Classifying human actions in daily life using computational intelligence techniques

Romina Torres, Mauricio Poblete, Rodrigo Salas

Resultado de la investigación: Conference contribution

Resumen

Nowadays, there are several effective computational intelligence techniques that, theoretically, could be useful to classify human daily life actions. Moreover, sensors are getting smaller, cheaper, portable and even wearable. In this paper, we have built an annotation tool by applying several computational intelligence techniques (K-Nearest Neighbor, the Support Vector Machine and the Multilayer Perceptron) to detect six types of human actions in daily life based on signals obtained from an accelerometer sensor (standing-up, walking, running, resting, jumping and sitting-down) with an accuracy over 85%. In the future, this component will be the base to infer abnormal behavior from common daily behavior that could be an emergency situation in evolution.

Idioma originalEnglish
Título de la publicación alojada2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-5
Número de páginas5
Volumen2017-January
ISBN (versión digital)9781538631232
DOI
EstadoPublished - 19 dic 2017
Evento2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Pucon, Chile
Duración: 18 oct 201720 oct 2017

Conference

Conference2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017
PaísChile
CiudadPucon
Período18/10/1720/10/17

Huella dactilar

Artificial intelligence
Sensors
Multilayer neural networks
Accelerometers
Support vector machines

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computer Networks and Communications
  • Control and Systems Engineering

Citar esto

Torres, R., Poblete, M., & Salas, R. (2017). Classifying human actions in daily life using computational intelligence techniques. En 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings (Vol. 2017-January, pp. 1-5). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRERA.2017.8229514
Torres, Romina ; Poblete, Mauricio ; Salas, Rodrigo. / Classifying human actions in daily life using computational intelligence techniques. 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-5
@inproceedings{78f6b86315ca42e48b1790b501364153,
title = "Classifying human actions in daily life using computational intelligence techniques",
abstract = "Nowadays, there are several effective computational intelligence techniques that, theoretically, could be useful to classify human daily life actions. Moreover, sensors are getting smaller, cheaper, portable and even wearable. In this paper, we have built an annotation tool by applying several computational intelligence techniques (K-Nearest Neighbor, the Support Vector Machine and the Multilayer Perceptron) to detect six types of human actions in daily life based on signals obtained from an accelerometer sensor (standing-up, walking, running, resting, jumping and sitting-down) with an accuracy over 85{\%}. In the future, this component will be the base to infer abnormal behavior from common daily behavior that could be an emergency situation in evolution.",
keywords = "Annotating tool, Computational Intelligence, Uman life monitoring",
author = "Romina Torres and Mauricio Poblete and Rodrigo Salas",
year = "2017",
month = "12",
day = "19",
doi = "10.1109/ICRERA.2017.8229514",
language = "English",
volume = "2017-January",
pages = "1--5",
booktitle = "2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Torres, R, Poblete, M & Salas, R 2017, Classifying human actions in daily life using computational intelligence techniques. En 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017, Pucon, Chile, 18/10/17. https://doi.org/10.1109/ICRERA.2017.8229514

Classifying human actions in daily life using computational intelligence techniques. / Torres, Romina; Poblete, Mauricio; Salas, Rodrigo.

2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-5.

Resultado de la investigación: Conference contribution

TY - GEN

T1 - Classifying human actions in daily life using computational intelligence techniques

AU - Torres, Romina

AU - Poblete, Mauricio

AU - Salas, Rodrigo

PY - 2017/12/19

Y1 - 2017/12/19

N2 - Nowadays, there are several effective computational intelligence techniques that, theoretically, could be useful to classify human daily life actions. Moreover, sensors are getting smaller, cheaper, portable and even wearable. In this paper, we have built an annotation tool by applying several computational intelligence techniques (K-Nearest Neighbor, the Support Vector Machine and the Multilayer Perceptron) to detect six types of human actions in daily life based on signals obtained from an accelerometer sensor (standing-up, walking, running, resting, jumping and sitting-down) with an accuracy over 85%. In the future, this component will be the base to infer abnormal behavior from common daily behavior that could be an emergency situation in evolution.

AB - Nowadays, there are several effective computational intelligence techniques that, theoretically, could be useful to classify human daily life actions. Moreover, sensors are getting smaller, cheaper, portable and even wearable. In this paper, we have built an annotation tool by applying several computational intelligence techniques (K-Nearest Neighbor, the Support Vector Machine and the Multilayer Perceptron) to detect six types of human actions in daily life based on signals obtained from an accelerometer sensor (standing-up, walking, running, resting, jumping and sitting-down) with an accuracy over 85%. In the future, this component will be the base to infer abnormal behavior from common daily behavior that could be an emergency situation in evolution.

KW - Annotating tool

KW - Computational Intelligence

KW - Uman life monitoring

UR - http://www.scopus.com/inward/record.url?scp=85043251106&partnerID=8YFLogxK

U2 - 10.1109/ICRERA.2017.8229514

DO - 10.1109/ICRERA.2017.8229514

M3 - Conference contribution

AN - SCOPUS:85043251106

VL - 2017-January

SP - 1

EP - 5

BT - 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Torres R, Poblete M, Salas R. Classifying human actions in daily life using computational intelligence techniques. En 2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2017 - Proceedings. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-5 https://doi.org/10.1109/ICRERA.2017.8229514