A tracing evoked potential estimator

Single-Trial Evoked Potential Estimating Based on Sparse Coding under Impulsive Noise Environment

Estimating single-trial evoked potentials (EPs) corrupted by the spontaneous electroencephalogram (EEG) can be regarded as signal denoising problem. Sparse coding has significant success in signal denoising and EPs have been proven to have strong sparsity over an appropriate dictionary. In sparse coding, the noise generally is considered to be a Gaussian random process. However, some studies have shown that the background noise in EPs may present an impulsive characteristic which is far from Gaussian but suitable to be modeled by the α-stable distribution (1 < α ≤ 2). Consequently, the performances of general sparse coding will degrade or even fail. In view of this, we present a new sparse coding algorithm using p-norm optimization in single-trial EPs estimating. The algorithm can track the underlying EPs corrupted by α-stable distribution noise, trial-by-trial, without the need to estimate the α value. Simulations and experiments on human visual evoked potentials and event-related potentials are carried out to examine the performance of the proposed approach. Experimental results show that the proposed method is effective in estimating single-trial EPs under impulsive noise environment.

Extracting patterns of single-trial EEG using an adaptive learning algorithm

The improvement of brain imaging technique brings about an opportunity for developing and investigating brain-computer interface (BCI) which is a way to interact with computer and environment. The measured brain activities usually constitute the signals of interest and noises. Applying the portable device and removing noise are the benefits to real-world BCI. In this study, one portable electroencephalogram (EEG) system non-invasively acquired brain dynamics through wireless transmission while six subjects participated in the rapid serial visual presentation (RSVP) paradigm. The event-related potential (ERP) was traditionally estimated by ensemble averaging (EA) to increase the signal-to-noise ratio. One adaptive filter of data-reusing radial basis function network (DR-RBFN) was also utilized as the estimator. The results showed that this portable EEG system stably acquired brain activities. Furthermore, the task-related potentials could be clearly explored from the limited samples of EEG data through DR-RBFN. According to the artifact-free data from the portable device, this study demonstrated the potential to move the BCI from laboratory research to real-life application in the near future.

Evaluation and Application of a RBF Neural Network for Online Single-Sweep Extraction of SEPs During Scoliosis Surgery

A method for on-line single sweep detection of somatosensory evoked potentials (SEPs) during intraoperative neuromonitoring is proposed. It is based on a radial-basis function neural network with Gaussian activations. In order to improve its tracking capabilities, the radial-basis functions location is partially learnt sweep-by-sweep; the training algorithm is effective, though consistent with real-time applications. This new detection method has been tested on simulated data so as to set the network parameters. Moreover, it has been applied to real recordings obtained from a new neuromonitoring technique which is based on the simultaneous observation of the SEP and of the evoked H-reflex elicited by the same electric stimulus. The SEPs have been extracted using the neural network and the results have then been compared to those obtained by ARX filtering and correlated with the spinal cord integrity information obtained by the H-reflex. The proposed algorithm has been proved to be particularly effective and suitable for single-sweep detection. It is able to track both sudden and smooth signal changes of both amplitude and latency and the needed computational time is moderate.

Visual evoked potential estimation by adaptive noise cancellation with neural-network-based fuzzy inference system

Visual evoked potentials (VEPs) are time-varying signals typically buried in relatively large background noise known as the electroencephalogram (EEG). In this paper, an adaptive noise cancellation with neural network-based fuzzy inference system (NNFIS) was used and the NNFIS was carefully designed to model the VEP signal. It is assumed that VEP responses can be modelled by NNFIS with the centres of its membership functions evenly distributed over time. The weights of NNFIS are adaptively determined by minimizing the variance of the error signal using the least mean squares (LMS) algorithm. As the NNFIS is dynamic to any change of VEP, the non-stationary characteristics of VEP can be tracked. Thus, this method should be able to track the VEP. Four sets of simulated data indicate that the proposed method is appropriate to estimate VEP. A total of 150 trials are processed to demonstrate the superior performance of the proposed method.

Visual evoked potentials estimation by adaptive noise cancellation with neural-network-based fuzzy inference system

Visual Evoked potentials (VEPs) are time-varying signals typically buried in relatively large background noise known as the electroencephalogram (EEG). An adaptive noise cancellation with neural-network-based fuzzy inference system was used and the NNFIS was carefully designed to model the VEP signal. An advantage of the method in this paper is that no reference signal is required. The NNFIS based on Takagi and Sugeno's fuzzy model has the advantage of being linear-in-parameter, which is able to closely fit any function mapping and can track the dynamic behavior of VEP in a real-time fashion. 4 sets of simulated data indicate that the proposed method is appropriate to estimate VEP. A total of 150 trials are processed to demonstrate the superior performance of the proposed method.

