Showing papers in "IEEE Transactions on Biomedical Engineering in 2004"

BCI2000: a general-purpose brain-computer interface (BCI) system

Abstract: Many laboratories have begun to develop brain-computer interface (BCI) systems that provide communication and control capabilities to people with severe motor disabilities. Further progress and realization of practical applications depends on systematic evaluations and comparisons of different brain signals, recording methods, processing algorithms, output formats, and operating protocols. However, the typical BCI system is designed specifically for one particular BCI method and is, therefore, not suited to the systematic studies that are essential for continued progress. In response to this problem, we have developed a documented general-purpose BCI research and development platform called BCI2000. BCI2000 can incorporate alone or in combination any brain signals, signal processing methods, output devices, and operating protocols. This report is intended to describe to investigators, biomedical engineers, and computer scientists the concepts that the BCI2000 system is based upon and gives examples of successful BCI implementations using this system. To date, we have used BCI2000 to create BCI systems for a variety of brain signals, processing methods, and applications. The data show that these systems function well in online operation and that BCI2000 satisfies the stringent real-time requirements of BCI systems. By substantially reducing labor and cost, BCI2000 facilitates the implementation of different BCI systems and other psychophysiological experiments. It is available with full documentation and free of charge for research or educational purposes and is currently being used in a variety of studies by many research groups.

A wavelet-based ECG delineator: evaluation on standard databases

Abstract: In this paper, we developed and evaluated a robust single-lead electrocardiogram (ECG) delineation system based on the wavelet transform (WT). In a first step, QRS complexes are detected. Then, each QRS is delineated by detecting and identifying the peaks of the individual waves, as well as the complex onset and end. Finally, the determination of P and T wave peaks, onsets and ends is performed. We evaluated the algorithm on several manually annotated databases, such as MIT-BIH Arrhythmia, QT, European ST-T and CSE databases, developed for validation purposes. The QRS detector obtained a sensitivity of Se=99.66% and a positive predictivity of P+=99.56% over the first lead of the validation databases (more than 980,000 beats), while for the well-known MIT-BIH Arrhythmia Database, Se and P+ over 99.8% were attained. As for the delineation of the ECG waves, the mean and standard deviation of the differences between the automatic and manual annotations were computed. The mean error obtained with the WT approach was found not to exceed one sampling interval, while the standard deviations were around the accepted tolerances between expert physicians, outperforming the results of other well known algorithms, especially in determining the end of T wave.

Automatic classification of heartbeats using ECG morphology and heartbeat interval features

Abstract: A method for the automatic processing of the electrocardiogram (ECG) for the classification of heartbeats is presented. The method allocates manually detected heartbeats to one of the five beat classes recommended by ANSI/AAMI EC57:1998 standard, i.e., normal beat, ventricular ectopic beat (VEB), supraventricular ectopic beat (SVEB), fusion of a normal and a VEB, or unknown beat type. Data was obtained from the 44 nonpacemaker recordings of the MIT-BIH arrhythmia database. The data was split into two datasets with each dataset containing approximately 50 000 beats from 22 recordings. The first dataset was used to select a classifier configuration from candidate configurations. Twelve configurations processing feature sets derived from two ECG leads were compared. Feature sets were based on ECG morphology, heartbeat intervals, and RR-intervals. All configurations adopted a statistical classifier model utilizing supervised learning. The second dataset was used to provide an independent performance assessment of the selected configuration. This assessment resulted in a sensitivity of 75.9%, a positive predictivity of 38.5%, and a false positive rate of 4.7% for the SVEB class. For the VEB class, the sensitivity was 77.7%, the positive predictivity was 81.9%, and the false positive rate was 1.2%. These results are an improvement on previously reported results for automated heartbeat classification systems.

Force modeling for needle insertion into soft tissue

Abstract: The modeling of forces during needle insertion into soft tissue is important for accurate surgical simulation, preoperative planning, and intelligent robotic assistance for percutaneous therapies. We present a force model for needle insertion and experimental procedures for acquiring data from ex vivo tissue to populate that model. Data were collected from bovine livers using a one-degree-of-freedom robot equipped with a load cell and needle attachment. computed tomography imaging was used to segment the needle insertion process into phases identifying different relative velocities between the needle and tissue. The data were measured and modeled in three parts: 1) capsule stiffness, a nonlinear spring model; 2) friction, a modified Karnopp model; and 3) cutting, a constant for a given tissue. In addition, we characterized the effects of needle diameter and tip type on insertion force using a silicone rubber phantom. In comparison to triangular and diamond tips, a bevel tip causes more needle bending and is more easily affected by tissue density variations. Forces for larger diameter needles are higher due to increased cutting and friction forces.

