Difference between revisions of "A genetic algorithm for automatic feature extraction from EEG data"

From AIRWiki
Jump to: navigation, search
(Documents)
m (Documents)
Line 40: Line 40:
 
== '''Part 3: documents and references''' ==
 
== '''Part 3: documents and references''' ==
 
===== Documents =====   
 
===== Documents =====   
[http://home.dei.polimi.it/dalseno/papers/2008/ijcnn08.pdf | A Genetic Algorithm for Automatic Feature Extraction in P300 Detection]
+
[http://home.dei.polimi.it/dalseno/papers/2008/ijcnn08.pdf A Genetic Algorithm for Automatic Feature Extraction in P300 Detection]
  
[http://www.cs.iastate.edu/~honavar/ga_tutorial.pdf | A Genetic Algorithm Tutorial]
+
[http://www.cs.iastate.edu/~honavar/ga_tutorial.pdf A Genetic Algorithm Tutorial]

Revision as of 01:50, 12 March 2009

Part 1: project profile

Project name

A genetic algorithm for automatic feature extraction from EEG data

Project short description

The identification of stimuli based on EEG-analysis needs a specific software capable to find and select a set of relevant stimula-related features from those EEG. Obviously, this is because everyone's P300 is different from everybody's else. Such an application, based upon an ad-hoc genetic algorithm, has already been developed at Politecnico with excellent results. The goal of this project is producing a c++ version of this software to maximize efficiency and portability.

Dates

  • Start date: 2008/10/01
  • End date: 2009/04/30

People involved

Project head(s)
Students currently working on the project

Part 2: project description

State of the art

It is currently under development the online component of the identification section of the code and the class to which is delegated the computation of the P300 template.

Preliminary studies and sketches

After a deep analysis of the pre-existing source code, a c++ flavor of an analogous matlab version, we moved towards the current phase of further development and conversion of the application.

Design notes and guidelines

Our attention is focused on portability and efficiency; due to this fact we are currently developing the software in the form of a c++ class.

Experiments (description and results)

After we will have developed the application in its entireness, it's been planned to carry on some experiments related to fitness, genes and parameters tweaking.

Repository

Savane - BioSignal Analysis Toolkit (you must be a registered user to log in the repository of Savane)

Part 3: documents and references

Documents

A Genetic Algorithm for Automatic Feature Extraction in P300 Detection

A Genetic Algorithm Tutorial