Engineering Commons^™

Multimodal Fusion For Audio-Image And Video Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

Multimodal Human Action Recognition (MHAR) is an important research topic in computer vision and event recognition fields. In this work, we address the problem of MHAR by developing a novel audio-image and video fusion-based deep learning framework that we call Multimodal Audio-Image and Video Action Recognizer (MAiVAR). We extract temporal information using image representations of audio signals and spatial information from video modality with the help of Convolutional Neutral Networks (CNN)-based feature extractors and fuse these features to recognize respective action classes. We apply a high-level weights assignment algorithm for improving audio-visual interaction and convergence. This proposed fusion-based framework utilizes …

Barriers And Enablers For Older Adults Participating In A Home-Based Pragmatic Exercise Program Delivered And Monitored By Amazon Alexa: A Qualitative Study, Paul Jansons, Jackson Fyfe, Jack Dalla Via, Robin M. Daly, Eugene Gvozdenko, David Scott

Research outputs 2022 to 2026

Background: The remote delivery and monitoring of individually-tailored exercise programs using voice-controlled intelligent personal assistants (VIPAs) that support conversation-based interactions may be an acceptable alternative model of digital health delivery for older adults. The aim of this study was to evaluate the enablers and barriers for older adults participating in a home-based exercise program delivered and monitored by VIPAs. Method: This qualitative study used videoconferencing to conduct semi-structured interviews following a 12-week, prospective single-arm pilot study in 15 adults aged 60 to 89 years living alone in the community. All participants were prescribed an individualized, brief (10 min, 2–4 times …

Green Underwater Wireless Communications Using Hybrid Optical-Acoustic Technologies, Kazi Y. Islam, Iftekhar Ahmad, Daryoush Habibi, M. Ishtiaque A. Zahed, Joarder Kamruzzaman

Research outputs 2014 to 2021

Underwater wireless communication is a rapidly growing field, especially with the recent emergence of technologies such as autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs). To support the high-bandwidth applications using these technologies, underwater optics has attracted significant attention, alongside its complementary technology – underwater acoustics. In this paper, we propose a hybrid opto-acoustic underwater wireless communication model that reduces network power consumption and supports high-data rate underwater applications by selecting appropriate communication links in response to varying traffic loads and dynamic weather conditions. Underwater optics offers high data rates and consumes less power. However, due to the severe …

Video Analysis And Verification Of Direct Head Impacts Recorded By Wearable Sensors In Junior Rugby League Players, Lauchlan Carey, Douglas P. Terry, Andrew S. Mcintosh, Peter Stanwell, Grant L. Iverson, Andrew J. Gardner

Research outputs 2014 to 2021

Background: Rugby league is a high-intensity collision sport that carries a risk of concussion. Youth athletes are considered to be more vulnerable and take longer to recover from concussion than adult athletes. Purpose: To review head impact events in elite-level junior representative rugby league and to verify and describe characteristics of X-patchTM-recorded impacts via video analysis. Study Design: Observational case series. Methods: The X-patchTM was used on twenty-one adolescent players (thirteen forwards and eight backs) during a 2017 junior representative rugby league competition. Game-day footage, recorded by a trained videographer from a single camera, was synchronised with X-patchTM-recorded timestamped events. …

Class Distribution-Aware Adaptive Margins And Cluster Embedding For Classification Of Fruit And Vegetables At Supermarket Self-Checkouts, Khurram Hameed, Douglas Chai, Alexander Rassau

Research outputs 2014 to 2021

The complex task of vision based fruit and vegetables classification at a supermarket self-checkout poses significant challenges. These challenges include the highly variable physical features of fruit and vegetables i.e. colour, texture shape and size which are dependent upon ripeness and storage conditions in a supermarket as well as general product variation. Supermarket environments are also significantly variable with respect to lighting conditions. Attempting to build an exhaustive dataset to capture all these variations, for example a dataset of a fruit consisting of all possible colour variations, is nearly impossible. Moreover, some fruit and vegetable classes have significant similar physical …

