TY - GEN
T1 - Opportunistic hierarchical classification for power optimization in wearable movement monitoring systems
AU - Fraternali, Francesco
AU - Rofouei, Mahsan
AU - Alshurafa, Nabil
AU - Ghasemzadeh, Hassan
AU - Benini, Luca
AU - Sarrafzadeh, Majid
PY - 2012
Y1 - 2012
N2 - Patient monitoring systems are becoming increasingly important in accurately diagnosing and treating growing worldwide chronic conditions especially the obesity epidemic. The ubiquitous nature of wearable sensors, such as the readily available embedded accelerometers in smart phones, provides physicians with an opportunity to remotely monitor their patient's daily activity. There have been several developments in the area of activity recognition using wearable sensors. However, due to power constraints, resource efficient algorithms are necessary in order to perform accurate realtime activity recognition while consuming minimal energy. In this paper, we present a two-tier architecture for optimizing power consumption in such systems. While the first tier relies on a hierarchical classification approach, the second one manages the activation and deactivation of the classification system. We demonstrate this using a series of binary Support Vector Machine classifiers. The proposed approach, however, is classifier independent. Experimenting with subjects performing different daily activities such as walking, going upstairs and down-stairs, standing and sitting, our approach achieves a power savings of 87%, while maintaining 92% classification accuracy.
AB - Patient monitoring systems are becoming increasingly important in accurately diagnosing and treating growing worldwide chronic conditions especially the obesity epidemic. The ubiquitous nature of wearable sensors, such as the readily available embedded accelerometers in smart phones, provides physicians with an opportunity to remotely monitor their patient's daily activity. There have been several developments in the area of activity recognition using wearable sensors. However, due to power constraints, resource efficient algorithms are necessary in order to perform accurate realtime activity recognition while consuming minimal energy. In this paper, we present a two-tier architecture for optimizing power consumption in such systems. While the first tier relies on a hierarchical classification approach, the second one manages the activation and deactivation of the classification system. We demonstrate this using a series of binary Support Vector Machine classifiers. The proposed approach, however, is classifier independent. Experimenting with subjects performing different daily activities such as walking, going upstairs and down-stairs, standing and sitting, our approach achieves a power savings of 87%, while maintaining 92% classification accuracy.
KW - Accelerometer
KW - Activity Monitoring
KW - Hierarchical Classifier
KW - Mobile Phone
KW - Power Optimization
KW - Support Vector Machines
UR - http://www.scopus.com/inward/record.url?scp=84871558065&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84871558065&partnerID=8YFLogxK
U2 - 10.1109/SIES.2012.6356575
DO - 10.1109/SIES.2012.6356575
M3 - Conference contribution
AN - SCOPUS:84871558065
SN - 9781467326841
T3 - 7th IEEE International Symposium on Industrial Embedded Systems, SIES 2012 - Conference Proceedings
SP - 102
EP - 111
BT - 7th IEEE International Symposium on Industrial Embedded Systems, SIES 2012 - Conference Proceedings
T2 - 7th IEEE International Symposium on Industrial Embedded Systems, SIES 2012
Y2 - 20 June 2012 through 22 June 2012
ER -