Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

9 Citations (Scopus)

Abstract

Long-term monitoring of health is essential in many chronic conditions, but automatic monitoring is not yet utilized routinely with mental stress. Accelerometers, magnetometers, ECG, respiratory effort, skin temperature and pulse oximetry were used with 12 health volunteers in this study for monitoring 1) heavy mental load, 2) normal mental load, 3) walking, 4) running and 5) lying. Heavy mental load consisted of a 20-min IQ test and normal mental load was represented by reading a comic book. Automatic feature selection using sequential forward search was used to select the best features for classification of the five activities. Normalized heart rate, utilizing activity context information was found to be the most powerful feature for discriminating heavy mental load from normal. Classification accuracy for all 5 activities was 89% with a custom decision tree and with a k-nearest neighbor classifier and 85% with an artificial neural network.
Original languageEnglish
Title of host publication10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010
PublisherIEEE Institute of Electrical and Electronic Engineers
Pages1-5
ISBN (Print)978-1-4244-6560-6
DOIs
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
Event10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010 - Corfu, Greece
Duration: 2 Nov 20105 Nov 2010

Conference

Conference10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010
Abbreviated titleITAB 2010
CountryGreece
CityCorfu
Period2/11/105/11/10

Fingerprint

Feature extraction
Monitoring
Health
Magnetometers
Decision trees
Electrocardiography
Accelerometers
Skin
Classifiers
Neural networks
Wearable sensors
Temperature

Cite this

Pärkkä, J., Ermes, M., & van Gils, M. (2010). Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors. In 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010 (pp. 1-5). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/ITAB.2010.5687813
Pärkkä, Juha ; Ermes, Miikka ; van Gils, Mark. / Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors. 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010. IEEE Institute of Electrical and Electronic Engineers , 2010. pp. 1-5
@inproceedings{db366868d2a14b4aa5f8ce8a6b878c7d,
title = "Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors",
abstract = "Long-term monitoring of health is essential in many chronic conditions, but automatic monitoring is not yet utilized routinely with mental stress. Accelerometers, magnetometers, ECG, respiratory effort, skin temperature and pulse oximetry were used with 12 health volunteers in this study for monitoring 1) heavy mental load, 2) normal mental load, 3) walking, 4) running and 5) lying. Heavy mental load consisted of a 20-min IQ test and normal mental load was represented by reading a comic book. Automatic feature selection using sequential forward search was used to select the best features for classification of the five activities. Normalized heart rate, utilizing activity context information was found to be the most powerful feature for discriminating heavy mental load from normal. Classification accuracy for all 5 activities was 89{\%} with a custom decision tree and with a k-nearest neighbor classifier and 85{\%} with an artificial neural network.",
author = "Juha P{\"a}rkk{\"a} and Miikka Ermes and {van Gils}, Mark",
note = "Project code: 18982",
year = "2010",
doi = "10.1109/ITAB.2010.5687813",
language = "English",
isbn = "978-1-4244-6560-6",
pages = "1--5",
booktitle = "10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Pärkkä, J, Ermes, M & van Gils, M 2010, Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors. in 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010. IEEE Institute of Electrical and Electronic Engineers , pp. 1-5, 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010, Corfu, Greece, 2/11/10. https://doi.org/10.1109/ITAB.2010.5687813

Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors. / Pärkkä, Juha; Ermes, Miikka; van Gils, Mark.

10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010. IEEE Institute of Electrical and Electronic Engineers , 2010. p. 1-5.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors

AU - Pärkkä, Juha

AU - Ermes, Miikka

AU - van Gils, Mark

N1 - Project code: 18982

PY - 2010

Y1 - 2010

N2 - Long-term monitoring of health is essential in many chronic conditions, but automatic monitoring is not yet utilized routinely with mental stress. Accelerometers, magnetometers, ECG, respiratory effort, skin temperature and pulse oximetry were used with 12 health volunteers in this study for monitoring 1) heavy mental load, 2) normal mental load, 3) walking, 4) running and 5) lying. Heavy mental load consisted of a 20-min IQ test and normal mental load was represented by reading a comic book. Automatic feature selection using sequential forward search was used to select the best features for classification of the five activities. Normalized heart rate, utilizing activity context information was found to be the most powerful feature for discriminating heavy mental load from normal. Classification accuracy for all 5 activities was 89% with a custom decision tree and with a k-nearest neighbor classifier and 85% with an artificial neural network.

AB - Long-term monitoring of health is essential in many chronic conditions, but automatic monitoring is not yet utilized routinely with mental stress. Accelerometers, magnetometers, ECG, respiratory effort, skin temperature and pulse oximetry were used with 12 health volunteers in this study for monitoring 1) heavy mental load, 2) normal mental load, 3) walking, 4) running and 5) lying. Heavy mental load consisted of a 20-min IQ test and normal mental load was represented by reading a comic book. Automatic feature selection using sequential forward search was used to select the best features for classification of the five activities. Normalized heart rate, utilizing activity context information was found to be the most powerful feature for discriminating heavy mental load from normal. Classification accuracy for all 5 activities was 89% with a custom decision tree and with a k-nearest neighbor classifier and 85% with an artificial neural network.

U2 - 10.1109/ITAB.2010.5687813

DO - 10.1109/ITAB.2010.5687813

M3 - Conference article in proceedings

SN - 978-1-4244-6560-6

SP - 1

EP - 5

BT - 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Pärkkä J, Ermes M, van Gils M. Automatic Feature Selection and Classification of Physical and Mental Load using Data from Wearable Sensors. In 10th IEEE International Conference on Information Technology and Applications in Biomedicine, ITAB 2010. Corfu, Greece, 2 - 5 Nov. 2010. IEEE Institute of Electrical and Electronic Engineers . 2010. p. 1-5 https://doi.org/10.1109/ITAB.2010.5687813