Wyniki wyszukiwania - BazTech

1

Wavelet-Hilbert transform based bidirectional least squares grey transform and modified binary grey wolf optimization for the identification of epileptic EEGs

Liu Chang, Chen Wanzhong, Zhang Tao

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 2

442--462

EN

Wavelet based seizure detection is an importance topic for epilepsy diagnosis via electroencephalogram (EEG), but its performance is closely related to the choice of wavelet bases. To overcome this issue, a fusion method of wavelet packet transformation (WPT), Hilbert transform based bidirectional least squares grey transform (HTBiLSGT), modified binary grey wolf optimization (MBGWO) and fuzzy K-Nearest Neighbor (FKNN) was proposed. The HTBiLSGTwas first proposed to model the envelope change of a signal, then WPT based HTBiLSGT was developed for EEG feature extraction by performing HTBiLSGT for each subband of each wavelet level. To select discriminative features, MBGWO was further put forward and employed to conduct feature selection, and the selected features were finally fed into FKNN for classification. The Bonn and CHB-MIT EEG datasets were used to verify the effectiveness of the proposed technique. Experimental results indicate the proposed WPT based HTBiLSGT, MBGWO and FKNN can respectively lead to the highest accuracies of 100% and 98.60 ± 1.35% for the ternary and quinary classification cases of Bonn dataset, it also results in the overall accuracy of 99.48 ± 0.61 for the CHB-MIT dataset, and the proposal is proven to be insensitive to the choice of wavelet bases.

2

Generative adversarial network and convolutional neural network-based EEG imbalanced classification model for seizure detection

Gao Bin, Zhou Jiazheng, Yang Yuying, Chi Jinxin, Yuan Qi

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

1--15

EN

Automatic seizure detection technology is of great significance to reduce workloads of neurologists for epilepsy diagnosis and treatments. Imbalanced classification is a challenge in seizure detection from long-term continuous EEG recordings, as the durations of the seizure events are much shorter than the non-seizure periods. An imbalanced deep learning model is proposed in this paper to improve the performance of seizure detection. To modify imbalanced EEG data distribution, a generative adversarial network (GAN) that is a strong candidate for data enhancement is built to produce the seizure-period EEG data used for forming a more balanced training set. Next, a pyramidal one-dimensional convolutional neural network (1DCNN) is designed to deal with 1D EEG signals and trained on the augmented training set that consists of both original and generated EEG data. Compared to the conventional 2DCNNs, the deep architecture of the 1DCNN reduces the training parameters so as to greatly increase the training speed. The proposed method is evaluated on three publicly available EEG databases. After data augmentation by the GAN, the designed 1DCNN shows much better classification for seizure detection, achieving competitive results over the three EEG databases, which demonstrates the generalizability of this method across different databases. Comparison with other published methods indicates its enhanced detection performance for imbalanced EEG data.

3

A new method of cardiac sympathetic index estimation using a 1D-convolutional neural network

Kołodziej Marcin, Majkowski Andrzej, Tarnowski Paweł, Rak Remigiusz Jan, Rysz Andrzej

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2021

|

Vol. 69, nr 3

art. no. e136921

EN

Epilepsy is a neurological disorder that causes seizures of many different types. The article presents an analysis of heart rate variability (HRV) for epileptic seizure prediction. Considering that HRV is nonstationary, our research focused on the quantitative analysis of a Poincare plot feature, i.e. cardiac sympathetic index (CSI). It is reported that the CSI value increases before the epileptic seizure. An algorithm using a 1D-convolutional neural network (1D-CNN) was proposed for CSI estimation. The usability of this method was checked for 40 epilepsy patients. Our algorithm was compared with the method proposed by Toichi et al. The mean squared error (MSE) for testing data was 0.046 and the mean absolute percentage error (MAPE) amounted to 0.097. The 1D-CNN algorithm was also compared with regression methods. For this purpose, a classical type of neural network (MLP), as well as linear regression and SVM regression, were tested. In the study, typical artifacts occurring in ECG signals before and during an epileptic seizure were simulated. The proposed 1D-CNN algorithm estimates CSI well and is resistant to noise and artifacts in the ECG signal.

