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

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1553
Author(s):  
Majd Abazid ◽  
Nesma Houmani ◽  
Jerome Boudy ◽  
Bernadette Dorizzi ◽  
Jean Mariani ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Network Analysis ◽  
Comparative Study ◽  
Cognitive Dysfunction ◽  
Brain Network ◽  
Clinical Severity ◽  
Entropy Measure ◽  
Support Vector ◽  
Phase Lag ◽  
Eeg Signals

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.

scholarly journals Affective Computing on Machine Learning-Based Emotion Recognition Using a Self-Made EEG Device

Sensors ◽  
2021 ◽  
Vol 21 (15) ◽  
pp. 5135
Author(s):  
Ngoc-Dau Mai ◽  
Boon-Giin Lee ◽  
Wan-Young Chung
Keyword(s):  
Machine Learning ◽  
Emotion Recognition ◽  
Temporal Lobe ◽  
Affective Computing ◽  
Electrode Placement ◽  
Entropy Measure ◽  
Support Vector ◽  
Emotion Classification ◽  
Eeg Signals ◽  
Computing Method

In this research, we develop an affective computing method based on machine learning for emotion recognition using a wireless protocol and a wearable electroencephalography (EEG) custom-designed device. The system collects EEG signals using an eight-electrode placement on the scalp; two of these electrodes were placed in the frontal lobe, and the other six electrodes were placed in the temporal lobe. We performed experiments on eight subjects while they watched emotive videos. Six entropy measures were employed for extracting suitable features from the EEG signals. Next, we evaluated our proposed models using three popular classifiers: a support vector machine (SVM), multi-layer perceptron (MLP), and one-dimensional convolutional neural network (1D-CNN) for emotion classification; both subject-dependent and subject-independent strategies were used. Our experiment results showed that the highest average accuracies achieved in the subject-dependent and subject-independent cases were 85.81% and 78.52%, respectively; these accuracies were achieved using a combination of the sample entropy measure and 1D-CNN. Moreover, our study investigates the T8 position (above the right ear) in the temporal lobe as the most critical channel among the proposed measurement positions for emotion classification through electrode selection. Our results prove the feasibility and efficiency of our proposed EEG-based affective computing method for emotion recognition in real-world applications.

Brain Network Analysis of Compressive Sensed High-Density EEG Signals in AD and MCI Subjects

2019 ◽  
Vol 15 (1) ◽  
pp. 527-536 ◽  
Author(s):  
Nadia Mammone ◽  
Simona De Salvo ◽  
Lilla Bonanno ◽  
Cosimo Ieracitano ◽  
Silvia Marino ◽  
...  
Keyword(s):  
Network Analysis ◽  
Brain Network ◽  
High Density ◽  
Eeg Signals

scholarly journals Right Frontoinsular Cortex: A Potential Imaging Biomarker to Evaluate T2DM-Induced Cognitive Impairment

2021 ◽  
Vol 13 ◽  
Author(s):  
Dongsheng Zhang ◽  
Yumeng Lei ◽  
Jie Gao ◽  
Fei Qi ◽  
Xuejiao Yan ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Cognitive Function ◽  
Cognitive Dysfunction ◽  
Inferior Frontal Gyrus ◽  
Brain Network ◽  
Imaging Biomarker ◽  
Linear Processes ◽  
Significant Difference ◽  
Normal Cognitive Function ◽  
The Right

Cognitive impairment in type 2 diabetes mellitus (T2DM) is associated with functional and structural abnormalities in the intrinsic brain network. The salience network (SN) is a neurocognitive network that maintains normal cognitive function, but it has received little attention in T2DM. We explored SN changes in patients with T2DM with normal cognitive function (DMCN) and in patients with T2DM with mild cognitive impairment (DMCI). Sixty-five T2DM patients and 31 healthy controls (HCs) underwent a neuropsychological assessment, independent component analysis (ICA), and voxel-based morphometry (VBM) analysis. The ICA extracted the SN for VBM to compare SN functional connectivity (FC) and gray matter (GM) volume (GMV) between groups. A correlation analysis examined the relationship between abnormal FC and GMV and clinical/cognitive variables. Compared with HCs, DMCN patients demonstrated increased FC in the left frontoinsular cortex (FIC), right anterior insula, and putamen, while DMCI patients demonstrated decreased right middle/inferior frontal gyrus FC. Compared with DMCN patients, DMCI patients showed decreased right FIC FC. There was no significant difference in SN GMV in DMCN and DMCI patients compared with HCs. FIC GMV was decreased in the DMCI patients compared with DMCN patients. In addition, right FIC FC and SN GMV positively correlated with Montreal Cognitive Assessment and Mini-Mental State Examination (MMSE) scores. These findings indicate that changes in SN FC, and GMV are complex non-linear processes accompanied by increased cognitive dysfunction in patients with T2DM. The right FIC may be a useful imaging biomarker for supplementary assessment of early cognitive dysfunction in patients with T2DM.

