Abstract
Localization for mobile devices has become important as the basis technology for various ubiquitous computing applications. While GPS is leveraged as the de-facto standard technology in outdoor localization, its accuracy is poor indoors. For twenty years, researchers have tried to investigate indoor localization technology using fingerprinting from received signal strength indicators (RSSIs). With the widespread use of smartphones in the last decade, device dependency (e.g. antenna characteristics) must be considered to avoid performance degradation, while most of the recent localization approaches assume that all the smartphone models have the same device characteristics.
In this paper, we propose a novel feature representation based on multiple RSSIs for compensating performance degradation against smartphone models changes. In contrast to the previous feature representation based on a single RSSI, our new feature representation, which we call Ellipsoid features, employs tuples of pair of RSSIs to eliminate device dependence in the path loss model for wave propagation. In contrast to recent advances in machine learning methods such as domain adaptation, multi-task learning, and semi-supervised learning, our approach requires no additional dataset nor retraining for the new target models. This simplicity would promote ubiquity of indoor localization in the era of smartphones. Moreover, our feature representation works well compared to the state-of-the-arts in feature representations based on multiple RSSIs even when only a small number of access points (APs) are available. Experimental result using smartphone devices including Android Nexus5, Nexus5X, Nexus6P, and Xperia X Performance shows that our approach achieves superior performance over the state-of-the-art indoor localization models as well as robust performance against device changes.
- P. Bahl and V. N. Padmanabhan. RADAR: An in-building RF-based user location and tracking system. In Proc. of INFOCOM2000, volume 2, pages 775--784.Google ScholarCross Ref
- Y.-C. Chen et al. Sensor-assisted Wi-Fi indoor location system for adapting to environmental dynamics. In Proc. of MSWiM2005, pages 118--125. Google ScholarDigital Library
- H. Daumé III. Frustratingly easy domain adaptation. arXiv preprint arXiv:0907.1815, 2009.Google Scholar
- F. Dong et al. A calibration-free localization solution for handling signal strength variance. In Mobile Entity Localization and Tracking in GPS-less Environnments 2009, pages 79--90. Google ScholarDigital Library
- J. Duchi et al. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12(Jul):2121--2159, 2011. Google ScholarDigital Library
- J. Duchi and Y. Singer. Efficient online and batch learning using forward backward splitting. Journal of Machine Learning Research, 10:2899--2934, 2009. Google ScholarDigital Library
- V. Erceg et al. An empirically based path loss model for wireless channels in suburban environments. IEEE Journal on selected areas in communications, 17(7):1205--1211, 1999. Google ScholarDigital Library
- S.-H. Fang and C.-H. Wang. A novel fused positioning feature for handling heterogeneous hardware problem. IEEE Trans. on Communications 2015, 63(7):2713--2723.Google Scholar
- B. Ferris et al. Wifi-slam using gaussian process latent variable models. In Proc. of IJCAI2007, pages 2480--2485. Google ScholarDigital Library
- D. Han et al. Building a practical wi-Fi-based indoor navigation system. IEEE Pervasive Computing, 13(2):72--79, 2014.Google ScholarCross Ref
- S. He and S.-H. G. Chan. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Communications Surveys 8 Tutorials 2016, 18(1):466--490.Google ScholarCross Ref
- G. Hinton. A practical guide to training restricted boltzmann machines. Momentum, 9(1):926, 2010.Google Scholar
- M. K. Hoang et al. Aligning training models with smartphone properties in Wi-Fi fingerprinting based indoor localization. In Proc. of ICASSP2015, 2015.Google Scholar
- A. M. Hossain et al. SSD: A robust RF location fingerprint addressing mobile devices’ heterogeneity. IEEE Trans. on Mobile Computing 2013, 12(1):65--77. Google ScholarDigital Library
- H. Kashima et al. A semi-supervised approach to indoor localization estimation. In IEEE ICDM Data Mining Contest 2007.Google Scholar
- R. Kawajiri et al. Frustratingly simplified deployment in WLAN localization by learning from route annotation. In Proc. of ACML2012, pages 191--204.Google Scholar
- D. Kingma and J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.Google Scholar
- M. B. Kjærgaard and C. V. Munk. Hyperbolic location fingerprinting: A calibration-free solution for handling differences in signal strength (concise contribution). In Proc. of PerCom2008, pages 110--116. Google ScholarDigital Library
- H. Liu et al. Survey of wireless indoor positioning techniques and systems. IEEE Trans. on SMC(C) 2007, 37(6):1067--1080. Google ScholarDigital Library
- M. Sugiyama et al. Direct importance estimation with model selection and its application to covariate shift adaptation. In Proc. of NIPS2008, pages 1433--1440. Google ScholarDigital Library
- J. Xiao et al. A survey on wireless indoor localization from the device perspective. ACM Computing Surveys (CSUR) 2016, 49(2):25. Google ScholarDigital Library
- K. Zhang et al. Covariate shift in Hilbert space: A solution via sorrogate kernels. In Proc. of ICML2013, pages 388--395. Google ScholarDigital Library
- V. W. Zheng et al. Cold-start heterogeneous-device wireless localization. In Proc. of AAAI2016. Google ScholarDigital Library
- V. W. Zheng et al. Transferring multi-device localization models using latent multi-task learning. In Proc. of AAAI2008, pages 1427--1432. Google ScholarDigital Library
Index Terms
- Robust Indoor Localization across Smartphone Models with Ellipsoid Features from Multiple RSSIs
Recommendations
SSD: A Robust RF Location Fingerprint Addressing Mobile Devices' Heterogeneity
Fingerprint-based methods are widely adopted for indoor localization purpose because of their cost-effectiveness compared to other infrastructure-based positioning systems. However, the popular location fingerprint, Received Signal Strength (RSS), is ...
MIMO CSI-based Super-resolution AoA Estimation for Wi-Fi Indoor Localization
ICMLC '20: Proceedings of the 2020 12th International Conference on Machine Learning and ComputingIndoor localization technology has always been a research hotspot in industry and academia. Indoor localization research using channel state information (CSI) of Wi-Fi signals has also received more and more attention. The existing Angle of Arrival (AoA)...
Smartphone based indoor localization using stable access points
Workshops ICDCN '18: Proceedings of the Workshop Program of the 19th International Conference on Distributed Computing and NetworkingIndoor localization, based on Wi-Fi signals, is becoming a popular approach for providing location based services in indoor environment. The challenging task of accurately finding the position of a device depends on prior efforts of fingerprinting. ...
Comments