A comparison of regression techniques for a two-dimensional sensorimotor rhythm-based brain-computer interface

Self-health monitoring and wearable neurotechnologies

Brain-computer interfaces and wearable neurotechnologies are now used to measure real-time neural and physiologic signals from the human body and hold immense potential for advancements in medical diagnostics, prevention, and intervention. Given the future role that wearable neurotechnologies will likely serve in the health sector, a critical state-of-the-art assessment is necessary to gain a better understanding of their current strengths and limitations. In this chapter we present wearable electroencephalography systems that reflect groundbreaking innovations and improvements in real-time data collection and health monitoring. We focus on specifications reflecting technical advantages and disadvantages, discuss their use in fundamental and clinical research, their current applications, limitations, and future directions. While many methodological and ethical challenges remain, these systems host the potential to facilitate large-scale data collection far beyond the reach of traditional research laboratory settings.

Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain-Computer Interfaces

Constructing accurate predictive models is at the heart of brain-computer interfaces (BCIs) because these models can ultimately translate brain activities into communication and control commands. The majority of the previous work in BCI use spatial, temporal, or spatiotemporal features of event-related potentials (ERPs). In this study, we examined the discriminatory effect of their spatiospectral features to capture the most relevant set of neural activities from electroencephalographic recordings that represent users' mental intent. In this regard, we model ERP waveforms using a sum of sinusoids with unknown amplitudes, frequencies, and phases. The effect of this signal modeling step is to represent high-dimensional ERP waveforms in a substantially lower dimensionality space, which includes their dominant power spectral contents. We found that the most discriminative frequencies for accurate decoding of visual attention modulated ERPs lie in a spectral range less than 6.4 Hz. This was empirically verified by treating dominant frequency contents of ERP waveforms as feature vectors in the state-of-the-art machine learning techniques used herein. The constructed predictive models achieved remarkable performance, which for some subjects was as high as 94% as measured by the area under curve. Using these spectral contents, we further studied the discriminatory effect of each channel and proposed an efficient strategy to choose subject-specific subsets of channels that generally led to classifiers with comparable performance.

Decoding unconstrained arm movements in primates using high-density electrocorticography signals for brain-machine interface use

Motor deficit is among the most debilitating aspects of injury to the central nervous system. Despite ongoing progress in brain-machine interface (BMI) development and in the functional electrical stimulation of muscles and nerves, little is understood about how neural signals in the brain may be used to potentially control movement in one’s own unconstrained paralyzed limb. We recorded from high-density electrocorticography (ECoG) electrode arrays in the ventral premotor cortex (PMv) of a rhesus macaque and used real-time motion tracking techniques to correlate spatial-temporal changes in neural activity with arm movements made towards objects in three-dimensional space at millisecond precision. We found that neural activity from a small number of electrodes within the PMv can be used to accurately predict reach-return movement onset and directionality. Also, whereas higher gamma frequency field activity was more predictive about movement direction during performance, mid-band (beta and low gamma) activity was more predictive of movement prior to onset. We speculate these dual spatiotemporal signals may be used to optimize both planning and execution of movement during natural reaching, with prospective relevance to the future development of neural prosthetics aimed at restoring motor control over one’s own paralyzed limb.

Generic and Specific Impressions Estimation and Their Application to KANSEI-Based Clothing Fabric Image Retrieval

Current image retrieval techniques are mainly based on text or visual contents. However, both text-based and contents-based methods lack the capability of utilizing human intuition and KANSEI (impression). In this paper, we proposed an impression-based image retrieval method in order to realize the image retrieval according to our impression presented by impression keywords. We first propose a generic and specific impressions estimation method based on machine learning and then apply it to impression-based clothing fabric image retrieval. We use a semantic differential (SD) method to measure the user’s impressions such as brightness and warmth while they view a cloth fabric image. We also extract both global and local features of cloth fabric images such as color and texture using computer vision techniques. Then we use support vector regression to model the mapping functions between the generic impression (or specific impression) and image features. The learnt mapping functions are used to estimate the generic and specific impressions of cloth fabric images. The retrieval is done by comparing the query impression with the estimated impression of images in the database.

EEG adaptive noise cancellation using information theoretic approach

OBJECTIVE

In this paper, an adaptive method based on error entropy criterion is presented in order to eliminate noise from Electroencephalogram (EEG) signals.

METHOD

Conventionally, the Mean-Squared Error (MSE) criterion is the dominant criterion deployed in the adaptive filters for this purpose. By deploying MSE, only second-order moment of the error distribution is optimized, which is not adequate for the noisy EEG signal in which the contaminating noises are typically non-Gaussian. By minimizing error entropy, all moments of the error distribution are minimized; hence, using the Minimum Error Entropy (MEE) algorithm instead of MSE-based adaptive algorithms will improve the performance of noise elimination.

RESULTS

Simulation results indicate that the proposed method has a better performance compared to conventional MSE-based algorithm in terms of signal to noise ratio and steady state error.

