Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Añadir filtros








Intervalo de año
1.
Journal of Biomedical Engineering ; (6): 1035-1042, 2021.
Artículo en Chino | WPRIM | ID: wpr-921843

RESUMEN

It is very important for epilepsy treatment to distinguish epileptic seizure and non-seizure. In this study, an automatic seizure detection algorithm based on dual density dual tree complex wavelet transform (DD-DT CWT) for intracranial electroencephalogram (iEEG) was proposed. The experimental data were collected from 15 719 competition data set up by the National Institutes of Health (NINDS) in Kaggle. The processed database consisted of 55 023 seizure epochs and 501 990 non-seizure epochs. Each epoch was 1 second long and contained 174 sampling points. Firstly, the signal was resampled. Then, DD-DT CWT was used for EEG signal processing. Four kinds of features include wavelet entropy, variance, energy and mean value were extracted from the signal. Finally, these features were sent to least squares-support vector machine (LS-SVM) for learning and classification. The appropriate decomposition level was selected by comparing the experimental results under different wavelet decomposition levels. The experimental results showed that the features selected in this paper were different between seizure and non-seizure. Among the eight patients, the average accuracy of three-level decomposition classification was 91.98%, the sensitivity was 90.15%, and the specificity was 93.81%. The work of this paper shows that our algorithm has excellent performance in the two classification of EEG signals of epileptic patients, and can detect the seizure period automatically and efficiently.


Asunto(s)
Humanos , Algoritmos , Electroencefalografía , Epilepsia/diagnóstico , Convulsiones/diagnóstico , Procesamiento de Señales Asistido por Computador , Máquina de Vectores de Soporte , Análisis de Ondículas
2.
Journal of Biomedical Engineering ; (6): 530-538, 2018.
Artículo en Chino | WPRIM | ID: wpr-687598

RESUMEN

The integral and individual-scale wavelet entropy of electroencephalogram (EEG) were employed to investigate the information complexity in EEG and to explore the dynamic mechanism of child absence epilepsy (CAE). The digital EEG signals were collected from patients with CAE and normal controls. Time-frequency features were extracted by continuous wavelet transformation. Individual scale power spectrum characteristics were represented by wavelet-transform. The integral and individual-scale wavelet entropy of EEG were computed on the basis of individual scale power spectrum. The evolutions of wavelet entropy across ictal EEG of CAE were investigated and compared with normal controls. The integral wavelet entropy of ictal EEG is lower than inter-ictal EEG for CAE, and it also lower than normal controls. The individual-scale wavelet entropies of 12th scale (centered at 3 Hz) of ictal EEG in CAE was significantly higher than normal controls. The individual-scale wavelet entropies for α band (centered at 10 Hz) of ictal EEG in CAE were much lower than normal controls. The integral wavelet entropy of EEG can be considered as a quantitative parameter of complexity for EEG signals. The complexity of ictal EEG for CAE is obviously declined in CAE. The wavelet entropies declined could become quantitative electrophysiological parameters for epileptic seizures, and it also could provide a theoretical basis for the study of neuromodulation techniques in epileptic seizures.

3.
International Journal of Biomedical Engineering ; (6): 122-125, 2014.
Artículo en Chino | WPRIM | ID: wpr-447589

RESUMEN

Wavelet entropy,as a powerful quantitative parameter to measure the ordering/disordering level of multi-scale dynamical behavior for nonlinear signals,provides information of complex degree in nonlinear dynamical process.Recently,the wavelet entropy is attracting more and more attention in electroencephalogram (EEG) signal analysis,which is employed by domestic and overseas scholars to investigate the complex degree of EEG,evoked potential and event-related potential,and to profoundly reveal the dynamic mechanism of physiological electrical activity in the brain.It is mainly used in the research of perception,cognitive activity,dynamic observation of epileptic EEG signals,sleeping,internet addiction and rehabilitation of brain after injury.Not only can the wavelet entropy represent the dynamic evolution process of the frequency synchronization for stimulated EEG signals,but also distinguish the states before and after epileptic seizure,as well as to deepen the understanding of brain dynamics mechanism.The wavelet entropy is becoming a new tool for investigating cognition and exhibits a good application prospect in EEG signal analysis.

4.
Space Medicine & Medical Engineering ; (6)2006.
Artículo en Chino | WPRIM | ID: wpr-580389

RESUMEN

Objective To seek a useful index for assessing the change of human gait function based on the application of wavelet entropy in the gait data analysis.Methods The ground reaction force(GRF)gait data of 2 groups(10 young and 10 elderly subjects)were acquired with Bertec 3 dimensional force measured system(a strain gauge force platform)during normal walking.The orthogonal discrete wavelet transform was used for decomposing the collected gait data.The relative wavelet energy and wavelet entropy were defined and calculated respectively.They were statistically analyzed with t-test technique respectively to evaluate the change of human gait function.Results There was significant difference between the relative wavelet energy from GRF gait data of the two subject groups.The average values of wavelet entropy from the GRF gait data of elderly subject group were obviously less than those from the GRF gait data of young subject group.With the value of significance level of t-test P

SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA