Thomas Potter

Classification of Motor Imagery EEG Signals with Support Vector Machines and Particle Swarm Optimization

Support vector machines are powerful tools used to solve the small sample and nonlinear classification problems, but their ultimate classification performance depends heavily upon the selection of appropriate kernel and penalty parameters. In this study, we propose using a particle swarm optimization algorithm to optimize the selection of both the kernel and penalty parameters in order to improve the classification performance of support vector machines. The performance of the optimized classifier was evaluated with motor imagery EEG signals in terms of both classification and prediction. Results show that the optimized classifier can significantly improve the classification accuracy of motor imagery EEG signals.

Enhancing Performance of a Hybrid EEG-fNIRS System Using Channel Selection and Early Temporal Features

Brain-Computer Interface (BCI) techniques hold a great promise for neuroprosthetic applications. A desirable BCI system should be portable, minimally invasive, and feature high classification accuracy and efficiency. As two commonly used non-invasive brain imaging modalities, Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) BCI system have often been incorporated in the development of hybrid BCI systems, largely due to their complimentary properties. In this study, we aimed to investigate whether the early temporal information extracted from singular EEG and fNIRS channels on each hemisphere can be used to enhance the accuracy and efficiency of a hybrid EEG-fNIRS BCI system. Eleven healthy volunteers were recruited and underwent simultaneous EEG-fNIRS recording during a motor execution task that included left and right hand movements. Singular EEG and fNIRS channels corresponding to the motor cortices of each hemisphere were selected using a general linear model. Early temporal information was extracted from the EEG channel (0–1 s) along with initial hemodynamic dip information from fNIRS (0–2 s) for classification using a support vector machine (SVM). Results demonstrated a lofty classification accuracy using a minimal number of channels and features derived from early temporal information. In conclusion, a hybrid EEG-fNIRS BCI system can achieve higher classification accuracy (91.02 ± 4.08%) and efficiency by integrating their complimentary properties, compared to using EEG (85.64 ± 7.4%) or fNIRS alone (85.55 ± 10.72%). Such a hybrid system can also achieve minimal response lag in application by focusing on rapidly-evolving brain dynamics.

EEG Source Imaging Guided by Spatiotemporal Specific fMRI: Toward an Understanding of Dynamic Cognitive Processes

Understanding the mechanism of neuroplasticity is the first step in treating neuromuscular system impairments with cognitive rehabilitation approaches. To characterize the dynamics of the neural networks and the underlying neuroplasticity of the central motor system, neuroimaging tools with high spatial and temporal accuracy are desirable. EEG and fMRI stand among the most popular noninvasive neuroimaging modalities with complementary features, yet achieving both high spatial and temporal accuracy remains a challenge. A novel multimodal EEG/fMRI integration method was developed in this study to achieve high spatiotemporal accuracy by employing the most probable fMRI spatial subsets to guide EEG source localization in a time-variant fashion. In comparison with the traditional fMRI constrained EEG source imaging method in a visual/motor activation task study, the proposed method demonstrated superior localization accuracy with lower variation and identified neural activity patterns that agreed well with previous studies. This spatiotemporal fMRI constrained source imaging method was then implemented in a “sequential multievent-related potential” paradigm where motor activation is evoked by emotion-related visual stimuli. Results demonstrate that the proposed method can be used as a powerful neuroimaging tool to unveil the dynamics and neural networks associated with the central motor system, providing insights into neuroplasticity modulation mechanism.

Intramuscular EMG Decomposition Basing on Motor Unit Action Potentials Detection and Superposition Resolution

A novel electromyography (EMG) signal decomposition framework is presented for the thorough and precise analysis of intramuscular EMG signals. This framework first detects all of the active motor unit action potentials (MUAPs) and assigns single MUAP segments to their corresponding motor units. MUAP waveforms that are found to be superimposed are then resolved into their constituent single MUAPs using a peel-off approach and similarly assigned. The method is composed of six stages of analytical procedures: preprocessing, segmentation, alignment and feature extraction, clustering and refinement, supervised classification, and superimposed waveform resolution. The performance of the proposed decomposition framework was evaluated using both synthetic EMG signals and real recordings obtained from healthy and stroke participants. The overall detection rate of MUAPs was 100% for both synthetic and real signals. The average accuracy for synthetic EMG signals was 87.23%. Average assignment accuracies of 88.63 and 94.45% were achieved for the real EMG signals obtained from healthy and stroke participants, respectively. Results demonstrated the ability of the developed framework to decompose intramuscular EMG signals with improved accuracy and efficiency, which we believe will greatly benefit the clinical utility of EMG for the diagnosis and rehabilitation of motor impairments in stroke patients.

