Machine learning techniques for detecting motor imagery in upper limbs

Juan Sebastian Ramirez Archila; Alvaro David Orjuela-Canon

doi:10.1109/ColCACI50549.2020.9247869

Machine learning techniques for detecting motor imagery in upper limbs

Título traducido de la contribución: Técnicas de aprendizaje automático para detectar imágenes motoras en miembros superiores

Juan Sebastian Ramirez Archila
, Alvaro David Orjuela-Canon

Producción científica: Capítulo en Libro/Informe › Contribución a la conferencia

1 Cita (Scopus)

Resumen

En la actualidad, las interfaces hombre-máquina han aumentado las aplicaciones para mejorar la calidad de vida de las personas lesionadas. A pesar de los avances en este campo, nuevas estrategias son importantes para contribuir a resolver nuevos problemas. Esta propuesta muestra el empleo de la extracción de características en los dominios de tiempo y frecuencia. Se utilizaron tres técnicas de aprendizaje automático como KNN, SVM y Random Forest para detectar imágenes motoras a partir de señales EEG. Se analizó la comparación entre la extracción de características y los modelos de detección empleados para encontrar la mejor elección en una aplicación para cerrar-abrir el puño en las manos. Los resultados alcanzaron más del 90% de precisión para ambos enfoques, mostrando como el dominio de la frecuencia es preferible para la extracción de características y el empleo del clasificador KNN como mejor estrategia para la presente demanda.

Título traducido de la contribución	Técnicas de aprendizaje automático para detectar imágenes motoras en miembros superiores
Idioma original	Inglés estadounidense
Título de la publicación alojada	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings
Editores	Alvaro David Orjuela-Canon
Editorial	Institute of Electrical and Electronics Engineers Inc.
Páginas	1-5
Número de páginas	5
ISBN (versión digital)	9781728194066
DOI	https://doi.org/10.1109/ColCACI50549.2020.9247869
Estado	Publicada - ago. 7 2020
Evento	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Virtual, Cali, Colombia Duración: ago. 7 2020 → ago. 9 2020

Serie de la publicación

Nombre	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

Conferencia

Conferencia	2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020
País/Territorio	Colombia
Ciudad	Virtual, Cali
Período	8/7/20 → 8/9/20

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

ODS 3: Salud y bienestar
ODS 4: Educación de calidad

Áreas temáticas de ASJC Scopus

Inteligencia artificial
Informática aplicada
Visión artificial y reconocimiento de patrones
Teoría de la decisión (miscelánea)
Gestión y sistemas de información
Control y optimización

Acceder al documento

10.1109/ColCACI50549.2020.9247869

Otros archivos y enlaces

Citar esto

Archila, J. S. R., & Orjuela-Canon, A. D. (2020). Machine learning techniques for detecting motor imagery in upper limbs. En A. D. Orjuela-Canon (Ed.), 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings (pp. 1-5). Artículo 9247869 (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ColCACI50549.2020.9247869

Archila, Juan Sebastian Ramirez ; Orjuela-Canon, Alvaro David. / Machine learning techniques for detecting motor imagery in upper limbs. 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. editor / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 1-5 (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings).

@inproceedings{41783320301e49e49b1bf8877cf81185,

title = "Machine learning techniques for detecting motor imagery in upper limbs",

abstract = "Nowadays, the human machine interfaces have increased the applications for improving the quality of life in injured people. In spite of the progress in the field, new strategies are important to contribute to solve new problems. This proposal shows the employing of feature extraction in time and frequency domains. Three machine learning techniques as KNN, SVM and Random Forest were used to detect motor imagery from EEG signals. Comparison for feature extraction and the employed detection models were analyzed to find the best election in an application for close-open fist in hands. The results achieved more than 90\% in accuracy for both approaches, showing as the frequency domain is preferable for feature extraction and the employment of the KNN classifier as best strategy for the present demand. ",

author = "Archila, \{Juan Sebastian Ramirez\} and Orjuela-Canon, \{Alvaro David\}",