Noninvasive brain-actuated control of a mobile robot by human EEG

Abstract: Brain activity recorded noninvasively is sufficient to control a mobile robot if advanced robotics is used in combination with asynchronous electroencephalogram (EEG) analysis and machine learning techniques. Until now brain-actuated control has mainly relied on implanted electrodes, since EEG-based systems have been considered too slow for controlling rapid and complex sequences of movements. We show that two human subjects successfully moved a robot between several rooms by mental control only, using an EEG-based brain-machine interface that recognized three mental states. Mental control was comparable to manual control on the same task with a performance ratio of 0.74.

The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials

Abstract: Interest in developing a new method of man-to-machine communication-a brain-computer interface (BCI)-has grown steadily over the past few decades. BCIs create a new communication channel between the brain and an output device by bypassing conventional motor output pathways of nerves and muscles. These systems use signals recorded from the scalp, the surface of the cortex, or from inside the brain to enable users to control a variety of applications including simple word-processing software and orthotics. BCI technology could therefore provide a new communication and control option for individuals who cannot otherwise express their wishes to the outside world. Signal processing and classification methods are essential tools in the development of improved BCI technology. We organized the BCI Competition 2003 to evaluate the current state of the art of these tools. Four laboratories well versed in EEG-based BCI research provided six data sets in a documented format. We made these data sets (i.e., labeled training sets and unlabeled test sets) and their descriptions available on the Internet. The goal in the competition was to maximize the performance measure for the test labels. Researchers worldwide tested their algorithms and competed for the best classification results. This paper describes the six data sets and the results and function of the most successful algorithms.

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

Abstract: 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 premovement 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.

Gait assessment in Parkinson's disease: toward an ambulatory system for long-term monitoring

Abstract: An ambulatory gait analysis method using body-attached gyroscopes to estimate spatio-temporal parameters of gait has been proposed and validated against a reference system for normal and pathologic gait. Later, ten Parkinson's disease (PD) patients with subthalamic nucleus deep brain stimulation (STN-DBS) implantation participated in gait measurements using our device. They walked one to three times on a 20-m walkway. Patients did the test twice: once STN-DBS was ON and once 180 min after turning it OFF. A group of ten age-matched normal subjects were also measured as controls. For each gait cycle, spatio-temporal parameters such as stride length (SL), stride velocity (SV), stance (ST), double support (DS), and gait cycle time (GC) were calculated. We found that PD patients had significantly different gait parameters comparing to controls. They had 52% less SV, 60% less SL, and 40% longer GC. Also they had significantly longer ST and DS (11% and 59% more, respectively) than controls. STN-DBS significantly improved gait parameters. During the stim ON period, PD patients had 31% faster SV, 26% longer SL, 6% shorter ST, and 26% shorter DS. GC, however, was not significantly different. Some of the gait parameters had high correlation with Unified Parkinson's Disease Rating Scale (UPDRS) subscores including SL with a significant correlation (r=-0.90) with UPDRS gait subscore. We concluded that our method provides a simple yet effective way of ambulatory gait analysis in PD patients with results confirming those obtained from much more complex and expensive methods used in gait labs.

Automated feature extraction in color retinal images by a model based approach

Abstract: Color retinal photography is an important tool to detect the evidence of various eye diseases. Novel methods to extract the main features in color retinal images have been developed in this paper. Principal component analysis is employed to locate optic disk; A modified active shape model is proposed in the shape detection of optic disk; A fundus coordinate system is established to provide a better description of the features in the retinal images; An approach to detect exudates by the combined region growing and edge detection is proposed. The success rates of disk localization, disk boundary detection, and fovea localization are 99%, 94%, and 100%, respectively. The sensitivity and specificity of exudate detection are 100 % and 71 %, correspondingly. The success of the proposed algorithms can be attributed to the utilization of the model-based methods. The detection and analysis could be applied to automatic mass screening and diagnosis of the retinal diseases.

