scholarly journals Методика пространственно-временного анализа электрической активности головного мозга

2020 ◽  
Vol 46 (11) ◽  
pp. 39
Author(s):  
А.Е. Руннова ◽  
М.О. Журавлев ◽  
А.Р. Киселёв ◽  
А.О. Сельский
Keyword(s):  
Wavelet Transform ◽  
Electrical Activity ◽  
Continuous Wavelet Transform ◽  
Temporal Dynamics ◽  
Brain Activity ◽  
Activity Patterns ◽  
Spatial Dynamics ◽  
Continuous Wavelet ◽  
Brain Electrical Activity ◽  
Spatio Temporal

In the framework of this work a new method based on continuous wavelet transform was proposed for analyzing the spatio-temporal dynamics of brain activity patterns. We described the example of this method application for the analysis of brain electrical activity signals. It is shown that this method has the ability to visually detect the occurrence and spatial dynamics of frequency patterns.

scholarly journals CNN-based Framework using Spatial Dropping for Enhanced Interpretation of Neural Activity in Motor Imagery Classification

2020 ◽  
Author(s):  
Diego Fabian Collazos Huertas ◽  
Andres Marino Alvarez Meza ◽  
German Castellanos Dominguez
Keyword(s):  
Wavelet Transform ◽  
Motor Imagery ◽  
Continuous Wavelet Transform ◽  
Brain Activity ◽  
Machine Learning Techniques ◽  
Continuous Wavelet ◽  
Brain Response ◽  
Power Spectral ◽  
Learning Techniques ◽  
Eeg Data

Abstract Interpretation of brain activity responses using Motor Imagery (MI) paradigms is vital for medical diagnosis and monitoring. Assessed by machine learning techniques, identification of imagined actions is hindered by substantial intra and inter subject variability. Here, we develop an architecture of Convolutional Neural Networks (CNN) with enhanced interpretation of the spatial brain neural patterns that mainly contribute to the classification of MI tasks. Two methods of 2D-feature extraction from EEG data are contrasted: Power Spectral Density and Continuous Wavelet Transform. For preserving the spatial interpretation of extracting EEG patterns, we project the multi-channel data using a topographic interpolation. Besides, we include a spatial dropping algorithm to remove the learned weights that reflect the localities not engaged with the elicited brain response. Obtained results in a bi-task MI database show that the thresholding strategy in combination with Continuous Wavelet Transform improves the accuracy and enhances the interpretability of CNN architecture, showing that the highest contribution clusters over the sensorimotor cortex with differentiated behavior between μ and β rhythms.

Recognition of true and false states of the brain by means of the electroencephalogram wavelet analysis

2021 ◽  
Author(s):  
S.S. Pertsov ◽  
E.A. Yumatov ◽  
N.A. Karatygin ◽  
E.N. Dudnik ◽  
A.E. Khramov ◽  
...  
Keyword(s):  
Wavelet Transform ◽  
Experimental Model ◽  
Continuous Wavelet Transform ◽  
Brain Activity ◽  
Mental States ◽  
Mental Activity ◽  
Continuous Wavelet ◽  
Wavelet Energy ◽  
True State ◽  
The Brain

It is a well-known fact that mental activity of the brain can be presented by two different states, i.e., the true state and the false state. A promising method of the electroencephalogram (EEG) wavelet transform has been developed over recent years. Using this method, we evaluated the principle possibility for direct objective registration of mental activity in the human brain. Previously we developed and described (published) a new experimental model and software for recognizing the true and false mental responses of a person with the EEG wavelet transform. The developed experimental model and software-and-data support allowed us to compare (by EEG parameters) two mental states of brain activity, one of which is the false state, while another is the true state. The goal of this study is to develop an absolutely new information technology for recognizing the true and false states in mental activity of the brain by means of the EEG wavelet transform. Our study showed that the true and false states of the brain can be distinguished using the method of continuous wavelet transform and calculation of the EEG wavelet energy. It was revealed that the main differences between truthful and false mental responses are observed in the delta and alpha ranges of the EEG. In the EEG delta rhythm, the wavelet energy is much higher under conditions of the false response as compared to that in the true response. In the EEG alpha rhythm, the wavelet energy is significantly higher with the true answer than in the false one. These data open a new principal possibility of revealing the true and false mental state of the brain by means of continuous wavelet transform and calculation of the EEG wavelet energy.

scholarly journals A New Approach for Motor Imagery Classification Based on Sorted Blind Source Separation, Continuous Wavelet Transform, and Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (20) ◽  
pp. 4541 ◽  
Author(s):  
César J. Ortiz-Echeverri ◽  
Sebastián Salazar-Colores ◽  
Juvenal Rodríguez-Reséndiz ◽  
Roberto A. Gómez-Loenzo
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Convolutional Neural Network ◽  
Blind Source Separation ◽  
Continuous Wavelet Transform ◽  
Signal To Noise Ratio ◽  
Brain Activity ◽  
Source Separation ◽  
Continuous Wavelet ◽  
Spectral Correlation

Brain-Computer Interfaces (BCI) are systems that allow the interaction of people and devices on the grounds of brain activity. The noninvasive and most viable way to obtain such information is by using electroencephalography (EEG). However, these signals have a low signal-to-noise ratio, as well as a low spatial resolution. This work proposes a new method built from the combination of a Blind Source Separation (BSS) to obtain estimated independent components, a 2D representation of these component signals using the Continuous Wavelet Transform (CWT), and a classification stage using a Convolutional Neural Network (CNN) approach. A criterion based on the spectral correlation with a Movement Related Independent Component (MRIC) is used to sort the estimated sources by BSS, thus reducing the spatial variance. The experimental results of 94.66% using a k-fold cross validation are competitive with techniques recently reported in the state-of-the-art.

SPATIO-TEMPORAL DYNAMICS OF BRAIN ELECTRICAL ACTIVITY IN EPILEPSY: ANALYSIS WITH CELLULAR NEURAL NETWORKS (CNNs)

2003 ◽  
Vol 12 (06) ◽  
pp. 825-844 ◽  
Author(s):  
R. KUNZ ◽  
R. TETZLAFF
Keyword(s):  
Neural Networks ◽  
Electrical Activity ◽  
Correlation Dimension ◽  
Temporal Dynamics ◽  
Cellular Neural Networks ◽  
Brain Electrical Activity ◽  
Accurate Approximation ◽  
Spatio Temporal

In this contribution a new procedure is proposed for the analysis of the spatio-temporal dynamics of brain electrical activity in epilepsy. Recent investigations1–3 have clarified that changes of estimates of the effective correlation dimension D2(k,m) from successive data segments allow a characterization of the epileptogenic process. These results provide important information for diagnostical purposes and enable a prediction of seizures in many cases. It will be shown that an accurate approximation of [Formula: see text] can be obtained by Cellular Neural Networks (CNNs),4,5 which form a unified paradigm. Moreover, the type of CNN presented here is optimized with respect to future implementations as VLSI realizations.6

Sign in / Sign up

Export Citation Format

Share Document