scholarly journals Objective Recognition of Tinnitus Location Using Electroencephalography Connectivity Features

2022 ◽  
Vol 15 ◽  
Author(s):  
Zhaobo Li ◽  
Xinzui Wang ◽  
Weidong Shen ◽  
Shiming Yang ◽  
David Y. Zhao ◽  
...  
Keyword(s):  
Resting State ◽  
Phase Locking ◽  
Pearson Correlation ◽  
Computing Time ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Phase Lag ◽  
Eeg Signals ◽  
Time Frequency ◽  
Phase Locking Value

Purpose: Tinnitus is a common but obscure auditory disease to be studied. This study will determine whether the connectivity features in electroencephalography (EEG) signals can be used as the biomarkers for an efficient and fast diagnosis method for chronic tinnitus.Methods: In this study, the resting-state EEG signals of tinnitus patients with different tinnitus locations were recorded. Four connectivity features [including the Phase-locking value (PLV), Phase lag index (PLI), Pearson correlation coefficient (PCC), and Transfer entropy (TE)] and two time-frequency domain features in the EEG signals were extracted, and four machine learning algorithms, included two support vector machine models (SVM), a multi-layer perception network (MLP) and a convolutional neural network (CNN), were used based on the selected features to classify different possible tinnitus sources.Results: Classification accuracy was highest when the SVM algorithm or the MLP algorithm was applied to the PCC feature sets, achieving final average classification accuracies of 99.42 or 99.1%, respectively. And based on the PLV feature, the classification result was also particularly good. And MLP ran the fastest, with an average computing time of only 4.2 s, which was more suitable than other methods when a real-time diagnosis was required.Conclusion: Connectivity features of the resting-state EEG signals could characterize the differentiation of tinnitus location. The connectivity features (PCC and PLV) were more suitable as the biomarkers for the objective diagnosing of tinnitus. And the results were helpful for clinicians in the initial diagnosis of tinnitus.

scholarly journals Comparison of Domain Specific Connectivity Metrics for Estimation Brain Network Indices in Boys With ADHD-C

2021 ◽  
Author(s):  
SERAP AYDIN ◽  
Fatih Hilmi CETIN ◽  
Merve UYTUN ◽  
Zehra BABADAG ◽  
Ahmet Sami GUVEN ◽  
...  
Keyword(s):  
Resting State ◽  
Classification Accuracy ◽  
Phase Locking ◽  
Pearson Correlation ◽  
Specific Treatment ◽  
Brain Network ◽  
Post Treatment ◽  
Support Vector ◽  
Phase Lag ◽  
The Impact

Abstract The study includes Graph Theoretic advanced EEG analysis in order to investigate the impact of pharmacological treatment with osmotic release oral system-methylphenidate for a month in 18 boys (aged between 7-12 years) with Attention-Deficit-Hyperactivity Disorder, combined type. In analysis, neurofunctional dependency levels across the cortex are estimated by using six different connectivity estimation approaches based on three separate domains such as time (Pearson Correlation, Spearman Correlation), frequency (Directed Transfer Function, Partial Directed Coherence) and phase (Phase Locking Value, Phase Lag Index). All methods are examined for eyes-opened resting-state EEG segments of 2 sec over a single trial of 1 min in both pre- and post-treatment recordings. Then, five quantitative brain network indices of transitivity, clustering coefficients, assortativity, global efficiency and modularity are computed from connectivity estimations. Performance of connectivity estimators are compared to each other with respect to two-class classifications (pre-treatment features vs post-treatment features) by using Support Vector Machines driven by brain network indices. The highest classification accuracy of 80.74% is obtained with Pearson Correlation. Statistical one-way Anova test, pair-wise multiple comparison test and step-wise logistic regression modelling are all used to observe the most sensitive network index estimated from Pearson Correlations. In addition to quantitative results, statistical box-plots of the estimated network indices are shown graphically. When modularity index is excluded from the features, classification accuracy is increased to 83.79%. Overall results reveal that brain segregation and resilience are increased by the treatment. In particular, the most meaningful brain network measures can be estimated from time domain statistical correlations between resting-state eyes open EEG segments in order to understand the alterations in neuronal transmission mechanism across the cortex in response to a specific treatment in pediatric psychiatry.

Sign in / Sign up

Export Citation Format

Share Document