Support vector channel selection in BCI

Abstract: Designing a brain computer interface (BCI) system one can choose from a variety of features that may be useful for classifying brain activity during a mental task. For the special case of classifying electroencephalogram (EEG) signals we propose the usage of the state of the art feature selection algorithms Recursive Feature Elimination and Zero-Norm Optimization which are based on the training of support vector machines (SVM) . These algorithms can provide more accurate solutions than standard filter methods for feature selection . We adapt the methods for the purpose of selecting EEG channels. For a motor imagery paradigm we show that the number of used channels can be reduced significantly without increasing the classification error. The resulting best channels agree well with the expected underlying cortical activity patterns during the mental tasks. Furthermore we show how time dependent task specific information can be visualized.

BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm

Abstract: We propose an approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines. In a conservative classification scheme, we found the correct solution after five repetitions. While the classification within the competition is designed for offline analysis, our approach is also well-suited for a real-world online solution: It is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.

Chronic neural recording using silicon-substrate microelectrode arrays implanted in cerebral cortex

Abstract: An important aspect of the development of cortical prostheses is the enhancement of suitable implantable microelectrode arrays for chronic neural recording. The objective of this study was to investigate the recording performance of silicon-substrate micromachined probes in terms of reliability and signal quality. These probes were found to consistently and reliably provide high-quality spike recordings over extended periods of time lasting up to 127 days. In a consecutive series of ten rodents involving 14 implanted probes, 13/14 (93%) of the devices remained functional throughout the assessment period. More than 90% of the probe sites consistently recorded spike activity with signal-to-noise ratios sufficient for amplitudes and waveform-based discrimination. Histological analysis of the tissue surrounding the probes generally indicated the development of a stable interface sufficient for sustained electrical contact. The results of this study demonstrate that these planar silicon probes are suitable for long-term recording in the cerebral cortex and provide an effective platform technology foundation for microscale intracortical neural interfaces for use in humans.

Support vector machine-based expert system for reliable heartbeat recognition

Abstract: This paper presents a new solution to the expert system for reliable heartbeat recognition. The recognition system uses the support vector machine (SVM) working in the classification mode. Two different preprocessing methods for generation of features are applied. One method involves the higher order statistics (HOS) while the second the Hermite characterization of QRS complex of the registered electrocardiogram (ECG) waveform. Combining the SVM network with these preprocessing methods yields two neural classifiers, which have been combined into one final expert system. The combination of classifiers utilizes the least mean square method to optimize the weights of the weighted voting integrating scheme. The results of the performed numerical experiments for the recognition of 13 heart rhythm types on the basis of ECG waveforms confirmed the reliability and advantage of the proposed approach.

Principles of a brain-computer interface (BCI) based on real-time functional magnetic resonance imaging (fMRI)

Abstract: A brain-computer interface (BCI) based on functional magnetic resonance imaging (fMRI) records noninvasively activity of the entire brain with a high spatial resolution. We present a fMRI-based BCI which performs data processing and feedback of the hemodynamic brain activity within 1.3 s. Using this technique, differential feedback and self-regulation is feasible as exemplified by the supplementary motor area (SMA) and parahippocampal place area (PPA). Technical and experimental aspects are discussed with respect to neurofeedback. The methodology now allows for studying behavioral effects and strategies of local self-regulation in healthy and diseased subjects.

BCI competition 2003-data sets Ib and IIb: feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram

Abstract: The t-CWT, a novel method for feature extraction from biological signals, is introduced. It is based on the continuous wavelet transform (CWT) and Student's t-statistic. Applied to event-related brain potential (ERP) data in brain- computer interface (BCI) paradigms, the method provides fully automated detection and quantification of the ERP components that best discriminate between two samples of EEG signals and are, therefore, particularly suitable for classification of single-trial ERPs. A simple and fast CWT computation algorithm is proposed for the transformation of large data sets and single trials. The method was validated in the BCI Competition 2003 , where it was a winner (provided best classification) on two data sets acquired in two different BCI paradigms, P300 speller and slow cortical potential (SCP) self-regulation. These results are presented here.

Determination of EEG activity propagation: pair-wise versus multichannel estimate

Abstract: Performance of different estimators describing propagation of electroencephalogram (EEG) activity, namely: Granger causality, directed transfer function (DTF), direct DTF (dDTF), short-time DTF (SDTF), bivariate coherence, and partial directed coherence are compared by means of simulations and on the examples of experimental signals. In particular, the differences between pair-wise and multichannel estimates are studied. The results show unequivocally that in most cases, the pair-wise estimates are incorrect and a complete set of signals involved in a given process has to be used to obtain the correct pattern of EEG flows. Different performance of multivariate estimators of propagation depending on their normalization is discussed. Advantages of multivariate autoregressive model are pointed out.

