Computer Engineering Commons^™

Computer Vision Based Classification Of Fruits And Vegetables For Self-Checkout At Supermarkets, Khurram Hameed

Theses: Doctorates and Masters

The field of machine learning, and, in particular, methods to improve the capability of machines to perform a wider variety of generalised tasks are among the most rapidly growing research areas in today’s world. The current applications of machine learning and artificial intelligence can be divided into many significant fields namely computer vision, data sciences, real time analytics and Natural Language Processing (NLP). All these applications are being used to help computer based systems to operate more usefully in everyday contexts. Computer vision research is currently active in a wide range of areas such as the development of autonomous vehicles, …

Application Of Advanced Algorithms And Statistical Techniques For Weed-Plant Discrimination, Saman Akbar Zadeh

Theses: Doctorates and Masters

Precision agriculture requires automated systems for weed detection as weeds compete with the crop for water, nutrients, and light. The purpose of this study is to investigate the use of machine learning methods to classify weeds/crops in agriculture. Statistical methods, support vector machines, convolutional neural networks (CNNs) are introduced, investigated and optimized as classifiers to provide high accuracy at high vehicular speed for weed detection.

Initially, Support Vector Machine (SVM) algorithms are developed for weed-crop discrimination and their accuracies are compared with a conventional data-aggregation method based on the evaluation of discrete Normalised Difference Vegetation Indices (NDVIs) at two different …

Proactive Content Caching In Future Generation Communication Networks: Energy And Security Considerations, Muhammad Ishtiaque Aziz Zahed

Theses: Doctorates and Masters

The proliferation of hand-held devices and Internet of Things (IoT) applications has heightened demand for popular content download. A high volume of content streaming/downloading services during peak hours can cause network congestion. Proactive content caching has emerged as a prospective solution to tackle this congestion problem. In proactive content caching, data storage units are used to store popular content in helper nodes at the network edge. This contributes to a reduction of peak traffic load and network congestion.

However, data storage units require additional energy, which offers a challenge to researchers that intend to reduce energy consumption up to 90% …

Development, Manufacture And Application Of A Solid-State Ph Sensor Using Ruthenium Oxide, Wade Lonsdale

Theses: Doctorates and Masters

The measurement of pH is undertaken frequently in numerous settings for many applications. The common glass pH probe is almost ideal for measuring pH, and as such, it is used almost ubiquitously. However, glass is not ideal for all applications due to its relatively large size, fragility, need for recalibration and wet-storage. Therefore, much research has been undertaken on the use of metal oxides as an alternative for the measurement of pH.

Here, a solid-state potentiometric pH sensor is developed using ruthenium metal oxide (RuO2). Initially, pH sensitive RuO2 electrodes were prepared by deposition with radio frequency magnetron sputtering (RFMS) …

Automated Optical Mark Recognition Scoring System For Multiple-Choice Questions, Murtadha Alomran

Theses: Doctorates and Masters

Multiple-choice questions are one of the questions commonly used in assessments. It is widely used because this type of examination can be an effective and reliable way to examine the level of student’s knowledge. So far, this type of examination can either be marked by hand or with specialised answer sheets and scanning equipment. There are specialised answer sheets and scanning equipment to mark multiple-choice questions automatically. However, these are expensive, specialised and restrictive answer sheets and optical mark recognition scanners.

This research aims to design and implement a multiple-choice answer sheet and a reliable image processing-based scoring system that …

Extraction Of Patterns In Selected Network Traffic For A Precise And Efficient Intrusion Detection Approach, Priya Naran Rabadia

Theses: Doctorates and Masters

This thesis investigates a precise and efficient pattern-based intrusion detection approach by extracting patterns from sequential adversarial commands. As organisations are further placing assets within the cyber domain, mitigating the potential exposure of these assets is becoming increasingly imperative. Machine learning is the application of learning algorithms to extract knowledge from data to determine patterns between data points and make predictions. Machine learning algorithms have been used to extract patterns from sequences of commands to precisely and efficiently detect adversaries using the Secure Shell (SSH) protocol. Seeing as SSH is one of the most predominant methods of accessing systems it …

Next Generation Wireless Communication Networks: Energy And Quality Of Service Considerations, Md Munjure Mowla

Theses: Doctorates and Masters

The rapid growth in global mobile phone users has resulted in an ever-increasing demand for bandwidth and enhanced quality-of-service (QoS). Several consortia comprising major international mobile operators, infrastructure manufacturers, and academic institutions are working to develop the next generation wireless communication systems fifth generation (5G) - to support high data rates and increased QoS. 5G systems are also expected to represent a greener alternative for communication systems, which is important because power consumption from the information and communication technology (ICT) sector is forecast to increase significantly by 2030. The deployment of ultra-dense heterogeneous small cell networks (SCNs) is expected to …

