Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop

Denis Delisle-Rodriguez; Ana Cecilia Villa-Parra; Alberto López-Delis; Anselmo Frizera-Neto; Eduardo Rocon; Teodiano Freire-Bastos

doi:10.1007/978-3-319-46669-9_241

Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop

Denis Delisle-Rodriguez, Ana Cecilia Villa-Parra, Alberto López-Delis, Anselmo Frizera-Neto, Eduardo Rocon, Teodiano Freire-Bastos

Biomedical Engineering Research Group (GIIB)

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Is presented a non-supervised method for feature selection based on similarity index, which is applied in a brain-computer interface (BCI) to recognize gait preparation/stops. Maximal information compression index is here used to obtain redundancies, while representation entropy value is employed to find the feature vectors with high entropy. EEG signals of six subjects were acquired on the primary cortex during walking, in order to evaluate this approach in a BCI. The maximum accuracy was 55% and 85% to recognize gait preparation/stops, respectively. Thus, this method can be used in a BCI to improve the time delay during dimensionality reduction.

Original language	English
Title of host publication	Biosystems and Biorobotics
Publisher	Springer International Publishing
Pages	1469-1474
Number of pages	6
DOIs	https://doi.org/10.1007/978-3-319-46669-9_241
State	Published - 2017

Publication series

Name	Biosystems and Biorobotics
Volume	15
ISSN (Print)	2195-3562
ISSN (Electronic)	2195-3570

Bibliographical note

Funding Information:
Acknowledgments Authors would like to thank CNPq, CAPES, FAPES and SENESCYT for supporting this research.

Publisher Copyright:
© 2017, Springer International Publishing AG.

Access to Document

10.1007/978-3-319-46669-9_241

Cite this

Delisle-Rodriguez, D., Villa-Parra, A. C., López-Delis, A., Frizera-Neto, A., Rocon, E., & Freire-Bastos, T. (2017). Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop. In Biosystems and Biorobotics (pp. 1469-1474). (Biosystems and Biorobotics; Vol. 15). Springer International Publishing. https://doi.org/10.1007/978-3-319-46669-9_241

@inbook{b6ac52dcbbbd4a909e728901f8139387,

title = "Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop",

abstract = "Is presented a non-supervised method for feature selection based on similarity index, which is applied in a brain-computer interface (BCI) to recognize gait preparation/stops. Maximal information compression index is here used to obtain redundancies, while representation entropy value is employed to find the feature vectors with high entropy. EEG signals of six subjects were acquired on the primary cortex during walking, in order to evaluate this approach in a BCI. The maximum accuracy was 55% and 85% to recognize gait preparation/stops, respectively. Thus, this method can be used in a BCI to improve the time delay during dimensionality reduction.",

author = "Denis Delisle-Rodriguez and Villa-Parra, {Ana Cecilia} and Alberto L{\'o}pez-Delis and Anselmo Frizera-Neto and Eduardo Rocon and Teodiano Freire-Bastos",

note = "Publisher Copyright: {\textcopyright} 2017, Springer International Publishing AG.",

year = "2017",

doi = "10.1007/978-3-319-46669-9_241",

language = "English",

series = "Biosystems and Biorobotics",

publisher = "Springer International Publishing",

pages = "1469--1474",

booktitle = "Biosystems and Biorobotics",

}

Delisle-Rodriguez, D, Villa-Parra, AC, López-Delis, A, Frizera-Neto, A, Rocon, E & Freire-Bastos, T 2017, Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop. in Biosystems and Biorobotics. Biosystems and Biorobotics, vol. 15, Springer International Publishing, pp. 1469-1474. https://doi.org/10.1007/978-3-319-46669-9_241

Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop. / Delisle-Rodriguez, Denis; Villa-Parra, Ana Cecilia; López-Delis, Alberto et al.
Biosystems and Biorobotics. Springer International Publishing, 2017. p. 1469-1474 (Biosystems and Biorobotics; Vol. 15).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Non-supervised Feature Selection

T2 - Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop

AU - Delisle-Rodriguez, Denis

AU - Villa-Parra, Ana Cecilia

AU - López-Delis, Alberto

AU - Frizera-Neto, Anselmo

AU - Rocon, Eduardo

AU - Freire-Bastos, Teodiano

PY - 2017

Y1 - 2017

N2 - Is presented a non-supervised method for feature selection based on similarity index, which is applied in a brain-computer interface (BCI) to recognize gait preparation/stops. Maximal information compression index is here used to obtain redundancies, while representation entropy value is employed to find the feature vectors with high entropy. EEG signals of six subjects were acquired on the primary cortex during walking, in order to evaluate this approach in a BCI. The maximum accuracy was 55% and 85% to recognize gait preparation/stops, respectively. Thus, this method can be used in a BCI to improve the time delay during dimensionality reduction.

AB - Is presented a non-supervised method for feature selection based on similarity index, which is applied in a brain-computer interface (BCI) to recognize gait preparation/stops. Maximal information compression index is here used to obtain redundancies, while representation entropy value is employed to find the feature vectors with high entropy. EEG signals of six subjects were acquired on the primary cortex during walking, in order to evaluate this approach in a BCI. The maximum accuracy was 55% and 85% to recognize gait preparation/stops, respectively. Thus, this method can be used in a BCI to improve the time delay during dimensionality reduction.

UR - http://www.scopus.com/inward/record.url?scp=85028318921&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-46669-9_241

DO - 10.1007/978-3-319-46669-9_241

M3 - Chapter

AN - SCOPUS:85028318921

T3 - Biosystems and Biorobotics

SP - 1469

EP - 1474

BT - Biosystems and Biorobotics

PB - Springer International Publishing

ER -

Non-supervised Feature Selection: Evaluation in a BCI for Single-Trial Recognition of Gait Preparation/Stop

Abstract

Publication series

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this