Automatic differentiation of multichannel EEG signals

A Novel Approach for Multichannel Epileptic Seizure Classification Based on Internet of Things Framework Using Critical Spectral Verge Feature Derived from Flower Pollination Algorithm

A novel approach for multichannel epilepsy seizure classification which will help to automatically locate seizure activity present in the focal brain region was proposed. This paper suggested an Internet of Things (IoT) framework based on a smart phone by utilizing a novel feature termed multiresolution critical spectral verge (MCSV), based on frequency-derived information for epileptic seizure classification which was optimized using a flower pollination algorithm (FPA). A wireless sensor technology (WSN) was utilized to record the electroencephalography (EEG) signal of epileptic patients. Next, the EEG signal was pre-processed utilizing a multiresolution-based adaptive filtering (MRAF) method. Then, the maximal frequency point at which the power spectral density (PSD) of each EEG segment was greater than the average spectral power of the corresponding frequency band was computed. This point was further optimized to extract a point termed as critical spectral verge (CSV) to extract the exact high frequency oscillations representing the actual seizure activity present in the EEG signal. Next, a support vector machine (SVM) classifier was used for channel-wise classification of the seizure and non-seizure regions using CSV as a feature. This process of classification using the CSV feature extracted from the MRAF output is referred to as the MCSV approach. As a final step, cloud-based services were employed to analyze the EEG information from the subject's smart phone. An exhaustive analysis was undertaken to assess the performance of the MCSV approach for two datasets. The presented approach showed an improved performance with a 93.83% average sensitivity, a 97.94% average specificity, a 97.38% average accuracy with the SVM classifier, and a 95.89% average detection rate as compared with other state-of-the-art studies such as deep learning. The methods presented in the literature were unable to precisely localize the origination of the seizure activity in the brain region and reported a low seizure detection rate. This work introduced an optimized CSV feature which was effectively used for multichannel seizure classification and localization of seizure origination. The proposed MCSV approach will help diagnose epileptic behavior from multichannel EEG signals which will be extremely useful for neuro-experts to analyze seizure details from different regions of the brain.

Recent Approaches on Classification and Feature Extraction of EEG Signal: A Review

Objective:

Electroencephalography (EEG) has an influential role in neuroscience and commercial applications. Most of the tools available for EEG signal analysis use machine learning to extract the required information. So, the study of robust techniques for feature extraction and classification is an important thing to understand the practical use of EEG. The paper aims that if there is any special tool for a particular task. Which feature domain or classifier has a significant role in EEG signal analysis?

Approach:

It presents a detailed report of the current trend for bio-electrical signals classification focusing on various classifiers’ advantages and disadvantages. This study includes literature from 2000 to 2021 with a brief description of EEG signal origin and advancement in classification techniques.

Results:

Randomly used classifiers for EEG signal can be categorized into five classes, namely Linear Classifiers, Nearest Neighbor Classifiers, Nonlinear Bayesian Classifiers, Neural Networks, and Combinations of Classifiers. Approximately 40% of studies use Support Vector Machine, Nearest Neighbor, and their combination with others. For specific tasks, particular classifiers are recommended in the survey. Features can be defined into four categories, namely TDFs, FDFs, TFDFs, and statistical features, where 39% of studies used TFDFs. Multi-domains features are preferred when the required information cannot be obtained from one domain.

Significance:

The paper summarizes the recent approaches for feature extraction and classification of EEG signals. It describes the brain waves with their classification, related behavior, and task with the physiological correlation. The comparative analysis of different classifiers, toolbox, the channel used, accuracy, and the number of subjects from various studies can help the practitioners choose a suitable classifier. Furthermore, future directions can cope up with the relevant problems and can lead to accurate classification.

