David A. Peterson

Comparison of linear, nonlinear, and feature selection methods for EEG signal classification

The reliable operation of brain-computer interfaces (BCIs) based on spontaneous electroencephalogram (EEG) signals requires accurate classification of multichannel EEG. The design of EEG representations and classifiers for BCI are open research questions whose difficulty stems from the need to extract complex spatial and temporal patterns from noisy multidimensional time series obtained from EEG measurements. The high-dimensional and noisy nature of EEG may limit the advantage of nonlinear classification methods over linear ones. This paper reports the results of a linear (linear discriminant analysis) and two nonlinear classifiers (neural networks and support vector machines) applied to the classification of spontaneous EEG during five mental tasks, showing that nonlinear classifiers produce only slightly better classification results. An approach to feature selection based on genetic algorithms is also presented with preliminary results of application to EEG during finger movement.

OB-BP1/Siglec-6 A LEPTIN- AND SIALIC ACID-BINDING PROTEIN OF THE IMMUNOGLOBULIN SUPERFAMILY

We report the expression cloning of a novel leptin-binding protein of the immunoglobulin superfamily (OB-BP1) and a cross-hybridizing clone (OB-BP2) that is identical to a recently described sialic acid-binding I-type lectin called Siglec-5. Comparisons to other known Siglec family members (CD22, CD33, myelin-associated glycoprotein, and sialoadhesin) show that OB-BP1, OB-BP2/Siglec-5, and CD33/Siglec-3 constitute a unique related subgroup with a high level of overall amino acid identity: OB-BP1versus Siglec-5 (59%), OB-BP1 versus CD33 (63%), and OB-BP2/Siglec-5 versus CD33 (56%). The cytoplasmic domains are not as highly conserved, but display novel motifs which are putative sites of tyrosine phosphorylation, including an immunoreceptor tyrosine kinase inhibitory motif and a motif found in SLAM and SLAM-like proteins. Human tissues showed high levels of OB-BP1 mRNA in placenta and moderate expression in spleen, peripheral blood leukocytes, and small intestine. OB-BP2/Siglec-5 mRNA was detected in peripheral blood leukocytes, lung, spleen, and placenta. A monoclonal antibody specific for OB-BP1 confirmed high expression in the cyto- and syncytiotrophoblasts of the placenta. Using this antibody on peripheral blood leukocytes showed an almost exclusive expression pattern on B cells. Recombinant forms of the extracellular domains of OB-BP1, OB-BP2/Siglec-5, and CD33/Siglec-3 were assayed for specific binding of leptin. While OB-BP1 exhibited tight binding (K d 91 nm), the other two showed weak binding with K d values in the 1–2 μmrange. Studies with sialylated ligands indicated that OB-BP1 selectively bound Neu5Acα2–6GalNAcα (sialyl-Tn) allowing its formal designation as Siglec-6. The identification of OB-BP1/Siglec-6 as a Siglec family member, coupled with its restricted expression pattern, suggests that it may mediate cell-cell recognition events by interacting with sialylated glycoprotein ligands expressed on specific cell populations. We also propose a role for OB-BP1 in leptin physiology, as a molecular sink to regulate leptin serum levels.

Temporal Entrainment of Cognitive Functions : Musical Mnemonics Induce Brain Plasticity and Oscillatory Synchrony in Neural Networks Underlying Memory

Abstract: In a series of experiments, we have begun to investigate the effect of music as a mnemonic device on learning and memory and the underlying plasticity of oscillatory neural networks. We used verbal learning and memory tests (standardized word lists, AVLT) in conjunction with electroencephalographic analysis to determine differences between verbal learning in either a spoken or musical (verbal materials as song lyrics) modality. In healthy adults, learning in both the spoken and music condition was associated with significant increases in oscillatory synchrony across all frequency bands. A significant difference between the spoken and music condition emerged in the cortical topography of the learning‐related synchronization. When using EEG measures as predictors during learning for subsequent successful memory recall, significantly increased coherence (phase‐locked synchronization) within and between oscillatory brain networks emerged for music in alpha and gamma bands. In a similar study with multiple sclerosis patients, superior learning and memory was shown in the music condition when controlled for word order recall, and subjects were instructed to sing back the word lists. Also, the music condition was associated with a significant power increase in the low‐alpha band in bilateral frontal networks, indicating increased neuronal synchronization. Musical learning may access compensatory pathways for memory functions during compromised PFC functions associated with learning and recall. Music learning may also confer a neurophysiological advantage through the stronger synchronization of the neuronal cell assemblies underlying verbal learning and memory. Collectively our data provide evidence that melodic‐rhythmic templates as temporal structures in music may drive internal rhythm formation in recurrent cortical networks involved in learning and memory.

