scholarly journals Epileptic Seizure Detection In EEG Signals Using Non-Linear Analysis

2018 ◽  
Vol 7 (3.12) ◽  
pp. 764
Author(s):  
Saneesh Cleatus T ◽  
Sunil S ◽  
Snigdha Naik ◽  
Swathi Sathyanarayana ◽  
Syed Afnan
Keyword(s):  
Epileptic Seizure ◽  
Nearest Neighbor ◽  
Neurological Diseases ◽  
Seizure Detection ◽  
World Health ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Epileptic Seizure Detection ◽  
Non Linear ◽  
The Brain

Epilepsy is a chronic disorder of the central nervous system that occurs irregularly and unpredictably, due to the temporary electrical disturbances in the brain. According to World Health Organization (WHO), approximately 50 million people worldwide have epilepsy, making it one of the most common neurological diseases globally [1]. It predisposes individuals to experience recurrent seizures. Electroencephalogram (EEG) is a technique used to measure the electrical activity of the brain signals for the diagnosis of neurological disorders, and it also paves the way for seizure detection using scalp and intra-cranial EEGs as the input data. In this paper, we have proposed a method for non-linear feature based epileptic seizure detection by extracting five features namely Entropy, Mean, Skewness, Standard Deviation and Band Power. The classification techniques used are K-nearest neighbor (KNN) and Support vector machine (SVM) which gave an accuracy of 95.33% and 100% respectively. 

Epileptic seizure detection on EEG signals using machine learning techniques and advanced preprocessing methods

2020 ◽  
Vol 65 (1) ◽  
pp. 33-50 ◽  
Author(s):  
Chahira Mahjoub ◽  
Régine Le Bouquin Jeannès ◽  
Tarek Lajnef ◽  
Abdennaceur Kachouri
Keyword(s):  
Epileptic Seizure ◽  
High Performance ◽  
Visual Analysis ◽  
Binary Classification ◽  
Seizure Detection ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Eeg Signals ◽  
Epileptic Seizure Detection

AbstractElectroencephalography (EEG) is a common tool used for the detection of epileptic seizures. However, the visual analysis of long-term EEG recordings is characterized by its subjectivity, time-consuming procedure and its erroneous detection. Various epileptic seizure detection algorithms have been proposed to deal with such issues. In this study, a novel automatic seizure-detection approach is proposed. Three different strategies are suggested to the user whereby he/she could choose the appropriate one for a given classification problem. Indeed, the feature extraction step, including both linear and nonlinear measures, is performed either directly from the EEG signals, or from the derived sub-bands of tunable-Q wavelet transform (TQWT), or even from the intrinsic mode functions (IMFs) of multivariate empirical mode decomposition (MEMD). The classification procedure is executed using a support vector machine (SVM). The performance of the proposed method is evaluated through a publicly available database from which six binary classification cases are formulated to discriminate between healthy, seizure and non-seizure EEG signals. Our results show high performance in terms of accuracy (ACC), sensitivity (SEN) and specificity (SPE) compared to the state-of-the-art approaches. Thus, the proposed approach for automatic seizure detection can be considered as a valuable alternative to existing methods, able to alleviate the overload of visual analysis and accelerate the seizure detection.

Epileptic Seizure Detection From EEG Signals Using Bagged Ensemble Approach

2020 ◽  
pp. 67-79
Author(s):  
Pradeep Singh ◽  
Sujith Kumar Appikatla
Keyword(s):  
Epileptic Seizure ◽  
Seizure Detection ◽  
Ensemble Classifier ◽  
High Accuracy ◽  
Machine Learning Algorithms ◽  
Eeg Signals ◽  
Epileptic Seizure Detection ◽  
Electrical Pulses ◽  
Two Phases ◽  
The Brain

Seizures are caused by irregular electrical pulses in the brain. Epileptic seizure detection on EEG signals is a long process, which is done manually by epileptologists. The aim of the study is automatically detecting the seizures of the brain, given the electroencephalogram signals by feature extraction and processing through different machine learning algorithms. Machines can be trained to do this type of observation and predict the output with high accuracy. In this chapter, the classification study of individual and ensemble classifier is performed for epileptic seizure detection. The proposed method consists of two phases: extraction of data from EEG signals and development of an individual and ensemble models. Bagging ensemble is developed to achieve better results. The development of the ensemble using various classification algorithms contributes towards increasing the diversity of the ensemble. An extensive comparative study with existing benchmark algorithm is performed for epileptic seizure detection.

AUTOMATED IDENTIFICATION OF EPILEPTIC AND ALCOHOLIC EEG SIGNALS USING RECURRENCE QUANTIFICATION ANALYSIS

2012 ◽  
Vol 12 (05) ◽  
pp. 1240028 ◽  
Author(s):  
EE PING NG ◽  
TEIK-CHENG LIM ◽  
SUBHAGATA CHATTOPADHYAY ◽  
MURALIDHAR BAIRY
Keyword(s):  
Nearest Neighbor ◽  
Probabilistic Neural Network ◽  
Gaussian Mixture ◽  
Recurrence Quantification Analysis ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Recurrence Quantification ◽  
Non Linear ◽  
Quantification Analysis

Epilepsy is a common neurological disorder characterized by recurrence seizures. Alcoholism causes organic changes in the brain, resulting in seizure attacks similar to epileptic fits. Hence, it is challenging to differentiate the cause of fits as epileptic or alcoholism, which is important for deciding on the treatment in the neurology ward. The focus of this paper is to automatically differentiate epileptic, normal, and alcoholic electroencephalogram (EEG) signals. As the EEG signals are non-linear and dynamic in nature, it is difficult to tell the subtle changes in these signals with the help of linear techniques or by the naked eye. Therefore, to analyze the normal (control), epileptic, and alcoholic EEG signals, two non-linear methods, such as recurrence plots (RPs) and then recurrence quantification analysis (RQA) are adopted. Approximately 10 RQA parameters have been used to classify the EEG signals into three distinct classes, i.e., normal, epileptic, and alcoholic. Six classifiers, such as support vector machine (SVM), radial basis probabilistic neural network (RBPNN), decision tree (DT), Gaussian mixture model (GMM), k-nearest neighbor (kNN), and fuzzy Sugeno classifiers have been developed to accomplish this task. Results show that the GMM classifier outperformed the other classifiers with a classification sensitivity of 99.6%, specificity of 98.3%, and accuracy of 98.6%.

Sign in / Sign up

Export Citation Format

Share Document