FOREST FIRE DETECTION SYSTEM

Capstone Project Report

Submitted by:

401703019 PRANAV KAKKAR

401703019 PRANAV KAKKAR

401703019 PRANAV KAKKAR

401703019 PRANAV KAKKAR

BE Third Year, COE-MBA

CPG No.

Under the Mentorship of

Dr. Ashima singh

Assistant Professor

Dr. 1234567890

Research Scholar

Computer Science and Engineering Department

Thapar Institute of Engineering and Technology, Patiala

May-Dec​,​ 2019
  
ABSTRACT

With the passage of time, the importance of the global positioning system has increased
exponentially in our lives. Most of the apps these days use the GPS technology as one of their
major underlying components. Be it google maps, uber eats, Ola or any other company, GPS
is widely used in our daily lives. Seen all the pros of GPS, it has some cons too. The simple
and basic requirement of GPS is the line of site. These systems thus perform tremendously
well outdoors but can’t be used for indoors. We have utilized this opportunity to create an
indoor positioning system which will be able to cater to the shortcomings of the GPS system.
The indoor positioning system aims to help navigate within a closed premise where there are
enough access points and WIFI connection availability. This indoor positioning system will
use the received signal strength values from the various access points and match them in a
database with the stored signal strength values corresponding to various different
co-ordinates.

The signal strength values will also be used to perform the trilateration process and the results of the
fingerprint matching process will be augmented by this trilateration process in order to
improve the accuracy. We aim to deploy this project in our college premise where there are
enough access points thus helping in saving the time which people waste when looking for a
teacher, guard or a lab. This automated and user-friendly service will be available to the
users, students, teachers via an android app installed on their phone.

2
 DECLARATION

We hereby declare that the design principles and working prototype model of the
project entitled ​INDOOR LOCALISATION SYSTEM is an authentic record of our own
work carried out in the Computer Science and Engineering Department, TIET, Patiala, under
the guidance of ​Dr. Smita Agrawal ​and ​Dr. PS Rana​ during 6th semester (2019).

Date:

Roll No. Name Signature

101610061 NEEL KUMAR
101603327 SHUBHAM JINDAL
101610052 MANRAJ SINGH
101603188 MAYANK SINGHAL

Counter Signed By:

Faculty Mentor: Co-Mentor:

Dr. Smita Agrawal Dr. PS Rana

Assistant Professor Assistant Professor

CSED, CSED,

TIET, Patiala TIET, Patiala

3
4
 ​ACKNOWLEDGEMENT

We would like to express our thanks to our mentors ​Dr. Smita Agrawal and ​Dr. PS Rana​.
They has been of great help in our venture, and an indispensable resource of technical
knowledge. They are truly an amazing mentor to have.

We are also thankful to ​Dr. Maninder Singh​, Head, Computer Science and Engineering
Department, entire faculty and staff of Computer Science and Engineering Department, and
also our friends who devoted their valuable time and helped us in all possible ways towards
successful completion of this project. We thank all those who have contributed either directly
or indirectly towards this project.

Lastly, we would also like to thank our families for their unyielding love and encouragement.
They always wanted the best for us and we admire their determination and sacrifice.

Date:

Roll No. Name Signature

101610061 NEEL KUMAR
101603327 SHUBHAM JINDAL
101610052 MANRAJ SINGH
101603188 MAYANK SINGHAL

5
 TABLE OF CONTENTS
ABSTRACT Ii
DECLARATION iii
ACKNOWLEDGEMENT iv
LIST OF FIGURES Vii
LIST OF TABLES viii
LIST OF ABBREVIATIONS Ix
CHAPTER 1- INTRODUCTION
1.1 ​PROJECT OVERVIEW 1
1.2 ​NEED ANALYSIS 4
1.3 ​RESEARCH GAPS 5
1.4 ​PROBLEM DEFINITION AND SCOPE
1.5 ​ASSUMPTIONS AND CONSTRAINTS
1.6 ​APPROVED OBJECTIVES
1.7 ​METHODOLOGY USED
1.8 ​PROJECT OUTCOMES AND DELIVERABLES
1.9 ​NOVELTY OF WORK
CHAPTER 2 - ​REQUIREMENT ANALYSIS
2.1 ​LITERATURE SURVEY
2.1.1 Theory Associated With Problem Area
2.1.2 Existing Systems and Solutions
2.1.3 Research Findings for Existing Literature
2.1.4 The Problem That Has Been Identified
2.1.5 Survey of Tools and Technologies Used
2.2 ​STANDARDS
2.3 ​SOFTWARE REQUIREMENTS SPECIFICATION
2.3.1 Introduction
2.3.1.1 Purpose
2.3.1.2 Intended Audience and Reading Suggestions
2.3.1.3 Project Scope
2.3.2 Overall Description
2.3.2.1 Product Perspective
2.3.2.2 Product Features
2.3.3 External Interface Requirements
2.3.3.1 User Interfaces
2.3.3.2 Hardware Interfaces
2.3.3.3 Software Interfaces
2.3.4 Other Non-functional Requirements
2.3.4.1 Performance Requirements

