A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance

Dat TRAN, Xu HUANG, Wanli MA

Research output: A Conference proceeding or a Chapter in BookConference contribution

1 Citation (Scopus)

Abstract

This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two stateof-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8% better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems
Original languageEnglish
Title of host publicationThe 2013 International Joint Conference on Neural Networks (IJCNN)
EditorsPlamen Angelov, Daniel Levine
Place of PublicationUSA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1297-1301
Number of pages5
Volume1
ISBN (Print)9781467361293
Publication statusPublished - 2013
Event2013 International Joint Conference on Neural Networks (IJCNN) - Dallas, Texas, United States
Duration: 4 Aug 20139 Aug 2013

Conference

Conference2013 International Joint Conference on Neural Networks (IJCNN)
CountryUnited States
CityTexas
Period4/08/139/08/13

Fingerprint

Brain computer interface
Brain
Design of experiments
Feature extraction
Experiments
Chemical activation

Cite this

TRAN, D., HUANG, X., & MA, W. (2013). A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance. In P. Angelov, & D. Levine (Eds.), The 2013 International Joint Conference on Neural Networks (IJCNN) (Vol. 1, pp. 1297-1301). USA: IEEE, Institute of Electrical and Electronics Engineers.
TRAN, Dat ; HUANG, Xu ; MA, Wanli. / A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance. The 2013 International Joint Conference on Neural Networks (IJCNN). editor / Plamen Angelov ; Daniel Levine. Vol. 1 USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. pp. 1297-1301
@inproceedings{48995c4069af4498b859eb06bff2a75e,
title = "A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance",
abstract = "This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two stateof-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8{\%} better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems",
keywords = "Brain-computer Interface, Aggregate Model",
author = "Dat TRAN and Xu HUANG and Wanli MA",
year = "2013",
language = "English",
isbn = "9781467361293",
volume = "1",
pages = "1297--1301",
editor = "Plamen Angelov and Daniel Levine",
booktitle = "The 2013 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States",

}

TRAN, D, HUANG, X & MA, W 2013, A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance. in P Angelov & D Levine (eds), The 2013 International Joint Conference on Neural Networks (IJCNN). vol. 1, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 1297-1301, 2013 International Joint Conference on Neural Networks (IJCNN), Texas, United States, 4/08/13.

A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance. / TRAN, Dat; HUANG, Xu; MA, Wanli.

The 2013 International Joint Conference on Neural Networks (IJCNN). ed. / Plamen Angelov; Daniel Levine. Vol. 1 USA : IEEE, Institute of Electrical and Electronics Engineers, 2013. p. 1297-1301.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance

AU - TRAN, Dat

AU - HUANG, Xu

AU - MA, Wanli

PY - 2013

Y1 - 2013

N2 - This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two stateof-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8% better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems

AB - This paper proposes a general aggregate model for improving performance of multi-class Brain-Computer Interface (BCI) systems. In BCI systems, activation and delay are well known issues in conducting experiments. The delay of meaningful brain signal depends on subjects, tasks and experimental design. Therefore, within a trial it is not easy to identify where meaningful brain signal starts and ends. Most of current methods estimate the delay and extract a portion of meaningful brain signal in a trial and use this signal as a representative for the whole trial. Instead of doing so, our proposed aggregate model divides a trial into overlapping frames and treat them equally. These frames are classified and their results are then aggregated together to form classification result of the trial. From the general aggregate model, we derive two specific aggregate models using two stateof-the-art Common Spatial Patterns (CSP)-based methods for feature extraction. We performed experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed models. This dataset was designed for motor imagery classification with 4 classes. Preliminary experimental results show that our proposed aggregate models are up to 8% better than the original CSP-based methods. Furthermore, we show that our aggregate model can be easily extended to online BCI systems

KW - Brain-computer Interface

KW - Aggregate Model

M3 - Conference contribution

SN - 9781467361293

VL - 1

SP - 1297

EP - 1301

BT - The 2013 International Joint Conference on Neural Networks (IJCNN)

A2 - Angelov, Plamen

A2 - Levine, Daniel

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - USA

ER -

TRAN D, HUANG X, MA W. A General Aggregate Model for Improving Multi-class Brain-computer interface Systems' Performance. In Angelov P, Levine D, editors, The 2013 International Joint Conference on Neural Networks (IJCNN). Vol. 1. USA: IEEE, Institute of Electrical and Electronics Engineers. 2013. p. 1297-1301