Search

Schizophrenia (SZ) is a prevalent mental disorder characterized by cognitive, emotional, and behavioral changes. Symptoms of SZ include hallucinations, illusions, delusions, lack of motivation, and difficulties in concentration. While the exact causes of SZ remain unproven, factors such as brain injuries, stress, and psychotropic drugs have been implicated in its development. SZ can be classified into different types, including paranoid, disorganized, catatonic, undifferentiated, and residual. Diagnosing SZ involves employing various tools, including clinical interviews, physical examinations, psychological evaluations, the Diagnostic and Statistical Manual of Mental Disorders (DSM), and neuroimaging techniques. Electroencephalography (EEG) recording is a significant functional neuroimaging modality that provides valuable insights into brain function during SZ. However, EEG signal analysis poses challenges for neurologists and scientists due to the presence of artifacts, long-term recordings, and the utilization of multiple channels. To address these challenges, researchers have introduced artificial intelligence (AI) techniques, encompassing conventional machine learning (ML) and deep learning (DL) methods, to aid in SZ diagnosis. This study reviews papers focused on SZ diagnosis utilizing EEG signals and AI methods. The introduction section provides a comprehensive explanation of SZ diagnosis methods and intervention techniques. Subsequently, review papers in this field are discussed, followed by an introduction to the AI methods employed for SZ diagnosis and a summary of relevant papers presented in tabular form. Additionally, this study reports on the most significant challenges encountered in SZ diagnosis, as identified through a review of papers in this field. Future directions to overcome these challenges are also addressed. The discussion section examines the specific details of each paper, culminating in the presentation of conclusions and findings. [ABSTRACT FROM AUTHOR]

This special issue is similar to our previous special issues (Kennedy et al. in Comput. Math. Organ. Theory 16(3):217-219, ; 17(3):225-228, ) in that it includes articles based on the award winning conference papers of the, here, 2011 BRiMS Annual Conference. These articles were reviewed by the editors, extended to journal article length, and then peer-reviewed and revised before being accepted. The articles include a new way to evaluate designs of interfaces for safety critical systems (Bolton in Comput. Math. Organ. Theory, ), an article that extends our understanding of how to model situation awareness (SA) in a cognitive architecture (Rodgers et al. in Comput. Math. Organ. Theory, ), an article that presents electroencephalography (EEG) data used to derive dynamic neurophysiologic models of engagement in teamwork (Stevens et al. in Comput. Math. Organ. Theory, ), and an article that demonstrates using machine learning to generate models and an example application of that tool (Best in Comput. Math. Organ. Theory, ). After presenting a brief summary of each paper we will see some recurrent themes of task analysis, team and individual models, spatial reasoning, usability issues, and particularly that they are models that interact with each other or systems. [ABSTRACT FROM AUTHOR]

Mental stress is a common problem that affects individuals all over the world. Stress reduces human functionality during routine work and may lead to severe health defects. Early detection of stress is important for preventing diseases and other negative health-related consequences of stress. Several neuroimaging techniques have been utilized to assess mental stress, however, due to its ease of use, robustness, and non-invasiveness, electroencephalography (EEG) is commonly used. This paper aims to fill a knowledge gap by reviewing the different EEG-related deep learning algorithms with a focus on Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for the evaluation of mental stress. The review focuses on data representation, individual deep neural network model architectures, hybrid models, and results amongst others. The contributions of the paper address important issues such as data representation and model architectures. Out of all reviewed papers, 67% used CNN, 9% LSTM, and 24% hybrid models. Based on the reviewed literature, we found that dataset size and different representations contributed to the performance of the proposed networks. Raw EEG data produced classification accuracy around 62% while using spectral and topographical representation produced up to 88%. Nevertheless, the roles of generalizability across different deep learning models and individual differences remain key areas of inquiry. The review encourages the exploration of innovative avenues, such as EEG data image representations concurrently with graph convolutional neural networks (GCN), to mitigate the impact of inter-subject variability. This novel approach not only allows us to harmonize structural nuances within the data but also facilitates the integration of temporal dynamics, thereby enabling a more comprehensive assessment of mental stress levels. [ABSTRACT FROM AUTHOR]

Historically, the analysis of stimulus-dependent time–frequency patterns has been the cornerstone of most electroencephalography (EEG) studies. The abnormal oscillations in high-frequency waves associated with psychotic disorders during sensory and cognitive tasks have been studied many times. However, any significant dissimilarity in the resting-state low-frequency bands is yet to be established. Spectral analysis of the alpha and delta band waves shows the effectiveness of stimulus-independent EEG in identifying the abnormal activity patterns of pathological brains. A generalized model incorporating multiple frequency bands should be more efficient in associating potential EEG biomarkers with first-episode psychosis (FEP), leading to an accurate diagnosis. We explore multiple machine-learning methods, including random-forest, support vector machine, and Gaussian process classifier (GPC), to demonstrate the practicality of resting-state power spectral density (PSD) to distinguish patients of FEP from healthy controls. A comprehensive discussion of our preprocessing methods for PSD analysis and a detailed comparison of different models are included in this paper. The GPC model outperforms the other models with a specificity of 95.78% to show that PSD can be used as an effective feature extraction technique for analyzing and classifying resting-state EEG signals of psychiatric disorders. [ABSTRACT FROM AUTHOR]

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

Computer Aided Diagnosis systems assist radiologists and doctors in the early diagnosis of mental disorders such as Alzheimer's, bipolar disorder, depression, autism, dementia, and schizophrenia using neuroimaging. Advancements in Artificial Intelligence (AI) have leveraged neuroimaging research to unfold numerous techniques for analyzing and interpreting thousands of scans in order to detect and classify various mental illnesses. Schizophrenia is a long-standing psychiatric disorder affecting millions of people worldwide. It causes hallucinations, delusions, and defacement in thinking, behavior, and cognition. Machine Learning and Deep Learning are the subsets of AI which are used for the detection and diagnosis of schizophrenia by gathering insights from different types of modalities. This paper work examines several methods of AI used for the automated diagnosis of schizophrenia using three primary modalities- EEG, structural MRI, and functional MRI. This paper explores different datasets available for schizophrenia along with the techniques and software used to pre-process the EEG and MR images. Further this paper focuses on the different feature extraction and selection techniques to retrieve an appropriate set of features along with the brief overview of machine learning & deep learning approaches. We have also reviewed numerous studies on the prognosis of schizophrenia and presented an exhaustive analysis of the machine learning and deep learning techniques used across EEG and MRI. [ABSTRACT FROM AUTHOR]