A Sound Idea: An Investigation Into Accessible Video Game Design For The Deaf And Hard Of Hearing, Luke James Brook

Theses: Doctorates and Masters

A widely accepted, and incorrect, assumption towards hearing accessibility in video games is that deaf and hard of hearing (DHH) users are those who encounter the least barriers and are generally well catered for. Rapid advancement in video game technology has seen video game sound evolve from simple blips generated by internal circuitry to fully realised digital audio used to convey critical information. To accommodate the DHH, this information needs to be conveyed in an alternative manner. However, evidence suggests existing accessible design solutions for the DHH lack specificity and are insufficient. Thus, the inability to hear, or hear well, …

An Investigation Into Off-Link Ipv6 Host Enumeration Search Methods, Clinton Carpene

Theses: Doctorates and Masters

This research investigated search methods for enumerating networked devices on off-link 64 bit Internet Protocol version 6 (IPv6) subnetworks. IPv6 host enumeration is an emerging research area involving strategies to enable detection of networked devices on IPv6 networks. Host enumeration is an integral component in vulnerability assessments (VAs), and can be used to strengthen the security profile of a system. Recently, host enumeration has been applied to Internet-wide VAs in an effort to detect devices that are vulnerable to specific threats. These host enumeration exercises rely on the fact that the existing Internet Protocol version 4 (IPv4) can be exhaustively …

Interfacing Of Neuromorphic Vision, Auditory And Olfactory Sensors With Digital Neuromorphic Circuits, Anup Vanarse

Theses: Doctorates and Masters

The conventional Von Neumann architecture imposes strict constraints on the development of intelligent adaptive systems. The requirements of substantial computing power to process and analyse complex data make such an approach impractical to be used in implementing smart systems.

Neuromorphic engineering has produced promising results in applications such as electronic sensing, networking architectures and complex data processing. This interdisciplinary field takes inspiration from neurobiological architecture and emulates these characteristics using analogue Very Large Scale Integration (VLSI). The unconventional approach of exploiting the non-linear current characteristics of transistors has aided in the development of low-power adaptive systems that can be implemented …

Intelligent Network Intrusion Detection Using An Evolutionary Computation Approach, Samaneh Rastegari

Theses: Doctorates and Masters

With the enormous growth of users' reliance on the Internet, the need for secure and reliable computer networks also increases. Availability of effective automatic tools for carrying out different types of network attacks raises the need for effective intrusion detection systems.

Generally, a comprehensive defence mechanism consists of three phases, namely, preparation, detection and reaction. In the preparation phase, network administrators aim to find and fix security vulnerabilities (e.g., insecure protocol and vulnerable computer systems or firewalls), that can be exploited to launch attacks. Although the preparation phase increases the level of security in a network, this will never completely …

Website Accessibility In Australia And The National Transition Strategy: Outcomes And Findings, Vivienne Conway

Theses: Doctorates and Masters

In the most recent statistics, published by the Australian Bureau of Statistics in 2012, it was reported that slightly under one in five people stated they had a disability. A further twenty-one percent of the population (4.7 million people) reported that they had a long-term health condition that did not restrict their everyday activities. This total group of people who suffer either a disability or a long-term health condition numbers 8.9 million people, or over thirty-nine percent of the Australian population. Of the people reporting a disability, 3.7 million or eighty-eight percent of that group experienced limitations in the activities …

Investigation On The Mobile Robot Navigation In An Unknown Environment, Ahmed S. Khusheef

Theses: Doctorates and Masters

Mobile robots could be used to search, find, and relocate objects in many types of manufacturing operations and environments. In this scenario, the target objects might reside with equal probability at any location in the environment and, therefore, the robot must navigate and search the whole area autonomously, and be equipped with specific sensors to detect objects. Novel challenges exist in developing a control system, which helps a mobile robot achieve such tasks, including constructing enhanced systems for navigation, and vision-based object recognition. The latter is important for undertaking the exploration task that requires an optimal object recognition technique.

In …

A Model For Systematically Investigating Relationships Between Variables That Affect The Performance Of Novice Programmers, Vivian Campbell

Theses: Doctorates and Masters

This research was motivated by an interest in novices learning to program

and a desire to understand the factors that affect their learning. The

traditional approach to performing such an investigation has been to select

factors which may be important and then perform statistical tests on a few

potential relationships. A new research model is proposed and tested to

ensure that a thorough and systematic investigation of the data is performed.

This thesis describes the data, defines the model and explains the

application and validation of the model.

