LYU0401 Location-Based Multimedia Mobile Service

1
LYU0401 Location-Based Multimedia Mobile Service

• Clarence Fung
• Tilen Ma
• Supervisor Professor Michael Lyu
• Marker Professor Alan Liew

2
Outline

• Introduction
• Objective
• Location-Based Service
• Current Localization Methods
• Experimental Study
• Wi-Fi Location System
• Future Work
• Conclusion

3
Introduction

• In this semester, we mainly focus on the problem
  of localization
• We have chosen the 1st floor of the Ho Sin-Hang
  Engineering Building to study the problem of
  localization
• Our goal is to locate a person when he/she is
  walking around on the floor

4
Objective

• To meet the need for Location-Based Service
• To find out if Wireless LAN provide enough
  information for localization in 2D space
• Study on different localization algorithms
• Develop an application in a mobile device

5
Location-Based Service

• Localization is necessary for many higher level
  sensor network functions such as tracking,
  monitoring and geometric-based routing
• Three categories
• Global location systems
• Wide-area location systems
• Indoor location systems
• Systems in indoor environment
• Infrared (IR)
• Ultrasound
• Radio signal

6
Wireless LAN (WLAN)-Based Positioning System

• Advantages over all other systems
• Economical
• WLAN network usually exists already as part of
  the communications infrastructure
• Covers a large area
• Work in a large building or even across many
  buildings.
• Stable system
• Video- or IR-based location systems are subject
  to restrictions, such as line-of-sight limitations

7
Current Localization Methods

• Point-based approach
• goal is to return a single point for the mobile
  object
• E.g. Simple Distance Matching
• Area-based approach
• goal is to return the possible locations of the
  mobile object as an area rather than a single
  point
• E.g. Simple-Point Matching, Area-Based Probability

8
Area-Based Probability (ABP)

• Advantages
• Presents the user an understanding of the system
  in a more natural and intuitive manner
• High accuracy
• More mathematical approach

9
Steps in using ABP
Decide the Areas
Measure Signals at Different Areas
Create a Training Set
Measure Signals at Current Position
Create a Testing Set
Find out the Probability of Being at Different
Areas
Calculate Probability Density
Return the Area with Highest Probability
10
Applying Area-based Approach
11
Some Terms and Definitions

• n Access Points
• AP1, AP2, , APn
• Training set T0
• Offline measured signal strengths at different
  locations an algorithm uses
• Consists of a set of fingerprints (Si) at m
  different areas Ai
• T0 ( Ai, Si ), i 1 m

12
Some Terms and Definitions

• Fingerprints Si
• Set of n signal strengths at Ai, one per each
  access point
• Si (si1, , sin), where sij is the expected
  average signal strength from APj

13
Generating Training Set

• In one particular Ai, we read a series of signal
  strengths (sijk ) for a particular APj with a
  constant time between samples
• k 1 oij ,where oij is the number of samples
  from APj at Ai
• We estimate sij by averaging the series, sij1,
  sij2, sijo

14
Generating Training Set

• We do the same for all n APs, so we have the
  fingerprints at Ai,
• Si (si1, , sin)
• We do the same for all m areas, so we have the
  training set
• T0 ( Ai, Si ), i 1 m

15
Collecting Signals

• At each area chosen, we measure the signal
  strength from the access points for 1 minute

Position 1 2 3 4 5 6 7 8 9 10 11 12
AP MAC address Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm)
00022d28be9e -70 -62 -58 -67 -73 -78 -83 -86 -84 -81 -78 -55
00022d28be5d -67 -59 -60 -71 -76 -79 -81 -86 -81 -83 -79 -52
00601d1e439b -79 -87 -85 -84 -89 -80 -76 -77 -66 -63 -77 -90
000f34f36040 -63 -69 -65 -74 -76 -72 -77 -84 -76 -74 -66 -79
00022d21391f -82 -78 -82 -59 -78 -73 -83 -85 -82
0011933d6fc0 -90 -85 -86 -89 -88
0011209365c0 -89 -89 -90
000f34bbdf20 -89 -90 -82 -88 -88
000cce211b9d -87
000c853533d2 -88 -88
001120936390 -89 -88
000c853533d4 -87
000476a7aba3 -90
16
Data Processing

• We have chosen 7 out of 13 access points
• least contribution to localization
• shorten computation time
• For missing signal strengths, we input -92 dBm as
  entry

17
Training Set
Position 1 2 3 4 5 6 7 8 9 10 11 12
AP MAC address Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm) Signal Strength (dBm)
00022d28be9e -70 -62 -58 -67 -73 -78 -83 -86 -84 -81 -78 -55
00022d28be5d -67 -59 -60 -71 -76 -79 -81 -86 -81 -83 -79 -52
00601d1e439b -79 -87 -85 -84 -89 -80 -76 -77 -66 -63 -77 -90
000f34f36040 -63 -69 -65 -74 -76 -72 -77 -84 -76 -74 -66 -79
00022d21391f -92 -92 -82 -78 -82 -59 -78 -73 -83 -85 -82 -92
0011933d6fc0 -92 -92 -92 -90 -85 -86 -89 -88 -92 -92 -92 -92
000f34bbdf20 -92 -92 -92 -89 -90 -82 -88 -88 -92 -92 -92 -92
18
Getting Testing Set