A radial basis function neural network for single sweep detection of somatosensory evoked potentials

The aim of this research is to evaluate the effectiveness of the employment of a Gaussian radial basis function neural network (RBFNN) for the on-line detection of single sweep somatosensory evoked potentials (SswSEPs), paying particular attention to the capability of tracking trial-to-trial variabilities. On the basis of simulations the parameters of the network have been set and the results have then been compared with those obtained from other methods, in particular with the ensemble averaging, the moving window averaging and the ARX filtering. This research shows a better performance of the RBFNN, because it is able to follow changes of the underlying signal even in noisy conditions and does not require prior assumptions.

Single trial somatosensory evoked potential extraction with ARX filtering for a combined spinal cord intraoperative neuromonitoring technique

Background

When spinal cord functional integrity is at risk during surgery, intraoperative neuromonitoring is recommended. Tibial Single Trial Somatosensory Evoked Potentials (SEPs) and H-reflex are here used in a combined neuromonitoring method: both signals monitor the spinal cord status, though involving different nervous pathways. However, SEPs express a trial-to-trial variability that is difficult to track because of the intrinsic low signal-to-noise ratio. For this reason single trial techniques are needed to extract SEPs from the background EEG.

Methods

The analysis is performed off line on data recorded in eight scoliosis surgery sessions during which the spinal cord was simultaneously monitored through classical SEPs and H-reflex responses elicited by the same tibial nerve electrical stimulation. The single trial extraction of SEPs from the background EEG is here performed through AutoRegressive filter with eXogenous input (ARX). The electroencephalographic recording can be modeled as the sum of the background EEG, which can be described as an autoregressive process not related to the stimulus, and the evoked potential (EP), which can be viewed as a filtered version of a reference signal related to the stimulus. The choice of the filter optimal orders is based on the Akaike Information Criterion (AIC). The reference signal used as exogenous input in the ARX model is a weighted average of the previous SEPs trials with exponential forgetting behavior.

Results

The moving average exponentially weighted, used as reference signal for the ARX model, shows a better sensibility than the standard moving average in tracking SEPs fast inter-trial changes. The ability to promptly detect changes allows highlighting relations between waveform changes and surgical maneuvers. It also allows a comparative study with H-reflex trends: in particular, the two signals show different fall and recovery dynamics following stressful conditions for the spinal cord.

Conclusion

The ARX filter showed good performances in single trial SEP extraction, enhancing the available information concerning the current spinal cord status. Moreover, the comparison between SEPs and H-reflex showed that the two signals are affected by the same surgical maneuvers, even if they monitor the spinal cord through anatomically different pathways.

Vibration syndrome diagnosis using a cooling test verified by computerized photoplethysmography

This study addresses the problem of vibration syndrome diagnosis by means of a cooling test verified by photoplethysmography. Measurement was taken on a small area on the fingertip plexus in which many arterio-venous anastomoses are present. In the opinion of many authors, flow disorders in this area are more typical for developing vibration syndrome than changes in the micro vessels. The study group comprised 128 subjects (58 women aged 40.9 +/- 5.4 years and 70 men aged 38.7 +/- 8.8 years) exposed to vibration. The control group consisted of 41 people (20 women aged 39.6 +/- 7.3 years and 21 men aged 39.3 +/- 6.4 years) who were not exposed to vibration. The patients were examined by a questionnaire and then a vibration perception threshold test and a cooling test were performed. The cooling test was verified both visually and using the computer method. Measurement data (S1, S2 and A) for each patient were obtained from averaging three pulse graphs. We departed from an average of 60 graphs (and more), the standard established in the literature, because of the cooling test specification, which causes huge thermodynamic parameter changeability in the plexus mass of the small finger under pulse waves coming one after another. A longer measurement time will reflect the thermal drift of the tested area in a direction to compensate for the reduced temperature. In the control group, all subjects showed an increase in planimetric indicators during the cooling test verified by computerized photoplethysmography. In the study group visual verification of the cooling test was positive in eight cases (6.2%) and the vibration perception threshold test was positive in seven cases (5.5%), but in computerized photoplethysmography the planimetric indicators decreased after cooling in 87 (67.4%) cases. Computer photoplethysmography is highly specific and shows greater sensitivity in detecting preclinical forms of vascular-type vibration syndrome when compared with palesthesiometry, the visually verified cooling test and the questionnaire. The proposed test enables the detection of vascular disorders in the prodromal period and gives time for preventive measures to be taken.