Aggregation of sparse linear discriminant analyses for event-related potential classification in brain-computer interface

Two main issues for event-related potential (ERP) classification in brain-computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time. This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently l1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples. Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of BCI.

EFFICIENT AUTOMATIC SELECTION AND COMBINATION OF EEG FEATURES IN LEAST SQUARES CLASSIFIERS FOR MOTOR IMAGERY BRAIN–COMPUTER INTERFACES

Discriminative features have to be properly extracted and selected from the electroencephalographic (EEG) signals of each specific subject in order to achieve an adaptive brain–computer interface (BCI) system. This work presents an efficient wrapper-based methodology for feature selection and least squares discrimination of high-dimensional EEG data with low computational complexity. Features are computed in different time segments using three widely used methods for motor imagery tasks and, then, they are concatenated or averaged in order to take into account the time course variability of the EEG signals. Once EEG features have been extracted, proposed framework comprises two stages. The first stage entails feature ranking and, in this work, two different procedures have been considered, the least angle regression (LARS) and the Wilcoxon rank sum test, to compare the performance of each one. The second stage selects the most relevant features using an efficient leave-one-out (LOO) estimation based on the Allen's PRESS statistic. Experimental comparisons with the state-of-the-art BCI methods shows that this approach gives better results than current state-of-the-art approaches in terms of recognition rates and computational requirements and, also with respect to the first ranking stage, it is confirmed that the LARS algorithm provides better results than the Wilcoxon rank sum test for these experiments.

Estimation of the velocity and trajectory of three-dimensional reaching movements from non-invasive magnetoencephalography signals

OBJECTIVE

Studies on the non-invasive brain-machine interface that controls prosthetic devices via movement intentions are at their very early stages. Here, we aimed to estimate three-dimensional arm movements using magnetoencephalography (MEG) signals with high accuracy.

APPROACH

Whole-head MEG signals were acquired during three-dimensional reaching movements (center-out paradigm). For movement decoding, we selected 68 MEG channels in motor-related areas, which were band-pass filtered using four subfrequency bands (0.5-8, 9-22, 25-40 and 57-97 Hz). After the filtering, the signals were resampled, and 11 data points preceding the current data point were used as features for estimating velocity. Multiple linear regressions were used to estimate movement velocities. Movement trajectories were calculated by integrating estimated velocities. We evaluated our results by calculating correlation coefficients (r) between real and estimated velocities.

MAIN RESULTS

Movement velocities could be estimated from the low-frequency MEG signals (0.5-8 Hz) with significant and considerably high accuracy (p <0.001, mean r > 0.7). We also showed that preceding (60-140 ms) MEG signals are important to estimate current movement velocities and the intervals of brain signals of 200-300 ms are sufficient for movement estimation.

SIGNIFICANCE

These results imply that disabled people will be able to control prosthetic devices without surgery in the near future.

Adaptive Laplacian filtering for sensorimotor rhythm-based brain-computer interfaces

OBJECTIVE

Sensorimotor rhythms (SMRs) are 8-30 Hz oscillations in the electroencephalogram (EEG) recorded from the scalp over sensorimotor cortex that change with movement and/or movement imagery. Many brain-computer interface (BCI) studies have shown that people can learn to control SMR amplitudes and can use that control to move cursors and other objects in one, two or three dimensions. At the same time, if SMR-based BCIs are to be useful for people with neuromuscular disabilities, their accuracy and reliability must be improved substantially. These BCIs often use spatial filtering methods such as common average reference (CAR), Laplacian (LAP) filter or common spatial pattern (CSP) filter to enhance the signal-to-noise ratio of EEG. Here, we test the hypothesis that a new filter design, called an 'adaptive Laplacian (ALAP) filter', can provide better performance for SMR-based BCIs.

APPROACH

An ALAP filter employs a Gaussian kernel to construct a smooth spatial gradient of channel weights and then simultaneously seeks the optimal kernel radius of this spatial filter and the regularization parameter of linear ridge regression. This optimization is based on minimizing the leave-one-out cross-validation error through a gradient descent method and is computationally feasible.

MAIN RESULTS

Using a variety of kinds of BCI data from a total of 22 individuals, we compare the performances of ALAP filter to CAR, small LAP, large LAP and CSP filters. With a large number of channels and limited data, ALAP performs significantly better than CSP, CAR, small LAP and large LAP both in classification accuracy and in mean-squared error. Using fewer channels restricted to motor areas, ALAP is still superior to CAR, small LAP and large LAP, but equally matched to CSP.

SIGNIFICANCE

Thus, ALAP may help to improve the accuracy and robustness of SMR-based BCIs.

