Bashar Awwad Shiekh Hasan

Multi-objective evolutionary methods for channel selection in Brain-Computer Interfaces: Some preliminary experimental results

This paper presents a comparative study among three evolutionary and search based methods to solve the problem of channel selection for Brain-Computer Interface (BCI) systems. Multi-Objective Particle Swarm Optimization (MOPSO) method is compared to Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) and single objective Sequential Floating Forward Search (SFFS) method. The methods are tested on the first data set for BCI-Competition IV. The results show the usefulness of the multi-objective evolutionary methods in achieving accuracy results similar to the extensive search method with fewer channels and less computational time.

Sequential EM for Unsupervised Adaptive Gaussian Mixture Model Based Classifier

In this paper we present a sequential expectation maximization algorithm to adapt in an unsupervised manner a Gaussian mixture model for a classification problem. The goal is to adapt the Gaussian mixture model to cope with the non-stationarity in the data to classify and hence preserve the classification accuracy. Experimental results on synthetic data show that this method is able to learn the time-varying statistical features in data by adapting a Gaussian mixture model online. In order to control the adaptation method and to ensure the stability of the adapted model, we introduce an index to detect when the adaptation would fail.

A filter-dominating hybrid sequential forward floating search method for feature subset selection in high-dimensional space

Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on five feature data sets, with different combinations of classifier and separability index as alternative criteria for evaluating the performance of potential feature subsets. The classifiers under consideration include linear discriminate analysis classifier, support vector machine, and K-nearest neighbors classifier, and the separability indexes include the Davies-Bouldin index and a mutual information based index. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection.

Electrophysiologic features of SYT2 mutations causing a treatable neuromuscular syndrome

Objectives: To describe the clinical and electrophysiologic features of synaptotagmin II (SYT2) mutations, a novel neuromuscular syndrome characterized by foot deformities and fatigable ocular and lower limb weakness, and the response to modulators of acetylcholine release. Methods: We performed detailed clinical and neurophysiologic assessment in 2 multigenerational families with dominant SYT2 mutations (c.920T>G [p.Asp307Ala] and c.923G>A [p.Pro308Leu]). Serial clinical and electrophysiologic assessments were performed in members of one family treated first with pyridostigmine and then with 3,4-diaminopyridine. Results: Electrophysiologic testing revealed features indicative of a presynaptic deficit in neurotransmitter release with posttetanic potentiation lasting up to 60 minutes. Treatment with 3,4-diaminopyridine produced both a clinical benefit and an improvement in neuromuscular transmission. Conclusion: SYT2 mutations cause a novel and potentially treatable complex presynaptic congenital myasthenic syndrome characterized by motor neuropathy causing lower limb wasting and foot deformities, with reflex potentiation following exercise and a uniquely prolonged period of posttetanic potentiation.

Unsupervised adaptive GMM for BCI

An unsupervised adaptive Gaussian mixture model is introduced for online brain-computer interfaces (BCI). The method is tested on two BCI data sets, demonstrating significant performance improvement in comparison with a static model.

Temporal modeling of EEG during self-paced hand movement and its application in onset detection

The temporal behavior of electroencephalography (EEG) recorded during self-paced hand movement is investigated for the purpose of improving EEG classification in general and onset detection in particular. Four temporal models based on conditional random fields are developed and applied to classify EEG data into the movement or idle class. They are further used for building an onset detection system and tested on self-paced EEG signals recorded from five subjects. True-false rates ranging from 74% to 98% have been achieved on different subjects, with significant improvement over non-temporal methods. The effectiveness of the proposed methods suggests their potential use in self-paced brain-computer interfaces.

Binary-SDMOPSO and its application in channel selection for Brain-Computer Interfaces

In [1], we introduced Smart Multi-Objective Particle Swarm Optimisation using Decomposition (SDMOPSO). The method uses the decomposition approach proposed in Multi-Objective Evolutionary Algorithms based on Decomposition (MOEA/D), whereby a multi-objective problem (MOP) is represented as several scalar aggregation problems. The scalar aggregation problems are viewed as particles in a swarm; each particle assigns weights to every optimisation objective. The problem is solved then as a Multi-Objective Particle Swarm Optimisation (MOPSO), in which every particle uses information from a set of defined neighbours. This work customize SDMOSPO to cover binary problems and applies the proposed binary method on the channel selection problem for Brain-Computer Interfaces(BCI).

Gender differences in the temporal voice areas

There is not only evidence for behavioral differences in voice perception between female and male listeners, but also recent suggestions for differences in neural correlates between genders. The fMRI functional voice localizer (comprising a univariate analysis contrasting stimulation with vocal vs. non-vocal sounds) is known to give robust estimates of the temporal voice areas (TVAs). However, there is growing interest in employing multivariate analysis approaches to fMRI data (e.g., multivariate pattern analysis; MVPA). The aim of the current study was to localize voice-related areas in both female and male listeners and to investigate whether brain maps may differ depending on the gender of the listener. After a univariate analysis, a random effects analysis was performed on female (n = 149) and male (n = 123) listeners and contrasts between them were computed. In addition, MVPA with a whole-brain searchlight approach was implemented and classification maps were entered into a second-level permutation based random effects models using statistical non-parametric mapping (SnPM; Nichols and Holmes, 2002). Gender differences were found only in the MVPA. Identified regions were located in the middle part of the middle temporal gyrus (bilateral) and the middle superior temporal gyrus (right hemisphere). Our results suggest differences in classifier performance between genders in response to the voice localizer with higher classification accuracy from local BOLD signal patterns in several temporal-lobe regions in female listeners.

Estimation of internal noise using double passes: does it matter how the second pass is delivered?

Human sensory processing is inherently noisy: if a participant is presented with the same set of stimuli multiple times and is asked to perform a task related to some property of the stimulus by pressing one of two buttons, the set of responses generated by the participant will differ on different presentations even though the set of stimuli remained the same. This response variability can be used to estimate the amount of internal noise (i.e. noise that is not present in the stimulus but in the participants decision making process). The procedure by which the same set of stimuli is presented twice is referred to as double-pass (DP) methodology. This procedure is well-established, but there is no accepted recipe for how the repeated trials may be delivered (e.g. in the same order as they were originally presented, or in a different order); more importantly, it is not known whether the choice of delivery matters to the resulting estimates. Our results show that this factor (as well as feedback) has no measurable impact. We conclude that, for the purpose of estimating internal noise using the DP method, the system can be assumed to have no inter-trial memory.

A hybrid approach to feature subset selection for brain-computer interface design

In brain-computer interface (BCI) development, temporal/spectral/ spatial/statistical features can be extracted from multiple electroencephalography (EEG) signals and the number of features available could be up to thousands. Therefore, feature subset selection is an important and challenging problem in BCI design. Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on BCI feature data, in which both linear and nonlinear classifiers as wrappers and Davies-Bouldin index and mutual information based index as filters are alternatively used to evaluate potential feature subsets. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection for BCI design.