6
 2.3.4.2 Safety Requirements
2.3.4.3 Security Requirements
2.4 ​COST ANALYSIS
2.5 ​RISK ANALYSIS
CHAPTER 3 – METHODOLOGY ADOPTED
3.1 ​INVESTIGATIVE TECHNIQUES
3.2 ​PROPOSED SOLUTION
3.3 ​WORK BREAKDOWN STRUCTURE
3.4 ​TOOLS AND TECHNOLOGIES USED
CHAPTER 4 - DESIGN SPECIFICATIONS
4.1 ​SYSTEM ARCHITECTURE
4.2 ​DESIGN LEVEL DIAGRAMS
4.3 ​USER INTERFACE DIAGRAMS
4.4 ​SNAPSHOTS OF WORKING PROTOTYPE MODEL
CHAPTER 5: ​CONCLUSION
5.1 Conclusions
5.2 Environmental​ ​Benefits
5.3 Reflections
APPENDIX A: ​REFERENCES

7
 LIST OF TABLES

Table No. Caption Page No.

Table 1 List of Assumptions 5
Table 2 List of Constraints 5
Table 3 List of various Research Papers 10
Table 4 List of various Investigative Projects Techniques 16

8
 LIST OF FIGURES

Figure No. Caption Page No.

Figure 1 Work Breakdown Structure 18
Figure 2 Three Tier Architecture 20
Figure 3 Context Diagram 20
Figure 4 Component Diagram 21
Figure 5 User Interface Diagrams 22
Figure 6 Home Page 23
Figure 7 Teacher’s Portal 24
Figure 8 Student’s Portal 24

9
 LIST OF ABBREVIATIONS

GSM Global System for Mobile Communication

RFID Radio Frequency Identification

ROI Region Of Interest

RSSI Received Signal Strength Information

GPS Global Positioning System

GLONASS Global Navigation Satellite System

RSS Received Signal Strength

TOA Time Of Arrival

TDOA Time Difference Of Arrival

AP Access Points

WLAN Wide Local Area Network

AWS Amazon Web Services

API Application Program Interface

10
  
INTRODUCTION

1.1  Project Overview

2 The project represents a new indoor positioning method based on Wi-Fi fingerprints
combined with the Trilateration technique. The Wi-Fi fingerprints and the Trilateration
technique uses the RSSI (Received Signal Strength Indicator) measurements multiple
Wi-Fi access points. The RSSI is a measurement of how well your device can receive a
signal from an access point or router. ​A clear distinction should be made between the
terms positioning and localization. Positioning is the determination of global world
coordinates (ie. 43.77568, 77.12243) while localization is the determination of relative
coordinates (ie. Petrie Science and Engineering Building, Room 101) [4].

3 Technique 1:-

4 During an offline phase fingerprints are collected at known positions in the building.
This database of locations and the associated fingerprints are called the radio map.
Bolliger [1], on the other hand, explored the issue of localization accuracy using multiple
deterministic and probabilistic methods based on WLAN fingerprinting and tested the
feasibility of crowdsourcing to improve the radio map precision in the database. In the
online mode, the current Wi-Fi fingerprint probability distributions are compared with
those of the radio map. The user location is estimated by applying the best suitable
matching algorithm, which matches the fingerprint of the current position of the user and
the fingerprints being stored in the database for the different positions thus calculating
the position of the user.

