Search

Virtual reality (VR)–guided motor imagery (MI) is a widely used approach for motor rehabilitation, especially for patients with severe motor impairments. Most approaches provide visual guidance from the first‐person perspective (1PP). MI training with visual guidance from the third‐person perspective (3PP) remains largely unexplored. We argue that 3PP MI training has its own advantages and can supplement 1PP MI. For some movements beyond the view of 1PP, such as shoulder shrugging and other axial movements, MI are suitable performed under 3PP. However, the efficiency of existing paradigms for 3PP MI is unsatisfactory. We speculate that the absence of sense of body ownership (SOO) from 3PP could be one possible factor and hypothesize that 3PP MI could be enhanced by eliciting SOO over a 3PP avatar. Based on our hypothesis, a novel paradigm was proposed to enhance 3PP MI by inducing full‐body illusion (FBI) from 3PP, which is similar to the so‐called out‐of‐body experience (OBE), using synchronous visuo‐tactile stimulus with VR. The event‐related Electroencephalograph (EEG) desynchronization (ERD) at motor‐related regions from 31 healthy participants were calculated and compared with a control paradigm without "OBE" FBI induction. This study attempts to enhance 3PP MI with FBI induction. It offers an opportunity to perform MI guided by action observation from 3PP with elicited SOO to the observed avatar. We believe that 3PP MI could provide more possibilities for effective rehabilitation training, when SOO could be elicited to a virtual avatar and the present work demonstrates its viability and effectiveness. [ABSTRACT FROM AUTHOR]

The analysis and detection of sleep stages continue to preoccupy researchers, particularly bioinformaticians and neurologists aiming to understand various aspects and functioning of the brain during sleep cycles. This understanding is crucial for developing systems capable of early diagnosis of sleep disorders and adapting these systems for use in operating rooms to monitor the brain activity of patients under sedation or anesthesia. In this study, we apply a set of methods to process and decompose the single-channel EEG neural signal into different brain waves such as beta, alpha, theta, and delta. We then focus on the analysis and optimization of the extracted non-linear features using Principal Component Analysis (PCA) to improve the performance and robustness of the classification of six sleep stages. Classifier validation is performed using the cross-validation method. The results show that when the dimensions of the combined non-linear features are reduced, the RF-PCA model achieves an accuracy of 95.2%, outperforming other models such as MLP, SVM, DT, and GB, as well as recent studies. These findings validate the effectiveness of the system, indicating its potential for embedded implementation in practical applications for sleep disorder diagnosis and monitoring.

Virtual reality (VR)-based rehabilitation training holds great potential for post-stroke motor recovery. Existing VR-based motor imagery (MI) paradigms mostly focus on the first-person perspective, and the benefit of the third-person perspective (3PP) remains to be further exploited. The 3PP is advantageous for movements involving the back or those with a large range because of its field coverage. Some movements are easier to imagine from the 3PP. However, the 3PP training efficiency may be unsatisfactory, which may be attributed to the difficulty encountered when generating a strong sense of ownership (SOO). In this work, we attempt to enhance a visual-guided 3PP MI in stroke patients by eliciting the SOO over a virtual avatar with VR. We propose to achieve this by inducing the so-called out-of-body experience (OBE), which is a full-body illusion (FBI) that people misperceive a 3PP virtual body as his/her own (i.e., generating the SOO to the virtual body). Electroencephalography signals of 13 stroke patients are recorded while MI of the affected upper limb is being performed. The proposed paradigm is evaluated by comparing event-related desynchronization (ERD) with a control paradigm without FBI induction. The results show that the proposed paradigm leads to a significantly larger ERD during MI, indicating a bilateral activation pattern consistent with that in previous studies. In conclusion, 3PP MI can be enhanced in stroke patients by eliciting the SOO through induction of the “OBE” FBI. This study offers more possibilities for virtual rehabilitation in stroke patients and can further facilitate VR application in rehabilitation.

Background: Chemotherapy‐induced peripheral neuropathy (CIPN) includes negative sensations that remain a major chronic problem for cancer survivors. Previous research demonstrated that neurofeedback (a closed‐loop brain–computer interface [BCI]) was effective at treating CIPN versus a waitlist control (WLC). The authors' a priori hypothesis was that BCI would be superior to placebo feedback (placebo control [PLC]) and to WLC in alleviating CIPN and that changes in brain activity would predict symptom report. Methods: Randomization to one of three conditions occurred between November 2014 and November 2018. Breast cancer survivors no longer in treatment were assessed at baseline, at the end of 20 treatment sessions, and 1 month later. Auditory and visual rewards were given over 20 sessions based on each patient's ability to modify their own electroencephalographic signals. The Pain Quality Assessment Scale (PQAS) at the end of treatment was the primary outcome, and changes in electroencephalographic signals and 1‐month data also were examined. Results: The BCI and PLC groups reported significant symptom reduction. The BCI group demonstrated larger effect size differences from the WLC group than the PLC group (mean change score: BCI vs. WLC, −2.60 vs. 0.38; 95% confidence interval, −3.67, −1.46 [p =.000; effect size, 1.07]; PLC, −2.26; 95% confidence interval, −3.33, −1.19 [p =.001 vs. WLC; effect size, 0.9]). At 1 month, symptoms continued to improve only for the BCI group. Targeted brain changes at the end of treatment predicted symptoms at 1 month for the BCI group only. Conclusions: BCI is a promising treatment for CIPN and may have a longer lasting effect than placebo (nonspecific BCI), which is an important consideration for long‐term symptom relief. Although scientifically interesting, the ability to separate real from placebo treatment may not be as important as understanding the placebo effects differently from effects of the intervention. Plain Language Summary: Chemotherapy‐induced nerve pain (neuropathy) can be disabling for cancer survivors; however, the way symptoms are felt depends on how the brain interprets the signals from nerves in the body.We determined that the perception of neuropathy can be changed by working directly with the brain.Survivors in our trial played 20 sessions of a type of video game that was designed to change the way the brain processed sensation and movement.In this, our second trial, we again observed significant improvement in symptoms that lasted after the treatment was complete. The current results demonstrated that a brain–computer interface was an effective treatment for chemotherapy‐induced peripheral neuropathy, with benefits maintained at the 1‐month follow‐up. Although scientifically interesting, the ability to separate real from placebo treatment may not be clinically helpful to obtain longer term significant relief for cancer survivors. [ABSTRACT FROM AUTHOR]

