Abstract
In recent years indoor localization technology has been regarded as a promising technology. To improve localization accuracy, Inertial Measurement Units (IMUs) embedded in smartphones have been utilized to find landmarks such as corridor, elevator and stairs. This chapter proposes an activity recognition method to identify the landmarks mentioned before. The activity recognition method first determines whether it’s elevator pattern. And then it uses C4.5 algorithm to build a decision tree model to classify walking and taking the stairs patterns. This chapter also discusses the impact of different AR orders and different sample rates to the classifier performance. At last it introduces a real-time activity recognition system based on previous research. The system can recognize activities in about 2 s. In addition, activity recognition and dead reckoning can be used for assisting localization. Compared with WiFi localization technology, this method can evidently save energy at a cost of little localization error.
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
Similar content being viewed by others
References
Akaike (1994) A new look at the statistical model indentification, IEEE Trans Autorn Control AC19:716–723
Alvina A, Muhammad U (2013) Activity recognition using smartphone sensors. In: First workshop on people centric sensing and communications, pp 914–919. doi:10.1109/CCNC.2013.6488584
Bao L, Intille S (2004)Activity recognition from user-annotated acceleration data, in Pro. Pervasive 1–17. doi:10.1007/978-3-540-24646-6_1
Bao L, Intille SS (2004b) Activity recognition from user-annotated acceleration data, pervasive. LNCS 300:1–17. doi:10.1007/978-3-540-24646-6_1
Ermes M, Parkka J, Mantyjarvi J, Korhonen I (2008) Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions. IEEE Trans Inf Technol Biomed 12(1):20–26. doi:10.1109/TITB.2007.899496
He Z (2010) Activity recognition from accelerometer signals based on Wavelet-AR model. In: IEEE international conference on progress in informatics and computing (PIC), pp 499–502. doi: 10.1109/PIC.2010.5687572
Kay SM (1988) Modern spectral estimation: theory and application. Prentice Hall, Englewood Cliffs
Khan AM, Lee Y-K, Lee SY,. Kim T-S (2010) Human activity recognition via an accelerometer-enabled-smartphone using kernel discriminant analysis. Future Inf Technol 1–6. doi:10.1109/FUTURETECH.2010.5482729
Khan AM, Lee Y-K, Lee SY, Kim T-S (2010b) A triacial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. IEEE Trans Inf Technol Biomed 14(5):1166–1172. doi:10.1109/TITB.2010.2051955
Kwapisz JR, Weiss GM, Mooew SA (2010) Activity recognition using cell phone acclerometers. In: ACM SIGKDD, vol 12(2), pp 74–82. doi:10.1145/1964897.1964918
Maurer U, Smailagic A, Siewiorek D, Deisher M (2006) Activity recognition and monitoring using multiple sensors on different body positions. In: Proceedings of the international workshop wearable implantable body sensor network, pp 113–116. doi:10.1109/BSN.2006.6
Minnen D, Starner T, Ward J, Lukowicz P, Troester G (2005) Recognizing and discovering human actions from on-body sensor data. In: IEEE international conference on multimedia and Expo, pp 1545–1548. doi:10.1109/ICME.2005.1521728
Wang H, Souvik S, Ahmed E, Moustafa F, Moustafa Y, Romit RC (2012) No need to war-drive: unsupervised indoor localization. In: MobiSys ‘12 proceedings of the 10th international conference on mobile systems, applications, and services, pp 197–210. doi:10.1145/2307636.2307655
Wireless Sensor Data Mining (WISDM) Project. Fordham University, Department of Computer and Information Sci-ence, http://storm.cis.fordham.edu/~gweiss/wisdm/
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China (61374214, 61070109), the Major Projects of Ministry of Industry and Information Technology (2014ZX03006003-002), the National High Technology Research and Development Program of China (2013AA12A201), the Electronic Information Industry Development Fund Project of Information Industry Department (2012-380) and Science and Technology Program of Shenzhen City (JSA201006040186A055).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Wang, F., Luo, H., Li, Z., Zhao, F., Li, D. (2014). Activity-Based Smartphone-Oriented Landmark Identification for Localization. In: Liu, C. (eds) Principle and Application Progress in Location-Based Services. Lecture Notes in Geoinformation and Cartography. Springer, Cham. https://doi.org/10.1007/978-3-319-04028-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-04028-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04027-1
Online ISBN: 978-3-319-04028-8
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)