5 Technique 2:-
6 Trilateration technique is a positioning method that uses geometric properties to estimate
the target location. Distance between transmitters and receivers can be measured using
either received signal strength (RSS), time of arrival (TOA) or time difference of arrival
(TDOA).The target location is determined by the strongest signal transmitted by the
predefined location of beacons or base stations. The accuracy of this method is
measured by the maximum signal range and density of the beacons. ​Computing the
distance between the user and a nearby AP requires knowledge of the signal path loss

1
 which can generally be represented using the Log-distance Path Loss equation explained
by Faria Daniel B [2]. ​ ​Note that the assumed parameters are similar to many other
empirically found values [3]. ​The accuracy of this technique is very sensitive to the
environment, therefore this technique when applied standalone may give unreliable
results.

1.1.1 Technical Terminology

The Technicality of the project revolves around the fingerprinting mechanism supported by
the Trilateration process. While the Fingerprinting alone is quite sufficient to produce
good results, but there may be a chance of some inaccuracy during the collection
phase of the fingerprinting. So, in such scenario, the Trilateration process will act as
the supporting mechanism.

1.1.2 Problem Statement

Till date GPS has been used and been remarkably great in terms of locating the object, but it
has considerably failed to provide accurate results for the indoor positioning purposes.
Therefore there is immense need for an indoor localization technology which
overcomes the barriers faced by the GPS. So the task is to device a new technology
which can accurately give position for indoor regions.

1.1.3 Goal
Project aims on building an application based on Wi-Fi Fingerprinting and Trilateration.
The basic objectives that the project intends to achieve are as follows :-
• Find current location of user.
• Find current location of any accessible teacher.
• Find current location of nearby guard of your building/floor.
• Find location of a particular class/lab/office on the map.
• Get shortest path from a source to a destination on the map

1.1.4 Solution
The objectives of the project listed above will be achieved in small steps as per the schedule
and plan. Firstly, received signal strength values will be calculated from the nearby

2
 access points. These received signal strength values will then be used by matching
them with the entries in the database. These entries/fingerprints will help determining
the current location of the user.
Now, the user generates the request to locate a teacher, guard or a lab in the campus. Once the
request is generated the location of the desired entity is again searched and mapped
based on received signal strength values and then the shortest route is generated and
displayed on the user interface guiding the user to his destination.
Locating the user/entity is done based on fingerprinting and trilateration to improve the
accuracy of the indoor localization system. Trilateration will complement the received
signal strength values and help in determining the location with better precision and
accuracy.
Once the data has been collected, an android app will be designed with a user- friendly
interface which will send data and receive data from the application server at the
backend. All the processing will be done remotely and the results will be displayed on
the user’s interface.
Alternative flows of control will also be taken into account, by showing prompts to the user in
scenarios where the rights to access the teacher’s location have not been granted, or
whenever the signal strengths are weak enough to be matched with the fingerprints, etc.
Whenever signal strength is weak wrong location will not be shown to the user, a
prompt will be shown regarding the inconvenience caused by the app. Major attempts
will be made to update the database of fingerprints regularly to ensure that the
fluctuations in the received signal strength values have been taken into account.

1.2  Need Analysis

 To date, the well-known Global Positioning System (GPS) and Global Navigation Satellite
System (GLONASS) are being remarkably considered as the accurate localization
systems due to their precision, cost comparable and effectiveness in determining a
target location.
However, both systems are not able to sense a room-grain indoor environment due to the weak
signal caused by concrete building structure. Thus, intense studies have been
conducted by academia and industries to design and develop an accurate and effective
indoor localization system. The recent growth of indoor positioning system and

3
 new demands in location-aware applications have encouraged researchers to develop
the most efficient and effective indoor positioning solution using various platforms
such as Wi-Fi, RFID technology, Bluetooth, Global System for Mobile
Communication (GSM) networks, magnetic field and hybrid system. But none have
been able to provide the accurate results up to 1.5 -2 m.
Although the possibilities with Indoor Navigation alone are very diverse, the same technology
also enables a much broader range of solutions such as Proximity, Asset Tracking and
Analytics. This is a door opener for many industries to include Indoor Positioning
services in their day-to-day business and thus increase efficiency and ROI. Be it
Proximity Marketing or Analytics for Retail, Navigation for patients and Asset
Tracking in Hospitals or for Heavy Engineering, or a Meeting room Finder for office
spaces. Everyone will find something tailored to their needs.