An asynchronously controlled EEG-based virtual keyboard: improvement of the spelling rate

Abstract: An improvement of the information transfer rate of brain-computer communication is necessary for the creation of more powerful and convenient applications. This paper presents an asynchronously controlled three-class brain-computer interface-based spelling device [virtual keyboard (VK)], operated by spontaneous electroencephalogram and modulated by motor imagery. Of the first results of three able-bodied subjects operating the VK, two were successful, showing an improvement of the spelling rate /spl sigma/, the number of correctly spelled letters/min, up to /spl sigma/=3.38 (average /spl sigma/=1.99).

Long-term stimulation and recording with a penetrating microelectrode array in cat sciatic nerve

Abstract: We studied the consequences of long-term implantation of a penetrating microelectrode array in peripheral nerve over the time course of 4-6 mo. Electrode arrays without lead wires were implanted to test the ability of different containment systems to protect the array and nerve during contractions of surrounding muscles. Treadmill walking was monitored and the animals showed no functional deficits as a result of implantation. In a different set of experiments, electrodes with lead wires were implanted for up to 7 mo and the animals were tested at 2-4 week intervals at which time stimulation thresholds and recorded sensory activity were monitored for every electrode. It was shown that surgical technique highly affected the long-term stimulation results. Results between measurement sessions were compared, and in the best case, the stimulation properties stabilized in 80% of the electrodes over the course of the experiment (162 days). The recorded sensory signals, however, were not stable over time. A histological analysis performed on all implanted tissues indicated that the morphology and fiber density of the nerve around the electrodes were normal.

Three-dimensional head model Simulation of transcranial magnetic stimulation

Abstract: This paper presents a finite element method used to evaluate the induced current density in a realistic model of the human head exposed to a time varying magnetic field. The tissue electric properties were varied to ascertain their influence on the induced currents. Current density magnitude and vector plots were generated throughout the tissue layers to determine the effects of tissue boundaries on the field. The current density magnitude correlated to the conductivity of the tissue in all the cases tested except where the tissue permittivity was raised to a level to allow for displacement currents. In this case, the permittivity of the tissue was the dominant factor. Current density components normal to the tissue interface were shown to exist in all solutions within the cortex contrary to the predictions of present models that rely on symmetrical geometries. Additionally, modifications in the cortical geometry were shown to perturb the field so that the site of activation could be altered in diseased patient populations. Finally, by varying the tissue permittivity values and the source frequency, we tested the effects of alpha dispersion theories on transcranial magnetic stimulation.

Long-term characterization of firing dynamics of spontaneous bursts in cultured neural networks

Abstract: Extracellular action potentials were recorded from developing dissociated rat neocortical networks continuously for up to 49 days in vitro using planar multielectrode arrays. Spontaneous neuronal activity emerged toward the end of the first week in vitro and from then on exhibited periods of elevated firing rates, lasting for a few days up to weeks, which were largely uncorrelated among different recording sites. On a time scale of seconds to minutes, network activity typically displayed an ongoing repetition of distinctive firing patterns, including short episodes of synchronous firing at many sites ( network bursts). Network bursts were highly variable in their individual spatio-temporal firing patterns but showed a remarkably stable underlying probabilistic structure (obtained by summing consecutive bursts) on a time scale of hours. On still longer time scales, network bursts evolved gradually, with a significant broadening (to about 2 s) in the third week in vitro, followed by a drastic shortening after about one month in vitro. Bursts at this age were characterized by highly synchronized onsets reaching peak firing levels within less than ca. 60 ms. This pattern persisted for the rest of the culture period. Throughout the recording period, active sites showed highly persistent temporal relationships within network bursts. These longitudinal recordings of network firing have, thus, brought to light a reproducible pattern of complex changes in spontaneous firing dynamics of bursts during the development of isolated cortical neurons into synaptically interconnected networks.

Skin cancer identification using multifrequency electrical impedance-a potential screening tool

Abstract: Electrical bio-impedance can be used to assess skin cancers and other cutaneous lesions. The aim of this study was to distinguish skin cancer from benign nevi using multifrequency impedance spectra. Electrical impedance spectra of about 100 skin cancers and 511 benign nevi were measured. Impedance of reference skin was measured ipsi-laterally to the lesions. The impedance relation between lesion and reference skin was used to distinguish the cancers from the nevi. It was found that it is possible to separate malignant melanoma from benign nevi with 75% specificity at 100% sensitivity, and to distinguish nonmelanoma skin cancer from benign nevi with 87% specificity at 100% sensitivity. The power of skin cancer detection using electrical impedance is as good as, or better than, conventional visual screening made by general practitioners.

