectral density estimate, and the coefficients of power spectral density estimate converted to the decibel scale, as the input to a shallow neural network. Our study showed that the variance introduced by multiple recording sessions affects sensitivity. We also showed that increasing the number of sessions above eight did not improve the results under our conditions. For 15 training sessions, the achieved accuracy was 96.7 ± 4.2%, and for eight training sessions and 12 test sessions, it was 94.9 ± 4.6%. For 15 training sessions, the rate of successful impostor attacks over all attack attempts was 3.1 ± 2.2%, but this number was not significantly different from using six recording sessions for training. Our findings indicate the need to include data from multiple recording sessions in EEG-based recognition for training, and that increasing the number of test sessions did not significantly affect the obtained results. Although the presented results are for the resting-state, they may serve as a baseline for other paradigms.

An Efficient Machine Learning-Based Emotional Valence Recognition Approach Towards Wearable EEG

Emotion artificial intelligence (AI) is being increasingly adopted in several industries such as healthcare and education. Facial expressions and tone of speech have been previously considered for emotion recognition, yet they have the drawback of being easily manipulated by subjects to mask their true emotions. Electroencephalography (EEG) has emerged as a reliable and cost-effective method to detect true human emotions. Recently, huge research effort has been put to develop efficient wearable EEG devices to be used by consumers in out of the lab scenarios. In this work, a subject-dependent emotional valence recognition method is implemented that is intended for utilization in emotion AI applications. Time and frequency features were computed from a single time series derived from the Fp1 and Fp2 channels. Several analyses were performed on the strongest valence emotions to determine the most relevant features, frequency bands, and EEG timeslots using the benchmark DEAP dataset. Binary classification experiments resulted in an accuracy of 97.42% using the alpha band, by that outperforming several approaches from literature by ~3-22%. Multiclass classification gave an accuracy of 95.0%. Feature computation and classification required less than 0.1 s. The proposed method thus has the advantage of reduced computational complexity as, unlike most methods in the literature, only two EEG channels were considered. In addition, minimal features concluded from the thorough analyses conducted in this study were used to achieve state-of-the-art performance. The implemented EEG emotion recognition method thus has the merits of being reliable and easily reproducible, making it well-suited for wearable EEG devices.

Stylized faces enhance ERP features used for the detection of emotional responses

For their ease of accessibility and low cost, current Brain-Computer Interfaces (BCI) used to detect subjective emotional and affective states rely largely on electroencephalographic (EEG) signals. Public datasets are available for researchers to design models for affect detection from EEG. However, few designs focus on optimally exploiting the nature of the stimulus elicitation to improve accuracy. The RSVP protocol is used in this experiment to present human faces of emotion to 28 participants while EEG was measured. We found that artificially enhanced human faces with exaggerated, cartoonish visual features significantly improve some commonly used neural correlates of emotion as measured by event-related potentials (ERPs). These images elicit an enhanced N170 component, well known to relate to the facial visual encoding process. Our findings suggest that the study of emotion elicitation could exploit consistent, high detail, AI generated stimuli transformations to study the characteristics of electrical brain activity related to visual affective stimuli. Furthermore, this specific result might be useful in the context of affective BCI design, where a higher accuracy in affect decoding from EEG can improve the experience of a user.

STGATE: Spatial-temporal graph attention network with a transformer encoder for EEG-based emotion recognition

Electroencephalogram (EEG) is a crucial and widely utilized technique in neuroscience research. In this paper, we introduce a novel graph neural network called the spatial-temporal graph attention network with a transformer encoder (STGATE) to learn graph representations of emotion EEG signals and improve emotion recognition performance. In STGATE, a transformer-encoder is applied for capturing time-frequency features which are fed into a spatial-temporal graph attention for emotion classification. Using a dynamic adjacency matrix, the proposed STGATE adaptively learns intrinsic connections between different EEG channels. To evaluate the cross-subject emotion recognition performance, leave-one-subject-out experiments are carried out on three public emotion recognition datasets, i.e., SEED, SEED-IV, and DREAMER. The proposed STGATE model achieved a state-of-the-art EEG-based emotion recognition performance accuracy of 90.37% in SEED, 76.43% in SEED-IV, and 76.35% in DREAMER dataset, respectively. The experiments demonstrated the effectiveness of the proposed STGATE model for cross-subject EEG emotion recognition and its potential for graph-based neuroscience research.

