Variability analysis of epileptic EEG using the maximal overlap discrete wavelet transform

Automated Detection of Seizure Types from the Higher-Order Moments of Maximal Overlap Wavelet Distribution

In this work, an attempt has been made to develop an automated system for detecting electroclinical seizures such as tonic-clonic seizures, complex partial seizures, and electrographic seizures (EGSZ) using higher-order moments of scalp electroencephalography (EEG). The scalp EEGs of the publicly available Temple University database are utilized in this study. The higher-order moments, namely skewness and kurtosis, are extracted from the temporal, spectral, and maximal overlap wavelet distributions of EEG. The features are computed from overlapping and non-overlapping moving windowing functions. The results show that the wavelet and spectral skewness of EEG is higher in EGSZ than in other types. All the extracted features are found to have significant differences (p < 0.05), except for temporal kurtosis and skewness. A support vector machine with a radial basis kernel designed using maximal overlap wavelet skewness yields a maximum accuracy of 87%. In order to improve the performance, the Bayesian optimization technique is utilized to determine the suitable kernel parameters. The optimized model achieves the highest accuracy of 96% and an MCC of 91% in three-class classification. The study is found to be promising, and it could facilitate the rapid identification process of life-threatening seizures.

Detection of the quality of vital signals by the Monte Carlo Markov Chain (MCMC) method and noise deleting

Vital signal renovation plays an important role in a wide range of applications, including signal analysis and diagnosing diseases through it. Therefore, it is salient to get the main content of the vital signal. In this research, a new approach to the problem of noise removal from vital signals is presented based on random optimization through Monte Carlo Markov Chain (MCMC) sampling. For this purpose, the problem of noise omission from the vital signal is described as a Bayesian squared minimization problem, and considering a non-parametric random approach to solve this problem, the Monte Carlo Markov Chain noise omission approach is flexibly adapted to the noise detection domain in vital signals. To test the performance of the proposed method, four types of vital signals have been used: Medical images, ECG electrocardiogram signals, EEG brain signals as well as ENG nerve and muscle signals. The results of the experiments show that the use of sampling technique based on Gaussian distribution and, retrieving the signal based on the weighted average in the selected samples allows a more accurate estimate of the ideal signal. This more accurate estimation minimizes the difference between the actual and the retrieved signals. As a result, in addition to reducing the mean error squares, the signal-to-noise ratio increases.