Functional and effective connectivity based features of EEG signals for object recognition

Classifying different object categories is one of the most important aims of brain-computer interface researches. Recently, interactions between brain regions were studied using different methods, such as functional and effective connectivity techniques. Functional and effective connectivity techniques are applied to estimate human brain areas connectivity. The main purpose of this study is to compare classification accuracy of the most advanced functional and effective methods in order to classify 12 basic object categories using Electroencephalography (EEG) signals. In this paper, 19 channels EEG signals were collected from 10 healthy subjects; when they were visiting color images and instructed to select the target images among others. Correlation, magnitude square coherence, wavelet coherence (WC), phase synchronization and mutual information were applied to estimate functional cortical connectivity. On the other hand, directed transfer function, partial directed coherence, generalized partial directed coherence (GPDC) were used to obtain effective cortical connectivity. After feature extraction, the scalar feature selection methods including T-test and one-sided-anova were applied to rank and select the most informative features. The selected features were classified by a one-against-one support vector machine classifier. The results indicated that the use of different techniques led to different classifying accuracy and brain lobes analysis. WC and GPDC are the most accurate methods with performances of 80.15% and 64.43%, respectively.

Learning Advanced Brain Computer Interface Technology

Feature extraction is an important step in electroencephalogram (EEG) processing of motor imagery, and the feature extraction of EEG directly affects the final classification results. Through the analysis of various feature extraction methods, this article finally selects Common Spatial Patterns (CSP) and wavelet packet analysis (WPA) to extract the feature and uses Support Vector Machine (SVM) to classify and compare these extracted features. For the EEG data provided by GRAZ University, the accuracy rate of feature extraction using CSP algorithm is 85.5%, and the accuracy rate of feature extraction using wavelet packet analysis is 92%. Then this paper analyzes the EEG data collected by Emotiv epoc+ system. The classification accuracy of wavelet packet extracted features can still be maintained at more than 80%, while the classification accuracy of CSP extracted feature is decreased obviously. Experimental results show that the method of wavelet packet analysis towards competition data and Emotiv epoc+ system data can both get a desirable outcome.

Tinnitus Abnormal Brain Region Detection Based on Dynamic Causal Modeling and Exponential Ranking

Dynamic Causal Modeling (DCM) has been extended for the analysis of electroencephalography (EEG) based on a specific biophysical and neurobiological generative model for EEG. Comparing to methods that summarize neural activities with linear relationships, the generative model enables DCM to better describe how signals are generated and better reveal the underlying mechanism of the activities occurring in human brains. Since DCM provides us with an approach to the effective connectivity between brain areas, with exponential ranking, the abnormality of the observed signals can be further located to a specific brain region. In this paper, a combination of DCM and exponential ranking is proposed as a new method aiming at searching for the abnormal brain regions which are associated with chronic tinnitus.

Classification of intelligence quotient via brainwave sub-band power ratio features and artificial neural network

This paper elaborates on the novel intelligence assessment method using the brainwave sub-band power ratio features. The study focuses only on the left hemisphere brainwave in its relaxed state. Distinct intelligence quotient groups have been established earlier from the score of the Raven Progressive Matrices. Sub-band power ratios are calculated from energy spectral density of theta, alpha and beta frequency bands. Synthetic data have been generated to increase dataset from 50 to 120. The features are used as input to the artificial neural network. Subsequently, the brain behaviour model has been developed using an artificial neural network that is trained with optimized learning rate, momentum constant and hidden nodes. Findings indicate that the distinct intelligence quotient groups can be classified from the brainwave sub-band power ratios with 100% training and 88.89% testing accuracies.

EEG-based analysis of human driving performance in turning left and right using Hopfield neural network

In this article a quantitative analysis was devised assessing driver's cognition responses by exploring the neurobiological information underlying electroencephalographic (EEG) brain signals in a left and right turning experiment on simulator environment. Driving brain signals have been collected by a 19-channel electroencephalogram recording system. The driving pathway has been selected with no obstacles, a set of indicators are used to inform the subjects when they had to turn left or right by means of keyboard left and right arrows. Subsequently in order to remove artifacts, preprocessing is performed on data to achieve high accuracy. Features of signals are extracted by using Fast Fourier Transform (FFT). Absolute power of FFT is used as a basic feature. Scalar Feature selection method is applied to reduce feature dimension. Thereafter dimension-reduced features are fed to Hopfield Neural Network (HNN) recognizing different brain potentials stimulated by turning to left and right. The performances of HNN are evaluated by considering five conditions; before feature extraction, after feature extraction, before reduction of features, after analyzing reduced features and finally subject-wise Hopfield performances respectively. An increase occurred in each level and continued until it has reached its highest 97.6% of accuracy on last condition.