Mixed-reality (MR) environments, in which virtual objects are overlaid on the real environment and shared with peers by wearing a transparent optical head-mounted display, are considered to be well suited for collaborative work. However, no studies have been conducted to provide neuroscientific evidence of its effectiveness. In contrast, inter-brain synchronization has been repeatedly observed in cooperative tasks and can be used as an index of the quality of cooperation. In this study, we used electroencephalography (EEG) to simultaneously measure the brain activity of pairs of participants, a technique known as hyperscanning, during a cooperative motor task to investigate whether inter-brain synchronization would be also observed in a shared MR environment. The participants were presented with virtual building blocks to grasp and build up an object cooperatively with a partner or individually. We found that inter-brain synchronization in the cooperative condition was stronger than that in the individual condition (F(1, 15) = 4.70, p < 0.05). In addition, there was a significant correlation between task performance and inter-brain synchronization in the cooperative condition (rs = 0.523, p < 0.05). Therefore, the shared MR environment was sufficiently effective to evoke inter-brain synchronization, which reflects the quality of cooperation. This study offers a promising neuroscientific method to objectively measure the effectiveness of MR technology.

In this study, the relationship between commercial ads and audiences’ audiovisual emotions has been investigated using neuromarketing approach. Considering research objective, it’s an applied study and regarding method it’s an experimental study. The statistical population of the study includes audience of commercial ads and the statistical sample includes 14 males and 5 females in the range of 22 to 55 years old which selected using purposive sampling method. In data gathering phase, customers’ brain reactions were recorded using Electroencephalogram applying OpenBCI processing software with a sampling rate of 512, in the range of 7-13 HZ and 30 frames per second using FP1. After elimination of the artifacts and calculating data average in the Excel software, commercial ads were classified into three special and one ordinary commercial ads. Analyzing the research data using SPSS software indicates that, there is a significant correlation between the emotions and feelings while watching the special commercial ads and the remembered words, sounds and images. Furthermore, there is not a significant relation between the emotions and feelings while watching the ordinary commercial ads and the remembered words, sounds and images. [ABSTRACT FROM AUTHOR]

Communication is a vital skill of a human's life. People with different types of disabilities may have Complex Communication Needs and may need a wearable device to help them to communicate. Augmentative and Alternative Communication (AAC) is a term which refers to the methods of facilitating or replacing people's communication abilities. Brain–computer interfaces (BCI) and Eye-Gaze Technology (EGT) are two widely used access technologies in AAC devices. However, there are only a few studies that have investigated the utilisation of these technologies in a Virtual Reality (VR) or Augmented Reality (AR) environment. VR and AR are both modern technologies which provide immersive environments. In addition, the Mixed Reality (MR) environment combines virtual reality with real life and may offer extra benefits such as better immersion, better interaction, and more information. This paper proposed an MR-based wearable AAC device and compared the usability and acceptability between its Eye-Gaze (EG) and BCI interaction options. Eight neurotypical participants and two participants with cerebral palsy participated. The result showed high usability (accuracy = 93.30%, the information transfer rate was 8.55 selections per minutes) and acceptability (QUEST 2.0 = 4.30, NASA-TLX = 2.14) in the EG session. In contrast, the usability of the BCI system in the current design was questionable. This novel interaction method using Electroencephalogram signals is not sufficiently exploited at the moment, and more research is suggested in the future. [ABSTRACT FROM AUTHOR]

Due to its convenience and safety, electroencephalography (EEG) data is one of the most widely used signals in motor imagery (MI) brain–computer interfaces (BCIs). In recent years, methods based on deep learning have been widely applied to the field of BCIs, and some studies have gradually tried to apply Transformer to EEG signal decoding due to its superior global information focusing ability. However, EEG signals vary from subject to subject. Based on Transformer, how to effectively use data from other subjects (source domain) to improve the classification performance of a single subject (target domain) remains a challenge. To fill this gap, we propose a novel architecture called MI-CAT. The architecture innovatively utilizes Transformer's self-attention and cross-attention mechanisms to interact features to resolve differential distribution between different domains. Specifically, we adopt a patch embedding layer for the extracted source and target features to divide the features into multiple patches. Then, we comprehensively focus on the intra-domain and inter-domain features by stacked multiple Cross-Transformer Blocks (CTBs), which can adaptively conduct bidirectional knowledge transfer and information exchange between domains. Furthermore, we also utilize two non-shared domain-based attention blocks to efficiently capture domain-dependent information, optimizing the features extracted from the source and target domains to assist in feature alignment. To evaluate our method, we conduct extensive experiments on two real public EEG datasets, Dataset IIb and Dataset IIa, achieving competitive performance with an average classification accuracy of 85.26% and 76.81%, respectively. Experimental results demonstrate that our method is a powerful model for decoding EEG signals and facilitates the development of the Transformer for brain–computer interfaces (BCIs). [ABSTRACT FROM AUTHOR]

Deception is a well-known term that involves acting in a way that it leads another person to believe something that is not true. Deception is a very common occurrence in daily life, and many times it becomes a big problem for national security. To cope with this problem, deception detection has gained a lot of attention recently. In this paper, we have tried to come up with a deceit identification system where we have used electroencephalograph (EEG) data collected by performing a concealed information test. To improve the performance of the system, first we have tried to select the optimal subset of the EEG channels using binary particle swarm optimization and secondly performed support vector machine hyper-parameter optimization using continuous version of PSO. The proposed model is validated using EEG dataset. The performance of the proposed system has resulted in increase of accuracy from 76.98 to 96.45% which is a significant improvement. Also, the proposed approach outperformed in terms of sensitivity, specificity, F1-score and G-measure when compared with state-of-the-art models. [ABSTRACT FROM AUTHOR]

Emotion analysis is the key technology in human–computer emotional interaction and has gradually become a research hotspot in the field of artificial intelligence. The key problems of emotion analysis based on EEG are feature extraction and classifier design. The existing methods of emotion analysis mainly use machine learning and rely on manually extracted features. As an end-to-end method, deep learning can automatically extract EEG features and classify them. However, most of the deep learning models of emotion recognition based on EEG still need manual screening and data pre-processing, and the accuracy and convenience are not high enough. Therefore, this paper proposes a CNN-Bi-LSTM-Attention model to automatically extract the features and classify emotions based on EEG signals. The original EEG data are used as input, a CNN and a Bi-LSTM network are used for feature extraction and fusion, and then the electrode channel weights are balanced through the attention mechanism layer. Finally, the EEG signals are classified to different kinds of emotions. An emotion classification experiment based on EEG is conducted on the SEED dataset to evaluate the performance of the proposed model. The experimental results show that the method proposed in this paper can effectively classify EEG emotions. The method was assessed on two distinctive classification tasks, one with three and one with four target classes. The average ten-fold cross-validation classification accuracy of this method is 99.55% and 99.79%, respectively, corresponding to three and four classification tasks, which is significantly better than the other methods. It can be concluded that our method is superior to the existing methods in emotion recognition, which can be widely used in many fields, including modern neuroscience, psychology, neural engineering, and computer science as well. [ABSTRACT FROM AUTHOR]