Feature extraction based on microstate sequences for EEG-based emotion recognition

Recognizing emotion from Electroencephalography (EEG) is a promising and valuable research issue in the field of affective brain-computer interfaces (aBCI). To improve the accuracy of emotion recognition, an emotional feature extraction method is proposed based on the temporal information in the EEG signal. This study adopts microstate analysis as a spatio-temporal analysis for EEG signals. Microstates are defined as a series of momentary quasi-stable scalp electric potential topographies. Brain electrical activity could be modeled as being composed of a time sequence of microstates. Microstate sequences provide an ideal macroscopic window for observing the temporal dynamics of spontaneous brain activity. To further analyze the fine structure of the microstate sequence, we propose a feature extraction method based on k-mer. K-mer is a k-length substring of a given sequence. It has been widely used in computational genomics and sequence analysis. We extract features that are based on the D 2 ∗ statistic of k-mer. In addition, we also extract four parameters (duration, occurrence, time coverage, GEV) of each microstate class as features at the coarse level. We conducted experiments on the DEAP dataset to evaluate the performance of the proposed features. The experimental results demonstrate that the fusion of features in fine and coarse levels can effectively improve classification accuracy.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

Development of Automatic Controlled Walking Assistive Device Based on Fatigue and Emotion Detection

The world’s aging population is increasing. The number of elderly individuals having walking impairments is also increasing. Adequate exercise is becoming necessary for them. Therefore, several walking assistive devices have been developed or are under development. However, elderly individuals may have low motivation for exercising, or they may experience physical damage by excessive fatigue. This study proposed a method to enable elderly individuals to exercise with a positive emotion and prevent damage such as muscle fatigue. We proposed a 3D human condition model to control the walking assistive device. It includes the arousal, pleasure, and fatigue dimensions. With regard to the arousal and pleasure dimensions, we used heartbeat and electromyography (EEG) signals to train a deep neural network (DNN) model to identify human emotions. For fatigue detection, we proposed a method based on near-infrared spectroscopy (NIRS) to detect muscle fatigue. All the sensors are portable. This implies that it can be used for outdoor activities. Then, we proposed a walking strategy based on a 3D human condition model to control the walking assistive device. Finally, we tested the effectiveness of the automatic control system. The wearing of the walking assistive device and implementation of the walking strategy can delay the fatigue time by approximately 24% and increase the walking distance by approximately 16%. In addition, we succeeded in visualizing the distribution of emotion during each walking method variation. It was verified that the walking strategy can improve the mental condition of a user to a certain extent. These results showed the effectiveness of the proposed system. It could help elderlies maintain higher levels of motivation and prevent muscle damage by walking exercise, using the walking assistive device.

Decoding the neural signatures of valence and arousal from portable EEG headset

Emotion classification using electroencephalography (EEG) data and machine learning techniques have been on the rise in the recent past. However, past studies use data from medical-grade EEG setups with long set-up times and environment constraints. This paper focuses on classifying emotions on the valence-arousal plane using various feature extraction, feature selection, and machine learning techniques. We evaluate different feature extraction and selection techniques and propose the optimal set of features and electrodes for emotion recognition. The images from the OASIS image dataset were used to elicit valence and arousal emotions, and the EEG data was recorded using the Emotiv Epoc X mobile EEG headset. The analysis is carried out on publicly available datasets: DEAP and DREAMER for benchmarking. We propose a novel feature ranking technique and incremental learning approach to analyze performance dependence on the number of participants. Leave-one-subject-out cross-validation was carried out to identify subject bias in emotion elicitation patterns. The importance of different electrode locations was calculated, which could be used for designing a headset for emotion recognition. The collected dataset and pipeline are also published. Our study achieved a root mean square score (RMSE) of 0.905 on DREAMER, 1.902 on DEAP, and 2.728 on our dataset for valence label and a score of 0.749 on DREAMER, 1.769 on DEAP, and 2.3 on our proposed dataset for arousal label.