Detecting missing signals in multichannel recordings by using higher order statistics

In real world applications, a multichannel acquisition system is susceptible of having one or many of its sensors displaced or detached, leading therefore to the loss or corruption of the recorded signals. In this paper, we present a technique for detecting missing or corrupted signals in multichannel recordings. Our approach is based on Higher Order Statistics (HOS) analysis. Our approach is tested on real uterine electromyogram (EMG) signals recorded by 4×4 electrode grid. Results have shown that HOS descriptors can discriminate between the two classes of signals (missing vs. non-missing). These results are supported by statistical analysis using the t-test which indicated good statistical significance of 95% confidence level.

Stochastic relevance analysis of epileptic EEG signals for channel selection and classification

Time-frequency decompositions (TFDs) are well known techniques that permit to extract useful information or features from EEG signals, being necessary to distinguish between irrelevant information and the features effectively representing the subjacent physiological phenomena, according to some evaluation measure. This work introduces a new method to obtain relevant features extracted from time-frequency plane for epileptic EEG signals. Particularly, EEG features are extracted by common spectral methods such as short time Fourier transform (STFT), wavelets transform and Empirical Mode Decomposition (EMD). Then, each method is evaluated by Stochastic Relevance Analysis (SRA) that is further used for EEG classification and channel selection. The classification measures are carried out based on the performance of the k-NN classifier, while the channels selected are validated by visual inspection and topographic scalp map. The study uses real and multi-channel EEG data and all the experiments have been supervised by an expert neurologist. Results obtained in this paper show that SRA is a good alternative for automatic seizure detection and also opens the possibility of formulating new criteria to select, classify or analyze abnormal EEG channels.

Classification of multichannel uterine EMG signals

Classification of multichannel uterine electromyogram (EMG) signals is addressed. Signals were recorded by a matrix of 16 electrodes. First, signals corresponding to each channel were individually classified using an artificial neural network (ANN) based on radial basis functions (RBF). The results have shown that the classification performance varies from one channel to another. Then, a decision fusion method based on these classification performances was tested. After fusion, the network yielded better classification accuracy than any individual channel could provide. The high percentage of correctly classified labor/non-labor events proves the efficiency of multichannel recordings in detecting labor. These findings can be very useful for the aim of classifying antepartum versus labor patients.

Classification of resting, anticipation and movement states in self-initiated arm movements for EEG brain computer interfaces

In the last years, there has been an increasing interest in using Brain Computer Interfaces (BCI) within motor rehabilitation therapies that use robotic devices or functional electro stimulation to help or guide the efforts of the patient to move her body. A crucial step of these therapies is to provide help to the user just when she is actually trying to accomplish a certain motion or task One of the most promising applications of BCI systems in this context is its ability to measure the user intentions and actions to trigger the rehabilitation devices accordingly. This paper studies the single-trial classification based on EEG measurements of three basic states during the execution of self-initiated motion: rest, motion preparation (or anticipation) and motion. We conducted an experiment where the participants had to reach at their will eight different locations from a fixed starting position. Results for seven healthy subjects show that it is possible to achieve good classification rates given that features are carefully selected for each subject and for each pair of states.

Localisation of cognitive tasks used in EEG-based BCIs

OBJECTIVE

To provide candidate electrode sites and neurophysiological reference information for cognitive tasks used in brain-computer interfacing research.

METHODS

Six cognitive tasks were tested against the idle state. Data representing the idle state were collected with active cognitive task data during each recording session. Cross subject candidate electrode sites were obtained via a wrapper method based upon a sequential forward floating search algorithm. Source localisation results were obtained using sLORETA software.

RESULTS

Spatial feature distributions and localisation results are presented. Primary centres of activity for motor imagery tasks are localised to the pre- and postcentral gyrus. Auditory-based tasks show activity in the middle temporal gyrus. Calculation activity was localised to the left inferior frontal gyrus and right supramarginal gyrus. Navigation imagery produced activity in the precuneus and anterior cingulate cortex.

CONCLUSIONS

Spatial areas of activation suggest that arithmetic and auditory tasks show promise for pairwise discrimination based on single recording sites. sLORETA significance levels suggest that motor imagery tasks will show greatest discrimination from baseline EEG activity.

SIGNIFICANCE

This is the first study to provide candidate electrode sites for multiple tasks used in brain-computer interfacing.

