Active learning for adaptive brain machine interface based on Software Agent

Author

Castillo-Garcia, Javier ; Hortal, Enrique ; Bastos, Teodiano ; Ianez, Eduardo ; Caicedo, Eduardo ; Azorin, Jose

Author_Institution

Sch. of Electr. & Electron. Eng., Univ. of Valle, Cali, Colombia

fYear

2015

fDate

16-19 June 2015

Firstpage

44

Lastpage

48

Abstract

Brain Machine Interface (BMI) and Software Agent (SA) can provide some new adaptive strategies for robust BMI implementations. In this work, a non-invasive Adaptive BMI is introduced, which has been designed to discriminate four mental tasks. The SA allows tracking features to contribute for an adaptive process, while the user´s engagement state provides a feedback between BMI and the environment. The Silhouette´s width is the performance measurement used for the active learning process. The results show that the implemented system allows high accuracy (75%) in the classification process.

Keywords

brain-computer interfaces; feature extraction; learning (artificial intelligence); pattern classification; software agents; SA; active learning process; adaptive brain machine interface; adaptive process; adaptive strategies; classification process; features tracking; mental tasks; noninvasive adaptive BMI; robust BMI implementations; silhouette width; software agent; user engagement state; Accuracy; Brain modeling; Brain-computer interfaces; Electroencephalography; Software agents; Training; Active learning; BMI; adaptive; software agent;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Automation (MED), 2015 23th Mediterranean Conference on

Conference_Location

Torremolinos

Type

conf

DOI

10.1109/MED.2015.7158727

Filename

7158727