Chapter 17 - Performance evaluation of fractal features toward seizure detection from electroencephalogram signals

Abstract

Electroencephalogram signals are the classical gold standard for the diagnosis of seizures. Important information that enables the effective detection of seizure is hidden due to the complex and chaotic nature of electroencephalogram signals. The capability of fractal dimension to extract complex information from signals or images is well utilized in various domains. In this chapter, the ability of three well-known fractal dimension feature extraction methods (e.g., Katz fractal dimension, Higuchi fractal dimension, and Petrosian fractal dimension) to classify epileptic and nonepileptic electroencephalogram signals is evaluated. The features are fed to support vector machine classifier for the classification of epileptic and nonepileptic electroencephalogram signals. The results of support vector machine classifier show that the fractal features are good measures to characterize the complex information of epileptic signals.