Nessi: an EEG-controlled web browser for severely paralyzed patients

We have previously demonstrated that an EEG-controlled web browser based on self-regulation of slow cortical potentials (SCPs) enables severely paralyzed patients to browse the internet independently of any voluntary muscle control. However, this system had several shortcomings, among them that patients could only browse within a limited number of web pages and had to select links from an alphabetical list, causing problems if the link names were identical or if they were unknown to the user (as in graphical links). Here we describe a new EEG-controlled web browser, called Nessi, which overcomes these shortcomings. In Nessi, the open source browser, Mozilla, was extended by graphical in-place markers, whereby different brain responses correspond to different frame colors placed around selectable items, enabling the user to select any link on a web page. Besides links, other interactive elements are accessible to the user, such as e-mail and virtual keyboards, opening up a wide range of hypertext-based applications.

Classification of sleep apnea through sub-band energy of abdominal effort signal using Wavelets + Neural Networks

Detection and classification of sleep apnea syndrome (SAS) is a critical problem. In this study an efficient method for classification sleep apnea through sub-band energy of abdominal effort using a particularly designed hybrid classifier as Wavelets + Neural Network is proposed. The Abdominal respiration signals were separated into spectral sub-band energy components with multi-resolution Discrete Wavelet Transform (DWT). The energy content of these spectral components was applied to the input of the artificial neural network (ANN). The ANN was configured to give three outputs dedicated to SAS cases; obstructive sleep apnea (OSA), central sleep apnea (CSA) and mixed sleep apnea (MSA). Through the network, satisfactory results that rewarding 85.62% mean accuracy in classifying SAS were obtained.

Effect of feature and channel selection on EEG classification

In this paper, we evaluate the significance of feature and channel selection on EEG classification. The selection process is performed by searching the feature/channel space using genetic algorithm, and evaluating the importance of subsets using a linear support vector machine classifier. Three approaches have been considered: (i) selecting a subset of features that will be used to represent a specified set of channels, (ii) selecting channels that are each represented by a specified set of features, and (iii) selecting individual features from different channels. When applied to a brain-computer interface (BCI) problem, results indicate that improvement in classification accuracy can be achieved by considering the correct combination of channels and features.

EEG features extraction for motor imagery

Motor imagery is the mental simulation of a motor act that includes preparation for movement, passive observations of action and mental operations of motor representations implicitly or explicitly. Motor imagery as preparation for immediate movement likely involves the motor executive brain regions. Implicit mental operations of motor representations are considered to underlie cognitive functions. Another problem concerning neuro-imaging studies on motor imagery is that the performance of imagination is very difficult to control. The ability of an individual to control its EEG may enable him to communicate without being able to control their voluntary muscles. Communication based on EEG signals does not require neuromuscular control and the individuals who have neuromuscular disorders and who may have no more control over any of their conventional communication abilities may still be able to communicate through a direct brain-computer interface. A brain-computer interface replaces the use of nerves and muscles and the movements they produce with electrophysiological signals and is coupled with the hardware and software that translate those signals into physical actions. One of the most important components of a brain-computer interface is the EEG feature extraction procedure. This paper presents an approach that uses self-organizing fuzzy neural network based time series prediction that performs EEG feature extraction in the time domain only. EEG is recorded from two electrodes placed on the scalp over the motor cortex. EEG signals from each electrode are predicted by a single fuzzy neural network. Features derived from the mean squared error of the predictions and from the mean squared of the predicted signals are extracted from EEG data by means of a sliding window. The architecture of the two auto-organizing fuzzy neural networks is a network with multi inputs and single output.

Detecting movement-related EEG change by wavelet decomposition-based neural networks trained with single thumb movement

OBJECTIVE

The main goal of this study was to develop a real-time detection algorithm of movement-related EEG changes for the naïve subjects with a very small amount of training data. Such an algorithm is vital for the realization of brain-computer interface.

METHODS

The target algorithm developed in this study was based on the wavelet decomposition neural network (WDNN). Surface Laplacian EEG was recorded at central cortical areas and processed with wavelet decomposition (WD) for feature extraction and neural network for pattern recognition. The new algorithm was compared with nother three methods, namely, threshold-based WD and short-time Fourier transform (STFT), and Fourier transform neural network (FTNN), for performance. The trainings of all algorithms were based, respectively, on the changes of mu and beta rhythms before and after voluntary movements. In order to investigate whether WDNN could adapt to the nonstationarity of EEG or not, we also compared two training modes, namely, fixed and updated weight. The significances of the success rates were tested by ANOVA (analysis of variance) and verified by ROC (receiver operating characteristic) analysis.