1.3 Research Gaps

A lot of research has been made in the last couple of years on Global indoor positioning
systems. Even after a lot of research still a number of gaps are left for improvement.
Firstly it is impossible to measure each and every inch point inside the building to store
in the database. Due to this it is not possible to get 100% accuracy. Implementation of
2.5D (2 perpendicular plane and a floor) is not correctly explained. There is no such
way to get the Signal Strength up to the mark when environmental barriers occur.
There is no such way to get the database changed accordingly if there is a physical
change in location of the access point. As even a single change can result in the
complete change in a database which is a cumbersome task.

1.4  Problem Definition And Scope

GPS has been used and been remarkably great in terms of locating the object, but it has
considerably failed to provide accurate results for the indoor positioning purposes.
Therefore there is immense need for an indoor localization technology which overcomes
the barriers faced by the GPS. So the task is to device a new technology which can
accurately give position for indoor regions.
Scope our app is limited to indoors only, because the presence of Wi-Fi signals is limited to
indoors only. Though Wi-Fi signals are also present outside the buildings but they do not

4
 have enough strength (not enough access points), so as to fulfill the requirements of our
algorithm.

1.5  Assumptions And Constraints

1.5.1 Assumptions
Table 1: List of Assumptions

S. No. Assumptions

1 User, teachers and guards should have android phones

2 Availability of Wi-Fi access points in the campus.

3 availability of good Wi-Fi signal strength in the area of

interest

1.5.2 Constraints
​Table 2: List of Constraints
S. No. Constraints

1 Requires a lot of Time and Manpower

2 Not Robust to Environmental Dynamics

1.6  Approved Objectives

Following Objectives have been identified:

• Find current location of user.

• Find current location of any accessible teacher.
• Find current location of nearby guard of your building/floor.
• Find location of a particular class/lab/office on the map.
• Get shortest path from a source to a destination on the map

5
 

6
1.7 Methodology Used
The objectives of the project listed above will be achieved in small steps as per the schedule
and plan. Firstly, received signal strength values will be calculated from the nearby
access points. These received signal strength values will then be used by matching
them with the entries in the database. These entries/fingerprints will help determining
the current location of the user.
Now, the user generates the request to locate a teacher, guard or a lab in the campus. Once
the request is generated the location of the desired entity is again searched and mapped
based on received signal strength values and then the shortest route is generated and
displayed on the user interface guiding the user to his destination.
Locating the user/entity is done based on fingerprinting and trilateration to improve the
accuracy of the indoor localization system. Trilateration will complement the received
signal strength values and help in determining the location with better precision and
accuracy.
Once the data has been collected, an android app will be designed with a user- friendly
interface which will send data and receive data from the application server at the
backend. All the processing will be done remotely and the results will be displayed on
the user’s interface.
Alternative flows of control will also be taken into account, by showing prompts to the user
in scenarios where the rights to access the teacher’s location have not been granted, or
whenever the signal strengths are weak enough to be matched with the fingerprints, etc.
Whenever signal strength is weak wrong location will not be shown to the user, a
prompt will be shown regarding the inconvenience caused by the app. Major attempts
will be made to update the database of fingerprints regularly to ensure that the
fluctuations in the received signal strength values have been taken into account.

7
 1.8  Project Outcomes And Deliverables
We will develop a support system based on facial recognition. In addition, you can work with
videos, identify the students that appears there and surround them with the face
delimiting box. The first part of the system is to automatically extract the relevant
characteristics of the image. These characteristics will be used later to determine if two
images belong to the same person or not. Following are the project outcomes of our
project.

1.9  Novelty Of Work

The novelty of this project is the use of Wifi – Fingerprinting in association with Trilateration.
We will be able to achieve high accuracy with the combination of 2 mechanisms
supporting each other. Along with this the cost of system is also very less .
In future we intend to increase the accuracy of the system by supporting it with the Machine
learning algorithms.

8
  
REQUIREMENT ANALYSIS

2.1   LITERATURE SURVEY

2.1.1 Theory Associated With Problem Area
Face recognition rises from the moment that machine started to become more and more
“intelligent" and had the advance of fill in, correct or help the lack of human abilities
and senses. The subject of face recognition is as old as computer vision both because
of the practical importance of the topic and theoretical interest from cognitive science.
Face recognition is not the only way of recognizing other people. Even humans
among each other use senses in order to recognize others. Machines have a wider
range for recognition purposes, which use thinks such as fingerprints, or iris scans.
Despite the fact that these methods of identification can be more accurate, face
recognition has always remained a major focus of research because of its non-invasive
nature and also because it is people's primary method of person identification.