The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection. [ABSTRACT FROM AUTHOR]

Introduction: The present paper discusses the findings of a systematic review of EEG measures in neuromarketing, identifying which EEG measures are the most robust predictor of customer preference in neuromarketing. The review investigated which TF effect (e.g., theta-band power), and ERP component (e.g., N400) was most consistently reflective of self-reported preference. Machine-learning prediction also investigated, along with the use of EEG when combined with physiological measures such as eye-tracking. Methods: Search terms ‘neuromarketing’ and ‘consumer neuroscience’ identified papers that used EEG measures. Publications were excluded if they were primarily written in a language other than English or were not published as journal articles (e.g., book chapters). 174 papers were included in the present review. Results: Frontal alpha asymmetry (FAA) was the most reliable TF signal of preference and was able to differentiate positive from negative consumer responses. Similarly, the late positive potential (LPP) was the most reliable ERP component, reflecting conscious emotional evaluation of products and advertising. However, there was limited consistency across papers, with each measure showing mixed results when related to preference and purchase behaviour. Conclusions and implications: FAA and the LPP were the most consistent markers of emotional responses to marketing stimuli, consumer preference and purchase intention. Predictive accuracy of FAA and the LPP was greatly improved through the use of machine-learning prediction, especially when combined with eye-tracking or facial expression analyses. [ABSTRACT FROM AUTHOR]

Stress has an impact not only on a person's physical health but also on his or her ability to perform at work, passion, and attitude in day-to-day life. It is one of the most difficult challenges to assess and monitor an individual's stress level because everyone experiences stress differently. This paper proposes a CIS-based KNORA-U dynamic ensemble selection (DES) model for stress level identification in humans. The UCI machine learning repository's physiological electroencephalogram (EEG) dataset is used for this research. The dataset has thirty-six subjects, with nineteen channels of EEG signals considered for each subject. In the first stage, channel signals are decomposed and extracted into five frequency bands using the discrete wavelet transform (DWT). The second stage features selection performed using a combination of statistical importance (CIS). In the third stage of extreme gradient boosting (XGBoost), linear discriminant analysis (LDA) and extra tree (ET) models are used to create a pool of classifiers for the K-Nearest Oracles Union (KNORA-U) dynamic ensemble selection (DES) classifying technique. The proposed model outperformed others on the classification of stress and relaxation levels using EEG signals and achieved 99.14% accuracy. KNORA-U DES is able to produce more accurate results as compared to KNORA-E and METADES models with different feature selection algorithms. [ABSTRACT FROM AUTHOR]

Virtual Reality (VR) allows users to interact with 3D immersive environments and has the potential to be a key technology across many domain applications, including access to a future metaverse. Yet, consumer adoption of VR technology is limited by cybersickness (CS)—a debilitating sensation accompanied by a cluster of symptoms, including nausea, oculomotor issues and dizziness. A leading problem is the lack of automated objective tools to predict or detect CS in individuals, which can then be used for resistance training, timely warning systems or clinical intervention. This paper explores the spatiotemporal brain dynamics and heart rate variability involved in cybersickness and uses this information to both predict and detect CS episodes. The present study applies deep learning of EEG in a spiking neural network (SNN) architecture to predict CS prior to using VR (85.9%, F7) and detect it (76.6%, FP1, Cz). ECG-derived sympathetic heart rate variability (HRV) parameters can be used for both prediction (74.2%) and detection (72.6%) but at a lower accuracy than EEG. Multimodal data fusion of EEG and sympathetic HRV does not change this accuracy compared to ECG alone. The study found that Cz (premotor and supplementary motor cortex) and O2 (primary visual cortex) are key hubs in functionally connected networks associated with both CS events and susceptibility to CS. F7 is also suggested as a key area involved in integrating information and implementing responses to incongruent environments that induce cybersickness. Consequently, Cz, O2 and F7 are presented here as promising targets for intervention. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) is the commonly employed electro-biological imaging technique for diagnosing brain functioning. The EEG signals are used to determine head injury, ascertain brain cell functioning, and monitor brain development. EEG can add multiple dimensions towards the identification of learning disability being an abnormality of the brain. Early and accurate detection of brain diseases can significantly reduce the mortality rate with a lesser treatment cost. The machine learning techniques can examine, classify, and process EEG signals to accurately understand brain activities and disorders. This paper is a comprehensive review of the application of machine learning techniques in the classification of EEG signals of dyslexia and analysis of an improved framework to extemporize the classifier's performance and accuracy in discriminating between dyslexics and controls. The presence of noises and artefacts often reduces the performance of classifiers and hampers results. This study reviews input pre-processing, feature selection, feature extraction techniques and machine learning algorithms for the early detection of disorder. The SVM was found to be outperforming other machine learning techniques for the classification of EEG signals. [ABSTRACT FROM AUTHOR]

People with impaired motor function could be helped by an effective brain–computer interface (BCI) based on a real-time electroencephalogram (EEG) and artificial intelligence algorithms. However, current methodologies for interpreting patient instructions from an EEG are not accurate enough to be completely safe in a real-world situation , where a poor decision would place their physical integrity at risk, such as when traveling in an electric wheelchair in a city. For various reasons, such as the low signal-to-noise ratio of portable EEGs or the effects of signal contamination (disturbances due to user movement, temporal variation of the features of EEG signals, etc.), a long short-term memory network (LSTM) (a type of recurrent neural network) that is able to learn data flow patterns from EEG signals could improve the classification of the actions taken by the user. In this paper, the effectiveness of using an LSTM with a low-cost wireless EEG device in real time is tested, and the time window that maximizes its classification accuracy is studied. The goal is to be able to implement it in the BCI of a smart wheelchair with a simple coded command protocol, such as opening or closing the eyes, which could be executed by patients with reduced mobility. Results show a higher resolution of the LSTM with an accuracy range between 77.61 and 92.14% compared to traditional classifiers (59.71%), and an optimal time window of around 7 s for the task done by users in this work. In addition, tests in real-life contexts show that a trade-off between accuracy and response times is necessary to ensure detection. [ABSTRACT FROM AUTHOR]