The research process is managed by a control algorithm that is the …

On A Joint Physical Layer And Medium Access Control Sublayer Design For Efficient Wireless Sensor Networks And Applications, Mahir Lumumba Meghji

Theses: Doctorates and Masters

Wireless sensor networks (WSNs) are distributed networks comprising small sensing devices equipped with a processor, memory, power source, and often with the capability for short range wireless communication. These networks are used in various applications, and have created interest in WSN research and commercial uses, including industrial, scientific, household, military, medical and environmental domains. These initiatives have also been stimulated by the finalisation of the IEEE 802.15.4 standard, which defines the medium access control (MAC) and physical layer (PHY) for low-rate wireless personal area networks (LR-WPAN).

Future applications may require large WSNs consisting of huge numbers of inexpensive wireless sensor …

Strategies For The Intelligent Selection Of Components, Valerie Maxville

Theses: Doctorates and Masters

It is becoming common to build applications as component-intensive systems - a mixture of fresh code and existing components. For application developers the selection of components to incorporate is key to overall system quality - so they want the `best'. For each selection task, the application developer will de ne requirements for the ideal component and use them to select the most suitable one. While many software selection processes exist there is a lack of repeatable, usable, exible, automated processes with tool support. This investigation has focussed on nding and implementing strategies to enhance the selection of software components. The …

An Improved Medium Access Control Protocol For Real-Time Applications In Wlans And Its Firmware Development, Sushil Dutt

Theses: Doctorates and Masters

The IEEE 802.11 Wireless Local Area Network (WLAN), commonly known as Wi-Fi, has emerged as a popular internet access technology and researchers are continuously working on improvement of the quality of service (QoS) in WLAN by proposing new and efficient schemes. Voice and video over Internet Protocol (VVoIP) applications are becoming very popular in Wi-Fi enabled portable/handheld devices because of recent technological advancements and lower service costs. Different from normal voice and video streaming, these applications demand symmetric throughput for the upstream and downstream. Existing Wi-Fi standards are optimised for generic internet applications and fail to provide symmetric throughput due …

An Investigation Into Internetworking Education, Woratat Makasiranondh

Theses: Doctorates and Masters

Computer network technology and the Internet grew rapidly in recent years. Their growth created a large demand from industry for the development of IT and internetworking professionals. These professionals need to be equipped with both technical hands-on skills and non-technical or soft skills. In order to supply new professionals to the industry, educational institutions need to address these skills training in their curricula. Technical hands-on skills in internetworking education can be emphasised through the practical use of equipment in classrooms. The provision of the networking equipment to the internetworking students is a challenge. Particularly, university students in developing countries may …

Survivable Mesh-Network Design & Optimization To Support Multiple Qop Service Classes, Hoang N. Nguyen

Theses: Doctorates and Masters

Every second, vast amounts of data are transferred over communication systems around the world, and as a result, the demands on optical infrastructures are extending beyond the traditional, ring-based architecture. The range of content and services available from the Internet is increasing, and network operations are constantly under pressure to expand their optical networks in order to keep pace with the ever increasing demand for higher speed and more reliable links.

A Jittered-Sampling Correction Technique For Adcs, Jamiil A. Tourabaly

Theses: Doctorates and Masters

In Analogue to Digital Converters (ADCs) jittered sampling raises the noise floor; this leads to a decrease in its Signal to Noise ratio (SNR) and its effective number of bits (ENOB). This research studies a technique that compensate for the effects of sampling with a jittered clock. A thorough understanding of sampling in various data converters is complied.

Design Of Survivable Wdm Network Based On Pre-Configured Protection Cycle, Byungkyu Kang

Theses: Doctorates and Masters

Wavelength Division Multiplexing (WDM) is an important technique which allows the trans- port of large quantities of data over optical networks. All optical WDM-based networks have been used to improve overall communication capacity and provide an excellent choice for the design of backbone networks. However, due to the high traffic load that each link can carry in a WDM network, survivability against failures becomes very important. Survivability in this context is the ability of the network to maintain continuity of service against failures, since a failure can lead to huge data losses. In recent years, many survivability mechanisms have been …

An Investigation Into The Use Of B-Nodes And State Models For Computer Network Technology And Education, Gurpreet Kohli

Theses: Doctorates and Masters

This thesis consists of a series of internationally published, peer reviewed, conference research papers and one journal paper. The papers evaluate and further develop two modelling methods for use in Information Technology (IT) design and for the educational and training needs of students within the area of computer and network technology. The IT age requires technical talent to fill positions such as network managers, web administrators, e-commerce consultants and network security experts as IT is changing rapidly, and this is placing considerable demands on higher educational institutions, both within Australia and internationally, to respond to these changes.