2.1.2 Existing Systems and Solutions

Several systems for face recognition attendance have been developed in the past by
researcher’s examples Wise grove, SYNEL, FINGERTEC, Egress Systems,
ZKTECO. There were various achievements and problems of these systems. Wise
grove is has capacity of 75 employee and it can store up to 700 faces. SYNEL is face
recognition system which are deployed in healthcare and school it has accuracy up to
99.99% and it come with user friendly interface. Despite their name, Finger Tec
produce more than fingerprint recognition technology. They offer 3 types of face
recognition time and attendance software: Face ID 4D; Face ID 3D; and Face ID
2D.EGRESS system provide Recognition options of face only; PIN + face; card only;
card +face Easy to use with voice prompts and Real time data makes it easy to
manage workforce attendance. These systems are costlier and require expert care.

9
2.1.3 Research Findings for Existing Literature
Many systems have been developed in the past like Wise Groove, SYNEL, FINGERTEC,
ZKTECO etc. These systems are expensive and require expert care. With the invent
of neural networks it has become feasible to use affordable and accurate systems.
Many types of recognition systems are possible like FACE ID (4D, 3D, 2D),
Pin+Face etc. Deep Learning and Computer vision are progressive fields and a lot of
developments and enhancements are achievable. A brief overview of studies made on
face detection and recognition will be introduced alongside some popular face
detection and recognition algorithms. This will give a general idea of the history of
systems and approaches that have been used so far.

​ Table 3: List of various Research Papers

Paper Title Tools / Findings

Technology

Deep Residual Learning Yolo DNN’s are difficult to train so they provide
for Image Recognition empirical evidence showing that residual networks
are easier to optimize and gain accuracy.

Recognizing Facial R-CNN Here they use neural networks to identify key
Expression using deep seven human emotions: anger, disgust, fear,
learning happiness, sadness, surprise and neutrality.

Deep Residual Learning Resnet, It represents a residual learning framework to ease

for Image Recognition VGG, the training of networks that are substantially
Google Net deeper than those used previously.

Face Detection and RBF Feature extraction and Facial recognition are
Recognition Technology studied in order to resolve problems like

10
for HCI based on RBF high-dimension problem, small size samples and
Neural Network no-linear separable problem that exist in facial
recognition technology.

Support Vector Machine SVM SVM is a classification method that separate two
Applied to Face data sets with maximum distance between them.
Recognition The concept is to extend the spatial resolution
around the margin by a conformal mapping, such
that the divisibility between classes is increased.

Comparison of face PCA uses image representation as weighted sum

Recognition Algorithms feature vector of Eigen faces which are stored in
on Dummy 1-D array. A probe image is compared against the
gallery image by measuring the distance between
Faces
their respective feature vectors then matching
result has been disclosed.

Fuzzy Hybrid Learning RBFNN The FHLA combines thegradient method and
Algorithm the linear least-squared method foradjusting
the RBF parameters and the neural
network connection weights. The RBFNN with
the proposed FHLA is used as a classifier in a face
recognition system.

Discriminant analysis on DARG Image are represented as Gaussian Mixture Model

Riemannian manifold of (GMM) comprising a number of Gaussian
Gaussian distributions for components with prior probabilities and seek to
face recognition with discriminate Gaussian components from different
image sets classes. In the light of information geometry, the
Gaussians lie on a specific Riemannian manifold.

11
2.1.4 The Problem That Has Been Identified
In order to locate the position of the user inside the building, the conventional GPS fails to
give the accurate results .GPS has been used and been remarkably great in terms of
locating the object, but it has considerably failed to provide accurate results for the
indoor positioning purposes. Therefore there is immense need for an indoor
localization technology which overcomes the barriers faced by the GPS.

2.2   STANDARDS
● IEEE 802.11 WLAN standards

2.3   SOFTWARE REQUIREMENTS SPECIFICATION

2.3.1 Introduction
2.3.1.1 Purpose
To develop a system that will facilitate in finding the location of the entity inside the
buildings.

2.3.1.2 Intended Audience and Reading Suggestions

For the implementation of this project, teachers and students will be our target audience
for all kinds of implementation and testing purposes.

2.3.1.3 Project Scope

The project scope is as follows :-

● Aim to provide an automated indoor positioning and navigation system

● To simplify the process of finding a lab manually and ultimately saving
one’s time.
● To offer an ease of access to a teacher or guard’s location
● To avoid the manual time consuming search process.

