TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Activity classification using realistic data from wearable sensors

Tutkimustuotosvertaisarvioitu

Standard

Activity classification using realistic data from wearable sensors. / Parkka, J; Ermes, M; Korpipää, P; Mäntyjärvi, J; Peltola, J; Korhonen, I.

julkaisussa: IEEE Transactions on Information Technology in Biomedicine, Vuosikerta 10, Nro 1, 01.2006, s. 119-128.

Tutkimustuotosvertaisarvioitu

Harvard

Parkka, J, Ermes, M, Korpipää, P, Mäntyjärvi, J, Peltola, J & Korhonen, I 2006, 'Activity classification using realistic data from wearable sensors', IEEE Transactions on Information Technology in Biomedicine, Vuosikerta. 10, Nro 1, Sivut 119-128. https://doi.org/10.1109/TITB.2005.856863

APA

Parkka, J., Ermes, M., Korpipää, P., Mäntyjärvi, J., Peltola, J., & Korhonen, I. (2006). Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine, 10(1), 119-128. https://doi.org/10.1109/TITB.2005.856863

Vancouver

Parkka J, Ermes M, Korpipää P, Mäntyjärvi J, Peltola J, Korhonen I. Activity classification using realistic data from wearable sensors. IEEE Transactions on Information Technology in Biomedicine. 2006 tammi;10(1):119-128. https://doi.org/10.1109/TITB.2005.856863

Author

Parkka, J ; Ermes, M ; Korpipää, P ; Mäntyjärvi, J ; Peltola, J ; Korhonen, I. / Activity classification using realistic data from wearable sensors. Julkaisussa: IEEE Transactions on Information Technology in Biomedicine. 2006 ; Vuosikerta 10, Nro 1. Sivut 119-128.

Bibtex - Lataa

@article{6ee91ecbce544dcbb8e65e7f835b25ca,
title = "Activity classification using realistic data from wearable sensors",
abstract = "Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree,, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97{\%} for custom decision tree classifier, from 56 to 97{\%} for automatically generated decision tree, and from 22 to 96{\%} for artificial neural network. Total classification accuracy is 82{\%} for custom decision tree classifier, 86{\%} for automatically generated decision tree, and 82{\%} for artificial neural network.",
keywords = "activity classification, context awareness, physical activity, wearable sensors, PHYSICAL-ACTIVITY, ACCELEROMETRY, PREVENTION, VALIDATION, CONTEXT, WALKING, POSTURE, MOTION, WOMEN",
author = "J Parkka and M Ermes and P Korpip{\"a}{\"a} and J M{\"a}ntyj{\"a}rvi and J Peltola and I Korhonen",
year = "2006",
month = "1",
doi = "10.1109/TITB.2005.856863",
language = "English",
volume = "10",
pages = "119--128",
journal = "IEEE Transactions on Information Technology in Biomedicine",
issn = "1089-7771",
publisher = "Institute of Electrical and Electronics Engineers",
number = "1",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Activity classification using realistic data from wearable sensors

AU - Parkka, J

AU - Ermes, M

AU - Korpipää, P

AU - Mäntyjärvi, J

AU - Peltola, J

AU - Korhonen, I

PY - 2006/1

Y1 - 2006/1

N2 - Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree,, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network.

AB - Automatic classification of everyday activities can be used for promotion of health-enhancing physical activities and a healthier lifestyle. In this paper, methods used for classification of everyday activities like walking, running, and cycling are described. The aim of the study was to find out how to recognize activities, which sensors are useful and what kind of signal processing and classification is required. A large and realistic data library of sensor data was collected. Sixteen test persons took part in the data collection, resulting in approximately 31 h of annotated, 35-channel data recorded in an everyday environment. The test persons carried a set of wearable sensors while performing several activities during the 2-h measurement session. Classification results of three classifiers are shown: custom decision tree, automatically generated decision tree,, and artificial neural network. The classification accuracies using leave-one-subject-out cross validation range from 58 to 97% for custom decision tree classifier, from 56 to 97% for automatically generated decision tree, and from 22 to 96% for artificial neural network. Total classification accuracy is 82% for custom decision tree classifier, 86% for automatically generated decision tree, and 82% for artificial neural network.

KW - activity classification

KW - context awareness

KW - physical activity

KW - wearable sensors

KW - PHYSICAL-ACTIVITY

KW - ACCELEROMETRY

KW - PREVENTION

KW - VALIDATION

KW - CONTEXT

KW - WALKING

KW - POSTURE

KW - MOTION

KW - WOMEN

U2 - 10.1109/TITB.2005.856863

DO - 10.1109/TITB.2005.856863

M3 - Article

VL - 10

SP - 119

EP - 128

JO - IEEE Transactions on Information Technology in Biomedicine

JF - IEEE Transactions on Information Technology in Biomedicine

SN - 1089-7771

IS - 1

ER -