A case study on Discrete Wavelet Transform based Hurst exponent for epilepsy detection.
TL;DR: An attempt has been made to provide an overview of the determination of epilepsy by implementation of Hurst exponent (HE)-based discrete wavelet transform techniques for feature extraction from EEG data sets obtained during ictal and pre-ictal stages of affected person and finally classifying EEG signals using SVM and KNN Classifiers.
Abstract: Epileptic seizures are manifestations of epilepsy. Careful analysis of EEG records can provide valuable insight and improved understanding of the mechanism causing epileptic disorders. The detectio...
Citations
More filters
01 Jan 2014
TL;DR: An attempt to develop a general-purpose feature extraction scheme, which can be utilized to extract features from different categories of EEG signals, which could acquire high accuracy in classification of epileptic EEG signals.
Abstract: In this paper, an effective approach for the feature extraction of raw Electroencephalogram (EEG) signals by means of one-dimensional local binary pattern (1D-LBP) was presented. For the importance of making the right decision, the proposed method was performed to be able to get better features of the EEG signals. The proposed method was consisted of two stages: feature extraction by 1D-LBP and classification by classifier algorithms with features extracted. On the classification stage, the several machine learning methods were employed to uniform and non-uniform 1D-LBP features. The proposed method was also compared with other existing techniques in the literature to find out benchmark for an epileptic data set. The implementation results showed that the proposed technique could acquire high accuracy in classification of epileptic EEG signals. Also, the present paper is an attempt to develop a general-purpose feature extraction scheme, which can be utilized to extract features from different categories of EEG signals.
187 citations
TL;DR: The proposed framework uses the 54-DWT mother wavelets analysis of EEG signals using the Genetic algorithm (GA) in combination with other four machine learning (ML) classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Naive Bayes.
Abstract: Electroencephalogram (EEG) is one of the most powerful tools that offer valuable information related to different abnormalities in the human brain. One of these abnormalities is the epileptic seizure. A framework is proposed for detecting epileptic seizures from EEG signals recorded from normal and epileptic patients. The suggested approach is designed to classify the abnormal signal from the normal one automatically. This work aims to improve the accuracy of epileptic seizure detection and reduce computational costs. To address this, the proposed framework uses the 54-DWT mother wavelets analysis of EEG signals using the Genetic algorithm (GA) in combination with other four machine learning (ML) classifiers: Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Artificial Neural Network (ANN), and Naive Bayes (NB). The performance of 14 different combinations of two-class epilepsy detection is investigated using these four ML classifiers. The experimental results show that the four classifiers produce comparable results for the derived statistical features from the 54-DWT mother wavelets; however, the ANN classifier achieved the best accuracy in most datasets combinations, and it outperformed the other examined classifiers.
41 citations
Cites methods from "A case study on Discrete Wavelet Tr..."
...The authors in [19] presented in their research an outline of the definition of epileptic seizure prognosis with the aid of way of making use of Hurst Exponent (HE) that primarily based on discrete wavelet for features functions extraction from EEG records....
[...]
TL;DR: A deep learning-based approach for emotion recognition through EEG signals, which includes data selection, feature extraction, feature selection and classification phases, achieves high accuracy compared to the methods used in past studies, which is considered a high performance for the emotion recognition model.