The detection of epileptic seizures by classifying electroencephalography (EEG) signals into ictal and interictal classes is a demanding challenge, because it identifies the seizure and seizure-free states of an epileptic patient. In previous works, several machine learning-based strategies were introduced to investigate and interpret EEG signals for the purpose of their accurate classification. However, non-linear and non-stationary characteristics of EEG signals make it complicated to get complete information about these dynamic biomedical signals. In order to address this issue, this paper focuses on extracting the most discriminating and distinguishing features of seizure EEG recordings to develop an approach that employs both fuzzy-based and traditional machine learning algorithms for epileptic seizure detection. The proposed framework classifies unknown EEG signal segments into ictal and interictal classes. The model is validated using empirical evaluation on two benchmark datasets, namely the Bonn and Children's Hospital of Boston-Massachusetts Institute of Technology (CHB-MIT) datasets. The obtained results show that in both cases, K-Nearest Neighbor (KNN) and Fuzzy Rough Nearest Neighbor (FRNN) give the highest classification accuracy scores, with improved sensitivity and specificity percentages. [ABSTRACT FROM AUTHOR]

Drowsy driving is a major cause of road accidents. Traffic accidents can be prevented by discriminating between driver states of alertness and drowsiness. This paper presents an efficient system for drowsiness detection based on EEG signals. The proposed system is efficient in providing consistent results regardless of the inherent characteristics of drivers. Our method is based on features extracted from well-defined sub-bands. These sub-bands obtained using a tunable Q-factor wavelet transform. The use of sub-bands solves the problem of interpersonal variability of EEG recordings, which is a major problem in detecting drowsiness. In addition, the use of kernel principal component analysis reduces the size of the features extracted from EEG signals without degrading the accuracy. Indeed, a single differential EEG channel with a minimal number of carefully selected features is sufficient to provide a fast, convenient, and accurate detection system. For drowsiness recognition, two different machine learning techniques, K-nearest neighbours and support vector machines, are proposed. The latter consists of a learning module for medical diagnosis based on EEG signals from a set of laboratory subjects. Laboratory conditions help identify characteristic and common features. These preparatory parameters make it possible to provide a real-time adaptive drowsiness diagnosis by assessing the driver's condition every second. By customizing the system, it can detect drowsiness with an accuracy of approximately 94%. [ABSTRACT FROM AUTHOR]

In the previous works on heat stress detection, various state-of-the-art machine learning techniques had been used to detect stress patterns from electroencephalographic (EEG) signals. Since the handcrafted feature engineering-based approaches pose certain limitations and are sensitive to transform the nonlinearities of EEG, deep learning techniques have drawn attention in the domain of EEG-based applications. Moreover, existing approaches for stress detection consider the whole frequency band (delta to gamma) which conceals the redundant and lossy information that increased the false detection rate. Also, these approaches were implemented only to identify the stress in binary classes and confined their application to identifying the level of stress. Therefore, a multi-scale channel-wise convolution-based multi-level heat stress assessment has been proposed in this paper. The novel contributions of this work are (1) designing a multi-scale convolutional neural network (MS-CNN) for extracting precise information from individual frequency bands of EEG, (2) use of sparse connectivity to reduce the redundant information and increase the performance with less trainable parameters, and (3) multi-level heat stress assessment for precise identification of the severity of stress. The proposed approaches were evaluated on pre-recorded data of 10 rats in a simulated laboratory environment. The high accuracy of approximately 96–97% and 90–92% has been achieved for binary and multi-level stress detection. There is approximately a 6 to 50% reduction in the trainable parameters with a 2% improvement of accuracy achieved on adopting channel-wise convolution over MS-CNN and deep convolutional neural network (DCNN). This demonstrates the effectiveness of the adopted multiscale feature extraction and sparse connectivity to improve the performance with a less complex model. [ABSTRACT FROM AUTHOR]

Delivering health care at home emerged as a key advancement to reduce healthcare costs and infection risks, as during the SARS-Cov2 pandemic. In particular, in motor training applications, wearable and portable devices can be employed for movement recognition and monitoring of the associated brain signals. This is one of the contexts where it is essential to minimize the monitoring setup and the amount of data to collect, process, and share. In this paper, we address this challenge for a monitoring system that includes high-dimensional EEG and EMG data for the classification of a specific type of hand movement. We fuse EEG and EMG into the magnitude squared coherence (MSC) signal, from which we extracted features using different algorithms (one from the authors) to solve binary classification problems. Finally, we propose a mapping-and-aggregation strategy to increase the interpretability of the machine learning results. The proposed approach provides very low mis-classification errors ( < 0.1 ), with very few and stable MSC features ( < 10 % of the initial set of available features). Furthermore, we identified a common pattern across algorithms and classification problems, i.e., the activation of the centro-parietal brain areas and arm's muscles in 8-80 Hz frequency band, in line with previous literature. Thus, this study represents a step forward to the minimization of a reliable EEG-EMG setup to enable gesture recognition. [ABSTRACT FROM AUTHOR]

Clustering is an attractive method to handle large-scale data which are explosively generated through digitization. This approach is specifically appropriate when labeling is very costly. In this paper, we constructed an unsupervised learning algorithm and focused on a finite mixture model based on multivariate Beta distribution. Our motivation is the flexibility and high potential that this distribution offers in modeling data. To learn this mixture model, we used an expectation propagation inference framework in which the parameters and the complexity of the model were evaluated concurrently in a single optimization framework. We evaluated the performance of our framework on publicly available datasets related to forgery detection, EEG-based sentiment analysis and human activity recognition. Our proposed model demonstrates comparable results to similar alternatives. [ABSTRACT FROM AUTHOR]

EEG-based emotion recognition has attracted substantial attention from researchers due to its extensive application prospects, and substantial progress has been made in feature extraction and classification modelling from EEG data. However, insufficient high-quality training data are available for building EEG-based emotion recognition models via machine learning or deep learning methods. The artificial generation of high-quality data is an effective approach for overcoming this problem. In this paper, a multi-generator conditional Wasserstein GAN method is proposed for the generation of high-quality artificial that covers a more comprehensive distribution of real data through the use of various generators. Experimental results demonstrate that the artificial data that are generated by the proposed model can effectively improve the performance of emotion classification models that are based on EEG. [ABSTRACT FROM AUTHOR]