A Sample Weight And Adaboost Cnn-Based Coarse To Fine Classification Of Fruit And Vegetables At A Supermarket Self-Checkout, Khurram Hameed, Douglas Chai, Alexander Rassau

Research outputs 2014 to 2021

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. The physical features of fruit and vegetables make the task of vision-based classification of fruit and vegetables challenging. The classification of fruit and vegetables at a supermarket self-checkout poses even more challenges due to variable lighting conditions and human factors arising from customer interactions with the system along with the challenges associated with the colour, texture, shape, and size of a fruit or vegetable. Considering this complex application, we have proposed a progressive coarse to fine classification technique to classify fruit and vegetables at supermarket checkouts. The image and weight of …

Real-Time Classification Of Multivariate Olfaction Data Using Spiking Neural Networks, Arnup Vanarse, Adam Osseiran, Alexander Rassau, Therese O'Sullivan, Jonny Lo, Amanda Devine

Research outputs 2014 to 2021

Recent studies in bioinspired artificial olfaction, especially those detailing the application of spike-based neuromorphic methods, have led to promising developments towards overcoming the limitations of traditional approaches, such as complexity in handling multivariate data, computational and power requirements, poor accuracy, and substantial delay for processing and classification of odors. Rank-order-based olfactory systems provide an interesting approach for detection of target gases by encoding multi-variate data generated by artificial olfactory systems into temporal signatures. However, the utilization of traditional pattern-matching methods and unpredictable shuffling of spikes in the rank-order impedes the performance of the system. In this paper, we present an …

A Hardware-Deployable Neuromorphic Solution For Encoding And Classification Of Electronic Nose Data, Anup Vanarse, Alexander Rassau, Peter Van Der Made

Research outputs 2014 to 2021

In several application domains, electronic nose systems employing conventional data processing approaches incur substantial power and computational costs and limitations, such as significant latency and poor accuracy for classification. Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements. Although these methods have addressed issues related to efficient data processing and classification accuracy, other areas, such as reducing the processing latency to support real-time application and deploying spike-based solutions on supported hardware, have yet to be studied in detail. Through this investigation, we proposed a spiking …

Effective Plant Discrimination Based On The Combination Of Local Binary Pattern Operators And Multiclass Support Vector Machine Methods, Vi N T Le, Beniamin Apopei, Kamal Alameh

Research outputs 2014 to 2021

Accurate crop and weed discrimination plays a critical role in addressing the challenges of weed management in agriculture. The use of herbicides is currently the most common approach to weed control. However, herbicide resistant plants have long been recognised as a major concern due to the excessive use of herbicides. Effective weed detection techniques can reduce the cost of weed management and improve crop quality and yield. A computationally efficient and robust plant classification algorithm is developed and applied to the classification of three crops: Brassica napus (canola), Zea mays (maize/corn), and radish. The developed algorithm is based on the …

An Entropy-Histogram Approach For Image Similarity And Face Recognition, Mohammed Aljanabi, Zahir Hussain, Song F. Lu

Research outputs 2014 to 2021

Image similarity and image recognition are modern and rapidly growing technologies because of their wide use in the field of digital image processing. It is possible to recognize the face image of a specific person by finding the similarity between the images of the same person face and this is what we will address in detail in this paper. In this paper, we designed two new measures for image similarity and image recognition simultaneously. The proposed measures are based mainly on a combination of information theory and joint histogram. Information theory has a high capability to predict the relationship between …

Application Of 3d Delaunay Triangulation In Fingerprint Authentication System, Wencheng Yang, Ahmed Ibrahim, Junaid Chaudhry, Song Wang, Jiankun Hu, Craig Valli

Research outputs 2014 to 2021

Biometric security has found many applications in Internet of Things (IoT) security. Many mobile devices including smart phones have supplied fingerprint authentication function. However, the authentication performance in such restricted environment has been downgraded significantly. A number of methods based on Delaunay triangulation have been proposed for minutiae-based fingerprint matching, due to some favorable properties of the Delaunay triangulation under image distortion. However, all existing methods are based on 2D pattern, of which each unit, a Delaunay triangle, can only provide limited discrimination ability and could cause low matching performance. In this paper, we propose a 3D Delaunay triangulation based …

