Various epileptic seizure detection techniques using biomedical signals: a review

Abstract

Epilepsy is a chronic chaos of the central nervous system that influences individual’s daily life by putting it at risk due to repeated seizures. Epilepsy affects more than 2% people worldwide of which developing countries are affected worse. A seizure is a transient irregularity in the brain’s electrical activity that produces disturbing physical symptoms such as a lapse in attention and memory, a sensory illusion, etc. Approximately one out of every three patients have frequent seizures, despite treatment with multiple anti-epileptic drugs. According to a survey, population aged 65 or above in European Union is predicted to rise from 16.4% (2004) to 29.9% (2050) and also this tremendous increase in aged population is also predicted for other countries by 2050. In this paper, seizure detection techniques are classified as time, frequency, wavelet (time–frequency), empirical mode decomposition and rational function techniques. The aim of this review paper is to present state-of-the-art methods and ideas that will lead to valid future research direction in the field of seizure detection.

Detection of Epileptic Seizure Using STFT and Statistical Analysis

“…In the literature, the amplitude of the signal, the distance between seizure and nonseizure intervals and the energy ratio of EEG have been investigated. These studies have been used as a criterion for the evaluation of epileptic activity [43][44][45][46][47]. Today, many mathematical methods are used in the analysis of EEG data [48][49][50].…”

Sleep states detection using halfwave and Franklin transformation

“…Thus, after applying the models on the signal we have a simple, reduced but more assertive signal for analysis, which gives best insight into the signal. In literature survey we have found that recent research in signal processing is surrounding around very famous transformations like wavelets, EMD, Fourier, Hilbert and Fast Fourier etc [17]. Therefore there is a need of adaptive methods and transformations which can solve the signal processing problems efficiently and we believe that using adaptive methods and transformations on these selected signals can perform better than all other existing methods.…”

“…A rectangular 1 sec (250 samples, over sampled to 256) long window is used for windowing the halfwave. Window size used here is 1 second [32] [17] for both time domain and frequency domain is considered as a best size window. Time domain features like total number of extrema points, slopes of extrema points, maximum of slopes, mean of extrema points, minimum of extrema points, maximum of extrema points have been chosen from each1-s-long window after analyzing their properties by means of histograms.…”

“…Here we over sampled the signal from 250 sample to 256 ( because Franklin coefficients used here are 256) [34]. KNN is non parametric, instance-based simple, robust, versatile, fast and supervised learning algorithm and in many applications it performs better than other modern classifiers like Artificial Neural Networks (ANN) and Support Vector Machines (SVM) [17]. Let x to denote a feature vector and y is class label, KNN Categorizing query points based on their distance (Euclidean distance, Minkowski distance, Chebychev distance etc) to points in a training data set.…”

Association between HLA-A*3201 allele and oxcarbazepine-induced cutaneous adverse reactions in Eastern Han Chinese population

“…Epilepsy is one of the most common neurological conditions, with more than 2% of the population worldwide affected according to the latest study [1]. As a chronic disease, epilepsy requires long-term treatment with anti-epileptic drugs (AEDs) [2].…”