Music increases frontal EEG coherence during verbal learning

Anecdotal and some empirical evidence suggests that music can enhance learning and memory. However, the mechanisms by which music modulates the neural activity associated with learning and memory remain largely unexplored. We evaluated coherent frontal oscillations in the electroencephalogram (EEG) while subjects were engaged in a modified version of Reys Auditory Verbal Learning Test (AVLT). Subjects heard either a spoken version of the AVLT or the conventional AVLT word list sung. Learning-related changes in coherence (LRCC) were measured by comparing the EEG during word encoding on correctly recalled trials to the immediately preceding trial on which the same word was not recalled. There were no significant changes in coherence associated with conventional verbal learning. However, musical verbal learning was associated with increased coherence within and between left and right frontal areas in theta, alpha, and gamma frequency bands. It is unlikely that the different patterns of LRCC reflect general performance differences; the groups exhibited similar learning performance. The results suggest that verbal learning with a musical template strengthens coherent oscillations in frontal cortical networks involved in verbal encoding.

Closed-Loop Brain–Machine–Body Interfaces for Noninvasive Rehabilitation of Movement Disorders

Traditional approaches for neurological rehabilitation of patients affected with movement disorders, such as Parkinson’s disease (PD), dystonia, and essential tremor (ET) consist mainly of oral medication, physical therapy, and botulinum toxin injections. Recently, the more invasive method of deep brain stimulation (DBS) showed significant improvement of the physical symptoms associated with these disorders. In the past several years, the adoption of feedback control theory helped DBS protocols to take into account the progressive and dynamic nature of these neurological movement disorders that had largely been ignored so far. As a result, a more efficient and effective management of PD cardinal symptoms has emerged. In this paper, we review closed-loop systems for rehabilitation of movement disorders, focusing on PD, for which several invasive and noninvasive methods have been developed during the last decade, reducing the complications and side effects associated with traditional rehabilitation approaches and paving the way for tailored individual therapeutics. We then present a novel, transformative, noninvasive closed-loop framework based on force neurofeedback and discuss several future developments of closed-loop systems that might bring us closer to individualized solutions for neurological rehabilitation of movement disorders.

Music mnemonics aid Verbal Memory and Induce Learning – Related Brain Plasticity in Multiple Sclerosis

Recent research on music and brain function has suggested that the temporal pattern structure in music and rhythm can enhance cognitive functions. To further elucidate this question specifically for memory, we investigated if a musical template can enhance verbal learning in patients with multiple sclerosis (MS) and if music-assisted learning will also influence short-term, system-level brain plasticity. We measured systems-level brain activity with oscillatory network synchronization during music-assisted learning. Specifically, we measured the spectral power of 128-channel electroencephalogram (EEG) in alpha and beta frequency bands in 54 patients with MS. The study sample was randomly divided into two groups, either hearing a spoken or a musical (sung) presentation of Rey’s auditory verbal learning test. We defined the “learning-related synchronization” (LRS) as the percent change in EEG spectral power from the first time the word was presented to the average of the subsequent word encoding trials. LRS differed significantly between the music and the spoken conditions in low alpha and upper beta bands. Patients in the music condition showed overall better word memory and better word order memory and stronger bilateral frontal alpha LRS than patients in the spoken condition. The evidence suggests that a musical mnemonic recruits stronger oscillatory network synchronization in prefrontal areas in MS patients during word learning. It is suggested that the temporal structure implicit in musical stimuli enhances “deep encoding” during verbal learning and sharpens the timing of neural dynamics in brain networks degraded by demyelination in MS.

