A Multivariate Approach for Patient-Specific EEG Seizure Detection Using Empirical Wavelet Transform

  title={A Multivariate Approach for Patient-Specific EEG Seizure Detection Using Empirical Wavelet Transform},
  author={Abhijit Bhattacharyya and Ram Bilas Pachori},
  journal={IEEE Transactions on Biomedical Engineering},
Objective: This paper investigates the multivariate oscillatory nature of electroencephalogram (EEG) signals in adaptive frequency scales for epileptic seizure detection. Methods: The empirical wavelet transform (EWT) has been explored for the multivariate signals in order to determine the joint instantaneous amplitudes and frequencies in signal adaptive frequency scales. The proposed multivariate extension of EWT has been studied on multivariate multicomponent synthetic signal, as well as on… 
Automated identification of epileptic seizure EEG signals using empirical wavelet transform based Hilbert marginal spectrum
Empirical wavelet transform based Hilbert marginal spectrum based HMS has been derived and achieved 99.3% classification accuracy with only 50% training rate which shows the usefulness of the proposed method for the classification of epileptic seizure EEG signals.
Automated Identification of Epileptic Seizures from EEG Signals Using FBSE-EWT Method
A new methodology based on Fourier-Bessel series expansion (FBSE) and empirical wavelet transform (EWT) for the classification of epileptic seizure EEG signals is introduced and may help the neurologists for the identification of healthy and epileptic subjects from EEG signals.
Identification of Epileptic Seizures from Scalp EEG Signals Based on TQWT
The proposed method for epileptic seizure detection from scalp electroencephalogram (EEG) signals is based on the application of tunable-Q wavelet transform (TQWT) and uses a feature-processing technique which clearly discriminates epileptic seizures in the scalp EEG signals.
Patient-specific seizure detection method using nonlinear mode decomposition for long-term EEG signals
The experimental results have indicated that the proposed method is not only quite reliable in diagnosing seizure with single type of feature yielding satisfied performance but also robust to variations of seizure types among patients.
Seizure Onset Detection Using Empirical Mode Decomposition and Common Spatial Pattern
Results indicate that the proposed system may provide a reference for seizure onset detection in clinical applications and showed that the CSP spatial filter was helpful to identify EEG channels involved in seizure onsets.
Early Epileptic Seizure Detection
  • S. Anand, M. Mukul
  • Computer Science
    2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT)
  • 2019
A special case of Blind Source Separation (BSS) algorithm i.e. AMUSE algorithm using Independent Component Analysis (ICA) methodology in addition with Empirical Wavelet Transform (EWT) to detect epileptic seizures in advance is implemented.
Epileptic Seizure Detection in EEG Signal using Discrete Stationary Wavelet-Based Stockwell Transform
An improved epilepsy seizure detecting system is improved with better accuracy with the use of Discrete Stationary wavelet-based Stockwell transform (DSWST) and a modified filter bank based particle swarm optimization (MF-PSO) helps for the feature selection and improves the classifier accuracy.


A novel approach for automated detection of focal EEG signals using empirical wavelet transform
An automatic approach has been presented to detect electroencephalogram (EEG) signals of non-focal and focal groups to determine the area linked to the focal epilepsy and the developed prototype can be used for the epileptic patients and aid the clinicians to confirm diagnosis.
Automated seizure detection in scalp EEG using multiple wavelet scales
The proposed research work designs a detector algorithm for automatic detection of epileptic seizures using a wavelet based feature extraction technique and the feature NCOV yielded better performance than the commonly used COV, σ<sup>2</sup>/μ<sup>.
Tracking and detection of epileptiform activity in multichannel ictal EEG using signal subspace correlation of seizure source scalp topographies
  • C. Hesse, C. James
  • Computer Science
    Medical & Biological Engineering & Computing
  • 2006
The work presents an alternative spatial approach to source tracking and detection in multichannel EEG that exploits prior knowledge of the spatial topographies of the sensor projections associated with the target sources, used to detect (transient) ocular artifacts and (sustained) seizure activity in two segments of 25-channel EEG data recorded from one epilepsy patient on two separate occasions.
Application of Machine Learning To Epileptic Seizure Detection
A machine learning approach to constructing patient-specific classifiers that detect the onset of an epileptic seizure through analysis of the scalp EEG, a non-invasive measure of the brain's electrical activity.
Feature extraction and classification of EEG for automatic seizure detection
A wavelet based feature extraction technique has been adopted and the database used is the CHB-MIT scalp EEG database, where statistical features, Inter-quartile range (IQR) and Median Absolute Deviation (MAD) form part of the feature vector.
Long-term epileptic EEG classification via 2D mapping and textural features
Feature extraction with stacked autoencoders for epileptic seizure detection
  • A. Supratak, Ling Li, Yike Guo
  • Computer Science
    2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • 2014
This paper develops patient-specific seizure detectors by using stacked autoencoders and logistic classifiers, and investigates the possibility of utilising unsupervised feature learning, the recent development of deep learning, to automatically learn features from raw, unlabelled EEG data that are representative enough to be used in seizure detection.
Automated seizure detection using a self-organizing neural network.