Exploiting the Cone of Influence for Improving the Performance of Wavelet Transform-Based Models for ERP/EEG Classification

Features extracted from the wavelet transform coefficient matrix are widely used in the design of machine learning models to classify event-related potential (ERP) and electroencephalography (EEG) signals in a wide range of brain activity research and clinical studies. This novel study is aimed at dramatically improving the performance of such wavelet-based classifiers by exploiting information offered by the cone of influence (COI) of the continuous wavelet transform (CWT). The COI is a boundary that is superimposed on the wavelet scalogram to delineate the coefficients that are accurate from those that are inaccurate due to edge effects. The features derived from the inaccurate coefficients are, therefore, unreliable. In this study, it is hypothesized that the classifier performance would improve if unreliable features, which are outside the COI, are zeroed out, and the performance would improve even further if those features are cropped out completely. The entire, zeroed out, and cropped scalograms are referred to as the "same" (S)-scalogram, "zeroed out" (Z)-scalogram, and the "valid" (V)-scalogram, respectively. The strategy to validate the hypotheses is to formulate three classification approaches in which the feature vectors are extracted from the (a) S-scalogram in the standard manner, (b) Z-scalogram, and (c) V-scalogram. A subsampling strategy is developed to generate small-sample ERP ensembles to enable customized classifier design for single subjects, and a strategy is developed to select a subset of channels from multiple ERP channels. The three scalogram approaches are implemented using support vector machines, random forests, k-nearest neighbor, multilayer perceptron neural networks, and deep learning convolution neural networks. In order to validate the performance hypotheses, experiments are designed to classify the multi-channel ERPs of five subjects engaged in distinguishing between synonymous and non-synonymous word pairs. The results confirm that the classifiers using the Z-scalogram features outperform those using the S-scalogram features, and the classifiers using the V-scalogram features outperform those using the Z-scalogram features. Most importantly, the relative improvement of the V-scalogram classifiers over the standard S-scalogram classifiers is dramatic. Additionally, enabling the design of customized classifiers for individual subjects is an important contribution to ERP/EEG-based studies and diagnoses of patient-specific disorders.

Electroencephalogram classification in motor-imagery brain-computer interface applications based on double-constraint nonnegative matrix factorization

OBJECTIVE

Brain-computer interfaces (BCIs) are aimed at providing a new way of communication between the human brain and external devices. One of the major tasks associated with the BCI system is to improve classification performance of the motor imagery (MI) signal. Electroencephalogram (EEG) signals are widely used for the MI BCI system. The raw EEG signals are usually non-stationary time series with weak class properties, degrading the classification performance.

APPROACH

Nonnegative matrix factorization (NMF) has been successfully applied to pattern extraction which provides meaningful data presentation. However, NMF is unsupervised and cannot make use of the label information. Based on the label information of MI EEG data, we propose a novel method, called double-constrained nonnegative matrix factorization (DCNMF), to improve the classification performance of NMF on MI BCI. The proposed method constructs a couple of label matrices as the constraints on the NMF procedure to make the EEGs with the same class labels have the similar representation in the low-dimensional space, while the EEGs with different class labels have dissimilar representations as much as possible. Accordingly, the extracted features obtain obvious class properties, which are optimal to the classification of MI EEG.

MAIN RESULTS

This study is conducted on the BCI competition III datasets (I and IVa). The proposed method helps to achieve a higher average accuracy across two datasets (79.00% for dataset I, 77.78% for dataset IVa); its performance is about 10% better than the existing studies in the literature.

SIGNIFICANCE

Our study provides a novel solution for MI BCI analysis from the perspective of label constraint; it provides convenience for semi-supervised learning of features and significantly improves the classification performance.

