Manifold Learning Applied on EEG Signal of the Epileptic Patients for Detection of Normal and Pre-Seizure States

Abstract

In this paper, several Manifold Learning (ML) techniques for dimension reduction of EEG feature vectors are introduced and applied on set of epileptic EEG signals. These include Principal Component Analysis (PCA), Multidimensional Scaling (MDS), Isometric Mapping (ISOMAP) and Locally Linear Embedding (LLE). While EEG signals of epileptic patients contain necessary information with regards to the various brain states of epileptic patients, for extraction of useful information in the EEG signals and for detection, often construction of high-dimensional feature vectors is utilized. Analysis of such high-dimensional feature vectors are complex and time consuming. This paper deals with dimension reduction of the extracted feature vectors and comparative analysis of the performance of several manifold learning techniques as applied on EEG signals of epileptic patients.

Diagnosis of breast cancer tumor based on manifold learning and Support Vector Machine

“…"Isometric mapping" or Isomap tries to solve the problem of flattening a curved manifold by building on classical multidimensional scaling but aims to recover the intrinsic geometry of the data by preserving geodesic distance within the manifold. That is, Isomap is classical scaling in which the distances have been replaced by estimates of intrinsic geodesic distance [8]. In practice, it is implemented as follows: for neighboring points the geodesic distances are approximated by Euclidean distances; for distant points the geodesic distances are approximated by the length of the shortest path in a graph with edges connecting nearby points.…”

Optimized feature subsets for epileptic seizure prediction studies

“…In recent years, the analysis of high-dimensional feature spaces [3], and the use of machine learning methods has been proposed [4]. Support Vector Machines (SVMs) is considered as a promising approach, with the advantage to create individually tailored solutions.…”

On the benefits of classical multidimensional scaling in Epileptic seizure prediction studies

“…It is important to select an appropriate feature vector dimension while maintaining as much information as possible [6].…”