Delay modulates spectral correlates in the human EEG of non-verbal auditory working memory

Studies using neuroimaging and electro- and magnetoencephalographic techniques have begun to identify the brain structures and dynamics that underlie auditory working memory. However, past research has not clearly characterized how the neural dynamics varies with the delay over which auditory information must be maintained. We used electroencephalogram band power as a measure of relative neuronal synchrony during a non-verbal auditory working memory task. Comparing the working memory task with a control recognition task, the relative synchrony in bilateral theta and alpha bands was unchanged using a two second delay. However, five and ten second delays produced increases and decreases in relative synchrony, respectively. The memory task also induced greater synchronization in beta and gamma bands over the right temporal cortex during the two and five second delays. The results suggest that the cortical dynamics that underlie auditory working memory are highly dependent upon a duration-dependent encoding strategy.

Model and feature selection in microarray classification

Microarray classification has a broad variety of biomedical applications. Support vector machines (SVMs) have emerged as a powerful and popular classifier for microarray data. At the same time, there is increasing interest in the development of methods for identifying important features in microarray data. Many of these methods use SVM classifiers either directly in the search for good features or indirectly as a measure of dissociating classes of microarray samples. The present study describes empirical results in model selection for SVM classification of DNA microarray data. We demonstrate that classifier performance is very sensitive to the SVMs kernel and model parameters. We also demonstrate that the optimal model parameters depend on the cardinality of feature subsets and can influence the evolution of a genetic search for good feature subsets. The results suggest that application of SVM classifiers to microarray data should include careful consideration of the space of possible SVM parameters. The results also suggest that feature selection search and model selection should be conducted jointly rather than independently.

Toward a Semi-Self-Paced EEG Brain Computer Interface: Decoding Initiation State from Non-Initiation State in Dedicated Time Slots

Brain computer interfaces (BCIs) offer a broad class of neurologically impaired individuals an alternative means to interact with the environment. Many BCIs are “synchronous” systems, in which the system sets the timing of the interaction and tries to infer what control command the subject is issuing at each prompting. In contrast, in “asynchronous” BCIs subjects pace the interaction and the system must determine when the subject’s control command occurs. In this paper we propose a new idea for BCI which draws upon the strengths of both approaches. The subjects are externally paced and the BCI is able to determine when control commands are issued by decoding the subject’s intention for initiating control in dedicated time slots. A single task with randomly interleaved trials was designed to test whether it can be used as stimulus for inducing initiation and non-initiation states when the sensory and motor requirements for the two types of trials are very nearly identical. Further, the essential problem on the discrimination between initiation state and non-initiation state was studied. We tested the ability of EEG spectral power to distinguish between these two states. Among the four standard EEG frequency bands, beta band power recorded over parietal-occipital cortices provided the best performance, achieving an average accuracy of 86% for the correct classification of initiation and non-initiation states. Moreover, delta band power recorded over parietal and motor areas yielded a good performance and thus could also be used as an alternative feature to discriminate these two mental states. The results demonstrate the viability of our proposed idea for a BCI design based on conventional EEG features. Our proposal offers the potential to mitigate the signal detection challenges of fully asynchronous BCIs, while providing greater flexibility to the subject than traditional synchronous BCIs.

Detecting Neural Decision Patterns Using SVM-Based EEG Classification

Brain dynamics were analyzed during decision making using human electroencephalographic signals. We sought to identify the pattern of brain activity for actions with and without decision-making, while subjects engaged in an instrumental reward based learning task. Event related potentials (ERPs) were analyzed for reference trials (no choice required) and decision trials. To detect brain activity during decision making, classification was applied to classify reference and decision trials. Support vector machine (SVM) with a nonlinear kernel function was used as a classifier. Classification performance was analyzed across subjects and channels to identify brain regions underlying decision-making. For most subjects, we found that reference and decision trials could be classified with greater than 85% accuracy. ERPs from frontocentral areas of the scalp provided, in general, best classification rates. Thus ERPs and SVM classifiers can be used to non-invasively detect decision making in humans.