Energy efficient activity recognition based on low resolution accelerometer in smart phones

Authors:
Yunji Liang;Xingshe Zhou;Zhiwen Yu;Bin Guo;Yue Yang
Affiliations:
School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China;School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China;School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China;School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China;School of Computer Science, Northwestern Polytechnical University, Xi'an, Shaanxi, China
Venue:
GPC'12 Proceedings of the 7th international conference on Advances in Grid and Pervasive Computing
Year:
2012

Citing 12
Cited 0

Activity Recognition and Monitoring Using Multiple Sensors on Different Body Positions

BSN '06 Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks
Mixed reality participants in smart meeting rooms and smart home environments

Personal and Ubiquitous Computing
An activity recognition system for mobile phones

Mobile Networks and Applications
A framework of energy efficient mobile sensing for automatic user state recognition

Proceedings of the 7th international conference on Mobile systems, applications, and services
Activity recognition from accelerometer data

IAAI'05 Proceedings of the 17th conference on Innovative applications of artificial intelligence - Volume 3
Human Activity Recognition and Pattern Discovery

IEEE Pervasive Computing
Recognition of hand movements using wearable accelerometers

Journal of Ambient Intelligence and Smart Environments
Activity recognition from on-body sensors: accuracy-power trade-off by dynamic sensor selection

EWSN'08 Proceedings of the 5th European conference on Wireless sensor networks
A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer

IEEE Transactions on Information Technology in Biomedicine
Activity recognition using cell phone accelerometers

ACM SIGKDD Explorations Newsletter
A Pattern Mining Approach to Sensor-Based Human Activity Recognition

IEEE Transactions on Knowledge and Data Engineering
Learning to Infer the Status of Heavy-Duty Sensors for Energy-Efficient Context-Sensing

ACM Transactions on Intelligent Systems and Technology (TIST)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Smart phone is becoming an ideal platform for continuous and transparent sensing with lots of built-in sensors. Activity recognition on smart phones is still a challenge due to the constraints of resources, such as battery lifetime, computational workload. Keeping in view the demand of low energy activity recognition for mobile devices, we propose an energy-efficient method to recognize user activities based on a single low resolution tri-axial accelerometer in smart phones. This paper presents a hierarchical recognition scheme with variable step size, which reduces the cost of time consuming frequency domain features for low energy consumption and adjusts the size of sliding window to improve the recognition accuracy. Experimental results demonstrate the effectiveness of the proposed algorithm with more than 85% recognition accuracy for 11 activities and 3.2 hours extended battery life for mobile phones.