# Identification of epileptic regions from electroencephalographic data: Feigenbaum graphs

## TL;DR

This paper introduces a novel method using Feigenbaum graphs to analyze EEG data, effectively distinguishing epileptic regions by characterizing data sets through graph metrics, aiding in epilepsy diagnosis.

## Contribution

The study presents a new approach applying Feigenbaum graphs to EEG signals for identifying epileptic zones, demonstrating its potential as a diagnostic aid.

## Key findings

- Successfully characterized focal and non-focal EEG data sets
- Achieved good results in identifying epileptic regions
- Method shows promise for assisting clinical diagnosis

## Abstract

Diagnosing epilepsy is a problem of crucial importance. So analysing EEG data is of much importance to help this diagnosis. Assembling the Feigenbaum graphs for EEG signals. And calculating their average clustering, average degree, and average shortest path length. We manage to characterize two different data sets from each other. Each data set consisted of focal and non-focal activity, from where epileptic regions could be identified. This method yields good results for identifying sets of data from epileptic zones. Suggesting our approach could be used to aid physicians with diagnosing epilepsy from EEG data.