Wyniki wyszukiwania - BazTech

1

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.

2

Application of intrinsic band function technique for automated detection of sleep apnea using HRV and EDR signals

Tripathy R. K.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 1

136--144

EN

Sleep apnea is the most common sleep disorder that causes respiratory, cardiac and brain diseases. The heart rate variability (HRV) and the electrocardiogram-derived respiration (EDR) signals to capture the cardio-respiratory information and the features extracted from these two signals have been used for the detection of sleep apnea. Detection of sleep apnea using the combination of HRV and EDR signals may provide more information. This paper proposes a novel method for the automated detection of sleep apnea based on the features extracted from HRV and EDR signals. The method involves the extraction of features from the intrinsic band functions (IBFs) of both EDR and HRV signals, and the classification using kernel extreme learning machine (KELM). The IBFs of HRV and EDR signals are evaluated using the Fourier decomposition method (FDM). The energy and the fuzzy entropy (FE) features are extracted from these IBFs. The kernel extreme learning machine (KELM) classifier with four kernel functions such as 'linear', 'polynomial', 'radial basis function (RBF)' and 'cosine wavelet kernel' is used for the automated detection of sleep apnea. The proposed technique yielded a sensitivity and a specificity of 78.02% and 74.64%, respectively using the public database. The method outperformed some of the reported works using HRV and EDR signals.

3

Automatic epilepsy detection using wavelet-based nonlinear analysis and optimized SVM

Li M., Chen W., Zhang T.

Biocybernetics and Biomedical Engineering

|

2016

|

Vol. 36, no. 4

708--718

EN

Aiming at the problems of low accuracy, poor universality and functional singleness for seizure detection, an effective approach using wavelet-based non-linear analysis and genetic algorithm optimized support vector machine (GA-SVM) is proposed to deal with five challenging classification problems in this study. Instead of the traditional discrete wavelet transform (DWT), we attempt to explore the ability of double-density discrete wavelet transform (DD-DWT) to decompose the original EEG into specific sub-bands. The Hurst exponent (HE) and fuzzy entropy (FuzzyEn) are extracted as input features and then fed into two classifiers. On using these ranking non-linear features, the GA-SVM configured with fewer features is found to achieve the prominent classification performance for various combinations such as AB-CD-E, A-D-E, ABCD-E, C-E and D-E, achieving accuracies of 99.36%, 99.60%, 99.40%, 100% and 100%, respectively. The results have indicated that our scheme is not only appropriate in solving problems with multiple classes but also of lower complexity and better expansibility. These characteristics would make this method become an attractive alternative for actual clinical diagnosis.

4

Badanie klasyfikatora rozmytego z wykorzystaniem entropii rozmytej

Sosnowski Z. A.

Symulacja w Badaniach i Rozwoju

|

2012

|

Vol. 3, nr 2

99--106

PL

W pracy przedstawiono architekturę klasyfikatora rozmytego opartego na entropii rozmytej oraz zbadano jego wydajność na standardowych zestawach danych: Iris i Wisconsin breast cancer. Wyniki symulacji pokazują, że przedstawiony klasyfikator daje zadawalające wskaźniki klasyfikacji.

EN

In this paper, we present the architecture of fuzzy classifier based on fuzzy entropy and examine its performance on Iris and Wisconsin breast cancer data sets. Simulation results show that the presented classifier has a satisfactory classification rate.