RESULTS

The experimental data showed that (1) success rates of movement detection were acceptable even when the training set was reduced to a single trial data, (2) WDNN performed better than WD or STFT without optimized thresholds and (3) when weights were updated and thresholds were optimized, WDNN still performed better than WD, while FTNN had a marginal advantage over STFT.

CONCLUSIONS

We developed a detection algorithm based on WDNN with the training set being reduced to a single trial data. The overall performance of this algorithm was better than the conventional methods as such.

SIGNIFICANCE

mu wave suppression could be detected more precisely by the wavelet decomposition with neural network than the conventional algorithms such as STFT and WD. The size of training data could be reduced to a single trial and the success rates were up to 75-80%.

A survey of signal processing algorithms in brain-computer interfaces based on electrical brain signals

Brain-computer interfaces (BCIs) aim at providing a non-muscular channel for sending commands to the external world using the electroencephalographic activity or other electrophysiological measures of the brain function. An essential factor in the successful operation of BCI systems is the methods used to process the brain signals. In the BCI literature, however, there is no comprehensive review of the signal processing techniques used. This work presents the first such comprehensive survey of all BCI designs using electrical signal recordings published prior to January 2006. Detailed results from this survey are presented and discussed. The following key research questions are addressed: (1) what are the key signal processing components of a BCI, (2) what signal processing algorithms have been used in BCIs and (3) which signal processing techniques have received more attention?

EMG and EOG artifacts in brain computer interface systems: A survey

It is widely accepted in the brain computer interface (BCI) research community that neurological phenomena are the only source of control in any BCI system. Artifacts are undesirable signals that can interfere with neurological phenomena. They may change the characteristics of neurological phenomena or even be mistakenly used as the source of control in BCI systems. Electrooculography (EOG) and electromyography (EMG) artifacts are considered among the most important sources of physiological artifacts in BCI systems. Currently, however, there is no comprehensive review of EMG and EOG artifacts in BCI literature. This paper reviews EOG and EMG artifacts associated with BCI systems and the current methods for dealing with them. More than 250 refereed journal and conference papers are reviewed and categorized based on the type of neurological phenomenon used and the methods employed for handling EOG and EMG artifacts. This study reveals weaknesses in BCI studies related to reporting the methods of handling EMG and EOG artifacts. Most BCI papers do not report whether or not they have considered the presence of EMG and EOG artifacts in the brain signals. Only a small percentage of BCI papers report automated methods for rejection or removal of artifacts in their systems. As the lack of dealing with artifacts may result in the deterioration of the performance of a particular BCI system during practical applications, it is necessary to develop automatic methods to handle artifacts or to design BCI systems whose performance is robust to the presence of artifacts.

Systematic identification for inert region of a brain from EEG

Evaluation of biomedical signals is important in the diagnosis of neurology diseases, such as dementia, in neurology through the use of electroencephalograms (EEG). While automated techniques exist for EEG analysis, it is likely that additional information can be extracted from EEG signal through the use of new methods. We describe a method for identifying inert region from EEG. This method uses EEG as input to an artificial neural network with five outputs: activity in whole regoin and inert region separated by four regions.

Enhancing feature extraction with sparse component analysis for brain-computer interface

Feature extraction is very important to EEG-based brain computer interfaces (BCI) in helping achieve high classification accuracy. Preprocessing of EEG signals plays an important role, because an effective preprocessing method will help enhance the efficiency of the feature extraction. In this paper, sparse component analysis (SCA) is employed as a preprocessing method for EEG based BCI. A combined feature vector is constructed. This feature vector consists of a dynamical power feature and a dynamical common spatial pattern (CSP) feature. The dynamical power feature is extracted from selected SCA components, while the dynamical CSP feature is extracted from raw EEG data. Using the presented preprocessing and feature extraction method, we analyze the data for a cursor control BCI carried out at Wadsworth Center. Our results show that SCA preprocessing is the most effective in extracting a component which reflects the subject's intention, and demonstrate the validity of SCA preprocessing for the enhancement of feature extraction.