2.3.2 Overall Description

12
2.3.2.1 Product Perspective
With the passage of time, the importance of the global positioning system has increased
exponentially in our lives. Most of the apps these days use the GPS technology as
one of their major underlying components. Be it google maps, uber eats, Ola or
any other company, GPS is widely used in our daily lives. Seen all the pros of
GPS, it has some cons too. The simple and basic requirement of GPS is the line of
site. These systems thus perform tremendously well outdoors but can’t be used for

indoors​.

2.3.2.2 Product Features

● No internet connectivity required for stand-alone purposes
● Better than GPS for predicting indoor locations as well as uses lesser
battery.
● Better range as compared to RFID based location based services.
● Software can be easily deployed on android operating systems, providing a
good user friendly interface helping in navigation within a building.
● Provides insights in applications where behavior is to be tracked based on
person’s movements and daily activities.

2.3.3 External Interface Requirements

2.3.3.1 User Interfaces
GUI along with meaningful frames and button in association with google maps.

2.3.3.2 Hardware Interfaces

• Wi-Fi module (IEEE 802.11)
2.3.3.3 Software Interfaces
Front End: Android, Java, XML

Back End: Python, Java

2.3.4 Other Non-functional Requirements

Non-functional requirements are set of requirements with specific criteria to judge the
systems operation. They cover ease of use to the client, security, support availability,
operational speed, and implementation considerations.
2.3.4.1 Performance Requirements

13
 1. The speed of locating the desired entity should be fast.
2. The accuracy of the result should be good.
3. App size should be small.

2.3.4.2 Safety Requirements

1. App should be compatible on various operating systems.
2. The received signal strength values should be reliable.
3. The app should be compatible with the various android versions.

2.3.4.3 Security Requirements

1. The system should be very secure as it contains blueprint of the building
which is being mapped.

2. The server data should be secured as it contains the location of the teacher,
which should not be accessed without their permission

3. For a small organization like in this case our college, we would store data on a
local server instead of a cloud to prevent it from external attacks.

2.4   COST ANALYSIS

Initial Cost Analysis
The implementation of our project: "Indoor Localization System" requires only an android
mobile and a server to operate. The mobile will be operated by the user and the server
will be deployed by our team.
For the initial part of the project, we will not be renting any outside server service (AWS),
because of which the total cost of our project will come out to be Zero.
Future Cost Analysis
In the future implementation of the project, we plan on renting the server through the Amazon
Web Services
(AWS), which would cost near around $40 – $50 USD per month if we get one medium
instance (server) with 2 CPUs and 4 GB RAM on AWS.
Also, uploading the Application on the Android Play Store has a onetime cost of $25 as
registration fee.

14
 2.5   RISK ANALYSIS
Though our project is taken care of every causality but certainly there can be many flaws and
further risks involved if not checked every part of our project's functioning. Some of the
major flaws can be :-
1. The teachers and guards we intend to find might not be using android phones.
2. Unavailability of good wifi signal strength in the area of interest.
3. RSSI (Recieved Signal Strength Identification) value may not be upto the mark
because of several environmental conditions.
4. Database collection is a vast process and their might be some errors in data collection
which may lead to error in position calculation process.

5. It might be possible that the user is not inside the mapped area.

15
  
METHODOLOGY ADOPTED

3
 
3.1INVESTIGATIVE TECHNIQUES
Table 4: List of various Investigative Projects Techniques

S. Investigative Investigative Techniques Description

No. Projects Techniques
1 Descriptive ● Motive is to detect the location of the User, Teacher and
Guards with as much accuracy as possible.
● Comparison of Signal Strength value received with the
value stored in the database to get the Location.
2 Comparative ● Wi-Fi Fingerprinting is used to generate the radio map of
the building.
● Using the Tri-alteration technique we detect the location
of an object from the predefined access point.
● Fingerprinting approach is better in finding accuracy as
compared to other technologies like RFID, GPS, etc.
3 Experimental ● Testing of prototype within a small building having
sufficient number of access points.
● Testing in various environmental conditions.
● Testing in location having sparse fingerprints.

