indoor.locky: LAN 1 1 LAN LAN LAN indoor.locky UGC(User Generated Content) LAN LAN Web LAN API indoor.locky: Wireless LAN Information Platform for Indoor Location Estimation Katsuhiko Kaji 1 and Nobuo Kawaguchi 1 Recently, mobile devices become common and wireless LAN access points are installed to various buildings so that location estimation using wireless LAN begins to making a mark. In the open air, several projects for location estimation are already exist. In contrast, there is no general platform for indoor location estimation. In this paper, we describe a location estimation platform based on wireless LAN named indoor.locky. This platform adopts UGC (User Generated Content) approach to correct indoor wireless LAN infromation from public users. Indoor.Locky consists of two modules. One is indoor.locky Web Service to manage the wireless LAN information posted by users. The other is indoor.locky Client to estimate current location. Any browsers and applications are able to treat current location through the client. 1. GPS GPS LAN RF IMES 1),3),5),6),8),10),15),18),19) LAN LAN 5-10 19) LAN 15),21) GPS LAN LAN UGC(User Generated Content) UGC 9),15),20),21) LAN LAN Web UGC LAN LAN Web 1 Graduate School of Engineering, Nagoya University 1234 c 2010 Information Processing Society of Japan
LAN LAN indoor.locky 2. 2),4),7),14) Foursquare 2010 8 250 1 10 Place Lab 5) Loki 11) Place Engine 21) Locky.jp 15) OpenStreetMap 9) Place Lab LAN GSM( ) Bluetooth Loki Place Engine Locky.jp LAN 1 OpenStreetMap GPS UGC DB Locky.jp 5 10 LAN 80 UGC LAN DB 15) 21) GPS LAN DB LAN 15),21) 16) Place Engine API Place Engine PC Place Engine W3C Web Geolocation API 13) Mozilla Google Chrome Opera, Mobile Safari Geolocation API 2 API twitter 12) tweet LAN 3 LAN LAN 3. indoor.locky LAN indoor.locky LAN UGC LAN Web Web (PC iphone/ipad ) 1 PlaceEngine 2010 6 LAN 2 Mozilla Opera Loki 1235 c 2010 Information Processing Society of Japan
(GMM) indoor.locky Web A LAN LAN LAN Google Maps Indoor.Locky LAN C API B Fig. 2 2 Registration form of building. 1 indoor.locky Fig. 1 Usage flow of indoor.locky platform. LAN ( 1 1 5) ( 1 A C) Web ( 1-1) ( 1-2) LAN ( 1-3) Web ( 1-4) Web LAN DB ( 1-5) LAN ( 1-A) LAN ( 1-B) API ( 1-C) LAN 3.1 Web 2 GoogleMaps CAD 1 1 1 3 2 2 1 1236 c 2010 Information Processing Society of Japan
2 2 3 1 Fig. 3 An example of floor map. Phisical relationships of these floors are not consistent. GoogleMaps () GoogleMaps Fig. 5 5 Mapping between a floor area and geographical coordinates. 1 4 2 Fig. 4 An example of floor map. The floors are as three-dimensionaly. 3 2 4 3 5 2 ( ) () GoogleMaps ( 5 ) 1 3.2 LAN GPS 1 1 ( ) 3 1 17) CAD 1237 c 2010 Information Processing Society of Japan
GMM 6 LAN (ipad) Fig. 6 Indoor WLAN observation client. 7 GMM LAN Fig. 7 WLAN information model using GMM. LAN 5),15),21) GPS LAN LAN LAN ( 6) 3.3 LAN indoor.locky Web Web GMM(Gaussian Mixture Model) 19) Web LAN GMM 3 1 2 GMM LAN 5% 3 7 LAN LAN LAN DB 3.4 Web GMM Particle Filter 19) 5-10 1 ( 8) API (Particle ) (Particle ) () ( ) 1 1238 c 2010 Information Processing Society of Japan
Fig. 8 4. Particle Filter 8 Particle Filter A scene of indoor location estimation using particle filter. LAN indoor.locky LAN UGC 1) Bahl, P., and Padmanabhan, V. N.: RADAR: An In-Building RF-based User Location and Tracking System, Proceedings of IEEE Infocom 2000, pp.775 784 (2000). 2) Booyah: MyTown, http://www.booyah.com/. 3) Cheverst, K., Davies, N., Mitchell, K., and Friday, A.: Experiences of developing and deploying a context-aware tourist guide: the GUIDE project, Proceedings of the Sixth of an Annual International Conferences on Mobile Computing and Networking (MOBICOM 2000), pp.20 31 (2000). 4) foursquare: http://foursquare.com/. 5) LaMarca, A., Chawathe, Y., Consolvo, S., et al.: Place Lab: Device Positioning Using Radio Beacons in the Wild, Third International Conference PERVASIVE 2005, Lecture Notes in Computer Science, Vol.LNCS3468, pp.116 133 (2005). 6) Lim, H., Kung, L.C., Hou, J.C., and Luo, H.: Zero-configuration indoor localization over IEEE 802.11 wireless infrastructure, Wireless Networks, Springer Netherlands, Vol.16, No.2, pp.405 420 (2010). 7) livedoor: http://tou.ch/. 8) Manandhar, D., Kawaguchi, S., Uchida, M., et al.: IMES for Mobile Users Social Implementation and Experiments based on Existing Cellular Phones for Seamless Positioning, International Symposium on GPS/GNSS (2008). 9) OpenStreetMap: http://www.openstreetmap.org/. 10) Seidel, S., and Papport T.: 914Mhz Path Loss Prediction Model for Indoor Wireless Communications in Multifloored Buildings, Proceedings of IEEE Transactions on Antennas and Propagation, pp.207 217 (1992). 11) Skyhook Wireless Inc.: Loki, http://loki.com/. 12) twitter: http://twitter.com/. 13) W3C: Geolocation API Specification, http://dev.w3.org/geo/api/spec-source.html. 14) http://pc.colopl.jp/pages/wl/welcome.html. 15) LAN Vol.47, No.12, pp.3124 3136 (2006). 16) (2008). http://www.meti.go.jp/press/20080703007/20080703007.html (access: 2010.8.9). 17) (2009). http://www.meti.go.jp/policy/it policy/gis/090319/090319.html (access: 2010.8.9). 18) Vol.48, No.3, pp.1349 1360 (2007). 19),, Gaussian Mixture Model LAN (DICOMO) pp.944 952 (2010). 20),,.Locky: LAN 6ZP-4 (2010). 21),,, PlaceEngine: WiFi pp.95 104 (2006). 1239 c 2010 Information Processing Society of Japan