A self-paced brain interface system that uses movement related potentials and changes in the power of brain rhythms

Movement execution results in the simultaneous generation of movement-related potentials (MRP) as well as changes in the power of Mu and Beta rhythms. This paper proposes a new self-paced multi-channel BI that combines features extracted from MRPs and from changes in the power of Mu and Beta rhythms. We developed a new algorithm to classify the high-dimensional feature space. It uses a two-stage multiple-classifier system (MCS). First, an MCS classifies each neurological phenomenon separately using the information extracted from specific EEG channels (EEG channels are selected by a genetic algorithm). In the second stage, another MCS combines the outputs of MCSs developed in the first stage. Analysis of the data of four able-bodied subjects shows the superior performance of the proposed algorithm compared with a scheme where the features were all combined in a single feature vector and then classified.

Localization of an inert region in the brain using modified Levenberg Marquarts neural network

We tested the localization accuracy of electroencephalograph (EEG) for an inert region in a simulation at sizes ranging from 1 to 8 cm at 1 cm intervals. We used international 10-20 system electrodes placements and three concentric shell model to calculate forward problems. From using the data, neural network could be used to solve inverse problems. In this case, we estimate the localization of inert region. To demonstrate the effectiveness of the method, we perform simulations on location of inert region from EEG data, consists of training and test data. Based on the results of extensive studies, we conclude that neural network are high feasible as localization of inert region. These EEG estimation tasks were created by using a set of calculated, artificial EEG signals based on a number of current dipoles. The experimental results indicate that the proposed method has several attractive features. 1) The size of inert region is becoming more large and more the RMS values low. 2) The following the distance is closer, the RMS values is low. That could be considered inert region exists near by the electrode which has low RMS potential. 3) The more larger inert region were, the more small estimation error become.

A Comprehensive Survey of Brain Interface Technology Designs

In this work we present the first comprehensive survey of Brain Interface (BI) technology designs published prior to January 2006. Detailed results from this survey, which was based on the Brain Interface Design Framework proposed by Mason and Birch, are presented and discussed to address the following research questions: (1) which BI technologies are directly comparable, (2) what technology designs exist, (3) which application areas (users, activities and environments) have been targeted in these designs, (4) which design approaches have received little or no research and are possible opportunities for new technology, and (5) how well are designs reported. The results of this work demonstrate that meta-analysis of high-level BI design attributes is possible and informative. The survey also produced a valuable, historical cross-reference where BI technology designers can identify what types of technology have been proposed and by whom.

Improved classification of medical data using abductive network committees trained on different feature subsets

This paper demonstrates the use of abductive network classifier committees trained on different features for improving classification accuracy in medical diagnosis. In an earlier publication, committee members were trained on different subsets of the training set to ensure enough diversity for improved committee performance. In situations characterized by high data dimensionality, i.e. a large number of features and a relatively few training examples, it may be more advantageous to split the feature set rather than the training set. We describe a novel approach for tentatively ranking the features and forming subsets of uniform predictive quality for training individual members. The abductive network training algorithm is used to select optimum predictors from the feature set at various levels of model complexity specified by the user. Using the resulting tentative ranking, the features are grouped into mutually exclusive subsets of approximately equal predictive power for training the members. The approach is demonstrated on three standard medical diagnosis datasets (breast cancer, heart disease, and diabetes). Three-member committees trained on different feature subsets and using simple output combination methods reduce classification errors by up to 20% compared to the best single model developed with the full feature set. Results are compared with those reported previously with members trained through splitting the training set. Training abductive committee members on feature subsets of approximately equal predictive power achieves both diversity and quality for improved committee performance. Ensemble feature subset selection can be performed using GMDH-based learning algorithms. The approach should be advantageous in situations characterized by high data dimensionality.

