Principle components analysis for seizures prediction using wavelet transform

TL;DR

This paper presents a machine learning approach combining wavelet transform, PCA, and SVM to predict epileptic seizures with high sensitivity, addressing challenges in preprocessing and feature extraction.

Contribution

It introduces a novel combination of wavelet transform and PCA for seizure prediction, improving detection accuracy over existing methods.

Findings

Average sensitivity of 93.1% across 23 subjects

Effective preictal state detection before seizures

Combines wavelet transform, PCA, and SVM for improved prediction

Abstract

Epilepsy is a disease in which frequent seizures occur due to abnormal activity of neurons. Patients affected by this disease can be treated with the help of medicines or surgical procedures. However, both of these methods are not quite useful. The only method to treat epilepsy patients effectively is to predict the seizure before its onset. It has been observed that abnormal activity in the brain signals starts before the occurrence of seizure known as the preictal state. Many researchers have proposed machine learning models for prediction of epileptic seizures by detecting the start of preictal state. However, pre-processing, feature extraction and classification remains a great challenge in the prediction of preictal state. Therefore, we propose a model that uses common spatial pattern filtering and wavelet transform for preprocessing, principal component analysis for feature extraction and support vector machines for detecting preictal state. We have applied our model on 23 subjects and an average sensitivity of 93.1% has been observed for 84 seizures.