M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Emotion recognition, or the ability of computers to interpret people's emotional states, is a very active research area with vast applications to improve people's lives. However, most image-based emotion recognition techniques are flawed, as humans can intentionally hide their emotions by changing facial expressions. Consequently, brain signals are being used to detect human emotions with improved accuracy, but most proposed systems demonstrate poor performance as EEG signals are difficult to classify using standard machine learning and deep learning techniques. This paper proposes two convolutional neural network (CNN) models (M1: heavily parameterized CNN model and M2: lightly parameterized CNN model) coupled with elegant feature extraction methods for effective recognition. In this study, the most popular EEG benchmark dataset, the DEAP, is utilized with two of its labels, valence, and arousal, for binary classification. We use Fast Fourier Transformation to extract the frequency domain features, convolutional layers for deep features, and complementary features to represent the dataset. The M1 and M2 CNN models achieve nearly perfect accuracy of 99.89% and 99.22%, respectively, which outperform every previous state-of-the-art model. We empirically demonstrate that the M2 model requires only 2 seconds of EEG signal for 99.22% accuracy, and it can achieve over 96% accuracy with only 125 milliseconds of EEG data for valence classification. Moreover, the proposed M2 model achieves 96.8% accuracy on valence using only 10% of the training dataset, demonstrating our proposed system's effectiveness. Documented implementation codes for every experiment are published for reproducibility.

Multi-Kernel Temporal and Spatial Convolution for EEG-Based Emotion Classification

Deep learning using an end-to-end convolutional neural network (ConvNet) has been applied to several electroencephalography (EEG)-based brain-computer interface tasks to extract feature maps and classify the target output. However, the EEG analysis remains challenging since it requires consideration of various architectural design components that influence the representational ability of extracted features. This study proposes an EEG-based emotion classification model called the multi-kernel temporal and spatial convolution network (MultiT-S ConvNet). The multi-scale kernel is used in the model to learn various time resolutions, and separable convolutions are applied to find related spatial patterns. In addition, we enhanced both the temporal and spatial filters with a lightweight gating mechanism. To validate the performance and classification accuracy of MultiT-S ConvNet, we conduct subject-dependent and subject-independent experiments on EEG-based emotion datasets: DEAP and SEED. Compared with existing methods, MultiT-S ConvNet outperforms with higher accuracy results and a few trainable parameters. Moreover, the proposed multi-scale module in temporal filtering enables extracting a wide range of EEG representations, covering short- to long-wavelength components. This module could be further implemented in any model of EEG-based convolution networks, and its ability potentially improves the model's learning capacity.

EEG diagnosis of depression based on multi-channel data fusion and clipping augmentation and convolutional neural network

Depression is an undetectable mental disease. Most of the patients with depressive symptoms do not know that they are suffering from depression. Since the novel Coronavirus pandemic 2019, the number of patients with depression has increased rapidly. There are two kinds of traditional depression diagnosis. One is that professional psychiatrists make diagnosis results for patients, but it is not conducive to large-scale depression detection. Another is to use electroencephalography (EEG) to record neuronal activity. Then, the features of the EEG are extracted using manual or traditional machine learning methods to diagnose the state and type of depression. Although this method achieves good results, it does not fully utilize the multi-channel information of EEG. Aiming at this problem, an EEG diagnosis method for depression based on multi-channel data fusion cropping enhancement and convolutional neural network is proposed. First, the multi-channel EEG data are transformed into 2D images after multi-channel fusion (MCF) and multi-scale clipping (MSC) augmentation. Second, it is trained by a multi-channel convolutional neural network (MCNN). Finally, the trained model is loaded into the detection device to classify the input EEG signals. The experimental results show that the combination of MCF and MSC can make full use of the information contained in the single sensor records, and significantly improve the classification accuracy and clustering effect of depression diagnosis. The method has the advantages of low complexity and good robustness in signal processing and feature extraction, which is beneficial to the wide application of detection systems.

Neural Decoding of Visual Information Across Different Neural Recording Modalities and Approaches

Vision plays a peculiar role in intelligence. Visual information, forming a large part of the sensory information, is fed into the human brain to formulate various types of cognition and behaviours that make humans become intelligent agents. Recent advances have led to the development of brain-inspired algorithms and models for machine vision. One of the key components of these methods is the utilization of the computational principles underlying biological neurons. Additionally, advanced experimental neuroscience techniques have generated different types of neural signals that carry essential visual information. Thus, there is a high demand for mapping out functional models for reading out visual information from neural signals. Here, we briefly review recent progress on this issue with a focus on how machine learning techniques can help in the development of models for contending various types of neural signals, from fine-scale neural spikes and single-cell calcium imaging to coarse-scale electroencephalography (EEG) and functional magnetic resonance imaging recordings of brain signals.