Review Of Deep Learning Methods In Robotic Grasp Detection, Shehan Caldera, Alexander Rassau, Douglas Chai

Research outputs 2014 to 2021

For robots to attain more general-purpose utility, grasping is a necessary skill to master. Such general-purpose robots may use their perception abilities to visually identify grasps for a given object. A grasp describes how a robotic end-effector can be arranged to securely grab an object and successfully lift it without slippage. Traditionally, grasp detection requires expert human knowledge to analytically form the task-specific algorithm, but this is an arduous and time-consuming approach. During the last five years, deep learning methods have enabled significant advancements in robotic vision, natural language processing, and automated driving applications. The successful results of these methods …

A Security Review Of Local Government Using Nist Csf: A Case Study, Ahmed Ibrahim, Craig Valli, Ian Mcateer, Junaid Chaudhry

Research outputs 2014 to 2021

Evaluating cyber security risk is a challenging task regardless of an organisation’s nature of business or size, however, an essential activity. This paper uses the National Institute of Standards and Technology (NIST) cyber security framework (CSF) to assess the cyber security posture of a local government organisation in Western Australia. Our approach enabled the quantification of risks for specific NIST CSF core functions and respective categories and allowed making recommendations to address the gaps discovered to attain the desired level of compliance. This has led the organisation to strategically target areas related to their people, processes, and technologies, thus mitigating …

A Novel Privacy Preserving User Identification Approach For Network Traffic, Nathan Clarke, Fudong Li, Steven Furnell

Research outputs 2014 to 2021

The prevalence of the Internet and cloud-based applications, alongside the technological evolution of smartphones, tablets and smartwatches, has resulted in users relying upon network connectivity more than ever before. This results in an increasingly voluminous footprint with respect to the network traffic that is created as a consequence. For network forensic examiners, this traffic represents a vital source of independent evidence in an environment where anti-forensics is increasingly challenging the validity of computer-based forensics. Performing network forensics today largely focuses upon an analysis based upon the Internet Protocol (IP) address – as this is the only characteristic available. More typically, …

A Feature-Based Structural Measure: An Image Similarity Measure For Face Recognition, Noor A. Shnain, Zahir Hussain, Song F. Lu

Research outputs 2014 to 2021

Facial recognition is one of the most challenging and interesting problems within the field of computer vision and pattern recognition. During the last few years, it has gained special attention due to its importance in relation to current issues such as security, surveillance systems and forensics analysis. Despite this high level of attention to facial recognition, the success is still limited by certain conditions; there is no method which gives reliable results in all situations. In this paper, we propose an efficient similarity index that resolves the shortcomings of the existing measures of feature and structural similarity. This measure, called …

Detecting And Tracing Slow Attacks On Mobile Phone User Service, Brian Cusack, Zhuang Tian

Australian Digital Forensics Conference

The lower bandwidth of mobile devices has until recently filtered the range of attacks on the Internet. However, recent research shows that DOS and DDOS attacks, worms and viruses, and a whole range of social engineering attacks are impacting on broadband smartphone users. In our research we have developed a metric-based system to detect the traditional slow attacks that can be effective using limited resources, and then employed combinations of Internet trace back techniques to identify sources of attacks. Our research question asked: What defence mechanisms are effective? We critically evaluate the available literature to appraise the current state of …

The Proceedings Of 14th Australian Digital Forensics Conference, 5-6 December 2016, Edith Cowan University, Perth, Australia, Craig Valli

Australian Digital Forensics Conference

Conference Foreword

This is the fifth year that the Australian Digital Forensics Conference has been held under the banner of the Security Research Institute, which is in part due to the success of the security conference program at ECU. As with previous years, the conference continues to see a quality papers with a number from local and international authors. 11 papers were submitted and following a double blind peer review process, 8 were accepted for final presentation and publication. Conferences such as these are simply not possible without willing volunteers who follow through with the commitment they have initially made, …

