A Personal Activity Recognition System Based on Smart Devices

Harold Murcia, Juanita Triana

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferencia

Resumen

With the continuous evolution of technology, mobile devices are becoming more and more important in people’s lives. In the same way, new needs related to the information provided by their users arise, making evident the need to develop systems that take advantage of their daily use. The recognition of personal activity based on the information provided by the last generation mobile devices can easily be considered as an useful tool for many purposes and future applications. This paper presents the use of information provided from two smart devices in different acquisition schemes, assessing conventional supervised classifiers to recognize personal activity by an identification of seven classes. The classifiers were trained with a generated database from eight users and were evaluated in offline mode with other two generated databases. The prediction experiments were qualified by using F1-score indicator and were compared with the native prediction from the cellphone. The obtained results presented a maximum F1-score of 100% for the first validation test and 80.7% for the second validation test.

Idioma originalInglés
Título de la publicación alojadaApplied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings
EditoresJuan Carlos Figueroa-García, Mario Duarte-González, Sebastián Jaramillo-Isaza, Alvaro David Orjuela-Cañon, Yesid Díaz-Gutierrez
EditorialSpringer Healthcare
Páginas487-499
Número de páginas13
ISBN (versión impresa)9783030310189
DOI
EstadoPublicada - 1 ene 2019
Evento6th Workshop on Engineering Applications, WEA 2019 - Santa Marta, Colombia
Duración: 16 oct 201918 oct 2019

Serie de la publicación

NombreCommunications in Computer and Information Science
Volumen1052
ISSN (versión impresa)1865-0929
ISSN (versión digital)1865-0937

Conferencia

Conferencia6th Workshop on Engineering Applications, WEA 2019
PaísColombia
CiudadSanta Marta
Período16/10/1918/10/19

Huella dactilar

Activity Recognition
Mobile devices
Classifiers
Mobile Devices
Classifier
Prediction
Experiments
Experiment

Citar esto

Murcia, H., & Triana, J. (2019). A Personal Activity Recognition System Based on Smart Devices. En J. C. Figueroa-García, M. Duarte-González, S. Jaramillo-Isaza, A. D. Orjuela-Cañon, & Y. Díaz-Gutierrez (Eds.), Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings (pp. 487-499). (Communications in Computer and Information Science; Vol. 1052). Springer Healthcare. https://doi.org/10.1007/978-3-030-31019-6_41
Murcia, Harold ; Triana, Juanita. / A Personal Activity Recognition System Based on Smart Devices. Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings. editor / Juan Carlos Figueroa-García ; Mario Duarte-González ; Sebastián Jaramillo-Isaza ; Alvaro David Orjuela-Cañon ; Yesid Díaz-Gutierrez. Springer Healthcare, 2019. pp. 487-499 (Communications in Computer and Information Science).
@inproceedings{232f0d858bdd4fbdb8fadda3d295c0cc,
title = "A Personal Activity Recognition System Based on Smart Devices",
abstract = "With the continuous evolution of technology, mobile devices are becoming more and more important in people’s lives. In the same way, new needs related to the information provided by their users arise, making evident the need to develop systems that take advantage of their daily use. The recognition of personal activity based on the information provided by the last generation mobile devices can easily be considered as an useful tool for many purposes and future applications. This paper presents the use of information provided from two smart devices in different acquisition schemes, assessing conventional supervised classifiers to recognize personal activity by an identification of seven classes. The classifiers were trained with a generated database from eight users and were evaluated in offline mode with other two generated databases. The prediction experiments were qualified by using F1-score indicator and were compared with the native prediction from the cellphone. The obtained results presented a maximum F1-score of 100{\%} for the first validation test and 80.7{\%} for the second validation test.",
keywords = "Activity recognition, Cell phone data, Machine learning, Myo armband, Wearable devices",
author = "Harold Murcia and Juanita Triana",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-31019-6_41",
language = "Ingl{\'e}s",
isbn = "9783030310189",
series = "Communications in Computer and Information Science",
publisher = "Springer Healthcare",
pages = "487--499",
editor = "Figueroa-Garc{\'i}a, {Juan Carlos} and Mario Duarte-Gonz{\'a}lez and Sebasti{\'a}n Jaramillo-Isaza and Orjuela-Ca{\~n}on, {Alvaro David} and Yesid D{\'i}az-Gutierrez",
booktitle = "Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings",
address = "Estados Unidos",