A pediatric near-infrared spectroscopy brain-computer interface based on the detection of emotional valence

Brain-computer interfaces (BCIs) are being investigated as an access pathway to communication for individuals with physical disabilities, as the technology obviates the need for voluntary motor control. However, to date, minimal research has investigated the use of BCIs for children. Traditional BCI communication paradigms may be suboptimal given that children with physical disabilities may face delays in cognitive development and acquisition of literacy skills. Instead, in this study we explored emotional state as an alternative access pathway to communication. We developed a pediatric BCI to identify positive and negative emotional states from changes in hemodynamic activity of the prefrontal cortex (PFC). To train and test the BCI, 10 neurotypical children aged 8–14 underwent a series of emotion-induction trials over four experimental sessions (one offline, three online) while their brain activity was measured with functional near-infrared spectroscopy (fNIRS). Visual neurofeedback was used to assist participants in regulating their emotional states and modulating their hemodynamic activity in response to the affective stimuli. Child-specific linear discriminant classifiers were trained on cumulatively available data from previous sessions and adaptively updated throughout each session. Average online valence classification exceeded chance across participants by the last two online sessions (with 7 and 8 of the 10 participants performing better than chance, respectively, in Sessions 3 and 4). There was a small significant positive correlation with online BCI performance and age, suggesting older participants were more successful at regulating their emotional state and/or brain activity. Variability was seen across participants in regards to BCI performance, hemodynamic response, and discriminatory features and channels. Retrospective offline analyses yielded accuracies comparable to those reported in adult affective BCI studies using fNIRS. Affective fNIRS-BCIs appear to be feasible for school-aged children, but to further gauge the practical potential of this type of BCI, replication with more training sessions, larger sample sizes, and end-users with disabilities is necessary.

Simultaneously exploring multi-scale and asymmetric EEG features for emotion recognition

In recent years, emotion recognition based on electroencephalography (EEG) has received growing interests in the brain-computer interaction (BCI) field. The neuroscience researches indicate that the left and right brain hemispheres demonstrate activity differences under different emotional activities, which could be an important principle for designing deep learning (DL) model for emotion recognition. Besides, owing to the nonstationarity of EEG signals, using convolution kernels of a single size may not sufficiently extract the abundant features for EEG classification tasks. Based on these two angles, we proposed a model termed Multi-Scales Bi-hemispheric Asymmetric Model (MSBAM) based on convolutional neural network (CNN) structure. Evaluated on the public DEAP and DREAMER datasets, MSBAM achieved over 99% accuracy for the two-class classification of low-level and high-level states in each of four emotional dimensions, i.e., arousal, valence, dominance and liking, respectively. This study further demonstrated the promising potential to design the DL model from the multi-scale characteristics of the EEG data and the neural mechanisms of the emotion cognition.

Motor Imagery Analysis from Extensive EEG Data Representations Using Convolutional Neural Networks

Motor imagery is a complex mental task that represents muscular movement without the execution of muscular action, involving cognitive processes of motor planning and sensorimotor proprioception of the body. Since the mental task has similar behavior to that of the motor execution process, it can be used to create rehabilitation routines for patients with some motor skill impairment. However, due to the nature of this mental task, its execution is complicated. Hence, the classification of these signals in scenarios such as brain-computer interface systems tends to have a poor performance. In this work, we study in depth different forms of data representation of motor imagery EEG signals for distinct CNN-based models as well as novel EEG data representations including spectrograms and multidimensional raw data. With the aid of transfer learning, we achieve results up to 93% accuracy, exceeding the current state of the art. However, although these results are strong, they entail the use of high computational resources to generate the samples, since they are based on spectrograms. Thus, we searched further for alternative forms of EEG representations, based on 1D, 2D, and 3D variations of the raw data, leading to promising results for motor imagery classification that still exceed the state of the art. Hence, in this work, we focus on exploring alternative methods to process and improve the classification of motor imagery features with few preprocessing techniques.

