SVM evaluation for brain computer interface systems

Mario Salerno, Giovanni Costantini, Daniele Casali, Giancarlo Orengo, Pietro Cavallo, Giovanni Saggio, Luigi Bianchi, Lucia Quitadamo, Maria Grazia Marciani

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A Support Vector Machine (SVM) classification method for data acquired by EEG registration for brain/computer interface systems is here proposed. The aim of this work is to evaluate the SVM performances in the recognition of a human mental task, among others. Such methodology could be very useful in important applications for disabled people. A prerequisite has been the developing of a system capable to recognize and classify the following four tasks: thinking to move the right hand, thinking to move the left hand, performing a simple mathematical operation, and thinking to a nursery rhyme. The data set exploited in the training and testing phases has been acquired by means of 61 EEG electrodes and consists of several time series. These time data sets were then transformed into the frequency domain, in order to obtain the power frequency spectrum. In such a way, for every electrode, 128 frequency channels were obtained. Finally, the SVM algorithm was used and evaluated to get the proposed classification.

Original languageEnglish
Title of host publicationBIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings
Pages240-244
Number of pages5
Publication statusPublished - 2010
Event3rd International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2010 - Valencia, Spain
Duration: Jan 20 2010Jan 23 2010

Other

Other3rd International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2010
CountrySpain
CityValencia
Period1/20/101/23/10

Fingerprint

Brain computer interface
Support vector machines
Electroencephalography
Electrodes
Time series
Testing

Keywords

  • Brain computer interface
  • Classification
  • Support Vector Machine

ASJC Scopus subject areas

  • Signal Processing

Cite this

Salerno, M., Costantini, G., Casali, D., Orengo, G., Cavallo, P., Saggio, G., ... Marciani, M. G. (2010). SVM evaluation for brain computer interface systems. In BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings (pp. 240-244)

SVM evaluation for brain computer interface systems. / Salerno, Mario; Costantini, Giovanni; Casali, Daniele; Orengo, Giancarlo; Cavallo, Pietro; Saggio, Giovanni; Bianchi, Luigi; Quitadamo, Lucia; Marciani, Maria Grazia.

BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings. 2010. p. 240-244.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Salerno, M, Costantini, G, Casali, D, Orengo, G, Cavallo, P, Saggio, G, Bianchi, L, Quitadamo, L & Marciani, MG 2010, SVM evaluation for brain computer interface systems. in BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings. pp. 240-244, 3rd International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2010, Valencia, Spain, 1/20/10.
Salerno M, Costantini G, Casali D, Orengo G, Cavallo P, Saggio G et al. SVM evaluation for brain computer interface systems. In BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings. 2010. p. 240-244
Salerno, Mario ; Costantini, Giovanni ; Casali, Daniele ; Orengo, Giancarlo ; Cavallo, Pietro ; Saggio, Giovanni ; Bianchi, Luigi ; Quitadamo, Lucia ; Marciani, Maria Grazia. / SVM evaluation for brain computer interface systems. BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings. 2010. pp. 240-244
@inproceedings{4e5197df06cd4f1b9ab303e55f77bf40,
title = "SVM evaluation for brain computer interface systems",
abstract = "A Support Vector Machine (SVM) classification method for data acquired by EEG registration for brain/computer interface systems is here proposed. The aim of this work is to evaluate the SVM performances in the recognition of a human mental task, among others. Such methodology could be very useful in important applications for disabled people. A prerequisite has been the developing of a system capable to recognize and classify the following four tasks: thinking to move the right hand, thinking to move the left hand, performing a simple mathematical operation, and thinking to a nursery rhyme. The data set exploited in the training and testing phases has been acquired by means of 61 EEG electrodes and consists of several time series. These time data sets were then transformed into the frequency domain, in order to obtain the power frequency spectrum. In such a way, for every electrode, 128 frequency channels were obtained. Finally, the SVM algorithm was used and evaluated to get the proposed classification.",
keywords = "Brain computer interface, Classification, Support Vector Machine",
author = "Mario Salerno and Giovanni Costantini and Daniele Casali and Giancarlo Orengo and Pietro Cavallo and Giovanni Saggio and Luigi Bianchi and Lucia Quitadamo and Marciani, {Maria Grazia}",
year = "2010",
language = "English",
isbn = "9789896740184",
pages = "240--244",
booktitle = "BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings",

}

TY - GEN

T1 - SVM evaluation for brain computer interface systems

AU - Salerno, Mario

AU - Costantini, Giovanni

AU - Casali, Daniele

AU - Orengo, Giancarlo

AU - Cavallo, Pietro

AU - Saggio, Giovanni

AU - Bianchi, Luigi

AU - Quitadamo, Lucia

AU - Marciani, Maria Grazia

PY - 2010

Y1 - 2010

N2 - A Support Vector Machine (SVM) classification method for data acquired by EEG registration for brain/computer interface systems is here proposed. The aim of this work is to evaluate the SVM performances in the recognition of a human mental task, among others. Such methodology could be very useful in important applications for disabled people. A prerequisite has been the developing of a system capable to recognize and classify the following four tasks: thinking to move the right hand, thinking to move the left hand, performing a simple mathematical operation, and thinking to a nursery rhyme. The data set exploited in the training and testing phases has been acquired by means of 61 EEG electrodes and consists of several time series. These time data sets were then transformed into the frequency domain, in order to obtain the power frequency spectrum. In such a way, for every electrode, 128 frequency channels were obtained. Finally, the SVM algorithm was used and evaluated to get the proposed classification.

AB - A Support Vector Machine (SVM) classification method for data acquired by EEG registration for brain/computer interface systems is here proposed. The aim of this work is to evaluate the SVM performances in the recognition of a human mental task, among others. Such methodology could be very useful in important applications for disabled people. A prerequisite has been the developing of a system capable to recognize and classify the following four tasks: thinking to move the right hand, thinking to move the left hand, performing a simple mathematical operation, and thinking to a nursery rhyme. The data set exploited in the training and testing phases has been acquired by means of 61 EEG electrodes and consists of several time series. These time data sets were then transformed into the frequency domain, in order to obtain the power frequency spectrum. In such a way, for every electrode, 128 frequency channels were obtained. Finally, the SVM algorithm was used and evaluated to get the proposed classification.

KW - Brain computer interface

KW - Classification

KW - Support Vector Machine

UR - http://www.scopus.com/inward/record.url?scp=77956447358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956447358&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789896740184

SP - 240

EP - 244

BT - BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings

ER -