For solving the problem of the inevitable decline in the accuracy of cross-subject emotion recognition via Electroencephalograph (EEG) signal transfer learning due to the negative transfer of data in the source domain, this paper offers a new method to dynamically select the data suitable for transfer learning and eliminate the data that may lead to negative transfer. The method which is called cross-subject source domain selection (CSDS) consists of the next three parts. 1) First, a Frank-copula model is established according to Copula function theory to study the correlation between the source domain and the target domain, which is described by the Kendall correlation coefficient. 2) The calculation method for the Maximum Mean Discrepancy is improved to determine the distance between classes in a single source. After normalization, the Kendall correlation coefficient is superimposed, and the threshold is set to identify the source-domain data most suitable for transfer learning. 3) In the process of transfer learning, on the basis of Manifold Embedded Distribution Alignment, the Local Tangent Space Alignment method is used to provide a low-dimensional linear estimation of the local geometry of nonlinear manifolds, which maintains the local characteristics of the sample data after dimensionality reduction. Experimental results show that compared with the traditional methods, the CSDS increases the accuracy of emotion classification by approximately 2.8% and reduces the runtime by approximately 65%.

Burst suppression is a brain state consisting of high-amplitude electrical activity alternating with periods of quieter suppression that can be brought about by disease or by certain anesthetics. Although burst suppression has been studied for decades, few studies have investigated the diverse manifestations of this state within and between human subjects. As part of a clinical trial examining the antidepressant effects of propofol, we gathered burst suppression electroencephalographic (EEG) data from 114 propofol infusions across 21 human subjects with treatment-resistant depression. This data was examined with the objective of describing and quantifying electrical signal diversity. We observed three types of EEG burst activity: canonical broadband bursts (as frequently described in the literature), spindles (narrow-band oscillations reminiscent of sleep spindles), and a new feature that we call low-frequency bursts (LFBs), which are brief deflections of mainly sub-3-Hz power. These three features were distinct in both the time and frequency domains and their occurrence differed significantly across subjects, with some subjects showing many LFBs or spindles and others showing very few. Spectral-power makeup of each feature was also significantly different across subjects. In a subset of nine participants with highdensity EEG recordings, we noted that each feature had a unique spatial pattern of amplitude and polarity when measured across the scalp. Finally, we observed that the Bispectral Index Monitor, a commonly used clinical EEG monitor, does not account for the diversity of EEG features when processing the burst suppression state. Overall, this study describes and quantifies variation in the burst suppression EEG state across subjects and repeated infusions of propofol. These findings have implications for the understanding of brain activity under anesthesia and for individualized dosing of anesthetic drugs. [ABSTRACT FROM AUTHOR]

A brain-computer interface (BCI) based on the electroencephalograph (EEG) signal is a novel technology that provides a direct pathway between human brain and outside world. For a traditional subject-dependent BCI system, a calibration procedure is required to collect sufficient data to build a subjectspecific adaptation model, which can be a huge challenge for stroke patients. In contrast, subject-independent BCI which can shorten or even eliminate the pre-calibration is more time-saving and meets the requirements of new users for quick access to the BCI. In this paper, we design a novel fusion neural network EEG classification framework that uses a specially designed generative adversarial network (GAN), called a filter bank GAN (FBGAN), to acquire high-quality EEG data for augmentation and a proposed discriminative feature network for motor imagery (MI) task recognition. Specifically, multiple sub-bands of MI EEG are first filtered using a filter bank approach, then sparse common spatial pattern (CSP) features are extracted from multiple bands of filtered EEG data, which constrains the GAN to maintain more spatial features of the EEG signal, and finally we design a convolutional recurrent network classification method with discriminative features (CRNN-DF) to recognize MI tasks based on the idea of feature enhancement. The hybrid neural network proposed in this study achieves an average classification accuracy of 72.74 ± 10.44% (mean ± std) in four-class tasks of BCI IV-2a, which is 4.77% higher than the state-of-the-art subject-independent classification method. A promising approach is provided to facilitate the practical application of BCI. [ABSTRACT FROM AUTHOR]

Mixed-reality (MR) environments, in which virtual objects are overlaid on the real environment and shared with peers by wearing a transparent optical head-mounted display, are considered to be well suited for collaborative work. However, no studies have been conducted to provide neuroscientific evidence of its effectiveness. In contrast, inter-brain synchronization has been repeatedly observed in cooperative tasks and can be used as an index of the quality of cooperation. In this study, we used electroencephalography (EEG) to simultaneously measure the brain activity of pairs of participants, a technique known as hyperscanning, during a cooperative motor task to investigate whether inter-brain synchronization would be also observed in a shared MR environment. The participants were presented with virtual building blocks to grasp and build up an object cooperatively with a partner or individually. We found that inter-brain synchronization in the cooperative condition was stronger than that in the individual condition (F(1, 15) = 4.70, p < 0.05). In addition, there was a significant correlation between task performance and inter-brain synchronization in the cooperative condition (rs = 0.523, p < 0.05). Therefore, the shared MR environment was sufficiently effective to evoke inter-brain synchronization, which reflects the quality of cooperation. This study offers a promising neuroscientific method to objectively measure the effectiveness of MR technology. [ABSTRACT FROM AUTHOR]

Burst suppression is a brain state consisting of high-amplitude electrical activity alternating with periods of quieter suppression that can be brought about by disease or by certain anesthetics. Although burst suppression has been studied for decades, few studies have investigated the diverse manifestations of this state within and between human subjects. As part of a clinical trial examining the antidepressant effects of propofol, we gathered burst suppression electroencephalographic (EEG) data from 114 propofol infusions across 21 human subjects with treatment-resistant depression. This data was examined with the objective of describing and quantifying electrical signal diversity. We observed three types of EEG burst activity: canonical broadband bursts (as frequently described in the literature), spindles (narrow-band oscillations reminiscent of sleep spindles), and a new feature that we call low-frequency bursts (LFBs), which are brief deflections of mainly sub-3-Hz power. These three features were distinct in both the time and frequency domains and their occurrence differed significantly across subjects, with some subjects showing many LFBs or spindles and others showing very few. Spectral-power makeup of each feature was also significantly different across subjects. In a subset of nine participants with high-density EEG recordings, we noted that each feature had a unique spatial pattern of amplitude and polarity when measured across the scalp. Finally, we observed that the Bispectral Index Monitor, a commonly used clinical EEG monitor, does not account for the diversity of EEG features when processing the burst suppression state. Overall, this study describes and quantifies variation in the burst suppression EEG state across subjects and repeated infusions of propofol. These findings have implications for the understanding of brain activity under anesthesia and for individualized dosing of anesthetic drugs.