Deep Unsupervised Domain Adaptation with Time Series Sensor Data: A Survey

Sensors are devices that output signals for sensing physical phenomena and are widely used in all aspects of our social production activities. The continuous recording of physical parameters allows effective analysis of the operational status of the monitored system and prediction of unknown risks. Thanks to the development of deep learning, the ability to analyze temporal signals collected by sensors has been greatly improved. However, models trained in the source domain do not perform well in the target domain due to the presence of domain gaps. In recent years, many researchers have used deep unsupervised domain adaptation techniques to address the domain gap between signals collected by sensors in different scenarios, i.e., using labeled data in the source domain and unlabeled data in the target domain to improve the performance of models in the target domain. This survey first summarizes the background of recent research on unsupervised domain adaptation with time series sensor data, the types of sensors used, the domain gap between the source and target domains, and commonly used datasets. Then, the paper classifies and compares different unsupervised domain adaptation methods according to the way of adaptation and summarizes different adaptation settings based on the number of source and target domains. Finally, this survey discusses the challenges of the current research and provides an outlook on future work. This survey systematically reviews and summarizes recent research on unsupervised domain adaptation for time series sensor data to provide the reader with a systematic understanding of the field.

Review of Artificial Intelligence and Machine Learning Technologies: Classification, Restrictions, Opportunities and Challenges

Artificial intelligence (AI) is an evolving set of technologies used for solving a wide range of applied issues. The core of AI is machine learning (ML)—a complex of algorithms and methods that address the problems of classification, clustering, and forecasting. The practical application of AI&ML holds promising prospects. Therefore, the researches in this area are intensive. However, the industrial applications of AI and its more intensive use in society are not widespread at the present time. The challenges of widespread AI applications need to be considered from both the AI (internal problems) and the societal (external problems) perspective. This consideration will identify the priority steps for more intensive practical application of AI technologies, their introduction, and involvement in industry and society. The article presents the identification and discussion of the challenges of the employment of AI technologies in the economy and society of resource-based countries. The systematization of AI&ML technologies is implemented based on publications in these areas. This systematization allows for the specification of the organizational, personnel, social and technological limitations. This paper outlines the directions of studies in AI and ML, which will allow us to overcome some of the limitations and achieve expansion of the scope of AI&ML applications.

Channel selection from source localization: A review of four EEG-based brain-computer interfaces paradigms

Channel selection is a critical part of the classification procedure for multichannel electroencephalogram (EEG)-based brain-computer interfaces (BCI). An optimized subset of electrodes reduces computational complexity and optimizes accuracy. Different tasks activate different sources in the brain and are characterized by distinctive channels. The goal of the current review is to define a subset of electrodes for each of four popular BCI paradigms: motor imagery, motor execution, steady-state visual evoked potentials and P300. Twenty-one studies have been reviewed to identify the most significant activations of cortical sources. The relevant EEG sensors are determined from the reported 3D Talairach coordinates. They are scored by their weighted mean Cohen's d and its confidence interval, providing the magnitude of the corresponding effect size and its statistical significance. Our goal is to create a knowledge-based channel selection framework with a sufficient statistical power. The core channel selection (CCS) could be used as a reference by EEG researchers and would have the advantages of practicality and rapidity, allowing for an easy implementation of semiparametric algorithms.

A Spherical Phase Space Partitioning Based Symbolic Time Series Analysis (SPSP—STSA) for Emotion Recognition Using EEG Signals

Emotion recognition systems have been of interest to researchers for a long time. Improvement of brain-computer interface systems currently makes EEG-based emotion recognition more attractive. These systems try to develop strategies that are capable of recognizing emotions automatically. There are many approaches due to different features extractions methods for analyzing the EEG signals. Still, Since the brain is supposed to be a nonlinear dynamic system, it seems a nonlinear dynamic analysis tool may yield more convenient results. A novel approach in Symbolic Time Series Analysis (STSA) for signal phase space partitioning and symbol sequence generating is introduced in this study. Symbolic sequences have been produced by means of spherical partitioning of phase space; then, they have been compared and classified based on the maximum value of a similarity index. Obtaining the automatic independent emotion recognition EEG-based system has always been discussed because of the subject-dependent content of emotion. Here we introduce a subject-independent protocol to solve the generalization problem. To prove our method’s effectiveness, we used the DEAP dataset, and we reached an accuracy of 98.44% for classifying happiness from sadness (two- emotion groups). It was 93.75% for three (happiness, sadness, and joy), 89.06% for four (happiness, sadness, joy, and terrible), and 85% for five emotional groups (happiness, sadness, joy, terrible and mellow). According to these results, it is evident that our subject-independent method is more accurate rather than many other methods in different studies. In addition, a subject-independent method has been proposed in this study, which is not considered in most of the studies in this field.

