Selection of relevant features for EEG signal classification of schizophrenic patients

In this paper, EEG signals of 20 schizophrenic patients and 20 age-matched control participants are analyzed with the objective of determining the more informative channels and finally distinguishing the two groups. For each case, 22 channels of EEG were recorded. A two-stage feature selection algorithm is designed, such that, the more informative channels are first selected to enhance the discriminative information. Two methods, bidirectional search and plus-L minus-R (LRS) techniques are employed to select these informative channels. The interesting point is that most of selected channels are located in the temporal lobes (containing the limbic system) that confirm the neuro-phychological differences in these areas between the schizophrenic and normal participants. After channel selection, genetic algorithm (GA) is employed to select the best features from the selected channels. In this case, in addition to elimination of the less informative channels, the redundant and less discriminant features are also eliminated. A computationally fast algorithm with excellent classification results is obtained. Implementation of this efficient approach involves several features including autoregressive (AR) model parameters, band power, fractal dimension and wavelet energy. To test the performance of the final subset of features, classifiers including linear discriminant analysis (LDA) and support vector machine (SVM) are employed to classify the reduced feature set of the two groups. Using the bidirectional search for channel selection, a classification accuracy of 84.62% and 99.38% is obtained for LDA and SVM, respectively. Using the LRS technique for channel selection, a classification accuracy of 88.23% and 99.54% is also obtained for LDA and SVM, respectively. Finally, the results are compared and contrasted with two well-known methods namely, the single-stage feature selection (evolutionary feature selection) and principal component analysis (PCA)-based feature selection. The results show improved accuracy of classification in relatively low computational time with the two-stage feature selection.     

Percutaneous Exposure to VX: Clinical Signs, Effects on Brain Acetylcholine Levels and EEG

The nerve agent VX has a variable and delayed absorption through the skin, which may have implications for treatment regimens. In the present study, central and peripheral effects of percutaneous VX intoxication were investigated in hairless guinea pigs. Although onset times of clinical signs varied considerably, the relative onset times of signs of poisoning were shown to have a predictive value for survival time. All animals showed elevation of brain choline (Ch) levels. Only two of six animals demonstrated seizure activity on EEG, which was accompanied by acetylcholine (ACh) accumulation. The non-seizing animals displayed only marginal increases of ACh levels, but significant changes in all EEG bands. Acetylcholinesterase activity was highly inhibited in brain and diaphragm. The increases in Ch levels and EEG effects observed in non-seizing animals probably reflected those of ischemia induced by peripheral effects leading to cardiorespiratory compromise. In conclusion, clinical signs will mainly serve as indicators for the onset and maintenance of treatment in subsequent studies. Special issue article in honor of Dr. Frode Fonnum.     

Neural processes underlying statistical learning for speech segmentation in dogs

Download : Download video (29MB)     

脑电超慢涨落图技术在癫痫研究中的应用

目的：观察脑内多种神经递质对癫痫发作的影响。方法：以癫痫患者和ＳＤ大鼠为实验对象,用脑功能检测的最新脑电超电涨落图分析仪（ｅｎｃｅｐｈａｌｏｆｌｕｃｔｕｏｇｒａｍ ｔｅｃｈｎｏｌｏｇｙ,ＥＴ）长时程采集脑电信号,提取在脑电中载有脑神经递质调节系统的震荡信息（即Ｓ谱线）,分析癫痫发作时的脑神经递质的变化。结果：患儿癫痫发作时,Ｓ谱线中Ｓ２（谷氨酸）增高;Ｓ１（γ－氨基丁酸）降低,造成Ｓ１＜Ｓ２。Ｓ５     

多发性抽动症的脑电图观察

目的:进一步探究脑电图对多发性抽动症患儿的辅助诊断价值。方法:本文对45例多发性抽动症患儿进行脑电图描记录,选择理想信号段进行分析。结果发现24例异常,异常率为53.3%。其中中度异常6例,占25%,脑波表现为在高幅δ、θ波长程阵发的背景上偶发尖波;轻度异常18例,占75%,表现背景脑波频率变慢,出现高幅δ、θ波及活动,伴短程出现;正常21例,较同年龄组的脑电图调节差,波形杂乱。结论:脑电图反映脑功能活动,通过计算机分析方法可提供更多信息,并且脑电图操作方便,无痛无创,易于被儿童接受,在多发性抽动症早期临床诊断中具有较高的应用价值。     