Epilepsy seizure classification has been an ongoing research from decades. Auto seizure detection methods are developed by many researchers. Year by year new methods and new approaches are introduced by researchers to improve the performance of these automatic detection methods. Electroencephalogram (EEG) is the most widely used tool for detecting seizure as it has high resolution which makes it more feasible for analysis. In this paper we are introducing an approach based on stacked bidirectional long short term memory with global average pooling (LSTM_GAP) neural network for detecting epileptic seizure events. We use open access EEG dataset available in Bonn University Germany for the experiment. The model is evaluated based on three performance metrics, specificity, sensitivity and accuracy. It resulted with outstanding performance with 100% accuracy, sensitivity and specificity in detecting epileptic seizure events which is the highest accuracy among all the techniques available in state-of-the art literature. Another advantage of LSTM_GAP model lies in its robustness in noise. In real, the EEG recorded in hospital laboratories consists of artefacts generated from eye blink and muscle activities of the patients. When our model will be put to practical use by the neurologists, the EEG recordings consisting of artefacts will be given as input to the model for detecting seizure events. Hence we need to develop a model which is robust against noise and which can provide good results even when the EEG data consisting artefacts is given as input. Hence we extended our experiment to check the performance of the LSTM_GAP model by adding eye blink artefacts and muscle artefacts to the input EEG data. The model was able to give superior results even after adding artefacts. We were able to achieve 97.67% sensitivity, 98.83% specificity and 97.65% accuracy. Thus LSTM_GAP model gives superior results for the EEG with and without noise compared to other methods in the literature. [ABSTRACT FROM AUTHOR]

Brain–computer interface (BCI) is the current trend in technology expansion as it provides an easy interface between human brain and machine. The demand for BCI-based applications is growing tremendously, and efforts are in progress to deploy BCI devices for real-world applications. One of the widely known applications of BCI technology is rehabilitation in which BCI devices can provide various types of assistance to specially abled persons. In this paper, the effect of hand actions on objects is analyzed for motor-related mental task. The proposed approach analyzes electroencephalogram (EEG)-based brain activity which was captured for images shown with different gripping actions on objects. The EEG recordings are first pre-processed, followed by extraction of epochs and frequency bands using discrete wavelet transform; afterward, feature extraction followed by training and classification steps is performed for classifying the grip action into congruent (correct) and incongruent (incorrect) grip categories. The proposed work makes use of average power and relative wavelet energy as discriminating features which are then fed to train an artificial neural network for automatically classifying the incoming EEG patterns into correct or incorrect object hand grips. The performance evaluation of the proposed system is done on real EEG dataset obtained from 14 subjects. Experimental results have shown an accuracy of 75%. Also, to evaluate the effectiveness of our work, a comparison of our work with other state-of-the-art works reported by different authors is presented at the end. The results show the effectiveness of proposed approach and suggest further that the system can be used to analyze and train subjects having motor-related disabilities for perceiving correct or incorrect hand grips on objects. [ABSTRACT FROM AUTHOR]

Neural network (NN) finds role in variety of applications due to combined effect of feature extraction and classification availability in deep learning algorithms. In this paper, we have chosen SVM, logistic regression machine learning algorithms and NN for EEG signal classification. Two-layer LSTM and four-layer improved NN deep learning algorithms are proposed to improve the performance in EEG classification. Novelty lies in one-dimensional gradient descent activation functions with radial basis operations used in the initial layers of improved NN which help in achieving better performance. Statistical features namely mean, standard deviation, kurtosis and skewness are extracted for input EEG collected from Bonn database and then applied for various classification techniques. Accuracy, precision, recall and F1 score are the performance metrics used for analyzing the algorithms. Improved NN and LSTM give better performance compared to all other architectures. The simulations are carried out with variety of activation functions, optimizers and loss models to analyze the performance using Python in keras. [ABSTRACT FROM AUTHOR]

BCI deals to map the brain signal or activity to evaluate the human behaviour, activities or disease. The aim of this research is to utilize the different features of EEG signal to recognize the brain activity. The composite feature model with ELM classification method is presented in this research to recognize the human activity. In this paper, multiple aspects including time domain, frequency domain and least square evaluation based features are processed under ELM classifier to recognize the human-activities. Multiple quantified features are generated under each time, frequency and the least square categories. These features are processed individually and mutually with probabilistic evaluation to expand the processing-featureset. This expanded-composite featureset is trained under ELM (Extreme Learning Machine) classifier to perform intra-class and inter-class classification. The experimentation is applied on five distinctive experiments of Dataset IIIa of BCI completion III. Each experiment is conducted with variant training and testing instances. The evaluation results identified that the proposed hybrid model has achieved the average accuracy over 80%. Comparative results are generated against ANN, SVM, KNN and Multiscale Wavelet Kernel ELM by utilizing each kind of individual and mutual feature. The results taken from various experimentations have validated that the proposed model has improved the accuracy against each of the existing feature processed classification methods. [ABSTRACT FROM AUTHOR]

Epilepsy is a chronic neurological disease, characterized by spontaneous, unprovoked, recurrent seizures that may lead to long-term disability and premature death. Despite significant efforts made to improve epilepsy detection clinically and pre-clinically, the pervasive presence of noise in EEG signals continues to pose substantial challenges to their effective application. In addition, discriminant features for epilepsy detection have not been investigated yet. The objective of this study is to develop a hybrid model for epilepsy detection from noisy and fragmented EEG signals. We hypothesized that a hybrid model could surpass existing single models in epilepsy detection. Our approach involves manual noise rejection and a novel statistical channel selection technique to detect epilepsy even from noisy EEG signals. Our proposed Base-2-Meta stacking classifier achieved notable accuracy (0.98 ± 0.05), precision (0.98 ± 0.07), recall (0.98 ± 0.05), and F1 score (0.98 ± 0.04) even with noisy 5-s segmented EEG signals. Application of our approach to the specific problem like detection of epilepsy from noisy and fragmented EEG data reveals a performance that is not only superior to others, but also is translationally relevant, highlighting its potential application in a clinic setting, where EEG signals are often noisy or scanty. Our proposed metric DF-A (Discriminant feature-accuracy), for the first time, identified the most discriminant feature with models that give A accuracy or above (A = 95 used in this study). This groundbreaking approach allows for detecting discriminant features and can be used as potential electrographic biomarkers in epilepsy detection research. Moreover, our study introduces innovative insights into the understanding of these features, epilepsy detection, and cross-validation, markedly improving epilepsy detection in ways previously unavailable. [ABSTRACT FROM AUTHOR]

The aim of the paper is to automatically select the optimal EEG rhythm/channel combinations capable of classifying human alertness states. Four alertness states were considered, namely ‘engaged’, ‘calm’, ‘drowsy’ and ‘asleep’. The features used in the automatic selection are the energies associated with the conventional rhythms, δ,θ,α,β and γ, extracted from overlapping windows of the different EEG channels. The selection process consists of two stages. In the first stage, the optimal brain regions, represented by sets of EEG channels, are selected using a simple search technique based on support vector machine (SVM), extreme learning machine (ELM) and LDA classifiers. In the second stage, a fuzzy rule-based alertness classification system (FRBACS) is used to identify, from the previously selected EEG channels, the optimal features and their supports. The IF-THEN rules used in FRBACS are constructed using a novel differential evolution-based search algorithm particularly designed for this task. Each alertness state is represented by a set of IF-THEN rules whose antecedent parts contain EEG rhythm/channel combination. The selected spatio-frequency features were found to be good indicators of the different alertness states, as judged by the classification performance of the FRBACS that was found to be comparable to those of the SVM, ELM and LDA classifiers. Moreover, the proposed classification system has the advantage of revealing simple and easy to interpret decision rules associated with each of the alertness states. [ABSTRACT FROM AUTHOR]