Data Collection Framework for Context-Aware Virtual Reality Application Development in Unity: Case of Avatar Embodiment

Virtual Reality (VR) has been adopted as a leading technology for the metaverse, yet most previous VR systems provide one-size-fits-all experiences to users. Context-awareness in VR enables personalized experiences in the metaverse, such as improved embodiment and deeper integration of the real world and virtual worlds. Personalization requires context data from diverse sources. We proposed a reusable and extensible context data collection framework, ManySense VR, which unifies data collection from diverse sources for VR applications. ManySense VR was implemented in Unity based on extensible context data managers collecting data from data sources such as an eye tracker, electroencephalogram, pulse, respiration, galvanic skin response, facial tracker, and Open Weather Map. We used ManySense VR to build a context-aware embodiment VR scene where the user's avatar is synchronized with their bodily actions. The performance evaluation of ManySense VR showed good performance in processor usage, frame rate, and memory footprint. Additionally, we conducted a qualitative formative evaluation by interviewing five developers (two males and three females; mean age: 22) after they used and extended ManySense VR. The participants expressed advantages (e.g., ease-of-use, learnability, familiarity, quickness, and extensibility), disadvantages (e.g., inconvenient/error-prone data query method and lack of diversity in callback methods), future application ideas, and improvement suggestions that indicate potential and can guide future development. In conclusion, ManySense VR is an efficient tool for researchers and developers to easily integrate context data into their Unity-based VR applications for the metaverse.

Multi-Classifier Fusion Based on MI–SFFS for Cross-Subject Emotion Recognition

With the widespread use of emotion recognition, cross-subject emotion recognition based on EEG signals has become a hot topic in affective computing. Electroencephalography (EEG) can be used to detect the brain’s electrical activity associated with different emotions. The aim of this research is to improve the accuracy by enhancing the generalization of features. A Multi-Classifier Fusion method based on mutual information with sequential forward floating selection (MI_SFFS) is proposed. The dataset used in this paper is DEAP, which is a multi-modal open dataset containing 32 EEG channels and multiple other physiological signals. First, high-dimensional features are extracted from 15 EEG channels of DEAP after using a 10 s time window for data slicing. Second, MI and SFFS are integrated as a novel feature-selection method. Then, support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) are employed to classify positive and negative emotions to obtain the output probabilities of classifiers as weighted features for further classification. To evaluate the model performance, leave-one-out cross-validation is adopted. Finally, cross-subject classification accuracies of 0.7089, 0.7106 and 0.7361 are achieved by the SVM, KNN and RF classifiers, respectively. The results demonstrate the feasibility of the model by splicing different classifiers’ output probabilities as a portion of the weighted features.

Human emotion recognition from EEG-based brain–computer interface using machine learning: a comprehensive review

Affective computing, a subcategory of artificial intelligence, detects, processes, interprets, and mimics human emotions. Thanks to the continued advancement of portable non-invasive human sensor technologies, like brain–computer interfaces (BCI), emotion recognition has piqued the interest of academics from a variety of domains. Facial expressions, speech, behavior (gesture/posture), and physiological signals can all be used to identify human emotions. However, the first three may be ineffectual because people may hide their true emotions consciously or unconsciously (so-called social masking). Physiological signals can provide more accurate and objective emotion recognition. Electroencephalogram (EEG) signals respond in real time and are more sensitive to changes in affective states than peripheral neurophysiological signals. Thus, EEG signals can reveal important features of emotional states. Recently, several EEG-based BCI emotion recognition techniques have been developed. In addition, rapid advances in machine and deep learning have enabled machines or computers to understand, recognize, and analyze emotions. This study reviews emotion recognition methods that rely on multi-channel EEG signal-based BCIs and provides an overview of what has been accomplished in this area. It also provides an overview of the datasets and methods used to elicit emotional states. According to the usual emotional recognition pathway, we review various EEG feature extraction, feature selection/reduction, machine learning methods (e.g., k-nearest neighbor), support vector machine, decision tree, artificial neural network, random forest, and naive Bayes) and deep learning methods (e.g., convolutional and recurrent neural networks with long short term memory). In addition, EEG rhythms that are strongly linked to emotions as well as the relationship between distinct brain areas and emotions are discussed. We also discuss several human emotion recognition studies, published between 2015 and 2021, that use EEG data and compare different machine and deep learning algorithms. Finally, this review suggests several challenges and future research directions in the recognition and classification of human emotional states using EEG.