Optical Fiber Sensors In Physical Intrusion Detection Systems: A Review, Gary Andrew Allwood, Graham Wild, Steven Hinkley

Research outputs 2014 to 2021

Fiber optic sensors have become a mainstream sensing technology within a large array of applications due to their inherent benefits. They are now used significantly in structural health monitoring, and are an essential solution for monitoring harsh environments. Since their first development over 30 years ago, they have also found promise in security applications. This paper reviews all of the optical fiber-based techniques used in physical intrusion detection systems. It details the different approaches used for sensing, interrogation, and networking, by research groups, attempting to secure both commercial and residential premises from physical security breaches. The advantages and the disadvantages …

Proactive Biometric-Enabled Forensic Imprinting, Abdulrahman Alruban, Nathan L. Clarke, Fudong Li, Steven M. Furnell

Research outputs 2014 to 2021

Threats to enterprises have become widespread in the last decade. A major source of such threats originates from insiders who have legitimate access to the organization's internal systems and databases. Therefore, preventing or responding to such incidents has become a challenging task. Digital forensics has grown into a de-facto standard in the examination of electronic evidence; however, a key barrier is often being able to associate an individual to the stolen data. Stolen credentials and the Trojan defense are two commonly cited arguments used. This paper proposes a model that can more inextricably links the use of information (e.g. images, …

The Social Life Of Big Data - Pawsey Resources, Luke Edwards

The Social Life of Big Data Symposium

The presentation covers the supercomputing facilities and services available at the Pawsey Supercomputing Centre, Western Australia.
The Pawsey Supercomputing Centre is an unincorporated joint venture between CSIRO, Curtin University, Edith Cowan University, Murdoch University and the University of Western Australia and is supported by the Western Australian Government.

Cyber Blackbox For Collecting Network Evidence, Jooyoung Lee, Sunoh Choi, Yangseo Choi, Jonghyun Kim, Ikkyun Kim, Youngseok Lee

Australian Digital Forensics Conference

In recent years, the hottest topics in the security field are related to the advanced and persistent attacks. As an approach to solve this problem, we propose a cyber blackbox which collects and preserves network traffic on a virtual volume based WORM device, called EvidenceLock to ensure data integrity for security and forensic analysis. As a strategy to retain traffic for long enough periods, we introduce a deduplication method. Also this paper includes a study on the network evidence which is collected and preserved for analyzing the cause of cyber incident. Then, a method is proposed to suggest a starting …

Forensic Analysis Of A Sony Playstation 4: A First Look, Matthew Davies, Huw Read, Konstantinos Xynos, Iain Sutherland

Research outputs 2014 to 2021

The primary function of a games console is that of an entertainment system. However the latest iteration of these consoles has added a number of new interactive features that may prove of value to the digital investigator. This paper highlights the value of these consoles, in particular Sony's latest version of their PlayStation. This console provides a number of features including web browsing, downloading of material and chat functionality; all communication features that will be of interest to forensic investigators. In this paper we undertake an initial investigation of the PlayStation 4 games console. This paper identifies potential information sources …

The Zombies Strike Back: Towards Client-Side Beef Detection, Maxim Chernyshev, Peter Hannay

Australian Digital Forensics Conference

A web browser is an application that comes bundled with every consumer operating system, including both desktop and mobile platforms. A modern web browser is complex software that has access to system-level features, includes various plugins and requires the availability of an Internet connection. Like any multifaceted software products, web browsers are prone to numerous vulnerabilities. Exploitation of these vulnerabilities can result in destructive consequences ranging from identity theft to network infrastructure damage. BeEF, the Browser Exploitation Framework, allows taking advantage of these vulnerabilities to launch a diverse range of readily available attacks from within the browser context. Existing defensive …

A User-Oriented Network Forensic Analyser: The Design Of A High-Level Protocol Analyser, D Joy, F Li, N L. Clarke, S M. Furnell