 
3.2PROPOSED SOLUTION
The objectives of the project listed above will be achieved in small steps as per the schedule and
plan. Firstly, received signal strength values will be calculated from the nearby access
points. These received signal strength values will then be used by matching them with the
entries in the database. These entries/fingerprints will help determining the current
location of the user.
Now, the user generates the request to locate a teacher, guard or a lab in the campus. Once the
request is generated the location of the desired entity is again searched and mapped based
on received signal strength values and then the shortest route is generated and displayed
on the user interface guiding the user to his destination.
Locating the user/entity is done based on fingerprinting and trilateration to improve the accuracy
of the indoor localization system. Trilateration will complement the received signal
strength values and help in determining the location with better precision and accuracy.

16
Once the data has been collected, an android app will be designed with a user- friendly interface
which will send data and receive data from the application server at the backend. All the
processing will be done remotely and the results will be displayed on the user’s interface.
Alternative flows of control will also be taken into account, by showing prompts to the user in
scenarios where the rights to access the teacher’s location have not been granted, or
whenever the signal strengths are weak enough to be matched with the fingerprints, etc.
Whenever signal strength is weak wrong location will not be shown to the user, a prompt
will be shown regarding the inconvenience caused by the app. Major attempts will be
made to update the database of fingerprints regularly to ensure that the fluctuations in the
received signal strength values have been taken into account.

17
  
3.3WORK BREAKDOWN STRUCTURE

FIGURE 1: Work Breakdown Structure

 
3.4TOOLS AND TECHNOLOGIES USED
3.4.1 Tools Used

Hardware:
● Laptop/ Android phone

Software:
● LINSSID
● Spyder
● Android Studio

3.4.2 Technologies Used

• WebApp Development

18
• Google maps API
• Wi-Fi fingerprinting
• Trilateration

19
  
DESIGN SPECIFICATIONS

4
 
4.1SYSTEM ARCHITECTURE

FIGURE 2: Three Tier Architecture

FIGURE 3: Context Diagram

 
4.2DESIGN LEVEL DIAGRAMS

20
 FIGURE 4: Component Diagram

 
4.3USER INTERFACE DIAGRAMS

21
 FIGURE 5: User Interface Diagrams

 
4.4SNAPSHOTS OF WORKING PROTOTYPE MODEL

22
FIGURE 6: Home Page

23
FIGURE 7: Teacher’s Portal

FIGURE 8: Student’s Portal

24
  
CONCLUSION

5
5.1 CONCLUSION
The technology used by us to locate a teacher, lab, or a guard is solely based on the concept of
fingerprint matching and trilateration. We have been able to test the code in the
directorate in our campus area and have successfully inferred the results which are quite
accurate and close to the actual value of the co-ordinates of the points. Considering this
first step done, we now aim to make an android app where we would deploy the
technology used above in the indoor positioning system. All in all, this app will help
teachers as well as students to navigate in the campus by avoiding them to waste their
time in finding a teacher, guard or a lab.

5.2 Environmental, Economic and Societal Benefits

Indoor Localization using Wifi fingerprinting can be very useful in many areas to provide
facilities to society and also this project can be helpful for economic benefits. One can
deploy this system for different purpose like security and by doing so we can decrease
the risk of any trespasser in the high security area.

5.3 Reflections
The innovation utilized by us to find an teacher, lab, or a guard is exclusively founded on the
idea of unique finger printing and trilateration. We have had the option to test the code in
the directorate in our grounds region and have effectively gathered the outcomes which
are very exact and near the genuine estimation of the co-ordinates of the focuses.
Considering this initial step done, we presently expect to make an android application
where we would send the innovation utilized above in the indoor situating framework.

25
  
REFERENCES

[1] Bolliger Philipp Lukas, “Robust Indoor Positioning through Adaptive Collaborative
Labeling of Location Fingerprints”, PhD‟s thesis, ETH Zurich,

http://e-collection.library.ethz.ch/eserv/eth:5267/eth-5267-02.pdf

[2] Cisco, 2008. “Wi-Fi Location-Based Services 4.1 Design Guide”

http://www.cisco.com/en/US/docs/solutions/Enterprise/Mobility/WiFiLBS-DG.htm

[3] Faria Daniel B., “Modeling Signal Attenuation in IEEE 802.11 Wireless LANs – Vol. 1”,
Standord university, 2006

[4] Haenselmann Thomas, 2005. “Lecture on Sensor Networks”, University of Mannheim,

Germany. http://www.slideshare.net/netfet/localization-presentation (13 Jan. 2012).

26