Some optimizations of WiFi- Based Indoor Positioning Hanqing Liu - PowerPoint PPT Presentation

Some optimizations of WiFi- Based Indoor Positioning Hanqing Liu

Research Related 02 01 Background Work CONTENTS Our Follow-up 04 03 Project Work

Research Background

Research Background I ndoor localization The implement of positioning in indoor environment. W HY? The signal from the satellite is too weak. How ? Using wireless communication, base station positioning, inertial navigation to form indoor location positioning system 4

Related Work

Basic Concept Received Signal Strength I ndication( RSSI ) The basis of Wifi-based indoor positioning system! Can be predicted by a LDPL m odel . LDPL Model If Pi and γi are known, then an RSS m easurem ent pij can be converted into the distance dij. 6

A Basic Positioning Method Triangular positioning and LDPL Model  The LDPL Model provide a connection between the location of the user and RSS.  The cross point does not always occur in real case! 7

Some Advanced Scheme of Indoor Positioning Fingerprint-based positioning  Offline phase: a site survey is conducted to collect the vectors of RSSI.  Online phase: a user samples or measures an RSSI vector at his/ her position and reports it to the server. 8

Some Advanced Scheme of Indoor Positioning Peer Assisted Positioning  The device broadcasts a special audio signal.  Distance between peers is calculate based on TOA. SLAM  The training phase  The operating phase 9

Our Project

Our indoor positioning based on RSS 1 1

Stage 1: Triangular Positioning Only 1 2

Stage 2: Triangular Positioning With Some Optimizations 1 .Estim ating position based on position history. 2 . Estim ating RSS value Prediction = last_est + kg* (rssi- through Kalm an filtering last_est) 1 3

Follow-up Work

Follow-up work of project To find W HY? 1 .Pressure test Bottleneck! 2 .Adjustm ent of API 1 5

Pressure Test Bottleneck: 1 .Connection to DB 2 .Max Connection to Apache 3 . CPU 1 6

THANKS