Australian Digital Forensics Conference

Network forensics is becoming an increasingly important tool in the investigation of cyber and computer-assisted crimes. Unfortunately, whilst much effort has been undertaken in developing computer forensic file system analysers (e.g. Encase and FTK), such focus has not been given to Network Forensic Analysis Tools (NFATs). The single biggest barrier to effective NFATs is the handling of large volumes of low-level traffic and being able to exact and interpret forensic artefacts and their context – for example, being able extract and render application-level objects (such as emails, web pages and documents) from the low-level TCP/IP traffic but also understand how …

A Forensic Overview Of The Lg Smart Tv, Iain Sutherland, Konstantino Xynos, Huw Read, Andy Jones, Tom Drange

Australian Digital Forensics Conference

The emerging Smart TV platform will likely replace traditional television sets over time as the entertainment and communication centrepiece in people’s homes. Given its expanded functionality and now, its online presence, there is a need to identify how they may become part of forensic investigations. The purpose of this paper is to introduce the area of Smart TVs and the potential forensic value these systems present in combination with their ever advancing functionality and capabilities. We provide an overview of Smart TV systems highlighting functionality and potential issues. We also take an initial look at two particular models, from the …

Locational Wireless And Social Media-Based Surveillance, Maxim Chernyshev

Australian Digital Forensics Conference

The number of smartphones and tablets as well as the volume of traffic generated by these devices has been growing constantly over the past decade and this growth is predicted to continue at an increasing rate over the next five years. Numerous native features built into contemporary smart devices enable highly accurate digital fingerprinting techniques. Furthermore, software developers have been taking advantage of locational capabilities of these devices by building applications and social media services that enable convenient sharing of information tied to geographical locations. Mass online sharing resulted in a large volume of locational and personal data being publicly …

Forensic Examination And Analysis Of The Prefetch Files On The Banking Trojan Malware Incidents, Andri P. Heriyanto

Australian Digital Forensics Conference

Whenever a program runs within the operating system, there will be data or artefacts created on the system. This condition applies to the malicious software (malware). Although they intend to obscure their presence on the system with anti-forensic techniques, still they have to run on the victim’s system to acquire their objective. Modern malware creates a significant challenge to the digital forensic community since they are being designed to leave limited traces and misdirect the examiner. Therefore, every examiner should consider performing all the forensics approaches such as memory forensic, live-response and Windows file analysis in the related malware incidents …

A Forensically-Enabled Iaas Cloud Computing Architecture, Saad Alqahtany, Nathan Clarke, Steven Furnell, Christoph Reich

Australian Digital Forensics Conference

Current cloud architectures do not support digital forensic investigators, nor comply with today’s digital forensics procedures largely due to the dynamic nature of the cloud. Whilst much research has focused upon identifying the problems that are introduced with a cloud-based system, to date there is a significant lack of research on adapting current digital forensic tools and techniques to a cloud environment. Data acquisition is the first and most important process within digital forensics – to ensure data integrity and admissibility. However, access to data and the control of resources in the cloud is still very much provider-dependent and complicated …

Up-Dating Investigation Models For Smart Phone Procedures, Brian Cusack, Raymond Lutui

Australian Digital Forensics Conference

The convergence of services in Smart Technologies such as iPhones, Androids and multiple tablet work surfaces challenges the scope of any forensic investigation to include cloud environments, devices and service media. The analysis of current investigation guidelines suggests that each element in an investigation requires an independent procedure to assure the preservation of evidence. However we dispute this view and review the possibility of consolidating current investigation guidelines into a unified best practice guideline. This exploratory research proposes to fill a gap in digital forensic investigation knowledge for smart technologies used in business environments and to propose a better way …

Listening To Botnet Communication Channels To Protect Information Systems, Brian Cusack, Sultan Almutairi

Australian Digital Forensics Conference

Botnets are a weapon of choice for people who wish to exploit information systems for economic advantage. A large percentage of high value commercial targets such as banking transaction systems and human customers are web connected so that access is gained through Internet services. A Botnet is designed to maximise the possibility of an economic success through the low cost of attacks and the high number that may be attempted in any small time unit. In this paper we report exploratory research into the communications of Botnets. The research question was: How do Botnets talk with the command and control …