Epileptic Seizure Detection With Permutation Fuzzy Entropy Using Robust Machine Learning Techniques

Abstract

The automatic and accurate determination of the epileptogenic area can assist doctors in presurgical evaluation by providing higher security and quality of life. Visual inspection of electroencephalogram (EEG) signals is expensive, time-consuming and prone to errors. Several numbers of automated seizure detection frameworks were proposed to replace the traditional methods and to assist neurophysiologists in identifying epileptic seizures accurately. However, these systems lagged in achieving high performance due to the anti-noise ability of feature extraction techniques, while EEG signals are highly susceptible to noise during acquisition. The present study put forwards a new entropy index Permutation Fuzzy Entropy (PFEN), which may delineate between ictal and interictal state of epileptic seizure using different machine learning classifiers. 10-fold cross-validation has been used to avoid the over-fitting of the classification model to achieve unbiased, stable, and reliable performance. The proposed index correctly distinguishes ictal and interictal states with an average accuracy of 98.72%, sensitivity of 98.82% and a specificity of 98.63%, across 21 patients with six epileptic seizure origins. The proposed system manifests the fact that lower PFEN characterizes the EEG during seizure state than in the Interictal seizure state. The study also helps us to investigate the more profound enactment of different classifiers in term of their distance metrics, learning rate, distance, weights, multiple scales, etc. rather than the conventional methods in the literature. Compared to other state of art entropy-based feature extraction methods, PFEN showed its potential to be a promising non-linear feature for achieving high accuracy and efficiency in seizure detection. It also show's its feasibility towards the development of a real-time EEG-based brain monitoring system for epileptic seizure detection.

Review of Methods for EEG Signal Classification and Development of New Fuzzy Classification-Based Approach

“…The most dynamically developed areas are humancomputer interaction studied in [1], [2] and medicine [3] - [8]. In medicine, the EEG signal analysis is used in epilepsy diagnosis [3], [6], [7], depression [4], stress [5], and other diagnoses [8]. The diagnostics of epilepsy is based mostly on analysis of EEG signal.…”

“…These seizures are consequences of the brain activity that can be characterized by the unexpected and sudden electrical disturbance of brain and excessive neuronal discharge. This activity is recorded using the EEG [11], therefore, the analysis of EEG signal is one of the most important tools in neurology diagnostics [3], [7], [12].…”

“…The signal preprocessing consists of two procedures that are feature extraction and dimensionality reduction. According to investigations in [7], [17], and [18], the preliminary transformation or signal preprocessing step has a significant influence on the result of the classification.…”

“…Several approaches of EEG signal classification in which the feature extraction, feature selection or dimensionality reduction procedures are developed based on fuzzy logic background have been proposed. The fuzzy entropy-based procedures have been used in the signal preprocessing step in researches [7], [34], and [35]. In other investigations, such as [36], [37], and [38], combined or join classification have been proposed.…”

A Novel Recognition Strategy for Epilepsy EEG Signals Based on Conditional Entropy of Ordinal Patterns

“…Harezlak and Kasprowski used fuzzy entropy (FE) in order to reveal eye movement signal characteristics, and this classification produced an improvement in the accuracy for saccadic latency and saccade [ 22 ]. Hussain and Wang put forward a new entropy index of permutation fuzzy entropy (PFEN), which may delineate the epileptic seizure between ictal and inter-ictal state while using different machine learning classifiers [ 23 ]. Nicolini and Forcellini used a novel information-theoretic approach based on Von-Neumann entropy.…”