Automatic and adaptive classification of electroencephalographic signals for brain computer interfaces

Extracting knowledge from electroencephalographic (EEG) signals has become an increasingly important research area in biomedical engineering. In addition to its clinical diagnostic purposes, in recent years there have been many efforts to develop brain computer interface (BCI) systems, which allow users to control external devices only by using their brain activity. Once the EEG signals have been acquired, it is necessary to use appropriate feature extraction and classification methods adapted to the user in order to improve the performance of the BCI system and, also, to make its design stage easier. This work introduces a novel fast adaptive BCI system for automatic feature extraction and classification of EEG signals. The proposed system efficiently combines several well-known feature extraction procedures and automatically chooses the most useful features for performing the classification task. Three different feature extraction techniques are applied: power spectral density, Hjorth parameters and autoregressive modelling. The most relevant features for linear discrimination are selected using a fast and robust wrapper methodology. The proposed method is evaluated using EEG signals from nine subjects during motor imagery tasks. Obtained experimental results show its advantages over the state-of-the-art methods, especially in terms of classification accuracy and computational cost.

Audio-visual feedback for electromyographic control of vowel synthesis

We describe the design and testing of a human machine interface to use surface electromyography (sEMG) collected from a covert location in response audio-visual feedback. Using sEMG collected from the Auricularis Posterior muscle, N=5 healthy participants participated in 6 sessions over multiple days to learn to transition from visual and vowel synthesis feedback to vowel synthesis feedback alone. Results indicate that individuals are able to learn sEMG control of vowel synthesis using auditory feedback alone with an average of 67% accuracy and that this skill can also generalize to new vowel targets. Control of vowel synthesis using covertly-recorded sEMG is a promising step toward more reliable mobile human machine interfaces for communication.

Brain-computer interface based on generation of visual images

This paper examines the task of recognizing EEG patterns that correspond to performing three mental tasks: relaxation and imagining of two types of pictures: faces and houses. The experiments were performed using two EEG headsets: BrainProducts ActiCap and Emotiv EPOC. The Emotiv headset becomes widely used in consumer BCI application allowing for conducting large-scale EEG experiments in the future. Since classification accuracy significantly exceeded the level of random classification during the first three days of the experiment with EPOC headset, a control experiment was performed on the fourth day using ActiCap. The control experiment has shown that utilization of high-quality research equipment can enhance classification accuracy (up to 68% in some subjects) and that the accuracy is independent of the presence of EEG artifacts related to blinking and eye movement. This study also shows that computationally-inexpensive bayesian classifier based on covariance matrix analysis yields similar classification accuracy in this problem as a more sophisticated Multi-class Common Spatial Patterns (MCSP) classifier.

Reconstruction of cortical sources activities for online classification of electroencephalographic signals

We compare the results given by different methods to reconstruct cortical sources activity in order to classify EEG in real time. Two motor imagery experiments were performed. The aim was to retrieve from 1-second windows of signal which motor imagery task the subjects were performing. The use of cortical activity reconstruction was compared to Laplacian filtering, which is often used in BCI. A recursive algorithm using Student's t-test was used to select relevant cortical sources. The Beamformer method led to an improvement of the classification for the first experiment, which included six motor imagery tasks. The weighted Minimum-Norm method required the use of a specific head model, extracted from the subject's MRI, to improve the classification. It then gave the best results on the second experiment, achieving a classification rate of 77% compared to 71% for direct use of electrode data and 75% for Laplacian filtering and Beamformer.

Neuroanatomical differences in toddler boys with fragile x syndrome and idiopathic autism

CONTEXT

Autism is an etiologically heterogeneous neurodevelopmental disorder for which there is no known unifying etiology or pathogenesis. Many conditions of atypical development can lead to autism, including fragile X syndrome (FXS), which is presently the most common known single-gene cause of autism.

OBJECTIVE

To examine whole-brain morphometric patterns that discriminate young boys with FXS from those with idiopathic autism (iAUT) as well as control participants.

DESIGN

Cross-sectional, in vivo neuroimaging study.

SETTING

Academic medical centers.

PATIENTS

Young boys (n = 165; aged 1.57-4.15 years) diagnosed as having FXS or iAUT as well as typically developing and idiopathic developmentally delayed controls.

MAIN OUTCOME MEASURES

Univariate voxel-based morphometric analyses, voxel-based morphometric multivariate pattern classification (linear support vector machine), and clustering analyses (self-organizing map).

RESULTS

We found that frontal and temporal gray and white matter regions often implicated in social cognition, including the medial prefrontal cortex, orbitofrontal cortex, superior temporal region, temporal pole, amygdala, insula, and dorsal cingulum, were aberrant in FXS and iAUT as compared with controls. However, these differences were in opposite directions for FXS and iAUT relative to controls; in general, greater volume was seen in iAUT compared with controls, who in turn had greater volume than FXS. Multivariate analysis showed that the overall pattern of brain structure in iAUT generally resembled that of the controls more than FXS, both with and without AUT.

CONCLUSIONS

Our findings demonstrate that FXS and iAUT are associated with distinct neuroanatomical patterns, further underscoring the neurobiological heterogeneity of iAUT.