Abstract: Emotions are an essential part of daily human communication. The emotional states and dynamics of the brain can be linked by electroencephalography (EEG) signals that can be used by the Brain–Computer Interface (BCI), to provide better human–machine interactions. Several studies have been conducted in the field of emotion recognition. However, one of the most important issues facing the emotion recognition process, using EEG signals, is the accuracy of recognition. This paper proposes a deep learning-based approach for emotion recognition through EEG signals, which includes data selection, feature extraction, feature selection and classification phases. This research serves the medical field, as the emotion recognition model helps diagnose psychological and behavioral disorders. The research contributes to improving the performance of the emotion recognition model to obtain more accurate results, which, in turn, aids in making the correct medical decisions. A standard pre-processed Database of Emotion Analysis using Physiological signaling (DEAP) was used in this work. The statistical features, wavelet features, and Hurst exponent were extracted from the dataset. The feature selection task was implemented through the Binary Gray Wolf Optimizer. At the classification stage, the stacked bi-directional Long Short-Term Memory (Bi-LSTM) Model was used to recognize human emotions. In this paper, emotions are classified into three main classes: arousal, valence and liking. The proposed approach achieved high accuracy compared to the methods used in past studies, with an average accuracy of 99.45%, 96.87% and 99.68% of valence, arousal, and liking, respectively, which is considered a high performance for the emotion recognition model.
25 citations
TL;DR: This study proposes a model based on complex networks of weakly connected dynamical systems (Hindmarsh–Rose neurons or Kuramoto oscillators), set to operate in a dynamic regime recognized as Collective Almost Synchronization (CAS).
Abstract: Understanding the brain is an important in the fields of science, medicine, and engineering. A promising approach to better understand the brain is through computing models. These models arewere adjusted to reproduce data collected from the brain. One of the most commonlymostly used types of data in neuroscience is the electroencephalogram comes from electroencephalography (EEG), which records the tiny voltages generated when neurons in the brain are activated. In this workstudy, we propose a model based on complex networks of weakly connected dynamical systems (Hindmarsh- Rose neurons or Kuramoto oscillators), set to operate in a dynamicaldynamic regime recognized as the Collective Almost Synchronisation (CAS). Our model not only successfully reproduces EEG data from both healthy and epileptic EEG signals, but it also predicts the EEG features, the Hurst exponent, and the power spectrum. The proposed model is able to forecast EEG signals 5.76s in the future. The average forecasting error was 9.22%. The random Kuramoto model produced the outstanding result for forecasting seizure EEG with an error of 11.21%.
12 citations
TL;DR: Differences between distributions of high HE and high kurtosis values indicate that while spikes are propagated through cortex from the epileptogenic zone, the persistent dynamical conditions under which the spikes are generated may not be propagated in a similar way.
Abstract: OBJECTIVE: Brain electromagnetic activity in patients with epilepsy is characterized by abnormal high-amplitude transient events (spikes) and abnormal patterns of synchronization of brain rhythms that accompany epileptic seizures. With the aim of improving methods for identifying epileptogenic sources in magnetoencephalographic (MEG) recordings of brain data, we applied methods previously used in the study of oceanic 'rogue waves' and other freak events in complex systems a#13; Approach. For data from 3 patients who were awaiting surgical treatment for epilepsy, we used a beamformer source-model to produce volumetric maps showing areas with a high proportion of spikes that could be classified as 'rogue waves', and areas with high Hurst Exponent (HE). The HE describes the extent to which a system is exhibiting persistent behavior, may predict the likelihood of freak events. These measures were compared with the more standard measure of kurtosis, known to be a reliable method for localizing interictal spikes.a#13; Main Results. There was partial concordance between the 3 different volumetric maps indicating that each measure provides different information about the underlying brain data. The HE, when combined with a simple connectivity analysis based on phase slope index, could identify the probable epileptogenic zone in all 3 patients, despite very different patterns of abnormal activity. The differences between distributions of high HE and high kurtosis values indicate that while spikes are propagated through cortex from the epileptogenic zone, the persistent dynamical conditions under which the spikes are generated may not be propagated in a similar way. Finally, patterns of persistent activity, indicating a departure from 'healthy criticality' in brain networks may explain the wide range of social and cognitive impairments that are seen in epilepsy patients. a#13; Significance. The HE is a potentially useful addition to the clinician's battery of measures which may be used convergently to guide surgical intervention.a#13; a#13.
9 citations
References
More filters
Book•
01 Jan 1995TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Abstract: Setting of the learning problem consistency of learning processes bounds on the rate of convergence of learning processes controlling the generalization ability of learning processes constructing learning algorithms what is important in learning theory?.