4

Scattering transform-based features for the automatic seizure detection

Jiang Yun, Chen Wanzhong, You Yang

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

77--89

EN

Developing the automatic detection system is of great clinical significance for assisting neurologists to detect epilepsy using electroencephalogram (EEG) signals. In this research, we explore the ability of a newly-developed algorithm named scattering transform in seizure detection. The preprocessed signal is initially decomposed into scattering coefficients with various orders and scales employing scattering transform. Fuzzy entropy (FuzzyEn) and Log energy entropy (LogEn) of the sub-band coefficients are obtained to characterize the epileptic seizure signals. Then the joint features are fed into five classifiers including support vector machine (SVM), least squares-support vector machine (LS-SVM), genetic algorithm-support vector machine (GA-SVM), extreme learning machine (ELM) and probabilistic neural network (PNN) for the verification of the effectiveness of the proposed scheme. Finally, we not only compare the classification results and the time efficiency derived from different classifiers, but also explore the discrimination performance of the proposed methodology based on ten different classification tasks with great clinical significance. The prominent classification accuracy (ACC) of 99.87 %, 99.59 %, 99.58 %, 99.56 % and 99.80 % are achieved using the above five classifiers respectively. The average ACC and Matthews correlation coefficient (MCC) of 99.75 % and 0.99 are also yielded based on all tasks. Furthermore, the result of Kruskal-Wallis Test for the verification of statistical significance confirms the reliability of the proposal. The comparison with the latest state-of-the-art techniques indicates the superior performance of the proposal. A tradeoff between classification accuracy and time complexity of the proposed approach is accomplished in our work and the possibility for clinical application is also demonstrated.

5

Complex-valued distribution entropy and its application for seizure detection

Zhang Tao, Chen Wanzhong, Li Mingyang

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

306--323

EN

Embedding entropies are powerful indicators in quantifying the complexity of signal, but most of them are only applicable for real-valued signal and the phase information is ignored if the analyzed signal is complex-valued. To assess the complexity of complex-valued signal, a new entropy called complex-valued distribution entropy (CVDistEn) was first proposed in this study. Two rules, namely equal width criterion and equal area criterion, were employed to demarcate the complex-valued space and two kinds of CVDistEn, i.e., CVDistEn1 and CVDistEn2 were raised. Furthermore, two novel feature extraction methods: (1) flexible analytic wavelet transform (FAWT)-based CVDistEn1 and logarithmic energy (LE) (FAWTC1L), (2) FAWT-based CVDistEn2 and LE (FAWTC2L) were subsequently put forward to characterize the interictal and ictal EEGs. Fuzzy k-nearest neighbors (FKNN) classifier was finally employed to classify these two types of EEGs automatically. Experiment results show the fusion method of FAWTC1L and FKNN leads to the best accuracies (ACCs)/Matthews correlation coefficients (MCCs) of 99.99%/99.97% and 100%/100% for Bonn and Neurology & Sleep Centre EEG datasets, respectively, while the other fusion scheme of FAWTC2L and FKNN results in the highest ACCs/MCCs of 99.97%/99.93% and 99.94%/99.89% for the same datasets. The proposed methods outperform other entropy-related seizure detection schemes and most of state-of-the-art techniques, they provide another new way for automated seizure detection in EEG.

6

Epileptic seizure detection based on improved wavelet neural networks in long-term intracranial EEG

Geng D., Zhou W., Zhang Y., Geng S.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 2

375--384

EN

Automatic seizure detection is of great importance for speeding up the inspection process and relieving the workload of medical staff in the analysis of EEG recordings. In this study, a method based on an improved wavelet neural network (WNN) is proposed for automatic seizure detection in long-term intracranial EEG. WNN combines the traditional back propagation neural network (BPNN) with wavelet transform. Compared with classic WNN architectures, a modified point symmetry-based fuzzy c-means (MSFCM) algorithm is applied to the initialization of wavelet transform's translations, which has been successful in multiclass cancer classification. In addition, Fast-decaying Morlet wavelet is chosen as the activation function to make the WNN learn faster. Relative amplitude and relative fluctuation index are extracted as a feature vector to describe the variation of EEG signals, and the feature vector is then fed into WNN for classification. At last, post-processing including smoothing, channel fusion and collar technique is adopted to achieve more accurate and stable results. This system performs efficiently with the average sensitivity of 96.72%, specificity of 98.91% and false-detection rate of 0.27 h_1. The proposed approach achieves high sensitivity and low false detection rate, which demonstrates its potential for clinical usage.