Hypnosis is a psychological intervention that is commonly used to enhance the effectiveness of therapeutic suggestions. Despite extensive fascination and study, the neural mechanisms behind hypnosis remain elusive. In the current study, we undertook a systematic exploration of these neural correlates. We first extracted well-studied neurophysiological features from EEG sensors and source-localized data using spectral analysis and two measures of functional connectivity: weighted phase lag index (wPLI) and power envelope correlation (PEC). Next, we developed classification models that predicted self-rated hypnotic experience based on the extracted feature sets. Our findings reveal that gamma power computed on sensor-level data and beta PEC computed between source-localized brain networks are the top predictors of hypnosis depth. Further, a SHapley Additive exPlanations (SHAP) analysis suggested reduced gamma power in the midline frontal area and increased beta PEC between interhemispheric Dorsal Attention Networks (DAN) contribute to the hypnotic experience. These results broaden our understanding of the neural correlates of deep hypnosis, highlighting potential targets for future research. Moreover, this study demonstrates the potential of using predictive models in understanding the neural underpinnings of self-reported hypnotic depth, offering a template for future investigations. [ABSTRACT FROM AUTHOR]

In this work, we investigate epilepsy seizure detection using machine learning. In the literature, a machine learning model is usually trained to help automate the epileptic detection process, eliminating the need for human intervention. Typically, the dataset is split into training and test sets in a way to maximize the detection accuracy. This requires the training set to include enough EEG samples for every possible patient in order to improve the accuracy numbers during the prediction. However, this might not be easy or practical in real life. A new patient might not have a previous record in the training set, and hence, the prediction for this particular patient might not meet the expected accuracy. The main contribution in this work is to study the impact of the training and test datasets selection from practical point of view on the accuracy and efficacy of the CNN prediction. In this work, a CNN model, namely AlexNet, is trained to detect epileptic states, namely preictal, interictal and ictal, in subjects using electroencephalogram (EEG) signals. The dataset includes the three epileptic zones of subjects taken from three medical centers, collected by the Fragility Multi-Center Retrospective Study. Furthermore, we propose a framework to utilize a feature extraction technique that exploits the available multiple channels of EEG signals to minimize information loss. As part of the main contribution, three different approaches are proposed to split the EEG sample dataset into the training and test sets. Thus, the prediction performance is evaluated based on the prior knowledge extracted from the particular samples picked for the training set. The results show that the proposed framework achieves an overall accuracy of 94.44% when the training contained samples from each patient. The accuracy is reduced to 92.98% when the training set contained a subset of the patient pool. A binary classification is also performed with up to 98% accuracy for both scenarios. [ABSTRACT FROM AUTHOR]

In the last years Python has gained more and more traction in the scientific community. Projects like NumPy, SciPy, and Matplotlib have created a strong foundation for scientific computing in Python and machine learning packages like scikit-learn or packages for data analysis like Pandas are building on top of it. In this paper we present Wyrm (), an open source BCI toolbox in Python. Wyrm is applicable to a broad range of neuroscientific problems. It can be used as a toolbox for analysis and visualization of neurophysiological data and in real-time settings, like an online BCI application. In order to prevent software defects, Wyrm makes extensive use of unit testing. We will explain the key aspects of Wyrm's software architecture and design decisions for its data structure, and demonstrate and validate the use of our toolbox by presenting our approach to the classification tasks of two different data sets from the BCI Competition III. Furthermore, we will give a brief analysis of the data sets using our toolbox, and demonstrate how we implemented an online experiment using Wyrm. With Wyrm we add the final piece to our ongoing effort to provide a complete, free and open source BCI system in Python. [ABSTRACT FROM AUTHOR]

Electroencephalogram(EEG)-based authentication has received increasing attention from researchers as they believe it could serve as an alternative to more conventional personal authentication methods. Unfortunately, EEG signals are non-stationary and could be easily contaminated by noise and artifacts. Therefore, further processing of data analysis is needed to retrieve useful information. Various machine learning approaches have been proposed and implemented in the EEG-based domain, with deep learning being the most current trend. However, retaining the performance of a deep learning model requires substantial computational effort and a vast amount of data, especially when the models go deeper to generate consistent results. Deep learning models trained with small data sets from scratch may experience an overfitting issue. Transfer learning becomes an alternative solution. It is a technique to recognize and apply the knowledge and skills learned from the previous tasks to a new domain with limited training data. This study attempts to explore the applicability of transferring various pre-trained models' knowledge to the EEG-based authentication domain. A self-collected database that consists of 30 subjects was utilized in the analysis. The database enrolment is divided into two sessions, with each session producing two sets of EEG recording data. The frequency spectrums of the preprocessed EEG signals are extracted and fed into the pre-trained models as the input data. Three experimental tests are carried out and the best performance is reported with accuracy in the range of 99.1–99.9%. The acquired results demonstrate the efficiency of transfer learning in authenticating an individual in this domain. [ABSTRACT FROM AUTHOR]

Emotion recognition using electroencephalography (EEG) is becoming an interesting topic among researchers. It has made a remarkable entry in the domain of biomedical, smart environment, brain-computer interface (BCI), communication, security, and safe driving. In the past decade, several studies have been published that viewed emotion recognition tasks in a variety of manners. Multiple algorithms have been developed to accurately capture the EEG signal and identify the emotions from such EEG signals. The advent of artificial intelligence (AI) has changed the landscape of every application including emotion recognition. Two categories of AI-based algorithms such as machine learning and deep learning algorithms are becoming popular in the emotion recognition domain. This narrative review is an attempt to provide deep insight into the AI-based techniques, their role in EEG-based emotion recognition, and their potential future possibilities in accurate emotion identification. Furthermore, this review also provides an overview of the several important topics in emotion recognition such as emotion paradigms, EEG and its processing, and the public databases. [ABSTRACT FROM AUTHOR]