In motor imagery (MI) brain–computer interface (BCI) research, some researchers have designed MI paradigms of force under a unilateral upper-limb static state. It is difficult to apply these paradigms to the dynamic force interaction process between the robot and the patient in a brain-controlled rehabilitation robot system, which needs to induce thinking states of the patient's demand for assistance. Therefore, in our research, according to the movement of wiping the table in human daily life, we designed a three-level-force MI paradigm under a unilateral upper-limb dynamic state. Based on the event-related de-synchronization (ERD) feature analysis of the electroencephalography (EEG) signals generated by the brain's force change motor imagination, we proposed a multi-scale temporal convolutional network with attention mechanism (MSTCN-AM) algorithm to recognize ERD features of MI-EEG signals. Aiming at the slight feature differences of single-trial MI-EEG signals among different levels of force, the MSTCN module was designed to extract fine-grained features of different dimensions in the time–frequency domain. The spatial convolution module was then used to learn the area differences of space domain features. Finally, the attention mechanism dynamically weighted the time–frequency–space domain features to improve the algorithm's sensitivity. The results showed that the accuracy of the algorithm was 86.4 ± 14.0% for the three-level-force MI-EEG data collected experimentally. Compared with the baseline algorithms (OVR-CSP+SVM (77.6 ± 14.5%), Deep ConvNet (75.3 ± 12.3%), Shallow ConvNet (77.6 ± 11.8%), EEGNet (82.3 ± 13.8%), and SCNN-BiLSTM (69.1 ± 16.8%)), our algorithm had higher classification accuracy with significant differences and better fitting performance. [ABSTRACT FROM AUTHOR]

Visual analysis of an electroencephalogram (EEG) by medical professionals is highly time-consuming and the information is difficult to process. To overcome these limitations, several automated seizure detection strategies have been introduced by combining signal processing and machine learning. This paper proposes a hybrid optimization-controlled ensemble classifier comprising the AdaBoost classifier, random forest (RF) classifier, and the decision tree (DT) classifier for the automatic analysis of an EEG signal dataset to predict an epileptic seizure. The EEG signal is pre-processed initially to make it suitable for feature selection. The feature selection process receives the alpha, beta, delta, theta, and gamma wave data from the EEG, where the significant features, such as statistical features, wavelet features, and entropy-based features, are extracted by the proposed hybrid seek optimization algorithm. These extracted features are fed forward to the proposed ensemble classifier that produces the predicted output. By the combination of corvid and gregarious search agent characteristics, the proposed hybrid seek optimization technique has been developed, and is used to evaluate the fusion parameters of the ensemble classifier. The suggested technique's accuracy, sensitivity, and specificity are determined to be 96.6120%, 94.6736%, and 91.3684%, respectively, for the CHB-MIT database. This demonstrates the effectiveness of the suggested technique for early seizure prediction. The accuracy, sensitivity, and specificity of the proposed technique are 95.3090%, 93.1766%, and 90.0654%, respectively, for the Siena Scalp database, again demonstrating its efficacy in the early seizure prediction process. [ABSTRACT FROM AUTHOR]

For solving the problem of the inevitable decline in the accuracy of cross-subject emotion recognition via Electroencephalograph (EEG) signal transfer learning due to the negative transfer of data in the source domain, this paper offers a new method to dynamically select the data suitable for transfer learning and eliminate the data that may lead to negative transfer. The method which is called cross-subject source domain selection (CSDS) consists of the next three parts. 1) First, a Frank-copula model is established according to Copula function theory to study the correlation between the source domain and the target domain, which is described by the Kendall correlation coefficient. 2) The calculation method for the Maximum Mean Discrepancy is improved to determine the distance between classes in a single source. After normalization, the Kendall correlation coefficient is superimposed, and the threshold is set to identify the source-domain data most suitable for transfer learning. 3) In the process of transfer learning, on the basis of Manifold Embedded Distribution Alignment, the Local Tangent Space Alignment method is used to provide a low-dimensional linear estimation of the local geometry of nonlinear manifolds, which maintains the local characteristics of the sample data after dimensionality reduction. Experimental results show that compared with the traditional methods, the CSDS increases the accuracy of emotion classification by approximately 2.8% and reduces the runtime by approximately 65%. [ABSTRACT FROM AUTHOR]

As human's simple tasks are being increasingly replaced by autonomous systems and robots, it is likely that the responsibility of handling more complex tasks will be more often placed on human workers. Thus, situations in which workplace tasks change before human workers become proficient at those tasks will arise more frequently due to rapid changes in business trends. Based on this background, the importance of preventing human error will become increasingly crucial. Existing studies on human error reveal how task errors are related to heart rate variability (HRV) indexes and electroencephalograph (EEG) indexes. However, in terms of preventing human error, analysis on their relationship with conditions before human error occurs (i.e., the human pre-error state) is still insufficient. This study aims at identifying biological indexes potentially useful for the detection of high-risk psychological states. As a result of correlation analysis between the number of errors in a Stroop task and the multiple HRV and EEG indexes obtained before and during the task, significant correlations were obtained with respect to several biological indexes. Specifically, we confirmed that conditions before the task are important for predicting the human error risk in high-cognitive-load tasks while conditions both before and during tasks are important in low-cognitive-load tasks. [ABSTRACT FROM AUTHOR]