Classification of EEG signals using neural network and logistic regression

Epileptic seizures are manifestations of epilepsy. Careful analyses of the electroencephalograph (EEG) records can provide valuable insight and improved understanding of the mechanisms causing epileptic disorders. The detection of epileptiform discharges in the EEG is an important component in the diagnosis of epilepsy. As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in diagnostic classification. This paper deals with a novel method of analysis of EEG signals using wavelet transform and classification using artificial neural network (ANN) and logistic regression (LR). Wavelet transform is particularly effective for representing various aspects of non-stationary signals such as trends, discontinuities and repeated patterns where other signal processing approaches fail or are not as effective. Through wavelet decomposition of the EEG records, transient features are accurately captured and localized in both time and frequency context. In epileptic seizure classification we used lifting-based discrete wavelet transform (LBDWT) as a preprocessing method to increase the computational speed. The proposed algorithm reduces the computational load of those algorithms that were based on classical wavelet transform (CWT). In this study, we introduce two fundamentally different approaches for designing classification models (classifiers) the traditional statistical method based on logistic regression and the emerging computationally powerful techniques based on ANN. Logistic regression as well as multilayer perceptron neural network (MLPNN) based classifiers were developed and compared in relation to their accuracy in classification of EEG signals. In these methods we used LBDWT coefficients of EEG signals as an input to classification system with two discrete outputs: epileptic seizure or non-epileptic seizure. By identifying features in the signal we want to provide an automatic system that will support a physician in the diagnosing process. By applying LBDWT in connection with MLPNN, we obtained novel and reliable classifier architecture. The comparisons between the developed classifiers were primarily based on analysis of the receiver operating characteristic (ROC) curves as well as a number of scalar performance measures pertaining to the classification. The MLPNN based classifier outperformed the LR based counterpart. Within the same group, the MLPNN based classifier was more accurate than the LR based classifier.

Classifying EEG-based motor imagery tasks by means of time–frequency synthesized spatial patterns

OBJECTIVE

To develop a single trial motor imagery (MI) classification strategy for the brain-computer interface (BCI) applications by using time-frequency synthesis approach to accommodate the individual difference, and using the spatial patterns derived from electroencephalogram (EEG) rhythmic components as the feature description.

METHODS

The EEGs are decomposed into a series of frequency bands, and the instantaneous power is represented by the envelop of oscillatory activity, which forms the spatial patterns for a given electrode montage at a time-frequency grid. Time-frequency weights determined by training process are used to synthesize the contributions from the time-frequency domains.

RESULTS

The present method was tested in nine human subjects performing left or right hand movement imagery tasks. The overall classification accuracies for nine human subjects were about 80% in the 10-fold cross-validation, without rejecting any trials from the dataset. The loci of MI activity were shown in the spatial topography of differential-mode patterns over the sensorimotor area.

CONCLUSIONS

The present method does not contain a priori subject-dependent parameters, and is computationally efficient. The testing results are promising considering the fact that no trials are excluded due to noise or artifact.

SIGNIFICANCE

The present method promises to provide a useful alternative as a general purpose classification procedure for MI classification.

Automatic recognition of alertness level by using wavelet transform and artificial neural network

We propose a novel method for automatic recognition of alertness level from full spectrum electroencephalogram (EEG) recordings. This procedure uses power spectral density (PSD) of discrete wavelet transform (DWT) of full spectrum EEG as an input to an artificial neural network (ANN) with three discrete outputs: alert, drowsy and sleep. The error back propagation neural network is selected as a classifier to discriminate the alertness level of a subject. EEG signals were obtained from 30 healthy subjects. The group consisted of 14 females and 16 males with ages ranging from 18 to 65 years and a mean age of 33.5 years, and a body mass index (BMI) of 32.4 +/- 7.3 kg/m2. Alertness level and classification properties of ANN were tested using the data recorded in 12 healthy subjects, whereby the EEG recordings were not used been used to train the ANN. The statistics were used as a measure of potential applicability of the ANN. The accuracy of the ANN was 96 +/- 3% alert, 95 +/- 4% drowsy and 94 +/- 5% sleep. The results suggest that the automatic recognition algorithm is applicable for distinguishing between alert, drowsy and sleep state in recordings that have not been used for the training.

Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms

Noninvasive electroencephalogram (EEG) recordings provide for easy and safe access to human neocortical processes which can be exploited for a brain-computer interface (BCI). At present, however, the use of BCIs is severely limited by low bit-transfer rates. We systematically analyze and develop two recent concepts, both capable of enhancing the information gain from multichannel scalp EEG recordings: 1) the combination of classifiers, each specifically tailored for different physiological phenomena, e.g., slow cortical potential shifts, such as the pre-movement Bereitschaftspotential or differences in spatio-spectral distributions of brain activity (i.e., focal event-related desynchronizations) and 2) behavioral paradigms inducing the subjects to generate one out of several brain states (multiclass approach) which all bare a distinctive spatio-temporal signature well discriminable in the standard scalp EEG. We derive information-theoretic predictions and demonstrate their relevance in experimental data. We will show that a suitably arranged interaction between these concepts can significantly boost BCI performances.

