Nonlinear dimension reduction for EEG-based epileptic seizure detection

  title={Nonlinear dimension reduction for EEG-based epileptic seizure detection},
  author={Javad Birjandtalab and Maziyar Baran Pouyan and Mehrdad Nourani},
  journal={2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)},
Approximately 0.1 percent of epileptic patients die from unexpected deaths. In general, for intractable seizures, it is crucial to have an algorithm to accurately and automatically detect the seizures and notify care-givers to assist patients. EEG signals are known as definitive diagnosis of seizure events. In this work, we utilize the frequency domain features (normalized in-band power spectral density) for the EEG channels. We applied a nonlinear data-embedding technique based on stochastic… 

Figures and Tables from this paper

Classification of EEG Signals for Epileptic Seizures Using Feature Dimension Reduction Algorithm based on LPP

The experimental result on recall, precision and F1 is superior to the common traditional dimensionality reduction algorithm, manifold learning algorithm and autoencoder based deep learning, which indicates this proposed method makes it possible to solve nonlinearity and cross-talk among channels in EEG, but also tackles the inherent difficulties regarding unbalanced epilepsy data with high metrics.

Unsupervised EEG analysis for automated epileptic seizure detection

This work presents an unsupervised technique to discriminate seizures and non-seizures events without having any prior knowledge on patient's history and employs power spectral density of EEG signals in different frequency bands that are informative features to accurately cluster seizure and non -seizure events.

Patient-dependent epilepsy seizure detection using random forest classification over one-dimension transformed EEG data

The proposed system is a patient-dependent offline system which performs an automatic detection of seizures in brainwaves applying a random forest classifier and has great potential for diagnosis support in clinical environments.

Patient-Specific Epilepsy Seizure Detection Using Random Forest Classification over One-Dimension Transformed EEG Data

The proposed system is a patient-specific system which performs an automatic detection of seizures from brainwaves applying a random forest classifier which has great potential for diagnosis support in clinical environments.

A Simple Distance Based Seizure Onset Detection Algorithm Using Common Spatial Patterns

The proposed framework first applies the common spatial patterns (CSP) method to enhance the signal-to-noise ratio and reduce the dimensionality of EEG signals, and then uses the autocorrelation of the averaged spatially filtered signal to classify incoming signals into a seizure or non-seizure state.

EEG-Based Epileptic Seizure Detection via Machine/Deep Learning Approaches: A Systematic Review

An extensive systematic review on the recent developments of EEG-based ML/DL technologies for epileptic seizure diagnosis is conducted to aid researchers in deciding the most efficient ML/ DL models with optimal feature extraction methods to improve the performance of EEG's low amplitude and nonstationary characteristics.

Epilepsy EEG classification method based on supervised locality preserving canonical correlation analysis

An epileptic signal classification method based on supervised locality preserving canonical correlation analysis (SLPCCA), which can effectively use both sample category information and nonlinear relationships between features, is proposed and achieves excellent results compared with several state-of-the-art methods.

Imbalance Learning Using Neural Networks for Seizure Detection

An imbalance learning approach is proposed to improve accuracy of highly imbalanced seizure dataset and provides an average F-measure accuracy above 86% for Physionet MIT dataset.



Semi-automated patient-specific scalp EEG seizure detection with unsupervised machine learning

  • O. SmartM. Chen
  • Computer Science
    2015 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
  • 2015
This research examines seizure detection performance for 24 patients using k-means, k-mediod, and hierarchical clustering, a Gaussian mixture model, and a hidden Markov model after using principal component analyses to reduce 45 measures to 2 measures.


An automated classification of EEG signals for the detection of epileptic seizures using wavelet transform and statistical pattern recognition and confirmed that the proposed algorithm has a potential in the classification ofEEG signals and detection of epilepsyptic seizures, and could thus further improve the diagnosis of epilepsy.

Application of machine learning to epileptic seizure onset detection and treatment

The feasibility of using the algorithm to control the Vagus Nerve Stimulator, to initiate ictal SPECT (a functional neuroimaging modality useful for localizing the cerebral site of origin of a seizure), and to enable delay-sensitive therapeutic and diagnostic applications are demonstrated.

Automatic Identification of Epileptic and Background EEG Signals Using Frequency Domain Parameters

This paper used the autoregressive moving average as well as from Yule-Walker and Burg's methods, to extract the power density spectrum from representative signal samples, and found that Burg's method for spectrum estimation together with a support vector machine classifier yields the best classification results.

EPILEPSIAE - A European epilepsy database

Ellen R. Grass Lecture: Extraordinary EEG

  • W. Tatum
  • Biology
    The Neurodiagnostic journal
  • 2014
Beyond the routine application of EEG analyzed for clinical use, special EEG techniques now provide a window to reveal detailed information about the seizure onset zone in patients with epilepsy, as well as advance the understanding of the functional processes of the brain itself.

Handbook of EEG Interpretation

This handbook is a highly useful tool for residents, fellows, clinicians, and neurophysiology technologists looking for quick and reliable EEG information, regardless of specialty or level of training.

Dimension Reduction by Local Principal Component Analysis

A local linear approach to dimension reduction that provides accurate representations and is fast to compute is developed and it is shown that the local linear techniques outperform neural network implementations.

Visualizing Data using t-SNE

A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.

Flow-SNE: A New Approach for Flow Cytometry Clustering and Visualization

  • M. PouyanM. Nourani
  • Computer Science, Biology
    2015 International Conference on Healthcare Informatics
  • 2015
This paper proposes a new automatic clustering technique to extract meaningful cell subtypes from the flow cytometry datasets that is able to visualize the dataset in 2D and is designed to easily handle very large flow cytometer datasets.