Globally, 14%–20% of road accidents are mainly due to driver fatigue, the causes of which are instance sickness, travelling for long distance, boredom as a result of driving along the same route consistently, lack of enough sleep, etc. This article presents a flexible analytic wavelet transform (FAWT)-based advanced machine learning method using single modality neurophysiological brain electroencephalogram signals to detect the driver fatigues (i.e., FATIGUE and REST) and to alarm the driver at the earliest to prevent the risks during driving. First, signals of undertaking study groups are subjected to the FAWT that separates the signals into LP and HP channels. Subsequently, relevant subband frequency components with proper setting of tuning parameters are extracted. Then, comprehensive low order features which are statistically significant for $p< 0.05$ , are evaluated from the input subband searched space and embedded them to various ensemble methods under multiboost strategy. Results are evaluated in terms of various parameters including accuracy, F-score, AUC, and $\kappa$. Results show that the proposed approach is promising in classification and it achieves optimum individual accuracies of 97.10% and 97.90% in categorizing FATIGUE and REST states with F-score of 97.50%, AUC of 0.975, and $\kappa$ of 0.950. Comparison of the proposed method with the prior methods in the context of feature, accuracy, and modality profiles undertaken, indicates the effectiveness and reliability of the proposed method for real-world applications. [ABSTRACT FROM AUTHOR]

In order to discriminate situation awareness (SA) levels on the basis of SA-sensitive electroencephalography (EEG) features, the high-SA (HSA) group and low-SA (LSA) groups, which are representative of two SA levels, were classified according to the situation awareness global assessment technology (SAGAT) scores measured in the multi-attribute task battery (MATB) II tasks. Furthermore, three types of EEG features, namely, absolute power, relative power, and slow-wave/fast-wave (SW/FW), were explored using spectral analysis. In addition, repeated analysis of variance (ANOVA) was conducted in three brain regions (frontal, central, and parietal) × three brain lateralities (left, middle, and right) × two SA groups (LSA and HSA) to explore SA-sensitive EEG features. The statistical results indicate a significant difference between the two SA groups according to SAGAT scores; moreover, no significant difference was found for the absolute power of four waves (delta (δ), theta (θ), alpha (α), and beta (β)). In addition, the LSA group had a significantly lower β relative power than the HSA group in central and partial regions. Lastly, compared with the HSA group, the LSA group had higher θ/β and (θ + α)/(α + β) in all analyzed brain regions, higher α/β in the parietal region, and higher (θ + α)/β in all analyzed regions except for the left and right laterality in the frontal region. The above SA-sensitive EEG features were fed into principal component analysis (PCA) and the Bayes method to discriminate different SA groups, and the accuracies were 83.3% for the original validation and 70.8% for the cross-validation. The results provide a basis for real-time assessment and discrimination of SA by investigating EEG features, thus contributing to monitoring SA decrement that might lead to threats to flight safety. [ABSTRACT FROM AUTHOR]

In recent studies, machine learning and deep learning strategies have been explored in many EEG-based application for best performance. More specifically, convolutional neural networks (CNNs) have demonstrated incredible capacity in electroencephalograph (EEG)-evoked emotion classification tasks. In preexisting case, CNN-based emotion classification techniques using EEG signals mostly involve a moderately intricate phase of feature extrication before any network model implementation. The CNNs are not able to well describe the natural interrelation among the various EEG channels, which basically provides essential data for the classification of different emotion states. In this paper, an efficacious and advanced version of CNN called Emotion-based Capsule Network (EmotionCapsNet) for multi-channel EEG-based emotion classification to achieve better classification accuracy is presented. EmotionCapsNet has been applied to the raw EEG signals as well as 2D image representation generated from EEG signals which can extricate descriptive and complex features from the EEG signals and decide the different emotional states. The proposed system is then compared with the other conventional machine learning and deep learning-based CNN model. Our strategy accomplishes an average accuracy of 77.50%, 78.44% and 79.38% for valence, arousal and dominance on the DEAP, 79.06%, 78.90% and 79.69% on AMIGOS and attains an average accuracy of 80.34%, 83.04% and 82.50% for valence, arousal and dominance on the DREAMER, respectively. These outcomes demonstrate that adapted strategy yields comparable precision on raw EEG signal and it also provides better classification results on spatiotemporal feature of EEG signal for emotion classification task. [ABSTRACT FROM AUTHOR]

High-quality sleep is linked with physical development, cognitive function, learning, and attention in children. Since early symptoms of sleep disorders in children are not obvious and require long-term monitoring, there is an urgent need to develop a method for monitoring children’s sleep that can prevent and diagnose these disorders in advance. Polysomnography (PSG) is the basic test for sleep disorders recommended by clinical guidelines. Sleep quality can be assessed and sleep disorders can be identified by observing the changes in patterns of PSG during each sleep period. Sleep staging in children was researched and single-channel electroencephalogram (EEG) signals recorded by PSG was used in this study. On the basis of Alexnet, we use a one-dimensional convolutional neural network (1D-CNN) model instead of a two-dimensional model to propose a 1D-CNN structure composed of five convolutional layers, three pooling layers, and three fully connected layers, as well as a batch normalization layer to 1D-CNN while keeping the size of the convolutional kernel constant. Moreover, the dataset was augmented with an overlapping method to address its small size. The experimental results showed that the accuracy of this model for children’s sleep staging was 84.3%. According to the normalized confusion matrix obtained from the PSG data of Beijing Children’s Hospital, the classification performance of wake, N2, N3, and REM stages of sleep was very good. Because stage N1 sleep was misclassified as wake, N2, and REM sleep in some cases, future research should focus on improving the accuracy of stage N1 sleep. Overall, the 1D-CNN model proposed in this paper can realize automatic sleep staging for children based on single-channel EEG with sleep stage markers. In the future, more research is needed to develop a more suitable sleep staging strategy for children and to conduct experiments with a larger amount of data.