Massively Parallel Classification of Single-Trial EEG Signals Using a Min-Max Modular Neural Network

This paper presents a method for classifying single-trial electroencephalogram (EEG) signals using min-max modular neural networks implemented in a massively parallel way. The method has three main steps. First, a large-scale, complex EEG classification problem is simply divided into a reasonable number of two-class subproblems, as small as needed. Second, the two-class subproblems are simply learned by individual smaller network modules in parallel. Finally, all the individual trained network modules are integrated into a hierarchical, parallel, and modular classifier according to two module combination laws. To demonstrate the effectiveness of the method, we perform simulations on fifteen different four-class EEG classification tasks, each of which consists of 1491 training and 636 test data. These EEG classification tasks were created using a set of non-averaged, single-trial hippocampal EEG signals recorded from rats; the features of the EEG signals are extracted using wavelet transform techniques. The experimental results indicate that the proposed method has several attractive features. 1) The method is appreciably faster than the existing approach that is based on conventional multilayer perceptrons. 2) Complete learning of complex EEG classification problems can be easily realized, and better generalization performance can be achieved. 3) The method scales up to large-scale, complex EEG classification problems.

Automatic recognition of alertness and drowsiness from EEG by an artificial neural network

We present a novel method for classifying alert vs drowsy states from 1 s long sequences of full spectrum EEG recordings in an arbitrary subject. This novel method uses time series of interhemispheric and intrahemispheric cross spectral densities of full spectrum EEG as the input to an artificial neural network (ANN) with two discrete outputs: drowsy and alert. The experimental data were collected from 17 subjects. Two experts in EEG interpretation visually inspected the data and provided the necessary expertise for the training of an ANN. We selected the following three ANNs as potential candidates: (1) the linear network with Widrow-Hoff (WH) algorithm; (2) the non-linear ANN with the Levenberg-Marquardt (LM) rule; and (3) the Learning Vector Quantization (LVQ) neural network. We showed that the LVQ neural network gives the best classification compared with the linear network that uses WH algorithm (the worst), and the non-linear network trained with the LM rule. Classification properties of LVQ were validated using the data recorded in 12 healthy volunteer subjects, yet whose EEG recordings have not been used for the training of the ANN. The statistics were used as a measure of potential applicability of the LVQ: the t-distribution showed that matching between the human assessment and the network output was 94.37+/-1.95%. This result suggests that the automatic recognition algorithm is applicable for distinguishing between alert and drowsy state in recordings that have not been used for the training.

Electroencephalogram processing using neural networks

The electroencephalogram (EEG), a highly complex signal, is one of the most common sources of information used to study brain function and neurological disorders. More than 100 current neural network applications dedicated to EEG processing are presented. Works are categorized according to their objective (sleep analysis, monitoring anesthesia depth, brain-computer interface, EEG artifact detection, EEG source-based localization, etc.). Each application involves a specific approach (long-term analysis or short-term EEG segment analysis, real-time or time delayed processing, single or multiple EEG-channel analysis, etc.), for which neural networks were generally successful. The promising performances observed are demonstrative of the efficiency and efficacy of systems developed. This review can aid researchers, clinicians and implementors to understand up-to-date interest in neural network tools for EEG processing. The extended bibliography provides a database to assist in possible new concepts and idea development.

Hidden Markov based autoregressive analysis of stationary and non-stationary electrophysiological signals for functional coupling studies

In this paper, we apply multivariate autoregressive (MAR) models to problems of spectral estimation for stationary and non-stationary electrophysiological data. We describe how to estimate spectral matrices and approximate confidence limits from MAR coefficients, and for stationary data spectral results obtained from the MAR approach are compared with fast Fourier transform (FFT) estimates. The hidden Markov MAR (HMMAR) model is derived for spectral estimation of non-stationary data, and traditional model order selection problems such as the number of states to include in the hidden Markov model or the choice of MAR model order are addressed through the use of a Bayesian formalism.