}

Murcia, H & Triana, J 2019, A Personal Activity Recognition System Based on Smart Devices. En JC Figueroa-García, M Duarte-González, S Jaramillo-Isaza, AD Orjuela-Cañon & Y Díaz-Gutierrez (eds.), Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings. Communications in Computer and Information Science, vol. 1052, Springer Healthcare, pp. 487-499, 6th Workshop on Engineering Applications, WEA 2019, Santa Marta, Colombia, 16/10/19. https://doi.org/10.1007/978-3-030-31019-6_41

A Personal Activity Recognition System Based on Smart Devices. / Murcia, Harold; Triana, Juanita.

Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings. ed. / Juan Carlos Figueroa-García; Mario Duarte-González; Sebastián Jaramillo-Isaza; Alvaro David Orjuela-Cañon; Yesid Díaz-Gutierrez. Springer Healthcare, 2019. p. 487-499 (Communications in Computer and Information Science; Vol. 1052).

Resultado de la investigación: Capítulo del libro/informe/acta de congresoContribución a la conferencia

TY - GEN

T1 - A Personal Activity Recognition System Based on Smart Devices

AU - Murcia, Harold

AU - Triana, Juanita

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With the continuous evolution of technology, mobile devices are becoming more and more important in people’s lives. In the same way, new needs related to the information provided by their users arise, making evident the need to develop systems that take advantage of their daily use. The recognition of personal activity based on the information provided by the last generation mobile devices can easily be considered as an useful tool for many purposes and future applications. This paper presents the use of information provided from two smart devices in different acquisition schemes, assessing conventional supervised classifiers to recognize personal activity by an identification of seven classes. The classifiers were trained with a generated database from eight users and were evaluated in offline mode with other two generated databases. The prediction experiments were qualified by using F1-score indicator and were compared with the native prediction from the cellphone. The obtained results presented a maximum F1-score of 100% for the first validation test and 80.7% for the second validation test.

AB - With the continuous evolution of technology, mobile devices are becoming more and more important in people’s lives. In the same way, new needs related to the information provided by their users arise, making evident the need to develop systems that take advantage of their daily use. The recognition of personal activity based on the information provided by the last generation mobile devices can easily be considered as an useful tool for many purposes and future applications. This paper presents the use of information provided from two smart devices in different acquisition schemes, assessing conventional supervised classifiers to recognize personal activity by an identification of seven classes. The classifiers were trained with a generated database from eight users and were evaluated in offline mode with other two generated databases. The prediction experiments were qualified by using F1-score indicator and were compared with the native prediction from the cellphone. The obtained results presented a maximum F1-score of 100% for the first validation test and 80.7% for the second validation test.

KW - Activity recognition

KW - Cell phone data

KW - Machine learning

KW - Myo armband

KW - Wearable devices

UR - http://www.scopus.com/inward/record.url?scp=85075680771&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-31019-6_41

DO - 10.1007/978-3-030-31019-6_41

M3 - Contribución a la conferencia

AN - SCOPUS:85075680771

SN - 9783030310189

T3 - Communications in Computer and Information Science

SP - 487

EP - 499

BT - Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings

A2 - Figueroa-García, Juan Carlos

A2 - Duarte-González, Mario

A2 - Jaramillo-Isaza, Sebastián

A2 - Orjuela-Cañon, Alvaro David

A2 - Díaz-Gutierrez, Yesid

PB - Springer Healthcare

ER -

Murcia H, Triana J. A Personal Activity Recognition System Based on Smart Devices. En Figueroa-García JC, Duarte-González M, Jaramillo-Isaza S, Orjuela-Cañon AD, Díaz-Gutierrez Y, editores, Applied Computer Sciences in Engineering - 6th Workshop on Engineering Applications, WEA 2019, Proceedings. Springer Healthcare. 2019. p. 487-499. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-030-31019-6_41