• Selecting the optimal set of preprocessing parameters that can enhance the classification results using the Random Search Optimization method. • Implementing multiple CNN architectures and selected the optimal one based on the mean accuracy of 10-fold cross-validation evaluation method. • Applying the automatic Hyperparameter tuning framework 'Optuna' to identify the optimal set of the CNN hyperparameters. • Fusing the CNN with Machine Learning classifiers (Deep Hybrid Learning). • Benefit from the power of the CNN in automatically extracting EEG features and the advantages of the ML classifiers. Driver drowsiness is a severe issue that has contributed to numerous fatal accidents and injuries. Thus, detecting driver drowsiness is an important task that has been the subject of intensive research in recent years. There have been numerous proposed physiological signals for detecting driver drowsiness. However, the Electroencephalographic (EEG) signal is the most commonly used due to its direct relationship with drowsiness and its simplicity of acquisition. Recently, different Machine Learning (ML) and Deep Learning (DL) models have been proposed to detect driver drowsiness. This study utilized a publicly accessible dataset containing twelve healthy participants. Reading numerous research papers, we determined no specific EEG-based drowsiness preprocessing parameter values. Consequently, as a first step, and for the first time, to our knowledge in this field, we applied an optimization algorithm to determine the optimal preprocessing parameter values using a CNN model and accuracy as the objective function. The obtained results demonstrated the importance of selecting the correct values, as the mean accuracy score increased from 91% before optimization to 95% after optimization for the proposed CNN. The training time has been reduced. Also, as a second step, we have used the Optuna Hyperparameter optimization framework to select the optimal CNN Hyperparameters, which increased the mean accuracy from 95% to 97%. Finally, to take advantage of Deep Hybrid learning, we have fused the CNN "features extractor" with seven ML classifiers, with the CNN-SVM classifier achieving the highest average accuracy of 99.9%, and the training time has been reduced to a shallow value. [ABSTRACT FROM AUTHOR]

• A novel dynamic graph attention network is proposed for EEG emotion recognition. • The high accuracy can be obtained from the DGAT model in EEG emotion recognition. • The channel connectivity can reflect the synergistic relationships within the brain. Deep learning classification models based on electroencephalogram (EEG) emotion recognition have demonstrated considerable proficiency in the categorization of emotional states. However, these models have limitations in their capability to analyze the active states and cooperative relationships among distinct brain regions. This study proposes a dynamic graph attention network (DGAT) for EEG emotion recognition, which learns the features of each channel and leverages multiple-head self-attention mechanisms to capture non-Euclidean relationships between channels. Then, we use differential entropy features of emotions signals on the SJTU emotion EEG dataset (SEED). The DGAT model achieved improved subject-dependent and cross-subject classification accuracy compared to previous models. Moreover, ablation studies show that the channel weight matrix(CWM) and appropriate hyper-parameters can improve the performance of the DGAT model significantly. Furthermore, by conducting interpretable analysis of the new connections and electrode weights learned by the model, we find that these connection weight relationships reflect a certain degree of coordination within the brain for EEG-based emotion recognition. These findings provide a new method for EEG emotion recognition and highlights the potential for using deep learning models to analyze the active state and synergistic relationships among brain regions. [ABSTRACT FROM AUTHOR]

Functional connectivity related to familiarity has recently been investigated in the context of various stimuli (e.g., words, faces, pictures, music, and video). However, the directed functional connectivity patterns with different attention indexes as a response to familiar/unfamiliar stimuli remain unclear. In the current study, we employed the Directed Transfer Function (DTF) to estimate the information flow between brain areas. This method was reported to be practically robust to volume conduction. Furthermore, the hierarchical clustering approach was utilized to group subjects based on the attention index, i.e., the alpha/theta ratio of fronto-central (frontal to central and central to frontal) features. Three major findings were revealed from this study. First, all subjects had different attention indexes when they watched familiar/unfamiliar videos. Then, subjects were sorted into three groups: low index (LI), middle index (MI), and high index (HI). Second, a competition between two states (familiar/unfamiliar) showed that the information flows of familiar stimuli were greater than unfamiliar stimuli, which involved significant effects in the frontal, temporal, and parietal areas. Third, comparison between groups (LI/MI/HI) demonstrated that the frontal and central regions were the primary sources that distributed information flows to almost the whole brain, particularly during familiar conditions. This result indicates that these two regions may play an important role in attentional processing.

Objective: Most of effectiveness assessments of the widely-used Massage therapy were based on subjective routine clinical assessment tools, such as Visual Analogue Scale (VAS) score. However, few studies demonstrated the impact of massage on the Electroencephalograph (EEG) rhythm decoding of Motor imagery (MI) and motion execution (ME) with trunk left/right bending in patients with skeletal muscle pain. Method: We used the sample entropy (SampEn), permutation entropy (PermuEn), common spatial pattern (CSP) features, support vector machine (SVM) and logic regression (LR) classifiers. We also used the convolutional neural network (CNN) and attention-based bi-directional long short-term memory (BiLSTM) for classification. Results: The averaged SampEn and PermuEn values of alpha rhythm decreased in almost fourteen channels for five statuses (quiet, MI with left/right bending, ME with left/right bending). It indicated that massage alleviates the pain for the patients of skeletal pain. Furthermore, compared with the SVM and LR classifiers, the BiLSTM method achieved a better area under curve (AUC) of 0.89 for the classification of MI with trunk left/right bending before massage. The AUC became smaller after massage than that before massage for the classification of MI with trunk left/right bending using CNN and BiLSTM methods. The Permutation direct indicator (PDI) score showed the significant difference for patients in different statuses (before vs after massage, and MI vs ME). Conclusions: Massage not only affects the quiet status, but also affects the MI and ME. Clinical Impact: Massage therapy may affect a bit on the accuracy of MI with trunk left/right bending and it change the topography of MI and ME with trunk left/right bending for the patients with skeletal muscle pain.

BACKGROUND: Swallowing disorders represent one of the most common complications after cerebral infarction. OBJECTIVE: To study the effects of different frequencies of repetitive transcranial magnetic stimulation (rTMS) on swallowing disorders after cerebral infarction. METHODS: Ninety patients with swallowing disorder after cerebral infarction were enrolled and randomly assigned to three groups: the 10 Hz frequency rTMS group (30 patients), the 5 Hz frequency rTMS group (30 patients), and the 1 Hz frequency rTMS group (30 patients); another 90 healthy persons without swallowing disorders were included as the control group. The Kubota's water-swallow test, the video fluoroscopic swallow study (VFSS), and the Electroencephalograph (EEG) were analyzed before and after treatment; the EEG of the control group was detected as the baseline. RESULTS: The Kubota's water-swallow test scores were significantly decreased while the scores of pharynx period and the aspiration degree of VFSS significantly increased in 10 Hz frequency rTMS group than before treatment (P≤0.05); the amplitudes of C3 of the EEG significantly increased in three frequency groups than before treatment (P≤0.05). CONCLUSIONS: 10 Hz frequency of rTMS is effective for the treatment of swallowing disorder after cerebral infarction, the excitement of C3 area maybe the therapeutic target of rTMS on swallowing disorder after cerebral infarction. [ABSTRACT FROM AUTHOR]

