Research on Channel Selection and Multi-Feature Fusion of EEG Signals for Mental Fatigue Detection

With the rapid development of modern social science and technology, the pace of life is getting faster, and brain fatigue has become a sub-health state that seriously affects the normal life of people. Electroencephalogram (EEG) signals reflect changes in the central nervous system. Using EEG signals to assess mental fatigue is a research hotspot in related fields. Most existing fatigue detection methods are time-consuming or don’t achieve satisfactory results due to insufficient features extracted from EEG signals. In this paper, a 2-back task is designed to induce fatigue. The weight value of each channel under a single feature is calculated by ReliefF algorithm. The classification accuracy of each channel under the corresponding features is analyzed. The classification accuracy of each single channel is combined to perform weighted summation to obtain the weight value of each channel. The first half channels sorted in descending order based on the weight value is chosen as the common channels. Multi-features in frequency and time domains are extracted from the common channel data, and the sparse representation method is used to perform feature fusion to obtain sparse fused features. Finally, the SRDA classifier is used to detect the fatigue state. Experimental results show that the proposed methods in our work effectively reduce the number of channels for computation and also improve the mental fatigue detection accuracy.     

Electro‐magneto‐encephalography for the three‐shell model : a single dipole in ellipsoidal geometry

Analytic formulae are presented for determining the position and the moment of a single dipole from either Electroencephalography or Magnetoencephalography (MEG) measurements, under the assumption of the three‐shell ellipsoidal model. It is remarkable that for this model all three components of the moment can be determined from the MEG measurements. This means that, in contrast to the spherical model, there exist no silent dipolar sources in MEG for the ellipsoidal model. Copyright © 2012 John Wiley & Sons, Ltd.     

Neonatal EEG signal characteristics using time frequency analysis

Time-frequency analysis is a way to represent the energy contents of a signal in the joint time-frequency domain. It provides a good visual way to separate the frequency contents of a multi-component signal, and display the changes of these components with respect to time. This paper outlines investigative work on neonatal EEG signals using time-frequency analysis. The Cohen’s class distributions are discussed, and kernel optimisation for the Cohen’s class distributions is outlined. Segments of EEG with different background continuity states are analysed using a Cohen’s class distribution, and their characteristics are discussed. Through this paper, interesting information that offers insight towards the EEG signal can be visualized from the time frequency analysis.     

Functional localization of brain sources using EEG and/or MEG data: volume conductor and source models

In this overview we examine the basic principles of properties of electroencephalogram and magnetoencephalogram and the corresponding models of sources and of the volume conductor. In particular we show how the dipolar model is anchored in neurophysiological findings and how the different conductivities of the brain and the tissue surrounding it can be estimated. Using these basic models as tools we show how the functional localization of the neural sources of rhythmic activities (alpha and mu rhythms and sleep spindles) and of epileptiform activities can be estimated and integrated with structural data of the brain obtained with MRI.     

Characterization of dynamical systems under noise using recurrence networks: Application to simulated and EEG data

In this letter, we study the influence of observational noise on recurrence network (RN) measures, the global clustering coefficient (C) and average path length (L  ) using the Rössler system and propose the application of RN measures to analyze the structural properties of electroencephalographic (EEG) data. We find that for an appropriate recurrence rate (RR>0.02$RR>0.02$) the influence of noise on C can be minimized while L is independent of RR for increasing levels of noise. Indications of structural complexity were found for healthy EEG, but to a lesser extent than epileptic EEG. Furthermore, C performed better than L in case of epileptic EEG. Our results show that RN measures can provide insights into the structural properties of EEG in normal and pathological states.     

Ant Colony System Optimization for Spatiotemporal Modelling of Combined EEG and MEG Data

Electroencephalography/Magnetoencephalography (EEG/MEG) source localization involves the estimation of neural activity inside the brain volume that underlies the EEG/MEG measures observed at the sensor array. In this paper, we consider a Bayesian finite spatial mixture model for source reconstruction and implement Ant Colony System (ACS) optimization coupled with Iterated Conditional Modes (ICM) for computing estimates of the neural source activity. Our approach is evaluated using simulation studies and a real data application in which we implement a nonparametric bootstrap for interval estimation. We demonstrate improved performance of the ACS-ICM algorithm as compared to existing methodology for the same spatiotemporal model.     