Sparse representations of high dimensional neural data

Conventional Vector Autoregressive (VAR) modelling methods applied to high dimensional neural time series data result in noisy solutions that are dense or have a large number of spurious coefficients. This reduces the speed and accuracy of auxiliary computations downstream and inflates the time required to compute functional connectivity networks by a factor that is at least inversely proportional to the true network density. As these noisy solutions have distorted coefficients, thresholding them as per some criterion, statistical or otherwise, does not alleviate the problem. Thus obtaining a sparse representation of such data is important since it provides an efficient representation of the data and facilitates its further analysis. We propose a fast Sparse Vector Autoregressive Greedy Search (SVARGS) method that works well for high dimensional data, even when the number of time points is relatively low, by incorporating only statistically significant coefficients. In numerical experiments, our methods show high accuracy in recovering the true sparse model. The relative absence of spurious coefficients permits accurate, stable and fast evaluation of derived quantities such as power spectrum, coherence and Granger causality. Consequently, sparse functional connectivity networks can be computed, in a reasonable time, from data comprising tens of thousands of channels/voxels. This enables a much higher resolution analysis of functional connectivity patterns and community structures in such large networks than is possible using existing time series methods. We apply our method to EEG data where computed network measures and community structures are used to distinguish emotional states as well as to ADHD fMRI data where it is used to distinguish children with ADHD from typically developing children.

Feature selection of EEG signals in neuromarketing

Brain-computer interface (BCI) technology uses electrophysiological (EEG) signals to detect user intent. Research on BCI has seen rapid advancement, with researchers proposing and implementing several signal processing and machine learning approaches for use in different contexts. BCI technology is also used in neuromarketing to study the brain's responses to marketing stimuli. This study sought to detect two preference states (like and dislike) in EEG neuromarketing data using the proposed EEG-based consumer preference recognition system. This study investigated the role of feature selection in BCI to improve the accuracy of preference detection for neuromarketing. Several feature selection methods were used for benchmark testing in multiple BCI studies. Four feature selection approaches, namely, principal component analysis (PCA), minimum redundancy maximum relevance (mRMR), recursive feature elimination (RFE), and ReliefF, were used with five different classifiers: deep neural network (DNN), support vector machine (SVM), k-nearest neighbors (KNN), linear discriminant analysis (LDA), and random forest (RF). The four approaches were compared to evaluate the importance of feature selection. Moreover, the performance of classification algorithms was evaluated before and after feature selection. It was found that feature selection for EEG signals improves the performance of all classifiers.

Two-dimensional CNN-based distinction of human emotions from EEG channels selected by multi-objective evolutionary algorithm

In this study we explore how different levels of emotional intensity (Arousal) and pleasantness (Valence) are reflected in electroencephalographic (EEG) signals. We performed the experiments on EEG data of 32 subjects from the DEAP public dataset, where the subjects were stimulated using 60-s videos to elicitate different levels of Arousal/Valence and then self-reported the rating from 1 to 9 using the self-assessment Manikin (SAM). The EEG data was pre-processed and used as input to a convolutional neural network (CNN). First, the 32 EEG channels were used to compute the maximum accuracy level obtainable for each subject as well as for creating a single model using data from all the subjects. The experiment was repeated using one channel at a time, to see if specific channels contain more information to discriminate between low vs high arousal/valence. The results indicate than using one channel the accuracy is lower compared to using all the 32 channels. An optimization process for EEG channel selection is then designed with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with the objective to obtain optimal channel combinations with high accuracy recognition. The genetic algorithm evaluates all possible combinations using a chromosome representation for all the 32 channels, and the EEG data from each chromosome in the different populations are tested iteratively solving two unconstrained objectives; to maximize classification accuracy and to reduce the number of required EEG channels for the classification process. Best combinations obtained from a Pareto-front suggests that as few as 8–10 channels can fulfill this condition and provide the basis for a lighter design of EEG systems for emotion recognition. In the best case, the results show accuracies of up to 1.00 for low vs high arousal using eight EEG channels, and 1.00 for low vs high valence using only two EEG channels. These results are encouraging for research and healthcare applications that will require automatic emotion recognition with wearable EEG.