Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic

Giovanni Saggio; Pietro Cavallo; Alessio Ferretti; Francesco Garzoli; Lucia Rita Quitadamo; Maria Grazia Marciani; Franco Giannini; Luigi Bianchi

doi:10.1109/WOWMOM.2009.5282406

Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic

Giovanni Saggio, Pietro Cavallo, Alessio Ferretti, Francesco Garzoli, Lucia Rita Quitadamo, Maria Grazia Marciani, Franco Giannini, Luigi Bianchi

Fondazione Santa Lucia

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This study is devoted to the classification of four-class mental tasks data for a Brain-Computer Interface protocol. In such view we adopted Multi Layer Perceptron Neural Network (MLP) and Fuzzy C-means analysis for classifying: left and right hand movement imagination, mental subtraction operation and mental recitation of a nursery rhyme. Five subjects participated to the experiment in two sessions recorded in distinct days. Different parameters were considered for the evaluation of the performances of the two classifiers: accuracy, that is, percentage of correct classifications, training time and size of the training dataset. The results show that even if the accuracies of the two classifiers are quite similar, the MLP classifier needs a smaller training set to reach them with respect to the Fuzzy one. This leads to the preference of MLP for the classification of mental tasks in Brain Computer Interface protocols.

Original language	English
Title of host publication	2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009
DOIs	https://doi.org/10.1109/WOWMOM.2009.5282406
Publication status	Published - 2009
Event	2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009 - Kos, Greece Duration: Jun 15 2009 → Jun 19 2009

Other

Other	2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009
Country	Greece
City	Kos
Period	6/15/09 → 6/19/09

ASJC Scopus subject areas

Computer Networks and Communications
Software

Access to Document

10.1109/WOWMOM.2009.5282406

Fingerprint Dive into the research topics of 'Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic'. Together they form a unique fingerprint.

Cite this

Saggio, G., Cavallo, P., Ferretti, A., Garzoli, F., Quitadamo, L. R., Marciani, M. G., Giannini, F., & Bianchi, L. (2009). Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic. In 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009 [5282406] https://doi.org/10.1109/WOWMOM.2009.5282406

Comparison of two different classifiers for mental tasks-based brain-computer interface : MLP Neural Networks vs. Fuzzy logic. / Saggio, Giovanni; Cavallo, Pietro; Ferretti, Alessio; Garzoli, Francesco; Quitadamo, Lucia Rita; Marciani, Maria Grazia; Giannini, Franco; Bianchi, Luigi.

2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009. 2009. 5282406.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Saggio, G, Cavallo, P, Ferretti, A, Garzoli, F, Quitadamo, LR, Marciani, MG, Giannini, F & Bianchi, L 2009, Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic. in 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009., 5282406, 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009, Kos, Greece, 6/15/09. https://doi.org/10.1109/WOWMOM.2009.5282406

Saggio G, Cavallo P, Ferretti A, Garzoli F, Quitadamo LR, Marciani MG et al. Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic. In 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009. 2009. 5282406 https://doi.org/10.1109/WOWMOM.2009.5282406

Saggio, Giovanni ; Cavallo, Pietro ; Ferretti, Alessio ; Garzoli, Francesco ; Quitadamo, Lucia Rita ; Marciani, Maria Grazia ; Giannini, Franco ; Bianchi, Luigi. / Comparison of two different classifiers for mental tasks-based brain-computer interface : MLP Neural Networks vs. Fuzzy logic. 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009. 2009.

@inproceedings{db03d15a1c42454aaf1067c4a40c7980,

title = "Comparison of two different classifiers for mental tasks-based brain-computer interface: MLP Neural Networks vs. Fuzzy logic",

abstract = "This study is devoted to the classification of four-class mental tasks data for a Brain-Computer Interface protocol. In such view we adopted Multi Layer Perceptron Neural Network (MLP) and Fuzzy C-means analysis for classifying: left and right hand movement imagination, mental subtraction operation and mental recitation of a nursery rhyme. Five subjects participated to the experiment in two sessions recorded in distinct days. Different parameters were considered for the evaluation of the performances of the two classifiers: accuracy, that is, percentage of correct classifications, training time and size of the training dataset. The results show that even if the accuracies of the two classifiers are quite similar, the MLP classifier needs a smaller training set to reach them with respect to the Fuzzy one. This leads to the preference of MLP for the classification of mental tasks in Brain Computer Interface protocols.",

author = "Giovanni Saggio and Pietro Cavallo and Alessio Ferretti and Francesco Garzoli and Quitadamo, {Lucia Rita} and Marciani, {Maria Grazia} and Franco Giannini and Luigi Bianchi",

year = "2009",

doi = "10.1109/WOWMOM.2009.5282406",

language = "English",

isbn = "9781424444397",

booktitle = "2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009",

note = "2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009 ; Conference date: 15-06-2009 Through 19-06-2009",

}

TY - GEN

T1 - Comparison of two different classifiers for mental tasks-based brain-computer interface

T2 - 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009

AU - Saggio, Giovanni

AU - Cavallo, Pietro

AU - Ferretti, Alessio

AU - Garzoli, Francesco

AU - Quitadamo, Lucia Rita

AU - Marciani, Maria Grazia

AU - Giannini, Franco

AU - Bianchi, Luigi

PY - 2009

Y1 - 2009

N2 - This study is devoted to the classification of four-class mental tasks data for a Brain-Computer Interface protocol. In such view we adopted Multi Layer Perceptron Neural Network (MLP) and Fuzzy C-means analysis for classifying: left and right hand movement imagination, mental subtraction operation and mental recitation of a nursery rhyme. Five subjects participated to the experiment in two sessions recorded in distinct days. Different parameters were considered for the evaluation of the performances of the two classifiers: accuracy, that is, percentage of correct classifications, training time and size of the training dataset. The results show that even if the accuracies of the two classifiers are quite similar, the MLP classifier needs a smaller training set to reach them with respect to the Fuzzy one. This leads to the preference of MLP for the classification of mental tasks in Brain Computer Interface protocols.

AB - This study is devoted to the classification of four-class mental tasks data for a Brain-Computer Interface protocol. In such view we adopted Multi Layer Perceptron Neural Network (MLP) and Fuzzy C-means analysis for classifying: left and right hand movement imagination, mental subtraction operation and mental recitation of a nursery rhyme. Five subjects participated to the experiment in two sessions recorded in distinct days. Different parameters were considered for the evaluation of the performances of the two classifiers: accuracy, that is, percentage of correct classifications, training time and size of the training dataset. The results show that even if the accuracies of the two classifiers are quite similar, the MLP classifier needs a smaller training set to reach them with respect to the Fuzzy one. This leads to the preference of MLP for the classification of mental tasks in Brain Computer Interface protocols.

UR - http://www.scopus.com/inward/record.url?scp=74349088790&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74349088790&partnerID=8YFLogxK

U2 - 10.1109/WOWMOM.2009.5282406

DO - 10.1109/WOWMOM.2009.5282406

M3 - Conference contribution

AN - SCOPUS:74349088790

SN - 9781424444397

BT - 2009 IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks and Workshops, WOWMOM 2009

Y2 - 15 June 2009 through 19 June 2009

ER -