摩擦诱发的事件相关电位认知成分特征研究

本研究旨在讨论人在探索物体表面时由物体表面摩擦属性的影响而引起的脑电变化.而事件相关电位技术是观测这一变化的理想手段.试验通过Neuroscan 64导事件相关电位采集系统来采集脑电信号,采用Oddball范式来诱发P300电位,并观察摩擦诱发的事件相关电位的认知成分P300的潜伏期和峰值特点.样本为摩擦系数不一样但其他属性基本一致的三种纸类.受试者通过手指主动触摸的方式判断物体表面摩擦力大小,观察此过程中的事件相关电位.试验发现,摩擦系数大样本诱发的P300的潜伏期小,峰值大.摩擦系数小的样本诱发的P300潜伏期大,峰值小.     

Analysis of brain electrical topography by spatio-temporal wavelet decomposition

Currently, the Functional Magnetic Resonance Imaging (fMRI), Positron Emission Tomography (PET), and Electroencephalography (EEG) recordings are the major techniques of neuroimaging. The EEG with its highest temporal resolution is still a crucial measurement for localization of activities arising from the electrical behaviour of the brain. A scalp topographic map for an EEG may be a superposition of several simpler subtopographic maps, each resulting from an individual electrical source located at a certain depth. Furthermore, this source may have a temporal characteristic as an oscillation or a rhythm that extends in a certain time window which has been a basis of assumption for the time-frequency analysis methods. A method for the spatio-temporal wavelet decomposition of multichannel EEG data is proposed which facilitates the localization of electrical sources separate and/or overlapping on a continuum of time, frequency and space domains. The subtopographic maps asociated with each of these individual components are then used in the MUSIC source localization algorithm. The validations are performed on simulated EEG data. Spatio-temporal wavelet decomposition as a preprocessing method improves the source localization by simplifying the topographic data formed by the superposition of EEG generators, having possible combinations of temporal, frequency and/or spatial overlappings. Spatio-temporal analysis of EEG will help enhance the accuracy of dipole source reconstruction in neuroimaging.     

Exploring the Alterations in the Distribution of Neural Network Weights in Dementia Due to Alzheimer’s Disease

Alzheimer’s disease (AD) is a neurodegenerative disorder which has become an outstanding social problem. The main objective of this study was to evaluate the alterations that dementia due to AD elicits in the distribution of functional network weights. Functional connectivity networks were obtained using the orthogonalized Amplitude Envelope Correlation (AEC), computed from source-reconstructed resting-state eletroencephalographic (EEG) data in a population formed by 45 cognitive healthy elderly controls, 69 mild cognitive impaired (MCI) patients and 81 AD patients. Our results indicated that AD induces a progressive alteration of network weights distribution; specifically, the Shannon entropy (SE) of the weights distribution showed statistically significant between-group differences (p < 0.05, Kruskal-Wallis test, False Discovery Rate corrected). Furthermore, an in-depth analysis of network weights distributions was performed in delta, alpha, and beta-1 frequency bands to discriminate the weight ranges showing statistical differences in SE. Our results showed that lower and higher weights were more affected by the disease, whereas mid-range connections remained unchanged. These findings support the importance of performing detailed analyses of the network weights distribution to further understand the impact of AD progression on functional brain activity.     

A Comparative Study of Functional Connectivity Measures for Brain Network Analysis in the Context of AD Detection with EEG

This work addresses brain network analysis considering different clinical severity stages of cognitive dysfunction, based on resting-state electroencephalography (EEG). We use a cohort acquired in real-life clinical conditions, which contains EEG data of subjective cognitive impairment (SCI) patients, mild cognitive impairment (MCI) patients, and Alzheimer’s disease (AD) patients. We propose to exploit an epoch-based entropy measure to quantify the connectivity links in the networks. This entropy measure relies on a refined statistical modeling of EEG signals with Hidden Markov Models, which allow a better estimation of the spatiotemporal characteristics of EEG signals. We also propose to conduct a comparative study by considering three other measures largely used in the literature: phase lag index, coherence, and mutual information. We calculated such measures at different frequency bands and computed different local graph parameters considering different proportional threshold values for a binary network analysis. After applying a feature selection procedure to determine the most relevant features for classification performance with a linear Support Vector Machine algorithm, our study demonstrates the effectiveness of the statistical entropy measure for analyzing the brain network in patients with different stages of cognitive dysfunction.