note = "Funding Information: Authors thank the Universidad del Rosario for the support in this work and the Semillero en Inteligencia Artificial en Salud - Semill-IAS. Also, the Universidad Antonio Nari?o developed an important role for the signals acquisition which can be devised this work. Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 ; Conference date: 07-08-2020 Through 09-08-2020",

year = "2020",

month = aug,

day = "7",

doi = "10.1109/ColCACI50549.2020.9247869",

language = "English (US)",

series = "2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--5",

editor = "Orjuela-Canon, \{Alvaro David\}",

booktitle = "2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings",

address = "United States",

}

Archila, JSR & Orjuela-Canon, AD 2020, Machine learning techniques for detecting motor imagery in upper limbs. En AD Orjuela-Canon (ed.), 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings., 9247869, 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020, Virtual, Cali, Colombia, 8/7/20. https://doi.org/10.1109/ColCACI50549.2020.9247869

Machine learning techniques for detecting motor imagery in upper limbs. / Archila, Juan Sebastian Ramirez; Orjuela-Canon, Alvaro David.
2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. ed. / Alvaro David Orjuela-Canon. Institute of Electrical and Electronics Engineers Inc., 2020. p. 1-5 9247869 (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings).

Producción científica: Capítulo en Libro/Informe › Contribución a la conferencia

TY - GEN

T1 - Machine learning techniques for detecting motor imagery in upper limbs

AU - Archila, Juan Sebastian Ramirez

AU - Orjuela-Canon, Alvaro David

N1 - Funding Information: Authors thank the Universidad del Rosario for the support in this work and the Semillero en Inteligencia Artificial en Salud - Semill-IAS. Also, the Universidad Antonio Nari?o developed an important role for the signals acquisition which can be devised this work. Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/8/7

Y1 - 2020/8/7

N2 - Nowadays, the human machine interfaces have increased the applications for improving the quality of life in injured people. In spite of the progress in the field, new strategies are important to contribute to solve new problems. This proposal shows the employing of feature extraction in time and frequency domains. Three machine learning techniques as KNN, SVM and Random Forest were used to detect motor imagery from EEG signals. Comparison for feature extraction and the employed detection models were analyzed to find the best election in an application for close-open fist in hands. The results achieved more than 90% in accuracy for both approaches, showing as the frequency domain is preferable for feature extraction and the employment of the KNN classifier as best strategy for the present demand.

AB - Nowadays, the human machine interfaces have increased the applications for improving the quality of life in injured people. In spite of the progress in the field, new strategies are important to contribute to solve new problems. This proposal shows the employing of feature extraction in time and frequency domains. Three machine learning techniques as KNN, SVM and Random Forest were used to detect motor imagery from EEG signals. Comparison for feature extraction and the employed detection models were analyzed to find the best election in an application for close-open fist in hands. The results achieved more than 90% in accuracy for both approaches, showing as the frequency domain is preferable for feature extraction and the employment of the KNN classifier as best strategy for the present demand.

UR - https://www.scopus.com/pages/publications/85097568278

UR - https://www.scopus.com/pages/publications/85097568278#tab=citedBy

U2 - 10.1109/ColCACI50549.2020.9247869

DO - 10.1109/ColCACI50549.2020.9247869

M3 - Conference contribution

AN - SCOPUS:85097568278

T3 - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

SP - 1

EP - 5

BT - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings

A2 - Orjuela-Canon, Alvaro David

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020

Y2 - 7 August 2020 through 9 August 2020

ER -

Archila JSR, Orjuela-Canon AD. Machine learning techniques for detecting motor imagery in upper limbs. En Orjuela-Canon AD, editor, 2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. p. 1-5. 9247869. (2020 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2020 - Proceedings). doi: 10.1109/ColCACI50549.2020.9247869

Machine learning techniques for detecting motor imagery in upper limbs

Resumen

Serie de la publicación

Conferencia

ODS de las Naciones Unidas

Áreas temáticas de ASJC Scopus

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto