This paper proposes a new brain-computer interface (BCI) design using fuzzy ARTMAP (FA) neural network, as well as an application of the design. The objective of this BCI-FA design is to classify the best three of the five available mental tasks for each subject using power spectral density (PSD) values of electroencephalogram (EEG) signals. These PSD values are extracted using the Wiener-Khinchine and autoregressive methods. Ten experiments employing different triplets of mental tasks are studied for each subject. The findings show that the average BCI-FA outputs for four subjects gave less than 6% of error using the best triplets of mental tasks identified from the classification performances of FA. This implies that the BCI-FA can be successfully used with a tri-state switching device. As an application, a proposed tri-state Morse code scheme could be utilized to translate the outputs of this BCI-FA design into English letters. In this scheme, the three BCI-FA outputs correspond to a dot and a dash, which are the two basic Morse code alphabets and a space to denote the end (or beginning) of a dot or a dash. The construction of English letters using this tri-state Morse code scheme is determined only by the sequence of mental tasks and is independent of the time duration of each mental task. This is especially useful for constructing letters that are represented as multiple dots or dashes. This combination of BCI-FA design and the tri-state Morse code scheme could be developed as a communication system for paralyzed patients.
In this paper, we have designed a two-state brain-computer interface (BCI) using neural network (NN) classification of autoregressive (AR) features from electroencephalogram (EEG) signals extracted during mental tasks. The main purpose of the study is to use Keirn and Aunon's data to investigate the performance of different mental task combinations and different AR features for BCI design for individual subjects. In the experimental study, EEG signals from five mental tasks were recorded from four subjects. Different combinations of two mental tasks were studied for each subject. Six different feature extraction methods were used to extract the features from the EEG signals: AR coefficients computed with Burg's algorithm, AR coefficients computed with a least-squares (LS) algorithm and adaptive autoregressive (AAR) coefficients computed with a least-mean-square (LMS) algorithm. All the methods used order six applied to 125 data points and these three methods were repeated with the same data but with segmentation into five segments in increments of 25 data points. The multilayer perceptron NN trained by the back-propagation algorithm (MLP-BP) and linear discriminant analysis (LDA) were used to classify the computed features into different categories that represent the mental tasks. We compared the classification performances among the six different feature extraction methods. The results showed that sixth-order AR coefficients with the LS algorithm without segmentation gave the best performance (93.10%) using MLP-BP and (97.00%) using LDA. The results also showed that the segmentation and AAR methods are not suitable for this set of EEG signals. We conclude that, for different subjects, the best mental task combinations are different and proper selection of mental tasks and feature extraction methods are essential for the BCI design.
Electroencephalogram (EEG) signal plays an important role in the diagnosis of epilepsy. The long-term EEG recordings of an epileptic patient obtained from the ambulatory recording systems contain a large volume of EEG data. Detection of the epileptic activity requires a time consuming analysis of the entire length of the EEG data by an expert. The traditional methods of analysis being tedious, many automated diagnostic systems for epilepsy have emerged in recent years. This paper discusses an automated diagnostic method for epileptic detection using a special type of recurrent neural network known as Elman network. The experiments are carried out by using time-domain as well as frequency-domain features of the EEG signal. Experimental results show that Elman network yields epileptic detection accuracy rates as high as 99.6% with a single input feature which is better than the results obtained by using other types of neural networks with two and more input features.
Two-stage lossless data compression methods involving predictors and encoders are well known. This paper discusses the application of context based error modeling techniques for neural network predictors used for the compression of EEG signals. Error modeling improves the performance of a compression algorithm by removing the statistical redundancy that exists among the error signals after the prediction stage. In this paper experiments are carried out by using human EEG signals recorded under various physiological conditions to evaluate the effect of context based error modeling in the EEG compression. It is found that the compression efficiency of the neural network based predictive techniques is significantly improved by using the error modeling schemes. It is shown that the bits per sample required for EEG compression with error modeling and entropy coding lie in the range of 2.92 to 6.62 which indicates a saving of 0.3 to 0.7 bits compared to the compression scheme without error modeling.
A "single-trial" signal subspace approach for extracting visual evoked potential (VEP) from the ongoing 'colored' electroencephalogram (EEG) noise is proposed. The algorithm applies the generalized eigendecomposition on the covariance matrices of the VEP and noise to transform them jointly into diagonal matrices in order to avoid a pre-whitening stage. The proposed generalized subspace approach (GSA) decomposes the corrupted VEP space into a signal subspace and noise subspace. Enhancement is achieved by removing the noise subspace and estimating the clean VEPs only from the signal subspace. The validity and effectiveness of the proposed GSA scheme in estimating the latencies of P100's (used in objective assessment of visual pathways) are evaluated using real data collected from Selayang Hospital in Kuala Lumpur. The performance of GSA is compared with the recently proposed single-trial technique called the Third Order Correlation (TOC).