Epilepsy is a recurrent chronic brain disease that affects nearly 75 million people around the world. Therefore, the ability to reliably predict epileptic seizures would be instrumental for implementing interventions to reduce brain injury and improve patients' quality of life. In addition to classical machine learning algorithms and feature engineering methods, the use of electroencephalography (EEG) to predict seizures has gradually become a mainstream trend. Here, we propose a patient-specific method to predict epileptic seizures based on EEG data acquired using spatial depth features of a three-dimensional–two-dimensional hybrid convolutional neural network (3D-2D HyCNN) model. This method facilitates the acquisition of abundant and reliable deep features from multi-channel EEG signals. We first developed a reliable data preprocessing method to reconstruct time-series EEG signals into 3D feature images. Then, the 3D-2D HyCNN model was used to extract correlation features between multiple channels of EEG signals, which are automatically exploited by the network to improve seizure prediction. The method achieved accuracy of 98.43% and 93.11%, sensitivity of 98.58% and 90.98%, and specificity of 96.86% and 92.39% on the CHB-MIT Scalp EEG dataset and the American Epilepsy Society Epilepsy Prediction Challenge dataset, respectively. The results revealed that the new algorithm is reliable. [ABSTRACT FROM AUTHOR]

Virtual reality exposure therapy (VRET) is a novel intervention technique that allows individuals to experience anxiety-evoking stimuli in a safe environment, recognise specific triggers and gradually increase their exposure to perceived threats. Public-speaking anxiety (PSA) is a prevalent form of social anxiety, characterised by stressful arousal and anxiety generated when presenting to an audience. In self-guided VRET, participants can gradually increase their tolerance to exposure and reduce anxiety-induced arousal and PSA over time. However, creating such a VR environment and determining physiological indices of anxiety-induced arousal or distress is an open challenge. Environment modelling, character creation and animation, psychological state determination and the use of machine learning (ML) models for anxiety or stress detection are equally important, and multi-disciplinary expertise is required. In this work, we have explored a series of ML models with publicly available data sets (using electroencephalogram and heart rate variability) to predict arousal states. If we can detect anxiety-induced arousal, we can trigger calming activities to allow individuals to cope with and overcome distress. Here, we discuss the means of effective selection of ML models and parameters in arousal detection. We propose a pipeline to overcome the model selection problem with different parameter settings in the context of virtual reality exposure therapy. This pipeline can be extended to other domains of interest where arousal detection is crucial. Finally, we have implemented a biofeedback framework for VRET where we successfully provided feedback as a form of heart rate and brain laterality index from our acquired multimodal data for psychological intervention to overcome anxiety. [ABSTRACT FROM AUTHOR]

This study explores how EEG connectivity measures in children with ADHD ages 7–10 (n = 140) differ from an age-matched nonclinical database. We differentiated connectivity in networks, Brodmann area pairs, and frequencies. Subjects were in the International Collaborative ADHD Neurofeedback study, which explored neurofeedback for ADHD. Inclusion criteria were mainly rigorously diagnosed ADHD and a theta/beta power ratio (TBR) ≤ 4.5. Using statistical and machine learning algorithms, connectivity values were extracted in coherence, phase, and lag coherence at all Brodmann, subcortical, and cerebellar areas within the main networks in all EEG frequencies and then compared with a normative database. There is a higher rate of dysregulation (more than ± 1.97SD), in some cases as much as 75%, of the Brodmann pairs observed in coherence and phase between BAs 7, 10, and 11 with secondary connections from these areas to BAs 21, 30, 35, 37, 39, and 40 in the ADHD children as compared to the normative database. Left and right Brodmann areas 10 and 11 are highly disconnected to each other. The most dysregulated Brodmann Areas in ADHD are 7, 10, and 11, relevant to ADHD executive-function deficits and provide important considerations when developing interventions for ADHD children. [ABSTRACT FROM AUTHOR]

Seizures in neonates happen to be one of the most difficult emergency circumstances to deal with. They are the first signs of significant neurological implications and should be precisely diagnosed for prompt medical intervention to avoid serious morbidities and occasional fatalities. In most cases, unlike adults, newborns show practically no physical indications of an epileptic fit. Hitherto, seizure diagnosis has relied solely on consistent laborious manual monitoring and interpretation of long-duration recordings of electroencephalograms (EEG). However, because the brains of the newborns remain nascent during the neonatal period, interpreting the EEG data necessitates the expertise of highly skilled experts. This study demonstrates a Deep Belief Network-based Machine Learning architecture for binary classification of seizure and seizure-free periods. The classifier was trained and its performance was assessed using a publicly available annotated dataset containing EEG recordings of 79 infants collected at Helsinki University Hospital. The proposed model was highly discriminative for seizure detection (AUC: 97.1%). Our architecture establishes a high accuracy of 98.7 percentage, when applied to multichannel EEG recordings. The mean sensitivity and specificity rates were observed to be 96.1% and 99.2%, respectively, deeming the model comparable to recent advancements in machine learning classifiers on our dataset. [ABSTRACT FROM AUTHOR]

The purpose of this study is to propose an e-learning system model for learning content personalisation based on students' emotions. The proposed system collects learners' brainwaves using a portable Electroencephalogram and processes them via a supervised machine learning algorithm, named K-nearest neighbours (KNN), to recognise real-time emotional status. Besides, it uses a reinforcement learning approach to analyse the learners' emotional states and automatically recommend the best-fitted content that keeps the students in a positive mood. The performance of the proposed system is evaluated in two forms: 1) the system performance and 2) student engagement, satisfaction, and learning. A convenience sampling method is used to select 30 students from the pollution of 281 PartII-undergraduate students who study computer science during the 2020-21 academic year at the University of Nottingham Ningbo China. The selected students are divided into homogenous control and experimental groups for learning English listening and reading skills. According to the machine learning results, the trained KNN recognises the emotional states with an accuracy of 74.3%, the precision of 70.8%, and recall of 69.3%. In addition, the results of the t-Test demonstrate that the proposed e-learning system model has no significant impact on learners' learning and engagement but enhances the student's satisfaction compared to traditional e-learning systems (p < 0.05). [ABSTRACT FROM AUTHOR]

