Abstract
Today sensors and wearable technologies are gaining popularity, with people increasingly surrounded by “smart” objects. Machine learning is used with great success in wearable devices and sensors in several real-world applications. In this paper we address the challenges of context recognition on low energy and self-sustainable wearable devices. We present an energy efficient multi-sensor context recognition system based on decision tree to classify 3 different indoor or outdoor contexts. An ultra-low power smart watch provided with a micro-power camera, microphone, accelerometer, and temperature sensors has been used to real field tests. Experimental results demonstrate both high mean accuracy of 81.5 % (up to 89 % peak) and low energy consumption (only 2.2 mJ for single classification) of the solution, and the possibility to achieve a self-sustainable system in combination with body worn energy harvesters.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ghasemzadeh, H., Jafari, R.: Ultra low-power signal processing in wearable monitoring systems: a tiered screening architecture with optimal bit resolution. ACM Trans. Embed. Comput. Syst. (TECS) 13, 9 (2013)
Kahn, J., Yuce, M.R., Bulger, G., Harding, B.: Wireless Body Area Network (WBAN) design techniques and performance evaluation. J. Med. Syst. 36(3), 1441–1457 (2012)
Hung, K., et al.: Ubiquitous health monitoring: integration of wearable sensors, novel sensing techniques, and body sensor networks. In: Adibi, S. (ed.) Mobile Health, pp. 319–342. Springer, Heidelberg (2015)
Pejovic, V., Musolesi, M.: Anticipatory mobile computing: a survey of the state of the art and research challenges. ACM Comput. Surv. (CSUR) 47(3), 47 (2015)
Perera, C., et al.: Context aware computing for the Internet of Things: a survey. IEEE Commun. Surv. Tutor. 16(1), 414–454 (2014)
Anjum, A., Ilyas, M.U.: Activity recognition using smartphone sensors. In: IEEE Consumer Communications and Networking Conference (CCNC) (2013)
Sharma, S., et al.: Machine learning techniques for data mining: a survey. In: IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) (2013)
Govindaraju, V., Rao, C.: Machine Learning: Theory and Applications. Elsevier, New York (2013)
Azizyan, M., et al.: SurroundSense: mobile phone localization via ambience fingerprinting. In: Mobicom, pp. 261–272 (2009)
Kerhet, A., et al.: Distributed video surveillance using hardware-friendly sparse large margin classifiers. In: IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 87–92 (2007)
Chon, Y., et al.: Mobility prediction-based smartphone energy optimization for everyday location monitoring. In: SenSys 2011, pp. 82–95 (2011)
Lara, O.D., Labrador, M.A.: A survey on human activity recognition using wearable sensors. IEEE Commun. Surv. Tutor. 15(3), 1192–1209 (2013)
Gokgoz, E., Subasi, A.: Comparison of decision tree algorithms for EMG signal classification using DWT. Biomed. Signal Process. Control 18, 138–144 (2015)
Silva, J., et al.: Human activity classification with inertial sensors. In: PHealth: International Conference on Wearable Micro and Nano Technologies for Personalized Health, vol. 200, p. 101 (2014)
Weddell, A.S., et al.: A survey of multi-source energy harvesting systems. In: Conference on Design, Automation and Test in Europe (DATE), pp. 905–908 (2013)
Maurer, U., et al.: eWatch: a wearable sensor and notification platform. In: International Workshop on Wearable and Implantable Body Sensor Networks (BSN), p. 145 (2006)
Porzi, L., et al.: A smart watch-based gesture recognition system for assisting people with visual impairments. In: ACM International Workshop on Interactive Multimedia on Mobile & Portable Devices (IMMPD), pp. 19–24 (2013)
Maekawa, T., Yanagisawa, Y., Kishino, Y., Ishiguro, K., Kamei, K., Sakurai, Y., Okadome, T.: Object-based activity recognition with heterogeneous sensors on wrist. In: Kay, J., Lukowicz, P., Tokuda, H., Olivier, P., Krüger, A. (eds.) Pervasive 2012. LNCS, vol. 7319, pp. 246–264. Springer, Heidelberg (2010). doi:10.1007/978-3-642-12654-3_15
Magno, M., et al.: InfiniTime: a multi-sensor energy neutral wearable bracelet. In: International Green Computing Conference (IGCC) (2014)
Seong, K.E., et al.: Self M2M based wearable watch platform for collecting personal activity in real-time. In: IEEE Conference on Big Data and Smart Computing (BIGCOMP), pp. 286–290 (2014)
Zhu, Z., et al.: Fusing on-body sensing with local and temporal cues for daily activity recognition. In: ICST International Conference on Body Area Networks, pp. 83–89 (2014)
Centeye, Inc., Centeye Stonyman/Haskbill silicon documentation (2013)
Acknowledgments
This work was supported by the SCOPES SNF project (IZ74Z0_160481).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Magno, M., Cavigelli, L., Andri, R., Benini, L. (2016). Ultra-Low Power Context Recognition Fusing Sensor Data from an Energy-Neutral Smart Watch. In: Mandler, B., et al. Internet of Things. IoT Infrastructures. IoT360 2015. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 170. Springer, Cham. https://doi.org/10.1007/978-3-319-47075-7_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-47075-7_38
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-47074-0
Online ISBN: 978-3-319-47075-7
eBook Packages: Computer ScienceComputer Science (R0)