Characterization of dynamic changes of current source localization based on spatiotemporal fMRI constrained EEG source imaging

OBJECTIVEnNeuroimaging has been employed as a promising approach to advance our understanding of brain networks in both basic and clinical neuroscience. Electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) represent two neuroimaging modalities with complementary features; EEG has high temporal resolution and low spatial resolution while fMRI has high spatial resolution and low temporal resolution. Multimodal EEG inverse methods have attempted to capitalize on these properties but have been subjected to localization error. The dynamic brain transition network (DBTN) approach, a spatiotemporal fMRI constrained EEG source imaging method, has recently been developed to address these issues by solving the EEG inverse problem in a Bayesian framework, utilizing fMRI priors in a spatial and temporal variant manner. This paper presents a computer simulation study to provide a detailed characterization of the spatial and temporal accuracy of the DBTN method.nnnAPPROACHnSynthetic EEG data were generated in a series of computer simulations, designed to represent realistic and complex brain activity at superficial and deep sources with highly dynamical activity time-courses. The source reconstruction performance of the DBTN method was tested against the fMRI-constrained minimum norm estimates algorithm (fMRIMNE). The performances of the two inverse methods were evaluated both in terms of spatial and temporal accuracy.nnnMAIN RESULTSnIn comparison with the commonly used fMRIMNE method, results showed that the DBTN method produces results with increased spatial and temporal accuracy. The DBTN method also demonstrated the capability to reduce crosstalk in the reconstructed cortical time-course(s) induced by neighboring regions, mitigate depth bias and improve overall localization accuracy.nnnSIGNIFICANCEnThe improved spatiotemporal accuracy of the reconstruction allows for an improved characterization of complex neural activity. This improvement can be extended to any subsequent brain connectivity analyses used to construct the associated dynamic brain networks.

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) are two of the fundamental noninvasive methods for identifying brain activity. Multimodal methods have sought to combine the high temporal resolution of EEG with the spatial precision of fMRI, but the complexity of this approach is currently in need of improvement. The protocol presented here describes the recently developed spatiotemporal fMRI-constrained EEG source imaging method, which seeks to rectify source biases and improve EEG-fMRI source localization through the dynamic recruitment of fMRI sub-regions. The process begins with the collection of multimodal data from concurrent EEG and fMRI scans, the generation of 3D cortical models, and independent EEG and fMRI processing. The processed fMRI activation maps are then split into multiple priors, according to their location and surrounding area. These are taken as priors in a two-level hierarchical Bayesian algorithm for EEG source localization. For each window of interest (defined by the operator), specific segments of the fMRI activation map will be identified as active to optimize a parameter known as model evidence. These will be used as soft constraints on the identified cortical activity, increasing the specificity of the multimodal imaging method by reducing cross-talk and avoiding erroneous activity in other conditionally active fMRI regions. The method generates cortical maps of activity and time-courses, which may be taken as final results, or used as a basis for further analyses (analyses of correlation, causation, etc.) While the method is somewhat limited by its modalities (it will not find EEG-invisible sources), it is broadly compatible with most major processing software, and is suitable for most neuroimaging studies.

Frequency-dependent anisotropic modeling and analysis using mfEIT: A computer simulation study

Electrical properties of human tissues are usually linked with structure of thin insulating membranes and thereby reflect physiological function of the tissues or organs. It is clinically important to characterize electrical properties of tissues in vivo. Electrical impedance tomography is a recently developed medical imaging technique, which has been exploited to characterize electrical properties (conductivity and permittivity) of human tissues by injecting currents and measuring the resulting voltages at boundary electrodes. The electrical characteristic of a majority of human tissues, such as bones, muscles, and brain white matter, exhibits an anisotropic property. The anisotropic phenomenon of human tissues is frequency dependent that vanishes at high frequencies. Previous electrical impedance tomography studies that aimed at the reconstruction of anisotropic subject tissues have been focused on the theoretical analysis of uniqueness up to a diffeomorphism or the establishment of an accurate forward model by using an anisotropic conductivity tensor. However, effects of the current frequency on the accuracy of the reconstructions of anisotropic subjects remain poorly studied. The goal of this study is to examine the feasibility of multifrequency electrical impedance tomography by using it in a simulation study to recover the frequency-dependent anisotropic properties of a phantom subject composed of alternating insulating and conductive layers. The anisotropic properties of the subject were analyzed by an effective admittivity tensor, and the responses of the current flow pathways and voltages were investigated at various applied current frequencies in the forward model. The linear reconstruction was performed following the sensitivity matrix approach at multiple frequencies. Simulation results achieved at various frequencies revealed that the anisotropy of the model was effectively reconstructed at low frequencies and disappeared at high frequencies, from which we validated the feasibility of multifrequency electrical impedance tomography method in reconstructing the anisotropic directions of the considered object.

Characterization of Volume-Based Changes in Cortical Auditory Evoked Potentials and Prepulse Inhibition

The auditory evoked startle reflex is a conserved response resulting in neurological and motor activity. The presence of a mild prepulse immediately before the main pulse inhibits startle responses, though the mechanism for this remains unknown. In this study, the electroencephalography (EEG) data recorded from 15 subjects was analyzed to study the N1 and P2 components of cortical auditory evoked potentials (CAEPs) evoked by 70, 80, 90, 100, and 110u2009dB stimuli both in the presence and absence of 70u2009dB prepulses. Results without a prepulse showed an evolution of N1 amplitudes, increasing with stimulus intensityxa0and showing largely significant differences. Results from prepulse trials only showed noteworthy changes in peak-to-peak amplitude in the 100u2009dB condition. Prepulse and non-prepulse conditions were then compared using peak amplitudes and theta power. Prepulse conditions significantly decreased the amplitude for both components in the 110u2009dB condition, i.e., pre-pulse inhibition, but significantly increased the N1 amplitude in the 70u2009dB condition, i.e., pre-pulse facilitation. Similarly theta band power significantly increased in the 70u2009dB prepulse condition and significantly decreased in the 110u2009dB prepulse condition. These results expand the basis of knowledge regarding how CAEPs change and elaborate on their neural function and representation.