Abstract
In this study a comparison among three different machine learning techniques for the classification of mental tasks for a Brain-Computer Interface system is presented: MLP neural network, Fuzzy C-Means Analysis and Support Vector Machine (SVM). In BCI literature, finding the best classifier is a very hard problem to solve, and it is still an open question. We considered only ten electrodes for our analysis, in order to lower the computational workload. Different parameters were analyzed for the evaluation of the performances of the classifiers: accuracy, training time and size of the training dataset. Results demonstrated how the accuracies of the three classifiers are nearly the same but the error margin of SVM on this reduced dataset is larger compared to the other two classifiers. Furthermore neural network needs a reduced number of trials for training purposes, reducing the recording session up to 8 times with respect to SVM and Fuzzy analysis. This suggests how, in the presented case, MLP neural network can be preferable for the classification of mental tasks in Brain Computer Interface systems.
| Original language | English |
|---|---|
| Title of host publication | BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings |
| Pages | 174-179 |
| Number of pages | 6 |
| Publication status | Published - 2010 |
| Event | 3rd International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2010 - Valencia, Spain Duration: Jan 20 2010 → Jan 23 2010 |
Other
| Other | 3rd International Conference on Bio-inspired Systems and Signal Processing, BIOSIGNALS 2010 |
|---|---|
| Country | Spain |
| City | Valencia |
| Period | 1/20/10 → 1/23/10 |
Fingerprint
Keywords
- BCI
- Fuzzy logic
- Neural networks
- SVM
ASJC Scopus subject areas
- Signal Processing
Cite this
Comparison of different classifiers on a reduced set of features for mental tasks-based brain computer interface. / Saggio, Giovanni; Cavallo, Pietro; Costantini, Giovanni; Susi, Gianluca; Quitadamo, Lucia Rita; Marciani, Maria Grazia; Bianchi, Luigi.
BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings. 2010. p. 174-179.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Comparison of different classifiers on a reduced set of features for mental tasks-based brain computer interface
AU - Saggio, Giovanni
AU - Cavallo, Pietro
AU - Costantini, Giovanni
AU - Susi, Gianluca
AU - Quitadamo, Lucia Rita
AU - Marciani, Maria Grazia
AU - Bianchi, Luigi
PY - 2010
Y1 - 2010
N2 - In this study a comparison among three different machine learning techniques for the classification of mental tasks for a Brain-Computer Interface system is presented: MLP neural network, Fuzzy C-Means Analysis and Support Vector Machine (SVM). In BCI literature, finding the best classifier is a very hard problem to solve, and it is still an open question. We considered only ten electrodes for our analysis, in order to lower the computational workload. Different parameters were analyzed for the evaluation of the performances of the classifiers: accuracy, training time and size of the training dataset. Results demonstrated how the accuracies of the three classifiers are nearly the same but the error margin of SVM on this reduced dataset is larger compared to the other two classifiers. Furthermore neural network needs a reduced number of trials for training purposes, reducing the recording session up to 8 times with respect to SVM and Fuzzy analysis. This suggests how, in the presented case, MLP neural network can be preferable for the classification of mental tasks in Brain Computer Interface systems.
AB - In this study a comparison among three different machine learning techniques for the classification of mental tasks for a Brain-Computer Interface system is presented: MLP neural network, Fuzzy C-Means Analysis and Support Vector Machine (SVM). In BCI literature, finding the best classifier is a very hard problem to solve, and it is still an open question. We considered only ten electrodes for our analysis, in order to lower the computational workload. Different parameters were analyzed for the evaluation of the performances of the classifiers: accuracy, training time and size of the training dataset. Results demonstrated how the accuracies of the three classifiers are nearly the same but the error margin of SVM on this reduced dataset is larger compared to the other two classifiers. Furthermore neural network needs a reduced number of trials for training purposes, reducing the recording session up to 8 times with respect to SVM and Fuzzy analysis. This suggests how, in the presented case, MLP neural network can be preferable for the classification of mental tasks in Brain Computer Interface systems.
KW - BCI
KW - Fuzzy logic
KW - Neural networks
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=77956429806&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77956429806&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9789896740184
SP - 174
EP - 179
BT - BIOSIGNALS 2010 - Proceedings of the 3rd International Conference on Bio-inpsired Systems and Signal Processing, Proceedings
ER -