Software technology enables computerized analysis to offer second opinion in various screening and diagnostic tasks to assist the clinicians. Yet, the performance of these computerized methods for medical images is questioned by experts in CAD research, owing to the use of different databases and criteria for evaluating the computer results for comparison. This paper intends to substantiate this statement by illustrating the effects of such issues with the use of 1D physiologic data and multiple databases. For this purpose, the detection of desaturation events in Sp02 and spike events in EEG are used. This is the first time that comparison between different algorithms on a common basis is carried out on an individual effort. The appraisal for all the algorithms is made on the same databases and criteria. It is surprising to find that issues for 2/3D images concur with those found in 1D data here. In evaluating the accuracy of a new algorithm, a single independent database gives results fast. This paper reveals weaknesses of such an approach. It is hoped that the supportive evidence shown here is enough for researchers to innovate a better platform for credibility in reporting performance comparison of computerized analysis algorithms.
The early identification of asphyxiated infants at high risk of adverse outcomes and the early selection of those who might benefit from neuroprotective therapies are required. A prospective observational study was conducted to determine if there were any early clinical, neuroimaging or neurophysiological parameters that might predict the outcome in term newborns with asphyxia.
The mu rhythm is an electroencephalogram (EEG) signal located at the central region of the brain that is frequently used for studies concerning motor activity. Quite often, the EEG data are contaminated with artifacts and the application of blind source separation (BSS) alone is insufficient to extract the mu rhythm component. We present a new two-stage approach to extract the mu rhythm component. The first stage uses second-order blind identification (SOBI) with stationary wavelet transform (SWT) to automatically remove the artifacts. In the second stage, SOBI is applied again to find the mu rhythm component. Our method is first compared with independent component analysis with discrete wavelet transform (ICA-DWT) as well as SOBI-DWT, ICA-SWT, and regression method for artifact removal using simulated EEG data. The results showed that the regression method is more effective in removing electrooculogram (EOG) artifacts, while SOBI-SWT is more effective in removing electromyogram (EMG) artifacts as compared to the other artifact removal methods. Then, all the methods are compared with the direct application of SOBI in extracting mu rhythm components on simulated and actual EEG data from ten subjects. The results showed that the proposed method of SOBI-SWT artifact removal enhances the extraction of the mu rhythm component.
In this paper, we investigate the use of heart rate variability (HRV) for automatic newborn seizure detection. The proposed method consists of a sequence of processing steps, namely, obtaining HRV from the ECG, extracting a discriminating HRV feature set, selecting an optimal subset from the full feature set, and, finally, classifying the HRV into seizure/nonseizure using a supervised statistical classifier. Due to the fact that HRV signals are nonstationary, a set of time-frequency features from the newborn HRV is proposed and extracted. In order to achieve efficient HRV-based automatic newborn seizure detection, a two-phase wrapper-based feature selection technique is used to select the feature subset with minimum redundancy and maximum class discriminability. Tested on ECG recordings obtained from eight newborns with identified EEG seizure, the proposed HRV-based neonatal seizure detection algorithm achieved 85.7% sensitivity and 84.6% specificity. These results suggest that the HRV is sensitive to changes in the cardioregulatory system induced by the seizure, and therefore, can be used as a basis for an automatic seizure detection.
This paper proposes non-Gaussian models for parametric spectral estimation with application to event-related desynchronization (ERD) estimation of nonstationary EEG. Existing approaches for time-varying spectral estimation use time-varying autoregressive (TVAR) state-space models with Gaussian state noise. The parameter estimation is solved by a conventional Kalman filtering. This study uses non-Gaussian state noise to model autoregressive (AR) parameter variation with estimation by a Monte Carlo particle filter (PF). Use of non-Gaussian noise such as heavy-tailed distribution is motivated by its ability to track abrupt and smooth AR parameter changes, which are inadequately modeled by Gaussian models. Thus, more accurate spectral estimates and better ERD tracking can be obtained. This study further proposes a non-Gaussian state space formulation of time-varying autoregressive moving average (TVARMA) models to improve the spectral estimation. Simulation on TVAR process with abrupt parameter variation shows superior tracking performance of non-Gaussian models. Evaluation on motor-imagery EEG data shows that the non-Gaussian models provide more accurate detection of abrupt changes in alpha rhythm ERD. Among the proposed non-Gaussian models, TVARMA shows better spectral representations while maintaining reasonable good ERD tracking performance.