40,147 citations
TL;DR: In this paper, it is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2 /sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions.
Abstract: Multiresolution representations are effective for analyzing the information content of images. The properties of the operator which approximates a signal at a given resolution were studied. It is shown that the difference of information between the approximation of a signal at the resolutions 2/sup j+1/ and 2/sup j/ (where j is an integer) can be extracted by decomposing this signal on a wavelet orthonormal basis of L/sup 2/(R/sup n/), the vector space of measurable, square-integrable n-dimensional functions. In L/sup 2/(R), a wavelet orthonormal basis is a family of functions which is built by dilating and translating a unique function psi (x). This decomposition defines an orthogonal multiresolution representation called a wavelet representation. It is computed with a pyramidal algorithm based on convolutions with quadrature mirror filters. Wavelet representation lies between the spatial and Fourier domains. For images, the wavelet representation differentiates several spatial orientations. The application of this representation to data compression in image coding, texture discrimination and fractal analysis is discussed. >
20,028 citations
TL;DR: There are several arguments which support the observed high accuracy of SVMs, which are reviewed and numerous examples and proofs of most of the key theorems are given.
Abstract: The tutorial starts with an overview of the concepts of VC dimension and structural risk minimization. We then describe linear Support Vector Machines (SVMs) for separable and non-separable data, working through a non-trivial example in detail. We describe a mechanical analogy, and discuss when SVM solutions are unique and when they are global. We describe how support vector training can be practically implemented, and discuss in detail the kernel mapping technique which is used to construct SVM solutions which are nonlinear in the data. We show how Support Vector machines can have very large (even infinite) VC dimension by computing the VC dimension for homogeneous polynomial and Gaussian radial basis function kernels. While very high VC dimension would normally bode ill for generalization performance, and while at present there exists no theory which shows that good generalization performance is guaranteed for SVMs, there are several arguments which support the observed high accuracy of SVMs, which we review. Results of some experiments which were inspired by these arguments are also presented. We give numerous examples and proofs of most of the key theorems. There is new material, and I hope that the reader will find that even old material is cast in a fresh light.
15,696 citations
TL;DR: Analysis of a recently developed family of formulas and statistics, approximate entropy (ApEn), suggests that ApEn can classify complex systems, given at least 1000 data values in diverse settings that include both deterministic chaotic and stochastic processes.
Abstract: Techniques to determine changing system complexity from data are evaluated. Convergence of a frequently used correlation dimension algorithm to a finite value does not necessarily imply an underlying deterministic model or chaos. Analysis of a recently developed family of formulas and statistics, approximate entropy (ApEn), suggests that ApEn can classify complex systems, given at least 1000 data values in diverse settings that include both deterministic chaotic and stochastic processes. The capability to discern changing complexity from such a relatively small amount of data holds promise for applications of ApEn in a variety of contexts.
5,055 citations
TL;DR: Dynamical properties of brain electrical activity from different recording regions and from different physiological and pathological brain states are compared and strongest indications of nonlinear deterministic dynamics were found for seizure activity.
Abstract: We compare dynamical properties of brain electrical activity from different recording regions and from different physiological and pathological brain states Using the nonlinear prediction error and an estimate of an effective correlation dimension in combination with the method of iterative amplitude adjusted surrogate data, we analyze sets of electroencephalographic (EEG) time series: surface EEG recordings from healthy volunteers with eyes closed and eyes open, and intracranial EEG recordings from epilepsy patients during the seizure free interval from within and from outside the seizure generating area as well as intracranial EEG recordings of epileptic seizures As a preanalysis step an inclusion criterion of weak stationarity was applied Surface EEG recordings with eyes open were compatible with the surrogates' null hypothesis of a Gaussian linear stochastic process Strongest indications of nonlinear deterministic dynamics were found for seizure activity Results of the other sets were found to be inbetween these two extremes
2,387 citations