Cognitive brain–computer interface (cBCI) is an emerging area with applications in neurorehabilitation and performance monitoring. cBCI works on the cognitive brain signal that does not require a person to pay much effort unlike the motor brain-computer interface (BCI) however existing cBCI systems currently offer lower accuracy than the motor BCI. Since attention is one of the cognitive signals that can be used to realise the cBCI, this work uses the multiple object tracking (MOT) task to acquire the desired electroencephalograph (EEG) signal from healthy subjects. The main objective of the paper is to explore the preliminary applications of support vector machine (SVM) classifier to classify the attentional load in multiple object tracking task. Results show that the attentional load can be classified using SVM with sensitivity, specificity, and accuracy of 94.03%, 92.50%, and 93.28%, respectively using the spectral entropy EEG feature. The classification performance promises the potential application of the current approach in the cognitive brain-computer interface for neurorehabilitation. [ABSTRACT FROM AUTHOR]

Integrating education practices and measurements of brain activity has the potential to make learning more engaging and productive. Direct recordings of electrical activity in the brain provide important information about the complex dynamics of the cognitive processes and mental states that occur during learning, which can ultimately empower learners. In this article, electroencephalographic (EEG) methodologies, including the time-frequency and event-related potential techniques, are introduced, and the application of these techniques to studies of digital learning studies is discussed. Considerations of how to collect high quality data in both laboratory and real world settings are also presented, along with potential research directions. Finally, a general guideline for publishing results is offered. These issues are critical for producing useful applications of EEG studies to the digital learning research community.

Purpose:: This study proposes a novel convolutional neural network (CNN) structure in conjunction with classical machine learning models, utilizing the raw electroencephalography (EEG) signal as the input to diagnose attention deficit hyperactivity disorder (ADHD) in children. The proposed EEG-based approach does not require transformation or artifact rejection techniques. Methods:: In the first step, the suggested method uses raw EEG to train a CNN to diagnose ADHD. Then, the feature maps from different layers of the trained CNN are extracted and used to train some classical classifiers such as support vector machine (SVM), logistic regression (LR), random forest (RF), etc. This study benefits from an extended version of a dataset acquired from 61 participants diagnosed with ADHD and 60 individuals in control group, age 7 through 12 years old. Results:: The initial CNN structure (without further use of feature maps) achieved an accuracy of 86.33±2.64% in 5-fold cross-validation scheme on training set, which is superior to results reported in previous studies. However, in order to increase the efficacy of the classifiers we used various feature representations across different CNN layers and after a rigorous evaluation of candidate classifiers, logistic regression provided an accuracy of 91.16±0.03% in training epochs using 5-fold cross-validation scheme and 95.83% in ADHD identification in unseen epochs, were achieved. Also, other metrics such as precision, sensitivity, F1-score and receiver of operating characteristic (ROC) were presented for better comparison of different hybrid methods. Conclusion:: The suggested method for detection of ADHD in children shows high performance in different metrics such as accuracy, sensitivity, and specificity, which is superior to previously reported results.

In motor imagery (MI) brain–computer interface (BCI) research, some researchers have designed MI paradigms of force under a unilateral upper-limb static state. It is difficult to apply these paradigms to the dynamic force interaction process between the robot and the patient in a brain-controlled rehabilitation robot system, which needs to induce thinking states of the patient’s demand for assistance. Therefore, in our research, according to the movement of wiping the table in human daily life, we designed a three-level-force MI paradigm under a unilateral upper-limb dynamic state. Based on the event-related de-synchronization (ERD) feature analysis of the electroencephalography (EEG) signals generated by the brain’s force change motor imagination, we proposed a multi-scale temporal convolutional network with attention mechanism (MSTCN-AM) algorithm to recognize ERD features of MI-EEG signals. Aiming at the slight feature differences of single-trial MI-EEG signals among different levels of force, the MSTCN module was designed to extract fine-grained features of different dimensions in the time–frequency domain. The spatial convolution module was then used to learn the area differences of space domain features. Finally, the attention mechanism dynamically weighted the time–frequency–space domain features to improve the algorithm’s sensitivity. The results showed that the accuracy of the algorithm was 86.4 ± 14.0% for the three-level-force MI-EEG data collected experimentally. Compared with the baseline algorithms (OVR-CSP+SVM (77.6 ± 14.5%), Deep ConvNet (75.3 ± 12.3%), Shallow ConvNet (77.6 ± 11.8%), EEGNet (82.3 ± 13.8%), and SCNN-BiLSTM (69.1 ± 16.8%)), our algorithm had higher classification accuracy with significant differences and better fitting performance.

Electroencephalograph (EEG) brain-computer interfaces (BCI) have potential to provide new paradigms for controlling computers and devices. The accuracy of brain pattern classification in EEG BCI is directly affected by the quality of features extracted from EEG signals. Currently, feature extraction heavily relies on prior knowledge to engineer features (for example from specific frequency bands); therefore, better extraction of EEG features is an important research direction. In this work, we propose an end-to-end deep neural network that automatically finds and combines features for motor imagery (MI) based EEG BCI with 4 or more imagery classes (multi-task). First, spectral domain features of EEG signals are learned by compact convolutional neural network (CCNN) layers. Then, gated recurrent unit (GRU) neural network layers automatically learn temporal patterns. Lastly, an attention mechanism dynamically combines (across EEG channels) the extracted spectral-temporal features, reducing redundancy. We test our method using BCI Competition IV-2a and a data set we collected. The average classification accuracy on 4-class BCI Competition IV-2a was 85.1 % ± 6.19 %, comparable to recent work in the field and showing low variability among participants; average classification accuracy on our 6-class data was 64.4 % ± 8.35 %. Our dynamic fusion of spectral-temporal features is end-to-end and has relatively few network parameters, and the experimental results show its effectiveness and potential., Competing Interests: Declaration of competing interest The authors declare that they have no competing financial interests or personal relationships that could influence the work reported in this article., (Copyright © 2024 Elsevier Ltd. All rights reserved.)