A signal subspace approach for extracting visual evoked potentials (VEPs) from the background electroencephalogram (EEG) colored noise without the need for a prewhitening stage is proposed. Linear estimation of the clean signal is performed by minimizing signal distortion while maintaining the residual noise energy below some given threshold. The generalized eigendecomposition of the covariance matrices of a VEP signal and brain background EEG noise is used to transform them jointly to diagonal matrices. The generalized subspace is then decomposed into signal subspace and noise subspace. Enhancement is performed by nulling the components in the noise subspace and retaining the components in the signal subspace. The performance of the proposed algorithm is tested with simulated and real data, and compared with the recently proposed signal subspace techniques. With the simulated data, the algorithms are used to estimate the latencies of P(100), P(200), and P(300) of VEP signals corrupted by additive colored noise at different values of SNR. With the real data, the VEP signals are collected at Selayang Hospital, Kuala Lumpur, Malaysia, and the capability of the proposed algorithm in detecting the latency of P(100) is obtained and compared with other subspace techniques. The ensemble averaging technique is used as a baseline for this comparison. The results indicated significant improvement by the proposed technique in terms of better accuracy and less failure rate.
This study investigated the proposition of relaxation offered by performing the Muslim prayers by measuring the alpha brain activity in the frontal (F3-F4), central (C3-C4), parietal (P3-P4), and occipital (O1-O2) electrode placements using the International 10-20 System. Nine Muslim subjects were asked to perform the four required cycles of movements of Dhuha prayer, and the EEG were subsequently recorded with open eyes under three conditions, namely, resting, performing four cycles of prayer while reciting the specific verses and supplications, and performing four cycles of acted salat condition (prayer movements without any recitations). Analysis of variance (ANOVA) tests revealed that there were no significant difference in the mean alpha relative power (RP(α)) between the alpha amplitude in the Dhuha prayer and the acted conditions in all eight electrode positions. However, the mean RP(α) showed higher alpha amplitude during the prostration position of the Dhuha prayer and acted condition at the parietal and occipital regions in comparison to the resting condition. Findings were similar to other studies documenting increased alpha amplitude in parietal and occipital regions during meditation and mental concentration. The incidence of increased alpha amplitude suggested parasympathetic activation, thus indicating a state of relaxation. Subsequent studies are needed to delineate the role of mental concentration, and eye focus, on alpha wave amplitude while performing worshipping acts.
Cerebral activation and autonomic nervous system have importance in studies such as mental stress. The aim of this study is to analyze variations in EEG scalp potential which may influence autonomic activation of heart while playing video games. Ten healthy participants were recruited in this study. Electroencephalogram (EEG) and electrocardiogram (ECG) signals were measured simultaneously during playing video game and rest conditions. Sympathetic and parasympathetic innervations of heart were evaluated from heart rate variability (HRV), derived from the ECG. Scalp potential was measured by the EEG. The results showed a significant upsurge in the value theta Fz/alpha Pz (p<0.001) while playing game. The results also showed tachycardia while playing video game as compared to rest condition (p<0.005). Normalized low frequency power and ratio of low frequency/high frequency power were significantly increased while playing video game and normalized high frequency power sank during video games. Results showed synchronized activity of cerebellum and sympathetic and parasympathetic innervation of heart.
This paper applies an expectation-maximization (EM) based Kalman smoother (KS) approach for single-trial event-related potential (ERP) estimation. Existing studies assume a Markov diffusion process for the dynamics of ERP parameters which is recursively estimated by optimal filtering approaches such as Kalman filter (KF). However, these studies only consider estimation of ERP state parameters while the model parameters are pre-specified using manual tuning, which is time-consuming for practical usage besides giving suboptimal estimates. We extend the KF approach by adding EM based maximum likelihood estimation of the model parameters to obtain more accurate ERP estimates automatically. We also introduce different model variants by allowing flexibility in the covariance structure of model noises. Optimal model selection is performed based on Akaike Information Criterion (AIC). The method is applied to estimation of chirp-evoked auditory brainstem responses (ABRs) for detection of wave V critical for assessment of hearing loss. Results shows that use of more complex covariances are better estimating inter-trial variability.
Driver drowsiness has been one of the major causes of road accidents that lead to severe trauma, such as physical injury, death, and economic loss, which highlights the need to develop a system that can alert drivers of their drowsy state prior to accidents. Researchers have therefore attempted to develop systems that can determine driver drowsiness using the following four measures: (1) subjective ratings from drivers, (2) vehicle-based measures, (3) behavioral measures and (4) physiological measures. In this study, we analyzed the various factors that contribute towards drowsiness. A total of 15 male subjects were asked to drive for 2 h at three different times of the day (00:00-02:00, 03:00-05:00 and 15:00-17:00 h) when the circadian rhythm is low. The less intrusive physiological signal measurements, ECG and EMG, are analyzed during this driving task. Statistically significant differences in the features of ECG and sEMG signals were observed between the alert and drowsy states of the drivers during different times of day. In the future, these physiological measures can be fused with vision-based measures for the development of an efficient drowsiness detection system.