Epilepsy is a common neurological disease that uses electroencephalogram (EEG) data for its detection purpose. Neurologists make the diagnosis by visual inspection of EEG reports. As it is time-consuming and due to the shortage of specialists worldwide, researchers have proposed automated systems to detect the disease. In the past decade, most of the systems were designed using hand-engineered features. However, identifying appropriate features is always a challenging task in the development of a seizure detector system. Deep learning networks eliminate the problem of selecting the best features but suffer from long training time, generally days or weeks. To overcome this problem, the authors have proposed a new 1D convolutional neural network (CNN) that automatically extracts features at an average of seven epochs, only followed by traditional machine learning (ML) classifier. 1D CNN architectures are intrinsically suitable for the processing of EEG time-series data. The proposed model doesn't require any preprocessing of EEG signal and results in approximately 94% reduced training time than end-to-end deep learning models. Different ML techniques have been applied to extracted features to check the robustness of the proposed 1D CNN. Maximum accuracy of 99.83% has been achieved by most of the classifiers to detect between healthy and seizure patients. The reduced number of processing steps and epochs makes it suitable for real-time clinical applications. [ABSTRACT FROM AUTHOR]

A time series is a sequence of numerical data points in equal time intervals and/or successive order. Time series are used in many fields to understand the behavior of systems, to make predictions, to create solutions to problems, etc. Electroencephalogram (EEG) and electrocardiogram (ECG) are frequently used in the diagnosis of diseases and research in this field. EEG signals examine the neural activity of the brain, while ECG examines the work of the heart muscle and neural conduction system. These signs contain a large amount of information about the functioning of the brain and heart functions. In order to use this information, experts in the field of signal processing must evaluate these signals. Due to the successful application methods of EEG and ECG signals in classification problems, various fields of artificial intelligence applications are frequently used by experts. In this study, a new hybrid model has been developed to classify EEG and ECG signals. These signals of five different classes have been used as the feature vector in the training of machine learning algorithms with 10 statistical parameters (8 normalized, 2 real signals). These algorithms are designed to give the best performance. In the proposed hybrid model, a machine learning model consisting of four stages is used. In the experimental studies, it has been observed that the proposed hybrid method gives better results than the normal classification process. The obtained results are given in the experimental studies section in detail. [ABSTRACT FROM AUTHOR]

Deep learning with convolutional neural networks (ConvNets) has dramatically improved the learning capabilities of computer vision applications just through considering raw data without any prior feature extraction. Nowadays, there is a rising curiosity in interpreting and analyzing electroencephalography (EEG) dynamics with ConvNets. Our study focused on ConvNets of different structures, the efficiency of multiple machine learning algorithms with optimization on ConvNets, constructing for predicting imagined left and right movements on a subject-independent basis through raw EEG data. We adapted novel lower-upper triangularization based extreme learning machines (LuELM) to the ConvNet architecture. Results showed that recently advanced methods in machine learning field, i.e. adaptive moments and batch normalization together with dropout strategy, improved ConvNets predicting ability, outperforming that of conventional fully-connected neural networks with widely-used spectral features. The proposed prediction model achieved improvements in classification performances with the rates of 90.33%, 91.00%, and 89.67% for accuracy, recall, and specificity, respectively. [ABSTRACT FROM AUTHOR]

Anaesthesia is a state of temporary controlled loss of awareness induced for medical operations. An accurate assessment of the depth of anaesthesia (DoA) helps anesthesiologists to avoid awareness during surgery and keep the recovery period short. However, the existing DoA algorithms have limitations, such as not robust enough for different patients and having time delay in assessment. In this study, to develop a reliable DoA measurement method, pre-denoised electroencephalograph (EEG) signals are divided into ten frequency bands (α, β1, β2, β3, β4, β, βγ, γ, δ and θ), and the features are extracted from different frequency bands using spectral entropy (SE) methods. SE from the beta-gamma frequency band (21.5–38.5 Hz) and SE from the beta frequency band show the highest correlation (R-squared value: 0.8458 and 0.7312, respectively) with the most popular DoA index, bispectral index (BIS). In this research, a new DoA index is developed based on these two SE features for monitoring the DoA. The highest Pearson correlation coefficient by comparing the BIS index for testing data is 0.918, and the average is 0.80. In addition, the proposed index shows an earlier reaction than the BIS index when the patient goes from deep anaesthesia to moderate anaesthesia, which means it is more suitable for the real-time DoA assessment. In the case of poor signal quality (SQ), while the BIS index exhibits inflexibility with cases of poor SQ, the new proposed index shows reliable assessment results that reflect the clinical observations. [ABSTRACT FROM AUTHOR]

Electrooculographical (EOG) artifacts are problematic to electroencephalographical (EEG) signal analysis and degrade performance of brain–computer interfaces. A novel, robust deep wavelet sparse autoencoder (DWSAE) method is presented and validated for fully automated EOG artifact removal. DWSAE takes advantage of wavelet transform and sparse autoencoder to become a universal EOG artifact corrector. After being trained without supervision, the sparse autoencoder performs EOG correction on time–frequency coefficients collected after brain wave signal wavelet decomposition. Corrected coefficients are then used for wavelet reconstruction of uncontaminated EEG signals. DWSAE is compared with five other methods: second-order blind identification, information maximization, joint approximation diagonalization of eigen-matrices, wavelet neural network (WNN) and wavelet thresholding (WT). Experimental results on a visual attention task dataset, a mental state recognition dataset and a semi-simulated contaminated EEG dataset show that DWSAE is capable of suppressing EOG artifacts effectively, while preserving the nature of background EEG signals. The mean square error of signals before and after correction by DWSAE on a semi-simulated contaminated EEG segment of 30 s is the lowest (65.62) when compared to the results produced by WNN and WT. DWSAE addresses limitations posed by these methods in three ways. First, DWSAE can be performed automatically and online in a single channel of EEG data; this has advantages over independent component analysis-based methods. Second, its results are robust and stable in comparison with those of other wavelet-based methods. Third, as an unsupervised learning scheme, DWSAE does not require the off-line training that is necessary for WNN and other supervised learning machine learning-based methods. [ABSTRACT FROM AUTHOR]

The cognitive processing and detection of errors is important in the adaptation of the behavioral and learning processes. This brain activity is often reflected as distinct patterns of event-related potentials (ERPs) that can be employed in the detection and interpretation of the cerebral responses to erroneous stimuli. However, high-accuracy cross-condition classification is challenging due to the significant variations of the error-related ERP components (ErrPs) between complexity conditions, thus hindering the development of error recognition systems. In this study, we employed support vector machines (SVM) classification methods, based on waveform characteristics of ErrPs from different time windows, to detect correct and incorrect responses in an audio identification task with two conditions of different complexity. Since the performance of the classifiers usually depends on the salience of the features employed, a combination of the sequential forward floating feature selection (SFFS) and sequential forward feature selection (SFS) methods was implemented to detect condition-independent and condition-specific feature subsets. Our framework achieved high accuracy using a small subset of the available features both for cross- and within-condition classification, hence supporting the notion that machine learning techniques can detect hidden patterns of ErrP-based features, irrespective of task complexity while additionally elucidating complexity-related error processing variations. Graphical abstract A schematic of the proposed approach. (a) EEG recordings in an auditory experiment in two conditions of different complexity. (b) Characteristic event related activity feature extraction. (c) Selection of feature vector subsets for easy and hard conditions corresponding to correct (Class1) and incorrect (Class2) responses. (d) Performance for individual and cross-condition classification. [ABSTRACT FROM AUTHOR]