Identification of a novel IVD mutation in a consanguineous family with isovaleric acidemia

Isovaleric acidemia (IVA) is a rare autosomal recessive disorder caused by a deficiency of isovaleryl-CoA dehydrogenase encoded by IVD gene. In this case study we report the first Saudi IVA patients from a consanguineous family with a novel transversion (p.G362V) and briefly discuss likely phenotype–genotype correlation of the disease in the Saudi population. We explored the functional consequences of the mutation by using various bioinformatics prediction algorithms and discussed the likely mechanism of the disease caused by the mutation.     

Quantification of Sleepiness Through Principal Component Analysis of the Electroencephalographic Spectrum

Although circadian and sleep research has made extraordinary progress in the recent years, one remaining challenge is the objective quantification of sleepiness in individuals suffering from sleep deprivation, sleep restriction, and excessive somnolence. The major goal of the present study was to apply principal component analysis to the wake electroencephalographic (EEG) spectrum in order to establish an objective measure of sleepiness. The present analysis was led by the hypothesis that in sleep-deprived individuals, the time course of self-rated sleepiness correlates with the time course score on the 2nd principal component of the EEG spectrum. The resting EEG of 15 young subjects was recorded at 2-h intervals for 32–50?h. Principal component analysis was performed on the sets of 16 single-Hz log-transformed EEG powers (1–16?Hz frequency range). The time course of self-perceived sleepiness correlated strongly with the time course of the 2nd principal component score, irrespective of derivation (frontal or occipital) and of analyzed section of the 7-min EEG record (2-min section with eyes open or any of the five 1-min sections with eyes closed). This result indicates the possibility of deriving an objective index of physiological sleepiness by applying principal component analysis to the wake EEG spectrum. (Author correspondence: putilov@ngs.ru)     

Major vault protein (MVP) gene polymorphisms and drug resistance in mesial temporal lobe epilepsy with hippocampal sclerosis

The human major vault protein (MVP) has been implicated in the development of drug resistance in cancer cells. Over expression of MVP has also been reported in brain tissue samples from antiepileptic drug (AED)-resistant human focal epilepsies. To investigate the relationship between single nucleotide polymorphisms (SNPs) involving the MVP gene and AED-resistance, we compared the distribution of three SNPs in the MVP gene, rs4788187, rs3815824 and rs3815823, among 220 patients with mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) (prototype of AED-resistant epilepsy syndrome), 201 patients with juvenile myoclonic epilepsy (JME) (prototype of AED-responsive epilepsy syndrome) and 213 ethnically matched non-epilepsy controls. All the patients and controls were residents of the South Indian state of Kerala for more than three generations. We did not find any significant difference in allele and genotypic frequencies of the studied SNPs between AED-resistant and AED-responsive cohorts, and between AED-resistant and AED-responsive cohorts independently and pooled together when compared with the controls. We conclude that rs4788187, rs3815824, rs3815823 variants of the MVP gene are associated neither with predisposition for epilepsy nor with AED-resistance in the population that we have studied. Our results suggest the need for further research into the link between MVP and AED-resistance.     

When mental fatigue maybe characterized by Event Related Potential (P300) during virtual wheelchair navigation

The goal of this study is to investigate the influence of mental fatigue on the event related potential P300 features (maximum pick, minimum amplitude, latency and period) during virtual wheelchair navigation. For this purpose, an experimental environment was set up based on customizable environmental parameters (luminosity, number of obstacles and obstacles velocities). A correlation study between P300 and fatigue ratings was conducted. Finally, the best correlated features supplied three classification algorithms which are MLP (Multi Layer Perceptron), Linear Discriminate Analysis and Support Vector Machine. The results showed that the maximum feature over visual and temporal regions as well as period feature over frontal, fronto-central and visual regions were correlated with mental fatigue levels. In the other hand, minimum amplitude and latency features didn’t show any correlation. Among classification techniques, MLP showed the best performance although the differences between classification techniques are minimal. Those findings can help us in order to design suitable mental fatigue based wheelchair control.