This article presents a new user-independent emotion classification method that classifies four distinct emotions using electroencephalograph (EEG) signals and the broad learning system (BLS). The public DEAP and MAHNOB-HCI databases are used. Just one EEG electrode channel is selected for the feature extraction process. Continuous wavelet transform (CWT) is then utilized to extract the proposed gray-scale image (GSI) feature which describes the EEG brain activation in both time and frequency domains. Finally, the new BLS is constructed for the emotion classification process, which successfully upgrades the efficiency of emotion classification based on EEG brain signals. The experiment results show that the proposed work produces a robust system with high accuracy of approximately 93.1% and training process time of approximately 0.7 s for the DEAP database, as well as, the high average accuracy of approximately 94.4% and training process time of approximately 0.6 s for MAHNOB-HCI database. [ABSTRACT FROM AUTHOR]

Background: Anorexia nervosa (AN) is a serious and life-threatening psychiatric condition. With a paucity of approved treatments, there is a desperate need for novel treatment avenues to be explored. Here, we present (1) an overview of the ways through which Public Patient Involvement (PPI) has informed a trial of psilocybin-assisted therapy for AN and (2) a protocol for a pilot study of psilocybin-assisted therapy in AN currently underway at Imperial College London. The study aims to assess the feasibility, brain mechanisms and preliminary outcomes of treating anorexia nervosa with psilocybin. Methods: (1) PPI: Across two online focus groups, eleven individuals with lived experience of AN were presented with an overview of the protocol. Their feedback not only identified solutions to possible barriers for future participants, but also helped the research team to better understand the concept of " recovery" from the perspective of those with lived experience. (2) Protocol: Twenty female participants [21–65 years old, body mass index (BMI) 15 kg/m2 or above] will receive three oral doses of psilocybin (up to 25 mg) over a 6-week period delivered in a therapeutic environment and enveloped by psychological preparation and integration. We will work with participant support networks (care teams and an identified support person) throughout and there will be an extended remote follow-up period of 12 months. Our two-fold primary outcomes are (1) psychopathology (Eating Disorder Examination) across the 6-month follow-up and (2) readiness and motivation to engage in recovery (Readiness and Motivation Questionnaire) across the 6-week trial period. Neurophysiological outcome measures will be: (1) functional magnetic resonance imaging (fMRI) brain changes from baseline to 6-week endpoint and (2) post-acute changes in electroencephalography (EEG) activity, including an electrophysiological marker of neuronal plasticity. Discussion: The results of this pilot study will not only shed light on the acceptability, brain mechanisms, and impression of the potential efficacy of psilocybin as an adjunct treatment for AN but will be essential in shaping a subsequent Randomised Control Trial (RCT) that would test this treatment against a suitable control condition. Clinical Trial Registration: identifier: NCT04505189. [ABSTRACT FROM AUTHOR]

Background: Anorexia nervosa (AN) is a serious and life-threatening psychiatric condition. With a paucity of approved treatments, there is a desperate need for novel treatment avenues to be explored. Here, we present (1) an overview of the ways through which Public Patient Involvement (PPI) has informed a trial of psilocybin-assisted therapy for AN and (2) a protocol for a pilot study of psilocybin-assisted therapy in AN currently underway at Imperial College London. The study aims to assess the feasibility, brain mechanisms and preliminary outcomes of treating anorexia nervosa with psilocybin.Methods: (1) PPI: Across two online focus groups, eleven individuals with lived experience of AN were presented with an overview of the protocol. Their feedback not only identified solutions to possible barriers for future participants, but also helped the research team to better understand the concept of “recovery” from the perspective of those with lived experience. (2) Protocol: Twenty female participants [21–65 years old, body mass index (BMI) 15 kg/m2 or above] will receive three oral doses of psilocybin (up to 25 mg) over a 6-week period delivered in a therapeutic environment and enveloped by psychological preparation and integration. We will work with participant support networks (care teams and an identified support person) throughout and there will be an extended remote follow-up period of 12 months. Our two-fold primary outcomes are (1) psychopathology (Eating Disorder Examination) across the 6-month follow-up and (2) readiness and motivation to engage in recovery (Readiness and Motivation Questionnaire) across the 6-week trial period. Neurophysiological outcome measures will be: (1) functional magnetic resonance imaging (fMRI) brain changes from baseline to 6-week endpoint and (2) post-acute changes in electroencephalography (EEG) activity, including an electrophysiological marker of neuronal plasticity.Discussion: The results of this pilot study will not only shed light on the acceptability, brain mechanisms, and impression of the potential efficacy of psilocybin as an adjunct treatment for AN but will be essential in shaping a subsequent Randomised Control Trial (RCT) that would test this treatment against a suitable control condition.Clinical Trial Registration: identifier: NCT04505189.

Visual analysis of an electroencephalogram (EEG) by medical professionals is highly time-consuming and the information is difficult to process. To overcome these limitations, several automated seizure detection strategies have been introduced by combining signal processing and machine learning. This paper proposes a hybrid optimization-controlled ensemble classifier comprising the AdaBoost classifier, random forest (RF) classifier, and the decision tree (DT) classifier for the automatic analysis of an EEG signal dataset to predict an epileptic seizure. The EEG signal is pre-processed initially to make it suitable for feature selection. The feature selection process receives the alpha, beta, delta, theta, and gamma wave data from the EEG, where the significant features, such as statistical features, wavelet features, and entropy-based features, are extracted by the proposed hybrid seek optimization algorithm. These extracted features are fed forward to the proposed ensemble classifier that produces the predicted output. By the combination of corvid and gregarious search agent characteristics, the proposed hybrid seek optimization technique has been developed, and is used to evaluate the fusion parameters of the ensemble classifier. The suggested technique’s accuracy, sensitivity, and specificity are determined to be 96.6120%, 94.6736%, and 91.3684%, respectively, for the CHB-MIT database. This demonstrates the effectiveness of the suggested technique for early seizure prediction. The accuracy, sensitivity, and specificity of the proposed technique are 95.3090%, 93.1766%, and 90.0654%, respectively, for the Siena Scalp database, again demonstrating its efficacy in the early seizure prediction process.

As human’s simple tasks are being increasingly replaced by autonomous systems and robots, it is likely that the responsibility of handling more complex tasks will be more often placed on human workers. Thus, situations in which workplace tasks change before human workers become proficient at those tasks will arise more frequently due to rapid changes in business trends. Based on this background, the importance of preventing human error will become increasingly crucial. Existing studies on human error reveal how task errors are related to heart rate variability (HRV) indexes and electroencephalograph (EEG) indexes. However, in terms of preventing human error, analysis on their relationship with conditions before human error occurs (i.e., the human pre-error state) is still insufficient. This study aims at identifying biological indexes potentially useful for the detection of high-risk psychological states. As a result of correlation analysis between the number of errors in a Stroop task and the multiple HRV and EEG indexes obtained before and during the task, significant correlations were obtained with respect to several biological indexes. Specifically, we confirmed that conditions before the task are important for predicting the human error risk in high-cognitive-load tasks while conditions both before and during tasks are important in low-cognitive-load tasks.