作者: Andrew G. Dempster , Binghao Li , Ishrat Quader
DOI: 10.1109/ISWPC.2008.4556177
关键词: Nearest neighbour 、 Measurement uncertainty 、 Global Positioning System 、 Transmitter 、 Artificial intelligence 、 Fingerprint recognition 、 Pattern recognition 、 Computer security 、 Computer science 、 Interpolation 、 Wireless 、 Wifi network
摘要: Fingerprinting is a technique that records vectors of received power from several transmitters, and later matches these to new measurement position the user. This paper examines data used in earlier fingerprinting experiments WiFi network characterize eventual positioning errors. The implied relationship between real distance ldquovectorrdquo fingerprints tested found be poor. However, because algorithms use nearest neighbour techniques, nearby were examined better behaved.