Evaluation of spike-detection algorithms fora brain-machine interface application

Abstract: Real time spike detection is an important requirement for developing brain machine interfaces (BMIs). We examined three classes of spike-detection algorithms to determine which is best suited for a wireless BMI with a limited transmission bandwidth and computational capabilities. The algorithms were analyzed by tabulating true and false detections when applied to a set of realistic artificial neural signals with known spike times and varying signal to noise ratios. A design-specific cost function was developed to score the relative merits of each detector; correct detections increased the score, while false detections and computational burden reduced it. Test signals both with and without overlapping action potentials were considered. We also investigated the utility of rejecting spikes that violate a minimum refractory period by occurring within a fixed time window after the preceding threshold crossing. Our results indicate that the cost-function scores for the absolute value operator were comparable to those for more elaborate nonlinear energy operator based detectors. The absolute value operator scores were enhanced when the refractory period check was used. Matched-filter-based detectors scored poorly due to their relatively large computational requirements that would be difficult to implement in a real-time system.

Detection of skin cancer by classification of Raman spectra

Abstract: Skin lesion classification based on in vitro Raman spectroscopy is approached using a nonlinear neural network classifier. The classification framework is probabilistic and highly automated. The framework includes a feature extraction for Raman spectra and a fully adaptive and robust feedforward neural network classifier. Moreover, classification rules learned by the neural network may be extracted and evaluated for reproducibility, making it possible to explain the class assignment. The classification performance for the present data set, involving 222 cases and five lesion types, was 80.5%/spl plusmn/5.3% correct classification of malignant melanoma, which is similar to that of trained dermatologists based on visual inspection. The skin cancer basal cell carcinoma has a classification rate of 95.8%/spl plusmn/2.7%, which is excellent. The overall classification rate of skin lesions is 94.8%/spl plusmn/3.0%. Spectral regions, which are important for network classification, are demonstrated to reproduce. Small distinctive bands in the spectrum, corresponding to specific lipids and proteins, are shown to hold the discriminating information which the network uses to diagnose skin lesions.

Atrial activity extraction for atrial fibrillation analysis using blind source separation

Abstract: This contribution addresses the extraction of atrial activity (AA) from real electrocardiogram (ECG) recordings of atrial fibrillation (AF). We show the appropriateness of independent component analysis (ICA) to tackle this biomedical challenge when regarded as a blind source separation (BSS) problem. ICA is a statistical tool able to reconstruct the unobservable independent sources of bioelectric activity which generate, through instantaneous linear mixing, a measurable set of signals. The three key hypothesis that make ICA applicable in the present scenario are discussed and validated: 1) AA and ventricular activity (VA) are generated by sources of independent bioelectric activity; 2) AA and VA present non-Gaussian distributions; and 3) the generation of the surface ECG potentials from the cardioelectric sources can be regarded as a narrow-band linear propagation process. To empirically endorse these claims, an ICA algorithm is applied to recordings from seven patients with persistent AF. We demonstrate that the AA source can be identified using a kurtosis-based reordering of the separated signals followed by spectral analysis of the sub-Gaussian sources. In contrast to traditional methods, the proposed BSS-based approach is able to obtain a unified AA signal by exploiting the atrial information present in every ECG lead, which results in an increased robustness with respect to electrode selection and placement.

Robot-assisted adaptive training: custom force fields for teaching movement patterns

Abstract: Based on recent studies of neuro-adaptive control, we tested a new iterative algorithm to generate custom training forces to "trick" subjects into altering their target-directed reaching movements to a prechosen movement as an after-effect of adaptation. The prechosen movement goal, a sinusoidal-shaped path from start to end point, was never explicitly conveyed to the subject. We hypothesized that the adaptation would cause an alteration in the feedforward command that would result in the prechosen movement. Our results showed that when forces were suddenly removed after a training period of 330 movements, trajectories were significantly shifted toward the prechosen movement. However, de-adaptation occurred (i.e., the after-effect "washed out") in the 50-75 movements that followed the removal of the training forces. A second experiment suppressed vision of hand location and found a detectable reduction in the washout of after-effects, suggesting that visual feedback of error critically influences learning. A final experiment demonstrated that after-effects were also present in the neighborhood of training-44% of original directional shift was seen in adjacent, unpracticed movement directions to targets that were 60/spl deg/ different from the targets used for training. These results demonstrate the potential for these methods for teaching motor skills and for neuro-rehabilitation of brain-injured patients. This is a form of "implicit learning," because unlike explicit training methods, subjects learn movements with minimal instructions, no knowledge of, and little attention to the trajectory.