Several neurological disorders, such as epilepsy, can be diagnosed by electroencephalogram (EEG). Data mining supported by machine learning (ML) techniques can be used to find patterns and to build classifiers for the data. In order to make it possible, data should be represented in an appropriate format, e.g. attribute-value table, which can be built by feature extraction approaches, such as the cross-correlation (CC) method, which uses one signal as reference and correlates it with other signals. However, the reference is commonly selected randomly and, to the best of our knowledge, no studies have been conducted to evaluate whether this choice can affect the ML method performance. Thereby, this work aims to verify whether the choice of an epileptic EEG segment as reference can affect the performance of classifiers built from data. Also, a CC with artificial reference (CCAR) method is proposed in order to reduce possible consequences of the random selection of a signal as reference. Two experimental evaluations were conducted in a set of 200 EEG segments to induce classifiers using ML algorithms, such as J48, 1NN, naive Bayes, BP-MLP, and SMO. In the first study, each epileptic EEG segment was selected as reference to apply CC and ML methods. The evaluation found extremely significant difference, evidencing that the choice of an EEG segment as reference can influence the performance of ML methods. In the second study, the CCAR method was performed, in which statistical tests, only in comparisons involving the SMO classifier, showed not-so-good results. [ABSTRACT FROM AUTHOR]

Through the use of brain-computer interfaces (BCIs), neurogames have become increasingly more advanced by incorporating immersive virtual environments and 3D worlds. However, training both the user and the system requires long and repetitive trials resulting in fatigue and low performance. Moreover, many users are unable to voluntarily modulate the amplitude of their brain activity to control the neurofeedback loop. In this study, we are focusing on the effect that gaming experience has in brain activity modulation as an attempt to systematically identify the elements that contribute to high BCI control and to be utilized in neurogame design. Based on the current literature, we argue that experienced gamers could have better performance in BCI training due to enhanced sensorimotor learning derived from gaming. To investigate this, two experimental studies were conducted with 20 participants overall, undergoing 3 BCI sessions, resulting in 88 EEG datasets. Results indicate (a) an effect from both demographic and gaming experience data to the activity patterns of EEG rhythms, and (b) increased gaming experience might not increase significantly performance, but it could provide faster learning for 'Hardcore' gamers. [ABSTRACT FROM AUTHOR]

In this research, we have explored the canonical correlation analysis (CCA) to improve the performance of the identification system that involves multiple correlated modalities. In particular, we consider the electroencephalogram signal of different mental task performed by the subject such as breathing, mental mathematics, and geometric figure rotation, visual counting and mental letter composing. Our motivation based on the fusion of feature vector of mental task using canonical correlation analysis, where feature set extraction using empirical mode decomposition and information theoretic measure and statistical measurement. In order to classify the fused vector from different mental, we have used linear vector quantization (LVQ) neural network and its extension LVQ2. The results of the experiments testing the performance have been evaluated with two profiles of the database. We have observed canonical correlation-based fusion providing the better results in comparison with simple fusion rule. The novelty of this research is the new feature generation using fused feature of distinct mental task based on CCA. [ABSTRACT FROM AUTHOR]

One crucial question in the design of electroencephalogram (EEG)-based brain–computer interface (BCI) experiments is the selection of EEG channels. While a setup with few channels is more convenient and requires less preparation time, a dense placement of electrodes provides more detailed information and henceforth could lead to a better classification performance. Here, we investigate this question for a specific setting: a BCI that uses the popular CSP algorithm in order to classify voluntary modulations of sensorimotor rhythms (SMR). In a first approach 13 different fixed channel configurations are compared to the full one consisting of 119 channels. The configuration with 48 channels results to be the best one, while configurations with less channels, from 32 to 8, performed not significantly worse than the best configuration in cases where only few training trials are available. In a second approach an optimal channel configuration is obtained by an iterative procedure in the spirit of stepwise variable selection with nonparametric multiple comparisons. As a surprising result, in the second approach a setting with 22 channels centered over the motor areas was selected. Thanks to the acquisition of a large data set recorded from 80 novice participants using 119 EEG channels, the results of this study can be expected to have a high degree of generalizability. [ABSTRACT FROM AUTHOR]

The perception of an external stimulus not only depends upon the characteristics of the stimulus but is also influenced by the ongoing brain activity prior to its presentation. In this work, we directly tested whether spontaneous electrical brain activities in prestimulus period could predict perceptual outcome in face pareidolia (visualizing face in noise images) on a trial-by-trial basis. Participants were presented with only noise images but with the prior information that some faces would be hidden in these images, while their electrical brain activities were recorded; participants reported their perceptual decision, face or no-face, on each trial. Using differential hemispheric asymmetry features based on large-scale neural oscillations in a machine learning classifier, we demonstrated that prestimulus brain activities could achieve a classification accuracy, discriminating face from no-face perception, of 75% across trials. The time-frequency features representing hemispheric asymmetry yielded the best classification performance, and prestimulus alpha oscillations were found to be mostly involved in predicting perceptual decision. These findings suggest a mechanism of how prior expectations in the prestimulus period may affect post-stimulus decision making. [ABSTRACT FROM AUTHOR]

Machine computer interfaces (MCI) are assistive technologies enabling paralyzed peoples to control and communicate their environments. This study aims to discover and represents a new approach on MCI using left/right motions of voluntary jaw movements stored in electroencephalogram (EEG). It extracts brain electrical activities on EEG produced by voluntary jaw movements and converts these activities to machine control commands. Jaw-operated machine computer interface is a new way of MCI entitled as jaw machine interface (JMI) provides new functionality for paralyzed people to assist available environmental devices using their jaw motions. In this article, root mean square (RMS) and standard deviation (STD) features of signals are extracted and hemispherical pattern changes are computed and compared as offline analysis approach. A statistical algorithm, principle component analysis (PCA), is used to reduce high dimensional data and two types of machine learning algorithms which are linear discriminant analysis (LDA) and support vector machine (SVM) incorporating k-fold cross validation technique are employed to identify pattern changes by utilizing the features of horizontal jaw movements stored in EEG. [ABSTRACT FROM AUTHOR]