A scalable indoor localization algorithm based on distance fitting and fingerprint mapping in Wi-Fi environments
- 13 Downloads
With ever-increasing demands on location-based services in indoor environments, indoor localization technologies have attracted considerable attention in both industrial and academic communities. In this work, we propose a scalable indoor localization algorithm (SILA) consisting of two components, namely an annulus-based localization (ABL) component and a local search-based localization (LSL) component, with the objectives of enhancing localization accuracy and reducing online computational overhead. First, the ABL component is developed based on distance fitting using received signal strength indicator (RSSI) of Wi-Fi-based devices. In particular, a distance-RSSI fitting model is proposed based on multinomial function fitting, which is adopted to estimate the distance between the Wi-Fi access point (AP) and the mobile device. On this basis, an annulus construction scheme is proposed to confine the online searching space for possible locations of the mobile device. In addition, based on the observation of signal attenuation characteristics in different physical environments, we design a subarea division scheme, which not only enables the system to choose proper distance-RSSI fitting functions in different areas, but also reduces the overhead of distance fitting. Second, the LSL component is developed based on fingerprint mapping using RSSIs collected at APs. In particular, an RSSI distribution probability model is derived to better map the signal features of an online point (OP) with that of reference points (RPs). Then, an online localization algorithm is proposed, which selects a set of candidate RPs based on Bayes theorem and estimates the final location of an OP using K-nearest-neighbor (KNN) method. Finally, we implement the system prototype and compare the performance of SILA with two representative solutions in the literature. An extensive performance evaluation is conducted in real-world environments, and the results conclusively demonstrate the superiority of SILA in terms of both localization accuracy and system scalability.
KeywordsIndoor localizaiton Fingerprint mapping Distance fitting Wi-Fi signal processing
This work was supported in part by the National Science Foundation of China under Grant Nos. 61872049, 61572088 and 61876025; the Frontier Interdisciplinary Research Funds for the Central Universities (Project No. 2018CDQYJSJ0034); and the Venture & Innovation Support Program for Chongqing Overseas Returnees (Project No. cx2018016).
Compliance with ethical standards
Conflict of interest
All authors declare that they have no conflict of interest.
- 1.Cui W, Zhang L, Li B, Guo J, Meng W, Wang H, Xie L (2017) Received-signal-strength based indoor positioning using random vector functional link network. IEEE Trans Ind Inf PP(99):1–1Google Scholar
- 13.Youssef M (2005) The horus wlan location determination system. In: Proceedings of International Conference on Mobile Systems, Applications, and Services, vol. 14, pp 357–374Google Scholar
- 15.Ferris B, Fox D, Lawrence N (2007) Wifi-slam using gaussian process latent variable models. International joint conference on artifical intelligence, pp 2480–2485Google Scholar
- 16.Bahl P, Padmanabhan VN (2000) Radar: an in-building rf-based user location and tracking system. In: Nineteenth joint conference of the IEEE computer and communications societies, vol. 2, pp 775–784Google Scholar
- 19.Chintalapudi K, Iyer AP, Padmanabhan VN (2010) Indoor localization without the pain. In: Sixteenth international conference on mobile computing and networking, vol. 49, pp. 173–184Google Scholar
- 20.Farid Z, Nordin R, Ismail M (2013) Recent advances in wireless indoor localization techniques and system. J Comput Netw Commun 2013:185138Google Scholar
- 21.Peng Y, Fan W, Dong X, Zhang X (2017) An iterative weighted KNN (IW-KNN) based indoor localization method in bluetooth low energy (BLE) environment. In: Ubiquitous intelligence computing, pp 794–800Google Scholar
- 23.Yin Z, Wu C (2017) Gain without pain: accurate wifi-based localization using fingerprint spatial gradient. Proc ACM Interact Mob Wearable Ubiquitous Technol 1(2):29Google Scholar
- 24.Katircioglu O, Isel H, Ceylan O, Taraktas F, Yagci HB (2012) Comparing ray tracing, free space path loss and logarithmic distance path loss models in success of indoor localization with RSSI. Telecommunications Forum, pp. 313–316Google Scholar
- 25.Bholowalia P, Kumar A (2014) Ebk-means: a clustering technique based on elbow method and k-means in WSN. Int J Comput Appl 105(9):17–24Google Scholar