Real-Time Data-Reusing Adaptive Learning of a Radial Basis Function Network for Tracking Evoked Potentials

Tracking variations in both the latency and amplitude of evoked potential (EP) is important in quantifying properties of the nervous system. Adaptive filtering is a powerful tool for tracking such variations. In this paper, a data-reusing non-linear adaptive filtering method, based on a radial basis function network (RBFN), is implemented to estimate EP. The RBFN consists of an input layer of source nodes, a single hidden layer of non-linear processing units and an output layer of linear weights. It has built-in nonlinear activation functions that allow learning of function mappings. Moreover, it produces satisfactory estimates of signals against a background noise without a priori knowledge of the signal, provided that the signal and noise are independent. In clinical situations where EP responses change rapidly, the convergence rate of the algorithm becomes a critical factor. A carefully designed data-reusing RBFN can accelerate the convergence rate markedly and, thus, enhance its performance. Both theoretical analysis and simulation results support the improved performance of our new algorithm.

Optical noninvasive monitoring of skin blood pulsations

Time-resolved detection and analysis of skin backscattered optical signals (remission photoplethysmography or PPG) provide rich information on skin blood volume pulsations and can serve for reliable cardiovascular assessment. Single- and multiple-channel PPG concepts are discussed. Simultaneous data flow from several locations on the human body allows us to study heartbeat pulse-wave propagation in real time and to evaluate vascular resistance. Portable single-, dual-, and four-channel PPG monitoring devices with special software have been designed for real-time data acquisition and processing. The prototype devices have been clinically studied, and their potential for monitoring heart arrhythmias, drug-efficiency tests, steady-state cardiovascular assessment, body fitness control, and express diagnostics of the arterial occlusions has been confirmed.

Application of adaptive noise cancellation with neural-network-based fuzzy inference system for visual evoked potentials estimation

This paper presents an application of adaptive noise cancellation with neural-network-based fuzzy inference system (NNFIS) for rapid estimation of visual evoked potentials (VEPs). Usually a recorded VEP is severely contaminated by background ongoing activities of the spontaneous EEG signal in the human brain. Many approaches have been adopted to enhance the signal-to-noise ratio (SNR) of the recorded signal. However, nonlinear dynamic methods are rarely investigated in view of their complexity, and the fact that the nonlinear characteristics of the signal are hard to determine in general. An adaptive noise cancellation method with NNFIS was carefully designed to estimate the VEP signal. NNFIS, based on Takagi and Sugeno's fuzzy model, has the advantage of being linear-in-parameter; thus the conventional adaptive methods can be efficiently utilized to estimate its parameters. Another advantage of NNFIS lies in that it can track the dynamic behavior of VEP in a real-time fashion because the VEP variation tracking is important for critical patient monitoring in the clinical situation. A series of computer experiments conducted on simulated and real-test responses have confirmed the superiority of the method developed in this paper.

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.

Adaptive filtering of evoked potentials with radial-basis-function neural network prefilter

Evoked potentials (EPs) are time-varying signals typically buried in relatively large background noise. To extract the EP more effectively from noise, we had previously developed an approach using an adaptive signal enhancer (ASE) (Chen et al., 1995). ASE requires a proper reference input signal for its optimal performance. Ensemble- and moving window-averages were formerly used with good results. In this paper, we present a new method to provide even more effective reference inputs for the ASE. Specifically, a Gaussian radial basis function neural network (RBFNN) was used to preprocess raw EP signals before serving as the reference input. Since the RBFNN has built-in nonlinear activation functions that enable it to closely fit any function mapping, the output of RBFNN can effectively track the signal variations of EP. Results confirmed the superior performance of ASE with RBFNN over the previous method.

Detection and multichannel SVD-based filtering of trigeminal somatosensory evoked potentials

Very weak and noisy trigeminal somatosensory evoked potentials (TSEPs) are considered, which are successfully evoked by electrical stimulation of the trigeminal nerve of 15 patients with endosseous oral implants. As TSEP analysis provides an objective means of assessing neuronal function, it is considered to be a promising tool for investigating tactile sensation through anchoring implants in bone. For this purpose, a study of TSEP signals acquired from patients with endosseous oral implants has been carried out. Since TSEPs are severely contaminated by background ongoing electrical activities of the brain, a methodology is developed for statistically detecting the transient signal (TSEP) in the biological noise (EEG). For nine out of 15 patients, transient signals are detected in the background EEG activity. The TSEPs of these nine patients are subjected to further analysis. A multichannel singular value decomposition (SVD)-based filtering method is applied which successfully separates out the most energetic TSEPs from the background EEG, thereby increasing significantly the SNR of the recorded signals and improving extraction of the characteristic components of the TSEPs. It is shown that the most prominent feature of the TSEP signals for patients with endosseous oral implants is a wave with peak latency between 9 and 15 ms, generally followed by a wave between 25 and 28 ms or 34 and 38 ms for the specific cortical response areas.