The tradeoff between computational complexity and speed, in addition to growing demands for real-time BMI (brain-machine interface) systems, expose the necessity of applying methods with least possible complexity. Willison amplitude (WAMP) and slope sign change (SSC) are two promising time-domain features only if the right threshold value is defined for them. To overcome the drawback of going through trial and error for the determination of a suitable threshold value, modified WAMP and modified SSC are proposed in this paper. Besides, a comprehensive assessment of statistical time-domain features in which their effectiveness is evaluated with a support vector machine (SVM) is presented. To ensure the accuracy of the results obtained by the SVM, the performance of each feature is reassessed with supervised fuzzy C-means. The general assessment shows that every subject had at least one of his performances near or greater than 80%. The obtained results prove that for BMI applications, in which a few errors can be tolerated, these combinations of feature-classifier are suitable. Moreover, features that could perform satisfactorily were selected for feature combination. Combinations of the selected features are evaluated with the SVM, and they could significantly improve the results, in some cases, up to full accuracy.
This paper explores the migration of adaptive filtering with swarm intelligence/evolutionary techniques employed in the field of electroencephalogram/event-related potential noise cancellation or extraction. A new approach is proposed in the form of controlled search space to stabilize the randomness of swarm intelligence techniques especially for the EEG signal. Swarm-based algorithms such as Particles Swarm Optimization, Artificial Bee Colony, and Cuckoo Optimization Algorithm with their variants are implemented to design optimized adaptive noise canceler. The proposed controlled search space technique is tested on each of the swarm intelligence techniques and is found to be more accurate and powerful. Adaptive noise canceler with traditional algorithms such as least-mean-square, normalized least-mean-square, and recursive least-mean-square algorithms are also implemented to compare the results. ERP signals such as simulated visual evoked potential, real visual evoked potential, and real sensorimotor evoked potential are used, due to their physiological importance in various EEG studies. Average computational time and shape measures of evolutionary techniques are observed 8.21E-01 sec and 1.73E-01, respectively. Though, traditional algorithms take negligible time consumption, but are unable to offer good shape preservation of ERP, noticed as average computational time and shape measure difference, 1.41E-02 sec and 2.60E+00, respectively.
Biosignal analysis is one of the most important topics that researchers have tried to develop during the last century to understand numerous human diseases. Electroencephalograms (EEGs) are one of the techniques which provides an electrical representation of biosignals that reflect changes in the activity of the human brain. Monitoring the levels of anesthesia is a very important subject, which has been proposed to avoid both patient awareness caused by inadequate dosage of anesthetic drugs and excessive use of anesthesia during surgery. This article reviews the bases of these techniques and their development within the last decades and provides a synopsis of the relevant methodologies and algorithms that are used to analyze EEG signals. In addition, it aims to present some of the physiological background of the EEG signal, developments in EEG signal processing, and the effective methods used to remove various types of noise. This review will hopefully increase efforts to develop methods that use EEG signals for determining and classifying the depth of anesthesia with a high data rate to produce a flexible and reliable detection device.
Electroencephalogram based brain-computer interfaces (BCIs) enable stroke and motor neuron disease patients to communicate and control devices. Mindfulness meditation has been claimed to enhance metacognitive regulation. The current study explores whether mindfulness meditation training can thus improve the performance of BCI users. To eliminate the possibility of expectation of improvement influencing the results, we introduced a music training condition. A norming study found that both meditation and music interventions elicited clear expectations for improvement on the BCI task, with the strength of expectation being closely matched. In the main 12 week intervention study, seventy-six healthy volunteers were randomly assigned to three groups: a meditation training group; a music training group; and a no treatment control group. The mindfulness meditation training group obtained a significantly higher BCI accuracy compared to both the music training and no-treatment control groups after the intervention, indicating effects of meditation above and beyond expectancy effects.
Human brain generates electromagnetic signals during certain activation inside the brain. The localization of the active sources which are responsible for such activation is termed as brain source localization. This process of source estimation with the help of EEG which is also known as EEG inverse problem is helpful to understand physiological, pathological, mental, functional abnormalities and cognitive behaviour of the brain. This understanding leads for the specification for diagnoses of various brain disorders such as epilepsy and tumour. Different approaches are devised to exactly localize the active sources with minimum localization error, less complexity and more validation which include minimum norm, low resolution brain electromagnetic tomography (LORETA), standardized LORETA, exact LORETA, Multiple Signal classifier, focal under determined system solution etc. This paper discusses and compares the ability of localizing the sources for two low resolution methods i.e., sLORETA and eLORETA respectively. The ERP data with visual stimulus is used for comparison at four different time instants for both methods (sLORETA and eLORETA) and then corresponding activation in terms of scalp map, slice view and cortex map is discussed.