EEG signal processing for epilepsy disease
C. Guerrero-Mosquera, A. Malanda-Trigueros and Angel Navia-Vazquez
InTech - Open Access Publisher
, Rijeka , Croatia
Since the integration between classical and modern biomedical signal processing with the engineering, new fields have been activated in a new area
as called “neuroengineering.” Clinical neuroengineering has active fields such
as neural prosthesis, brain computer interface (BCI), new clinical imaging techniques and treatment tools with EEG, evoked potentials (EPs), MEG and fMRI discussed in Thakor and Tong . Nowadays, there are several methods, tools and algorithms oriented to EEG signal processing for helping
in new treatments, obtaining new measurements of brain activity and detecting
brain diseases based on EEG signals.
Understanding and developing new signal processing techniques for the analysis of EEG signals is decisive in the area of biomedical research. In addition, the EEG not only represents the brain function but also the status of the whole body, i.e., a simple action as blinking the eyes introduces oscillations in the EEG. Then, the EEG is a direct way to neural activities measurements.
In EEG analysis, there are crucial considerations to have account:
• It is a dynamic signal which exhibits a nonstationary behavior, and it could be necessary to use segmentation signal segmentation or EEG.
• Some abnormal EEG patterns may be normal at younger ages being necessary then detection and classification algorithms.
Following Lotte et al. , EEG signal pre-processing and processing could be considered as a “pattern recognition system” and focus on the classification algorithms used to design them. Pre-processing methods include EEG signal modelling, segmentation, filtering and denoising, and EEG processing methods consist of two tasks: feature extraction and classification. The aim of the first ones is to identify “patterns” of brain activity and their results will be used as input to the classifier. It can say that the performance of a pattern recognition system depends on both the features and the classification algorithm employed.
In this chapter will introduce several typical methods in which EEG signal pre-processing and processing in EEG signals with epilepsy. The chapter is organized as follows: Section 2.2 presents a brief outline of electroencephalography, Section 2.3 is an overview of different alternatives in EEG signal modeling, 2.4 presents the state of art in EEG epilepsy detection and classification, Section 2.5 shows different methods to epilepsy prediction or anticipation and Section 2.6 gives a summary and conclusions of this chapter.