A Study Of The Security Implications Involved With The Use Of Executable World Wide Web Content, Christopher Hu

Theses: Doctorates and Masters

Malicious executable code is nothing new. While many consider that the concept of malicious code began in the 1980s when the first PC viruses began to emerge, the concept does in fact date back even earlier. Throughout the history of malicious code, methods of hostile code delivery have mirrored prevailing patterns of code distribution. In the 1980s, file infecting and boot sector viruses were common, mirroring the fact that during this time, executable code was commonly transferred via floppy disks. Since the 1990s email has been a major vector for malicious code attacks. Again, this mirrors the fact that during …

Determining The Effectiveness Of Deceptive Honeynets, Nirbhay Gupta

Theses: Doctorates and Masters

Over the last few years, incidents of network based intrusions have rapidly increased, due to the increase and popularity of various attack tools easily available for download from the Internet. Due to this increase in intrusions, the concept of a network defence known as Honeypots developed. These honeypots are designed to ensnare attackers and monitor their activities. Honeypots use the principles of deception such as masking, mimicry, decoying, inventing, repackaging and dazzling to deceive attackers. Deception exists in various forms. It is a tactic to survive and defeat the motives of attackers. Due to its presence in the nature, deception …

The Mediated Data Integration (Medint) : An Approach To The Integration Of Database And Legacy Systems, Suvimol Mukviboonchai

Theses: Doctorates and Masters

The information required for decision making by executives in organizations is normally scattered across disparate data sources including databases and legacy systems. To gain a competitive advantage, it is extremely important for executives to be able to obtain one unique view of information in an accurate and timely manner. To do this, it is necessary to interoperate multiple data sources, which differ structurally and semantically. Particular problems occur when applying traditional integration approaches, for example, the global schema needs to be recreated when the component schema has been modified. This research investigates the following heterogeneities between heterogeneous data sources: Data …

Automatic Human Face Detection In Color Images, Son Lam Phung

Theses: Doctorates and Masters

Automatic human face detection in digital image has been an active area of research over the past decade. Among its numerous applications, face detection plays a key role in face recognition system for biometric personal identification, face tracking for intelligent human computer interface (HCI), and face segmentation for object-based video coding. Despite significant progress in the field in recent years, detecting human faces in unconstrained and complex images remains a challenging problem in computer vision. An automatic system that possesses a similar capability as the human vision system in detecting faces is still a far-reaching goal. This thesis focuses on …

Database Development And Intranet Based Image Included Database Management System For Ballistic Firearm Identification System, Toni C. Jiao

Theses: Doctorates and Masters

The process of imaging, collecting and searching a cartridge case to identifying its suspected firearm is a time consuming procedure. Within this study, a cartridge case identification database management system in an Intranet environment is designed and implemented, thus enabling firearm examiners from different forensic laboratories to engage firearm identification without the constraints of time and location. Specifically, the study investigates appropriate database management system for image involved and Intranet secured ballistics firearm identification database. The results demonstrated that a computerized firearm identification system could be implemented in Intranet with a secure, scalable, performable Intranet database management system.

Factors Affecting The Bit Error Rate Performance Of The Indoor Radio Propagation Channel For 2.3-2.5 Ghz Frequency Band, Edward A. Walker

Theses: Doctorates and Masters

The use of wireless in buildings based on microwave radio technology has recently become a viable alternative to the traditional wired transmission media. Because of the portable nature of radio transceivers, the need for extensive cabling of buildings with either twisted pair, coaxial, or optical fibre cable is eliminated. This is particularly desirable where high user mobility occurs and existing wiring is not in place, or buildings are heritage in nature and extensive cabling is seen as intrusive. Economic analysis bas also shown that significant labour cost savings can result by using a radio system or a hybrid mix of …

Vlsi Implementation Of A Massively Parallel Wavelet Based Zerotree Coder For The Intelligent Pixel Array, Geoffrey N. Alagoda

Theses: Doctorates and Masters

In the span of a few years, mobile multimedia communication has rapidly become a significant area of research and development constantly challenging boundaries on a variety of technologic fronts. Mobile video communications in particular encompasses a number of technical hurdles that generally steer technological advancements towards devices that are low in complexity, low in power usage yet perform the given task efficiently. Devices of this nature have been made available through the use of massively parallel processing arrays such as the Intelligent Pixel Processing Array. The Intelligent Pixel Processing array is a novel concept that integrates a parallel image capture …

Statistical Multiplexing And Connection Admission Control In Atm Networks, Guoqiang Mao

Theses: Doctorates and Masters

Asynchronous Transfer Mode (ATM) technology is widely employed for the transport of network traffic, and has the potential to be the base technology for the next generation of global communications. Connection Admission Control (CAC) is the effective traffic control mechanism which is necessary in ATM networks in order to avoid possible congestion at each network node and to achieve the Quality-of-Service (QoS) requested by each connection. CAC determines whether or not the network should accept a new connection. A new connection will only be accepted if the network has sufficient resources to meet its QoS requirements without affecting the QoS …