Abstract
The information about a person’s activity, as a special type of contextual information, can be used for a multitude of applications. Thus, activity detection is a focus in research. For activity detection, usually measured sensor data are processed and matched to known activities. Unfortunately, measured sensor data can be inconsistent for the same activity. Depending on the device orientation and in which direction of compass the user is heading (while carrying out an activity) the sensor data changes. As a result, expected values on one sensor axis appear on another one and it is challenging for a pre-generated activity detection model to match the sensor data to the activity. However, the intuitive solution seems to be easy: focus on the user. Regardless of the device orientation or the cardinal direction, the activity never change for the user. In this paper, we present an approach to focus on the user in activity detection. We convert sensor data into a representation relative to the user. Thus, the sensor data stay consistent regardless of the device orientation or the cardinal direction. We show that by using the focus on the user approach the detection rates increase up to 21.7%. Also, the detection is more reliable (lower standard deviation). We prove the reliable activity detection for different device orientations, cardinal directions, types of algorithms, sensor sets, activities, and sensor positions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Weka 3 - Data Mining with Open Source Machine Learning Software in Java (2016). http://www.cs.waikato.ac.nz/ml/weka/index.html
Ali, A.S., Georgy, J., Bruce Wright, D.: Estimation of heading misalignment between a pedestrian and a wearable device. In: International Conference on Localization and GNSS (ICL-GNSS), pp. 1–6, June 2014
Borazio, M., Van Laerhoven, K.: Using time use with mobile sensor data: a road to practical mobile activity recognition? In: International Conference on Mobile and Ubiquitous Multimedia, pp. 1–10. ACM, Luleå (2013)
Dernbach, S., Das, B., Krishnan, N.C., Thomas, B., Cook, D.: Simple and complex activity recognition through smart phones. In: Intelligent Environments (IE), pp. 214–221, June 2012
Henpraserttae, A., Thiemjarus, S., Marukatat, S.: Accurate activity recognition using a mobile phone regardless of device orientation and location. In: International Conference on Body Sensor Networks (BSN), pp. 41–46, May 2011
Ichikawa, F., Chipchase, J., Grignani, R.: Where’s the phone? A study of mobile phone location in public spaces. In: Mobile Technology, Applications and Systems, pp. 1–8. IEEE (2005)
Kunze, K., Lukowicz, P., Partridge, K., Begole, B.: Which way am I facing: inferring horizontal device orientation from an accelerometer signal. In: International Symposium on Wearable Computers (ISWC), pp. 149–150. IEEE, Linz, September 2009
Kusber, R., David, K., Klein, B.N.: A novel future internet smart grid application for energy management in offices. In: Future Network and Mobile Summit (FutureNetworkSummit), pp. 1–10, July 2013
Kusber, R., Memon, A.Q., Kroll, D., David, K.: Direction detection of users independent of smartphone orientations. In: Vehicular Technology Conference (VTC Fall), pp. 1–6. IEEE, September 2015
Lau, S.L.: Comparison of orientation-independent-based-independent-based movement recognition system using classification algorithms. In: IEEE Symposium on Wireless Technology and Applications (ISWTA), pp. 322–326, September 2013
Lau, S.L., Konig, I., David, K., Parandian, B., Carius-Dussel, C., Schultz, M.: Supporting patient monitoring using activity recognition with a smartphone. In: International Symposium on Wireless Communication Systems (ISWCS), pp. 810–814 (2010)
Mizell, D.: Using gravity to estimate accelerometer orientation. In: International Symposium on Wearable Computers (ISWC), p. 252. IEEE (2003)
Scholl, P., van Laerhoven, K.: A feasibility study of wrist-worn accelerometer based detection of smoking habits. In: Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS), pp. 886–891, July 2012
Shoaib, M., Bosch, S., Incel, O., Scholten, H., Havinga, P.: A survey of online activity recognition using mobile phones. Sensors 15(1), 2059–2085 (2015)
Shoaib, M., Scholten, H., Havinga, P.: Towards physical activity recognition using smartphone sensors. In: IEEE Conference on Ubiquitous Intelligence and Computing and Conference on Autonomic and Trusted Computing (UIC/ATC), pp. 80–87, December 2013
Thiemjarus, S.: A device-orientation independent method for activity recognition. In: Body Sensor Networks (BSN), pp. 19–23. IEEE, June 2010
Ustev, Y.E., Durmaz Incel, O., Ersoy, C.: User, device and orientation independent human activity recognition on mobile phones: challenges and a proposal. In: Pervasive and Ubiquitous Computing Adjunct Publication, pp. 1427–1436. ACM (2013)
Yang, J.: Toward physical activity diary: motion recognition using simple acceleration features with mobile phones. In: Proceedings of 1st International Workshop on Interactive Multimedia for Consumer Electronics. ACM, Beijing (2009)
Acknowledgments
This work has been [co-]funded by the Social Link Project within the Loewe Program of Excellence in Research, Hesse, Germany.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Jahn, A., Bachmann, M., Wenzel, P., David, K. (2017). Focus on the User: A User Relative Coordinate System for Activity Detection. In: Brézillon, P., Turner, R., Penco, C. (eds) Modeling and Using Context. CONTEXT 2017. Lecture Notes in Computer Science(), vol 10257. Springer, Cham. https://doi.org/10.1007/978-3-319-57837-8_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-57837-8_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-57836-1
Online ISBN: 978-3-319-57837-8
eBook Packages: Computer ScienceComputer Science (R0)