Improving the performance of empirical mode decomposition via Tsallis entropy: Application to Alzheimer EEG analysis

Alzheimer is a degenerative disorder that attacks neurons, resulting in loss of memory, thinking, language skills, and behavioral changes. Computer-aided detection methods can uncover crucial information recorded by electroencephalograms. A systematic literature search presents the wavelet transform as a frequently used technique in Alzheimer's detection. However, it requires a defined basis function considered a significant problem. In this work, the concept of empirical mode decomposition is introduced as an alternative to process Alzheimer signals. The performance of empirical mode decomposition heavily relies on a parameter called threshold. In our previous works, we found that the existing thresholding techniques were not able to highlight relevant information. The use of Tsallis entropy as a thresholder is evaluated through the combination of empirical mode decomposition and neural networks. Thanks to the extraction of better features that boost the classification accuracy, the proposed approach outperforms the state-of-the-art in terms of peak signal to noise ratio and root mean square error. Hence, our methodology is more likely to succeed than methods based on other landmarks such as Bayes, Normal and Visu shrink. We finally report an accuracy rate of 80%, while the aforementioned techniques only yield performances of 65%, 60% and 40%, respectively.

High-frequency EEG covaries with spike burst patterns detected in cortical neurons

Invasive microelectrode recordings measure neuronal spikes, which are commonly considered inaccessible through standard surface electroencephalogram (EEG). Yet high-frequency EEG potentials (hf-EEG, f > 400 Hz) found in somatosensory evoked potentials of primates may reflect the mean population spike responses of coactivated cortical neurons. Since cortical responses to electrical nerve stimulation vary strongly from trial to trial, we investigated whether the hf-EEG signal can also echo single-trial variability observed at the single-unit level. We recorded extracellular single-unit activity in the primary somatosensory cortex of behaving macaque monkeys and identified variable spike burst responses following peripheral stimulation. Each of these responses was classified according to the timing of its spike constituents, conforming to one of a discrete set of spike patterns. We here show that these spike patterns are accompanied by variations in the concomitant epidural hf-EEG. These variations cannot be explained by fluctuating stimulus efficacy, suggesting that they were generated within the thalamocortical network. As high-frequency EEG signals can also be reliably recorded from the scalp of human subjects, they may provide a noninvasive window on fluctuating cortical spike activity in humans.

Single-trial evoked potentials study by combining wavelet denoising and principal component analysis methods

The authors have developed a new approach by combining the wavelet denoising and principal component analysis methods to reduce the number of required trials for efficient extraction of brain evoked-related potentials (ERPs). Evoked-related potentials were initially extracted using wavelet denoising to enhance the signal-to-noise ratio of raw EEG measurements. Principal components of ERPs accounting for 80% of the total variance were extracted as part of the subspace of the ERPs. Finally, the ERPs were reconstructed from the selected principal components. Computer simulation results showed that the combined approach provided estimations with higher signal-to-noise ratio and lower root mean squared error than each of them alone. The authors further tested this proposed approach in single-trial ERPs extraction during an emotional process and brain responses analysis to emotional stimuli. The experimental results also demonstrated the effectiveness of this combined approach in ERPs extraction and further supported the view that emotional stimuli are processed more intensely.

Visual motion direction is represented in population-level neural response as measured by magnetoencephalography

We investigated whether direction information is represented in the population-level neural response evoked by the visual motion stimulus, as measured by magnetoencephalography. Coherent motions with varied speed, varied direction, and different coherence level were presented using random dot kinematography. Peak latency of responses to motion onset was inversely related to speed in all directions, as previously reported, but no significant effect of direction on latency changes was identified. Mutual information entropy (IE) calculated using four-direction response data increased significantly (>2.14) after motion onset in 41.3% of response data and maximum IE was distributed at approximately 20 ms after peak response latency. When response waveforms showing significant differences (by multivariate discriminant analysis) in distribution of the three waveform parameters (peak amplitude, peak latency, and 75% waveform width) with stimulus directions were analyzed, 87 waveform stimulus directions (80.6%) were correctly estimated using these parameters. Correct estimation rate was unaffected by stimulus speed, but was affected by coherence level, even though both speed and coherence affected response amplitude similarly. Our results indicate that speed and direction of stimulus motion are represented in the distinct properties of a response waveform, suggesting that the human brain processes speed and direction separately, at least in part.