An innovative intelligent system for child care & safety applications using ZigBee Wireless Sensing Networks

Goold, Bradley (2014) An innovative intelligent system for child care & safety applications using ZigBee Wireless Sensing Networks. [USQ Project]

[img]
Preview
Text
Goold_2014.pdf

Download (47MB) | Preview

Abstract

The focus of this paper is to outline the research undertaken of Wireless Sensor Net-works and how they can be used to assist in home health and safety applications. The
particular area of interest is a computer controlled system that tracks a wireless sensor attached to a child indoors for the purpose of alarming when the child enters a prede-termined unsafe area. The system must also define boundaries and have the ability to alert a parent/guardian in the case of the boundaries being breached.

A thorough review of the available literature was undertaken which gave the author background information as to techniques for localisation and their suitability in indoor applications.

An empirical approach to localisation using the Profiling/Fingerprinting method was used. A centralised system design was implemented and an application called Adapt-able Infant Monitoring System was written and tested to perform the localisation and boundary alarming and to provide the ability for remote location retrieval via storing relevant data in a database.

Algorithms were proposed to reduce the localisation error. These algorithms have been rigorously tested in two scenarios. A baseline test was applied to create a benchmark, then testing was applied to a real residential situation. The results are analysed and discussed.

The results concluded that localisation using the specified hardware and the finger-printing technique was inadequate for the application domain. Factors attributing to the localisation error have been discussed including irregular radio signal propogation which has been earmarked for further work.

The localisation accuracy does not render the research work invalid. Providing an omni-directional radio signal and additional research and testing will see the full potential of the system design.
The system proposed in this research allows for user-defined boundaries to be set for the alarming mechanism. This feature alone provides, versatility and expandability which is one of a kind and has potiential to enter the market-place covering unlimited application scenarios.


Statistics for USQ ePrint 27370
Statistics for this ePrint Item
Item Type: USQ Project
Item Status: Live Archive
Additional Information: Bachelor of Computer Systems Engineering project.
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Mechanical and Electrical Engineering (1 Jul 2013 - 31 Dec 2021)
Supervisors: Zhou, Hong
Date Deposited: 09 Sep 2015 04:50
Last Modified: 03 Mar 2016 04:30
Uncontrolled Keywords: wireless sensor networks; indoor localisation, adaptable infant monitoring system, profiling, fingerprinting, home health, safety applications, child care, intelligent system, ZigBee
Fields of Research (2008): 08 Information and Computing Sciences > 0805 Distributed Computing > 080503 Networking and Communications
09 Engineering > 0909 Geomatic Engineering > 090903 Geospatial Information Systems
09 Engineering > 0906 Electrical and Electronic Engineering > 090699 Electrical and Electronic Engineering not elsewhere classified
10 Technology > 1005 Communications Technologies > 100510 Wireless Communications
Fields of Research (2020): 46 INFORMATION AND COMPUTING SCIENCES > 4606 Distributed computing and systems software > 460609 Networking and communications
40 ENGINEERING > 4013 Geomatic engineering > 401302 Geospatial information systems and geospatial data modelling
40 ENGINEERING > 4008 Electrical engineering > 400899 Electrical engineering not elsewhere classified
40 ENGINEERING > 4006 Communications engineering > 400608 Wireless communication systems and technologies (incl. microwave and millimetrewave)
URI: https://sear.unisq.edu.au/id/eprint/27370

Actions (login required)

View Item Archive Repository Staff Only