BCI competition 2003-data set IIb: enhancing P300 wave detection using ICA-based subspace projections for BCI applications

Abstract: An algorithm based on independent component analysis (ICA) is introduced for P300 detection. After ICA decomposition, P300-related independent components are selected according to the a priori knowledge of P300 spatio-temporal pattern, and clear P300 peak is reconstructed by back projection of ICA. Applied to the dataset IIb of BCI Competition 2003, the algorithm achieved an accuracy of 100% in P300 detection within five repetitions.

Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors

Abstract: It is well known that vocal and voice diseases do not necessarily cause perceptible changes in the acoustic voice signal. Acoustic analysis is a useful tool to diagnose voice diseases being a complementary technique to other methods based on direct observation of the vocal folds by laryngoscopy. Through the present paper two neural-network based classification approaches applied to the automatic detection of voice disorders will be studied. Structures studied are multilayer perceptron and learning vector quantization fed using short-term vectors calculated accordingly to the well-known Mel Frequency Coefficient cepstral parameterization. The paper shows that these architectures allow the detection of voice disorders-including glottic cancer-under highly reliable conditions. Within this context, the Learning Vector quantization methodology demonstrated to be more reliable than the multilayer perceptron architecture yielding 96% frame accuracy under similar working conditions.

Using wavelet transform and fuzzy neural network for VPC detection from the holter ECG

Abstract: A novel method for detecting ventricular premature contraction (VPC) from the Holter system is proposed using wavelet transform (WT) and fuzzy neural network (FNN). The basic ideal and major advantage of this method is to reuse information that is used during QRS detection, a necessary step for most ECG classification algorithm, for VPC detection. To reduce the influence of different artifacts, the filter bank property of quadratic spline WT is explored. The QRS duration in scale three and the area under the QRS complex in scale four are selected as the characteristic features. It is found that the R wave amplitude has a marked influence on the computation of proposed characteristic features. Thus, it is necessary to normalize these features. This normalization process can reduce the effect of alternating R wave amplitude and achieve reliable VPC detection. After normalization and excluding the left bundle branch block beats, the accuracies for VPC classification using FNN is 99.79%. Features that are extracted using quadratic spline wavelet were used successfully by previous investigators for QRS detection. In this study, using the same wavelet, it is demonstrated that the proposed feature extraction method from different WT scales can effectively eliminate the influence of high and low-frequency noise and achieve reliable VPC classification. The two primary advantages of using same wavelet for QRS detection and VPC classification are less computation and less complexity during actual implementation.

Modeling and decoding motor cortical activity using a switching Kalman filter

Abstract: We present a switching Kalman filter model for the real-time inference of hand kinematics from a population of motor cortical neurons. Firing rates are modeled as a Gaussian mixture where the mean of each Gaussian component is a linear function of hand kinematics. A "hidden state" models the probability of each mixture component and evolves over time in a Markov chain. The model generalizes previous encoding and decoding methods, addresses the non-Gaussian nature of firing rates, and can cope with crudely sorted neural data common in on-line prosthetic applications.

BCI competition 2003-data set III: probabilistic modeling of sensorimotor /spl mu/ rhythms for classification of imaginary hand movements

Abstract: Brain-computer interfaces require effective online processing of electroencephalogram (EEG) measurements, e.g., as a part of feedback systems. We present an algorithm for single-trial online classification of imaginary left and right hand movements, based on time-frequency information derived from filtering EEG wideband raw data with causal Morlet wavelets, which are adapted to individual EEG spectra. Since imaginary hand movements lead to perturbations of the ongoing pericentral /spl mu/ rhythm, we estimate probabilistic models for amplitude modulation in lower (10 Hz) and upper (20 Hz) frequency bands over the sensorimotor hand cortices both contra- and ipsilaterally to the imagined movements (i.e., at EEG channels C3 and C4). We use an integrative approach to accumulate over time evidence for the subject's unknown motor intention. Disclosure of test data labels after the competition showed this approach to succeed with an error rate as low as 10.7%.