• The object to be localized collects a set of
  received signal strengths (RSS) when it is at
  certain location
• A testing set (St) is created similar to the
  fingerprints in the training set
• It is a set of average signal strengths from APs,
  St (st1, , stn)

19
RSS
AP MAC address Signal Strength (dBm)
00022d28be9e -71
00022d28be5d -72
00601d1e439b -89
000f34f36040 -49
20
Testing Set
AP MAC address Signal Strength (dBm)
00022d28be9e -71
00022d28be5d -72
00601d1e439b -89
000f34f36040 -49
00022d21391f -92
0011933d6fc0 -92
000f34bbdf20 -92
21
Applying ABP

• Goal return the area with a highest probability
• Approach compute the likelihood of the testing
  set (St) that matches the fingerprint for each
  area (Si)

22
Applying ABP

• Assumptions
• Signal received from different APs are
  independent
• For each APj, j 1n, the sequence of RSS sijk,
  k 1 oij, at each Ai in To is modeled as a
  Gaussian distribution

23
Applying Bayes rule

• We compute the probability of being at different
  areas Ai, on given the testing set St
• P(Ai St) P(St Ai) P(Ai)/ P(St)
  (1)
• P(St) is a constant
• Assume the object is equally likely to be at any
  location. P(Ai) is a constant
• P(Ai St) cP(St Ai) (2)

24
Area Based Probability

• We compute P(St Ai) for every area Ai ,i1m,
  using the Gaussian assumption
• Finding Probability Density
• the object must be at one of the 12 areas
• SP(Ai St) 1 for all i
• MaxP(Ai St) MaxcP(St Ai)
• MaxP(St Ai)
• Return the area Ai with top probability

25
Gaussian Distribution

• In our application, we can take µ as the expected
  average signal strengths for the access point to
  be calculated
• we take s as 8.5

26
Integral of Normal Function

• Find probability by integration
• Take interval as 1

27
Error function erf(x)

• Express Integral of Normal Function in terms of
  erf
• Approximate value of erf by a series
• Choose iteration of 50

28
Experimental Study

• Area 5 is near the North-West stairway on the 1st
  floor
• deep purple line is on the top of other lines
• Localization system returns the correct result

29
Accuracy of Localization System

• Default sample size of testing set 4
• 80 testing sets for each of the 12 locations

30
Accuracy of Localization System
31
Other Factors affecting Accuracy

• Property of signals
• The strength of signals fluctuates
• Hardware failure
• access points fails to give out signals or give
  out signals at unusual strength
• Change in environment
• addition access points on the floor
• opening the doors
• Orientation in collecting signal

32
Wi-Fi Location System (WLS)

• Development Tool for Location-Based System
• Simplify development steps
• Increase the efficiency and productivity
• It divides into 3 components
• Wi-Fi Signal Scanner (WSS)
• Wi-Fi Data Processor (WDP)
• Wi-Fi Location Detector (WLD)

33
Wireless LAN Terminology

• Media Access Control address (MAC Address)
• 48 bits long
• unique hardware address
• e.g. 0050FC2AA9C9
• Service set identifier (SSID)
• 32 character
• Wireless LAN identifier
• Receive Signal Strength Indicator (RSSI)
• signal strength
• unit is in dBm

34
Overview

• Platform
• Window CE
• Window XP, 2000
• Technology
• IEEE 802.11b
• Tools
• Embedded Visual C 4.0
• Visual Studio .NET 2003

35
Tradition Development Procedure (TDP)

• The followings in the Tradition Development
  Procedure

1-2 week
Studying the technology
Software Design
2-3 week
1-2 week
Algorithm design
Final System
36
Wi-Fi Location System Development Procedure (WLP)
Collecting Data
Using Wi-Fi Signal Scanner
Several hours
Processing Data
Using Wi-Fi Data Processor
1 day
Deploying and Test System
Using Wi-Fi Location Detector
Several days
Final System
37
Comparison between TDP and WLP

• Using WLP, we can develop Location-Based System
  in a short time.
• This work can be done by non-professionals
• It simplifies Development Steps

38
Wi-Fi Signal Scanner

• To collect the signal strength received from
  access points

39
Collected Data
Number of Received Signal
Total of Received Signal
Mean of Received Signal
Strength Signal
40
Wi-Fi Data Processor

• To process collected data

Access Point Region
Setting and Information Region
Position Region
41
Wi-Fi Data Processor

• Two main steps in WDP
• Filter out useless data
• Set parameters at each position
• Data
• Name
• Point at Map Picture

42
Wi-Fi Location Detector

• Three functions in WLD
• To detect the location in the target place
• To show the detected position name and
  corresponding position at the Map Picture
• To show calculated probability
• Three modes in WLD
• Data Mode
• Map Mode
• Probability Mode

43
Data Mode

• To show the sample data

44
Map Mode
Position
Name
45
Probability Mode

• To show calculated probability at each position

46
Conclusion

• We are success in applying Area-Based Probability
• We have done experiments on accuracy of algorithm
• We have implemented Location-Based Development
  ToolWi-Fi Location System
• Based on our knowledge and developed tools in
  localization, we are able to further develop a
  location-based service

47
Future Work

• Ho Sin-Hang Engineering Building Tour Guide
  Service
• Multimedia Application with video streaming
• Improvement in Localization Algorithm
• Increase the Accuracy in Localization
• Research on 3D localization algorithm in an
  building

48
QA
49
DEMO
50
THE END