- Software Engineering Research
- Distributed and Parallel Computing Systems
- Advanced Software Engineering Methodologies
- Parallel Computing and Optimization Techniques
- Software Engineering Techniques and Practices
- Online Learning and Analytics
- Teaching and Learning Programming
- Open Education and E-Learning
- Cloud Computing and Resource Management
- Mobile Learning in Education
- Mobile Health and mHealth Applications
- Advanced Data Storage Technologies
- Health, Environment, Cognitive Aging
- Digital Mental Health Interventions
- Image Processing and 3D Reconstruction
- Image and Object Detection Techniques
- Educational Games and Gamification
- Software Engineering and Design Patterns
- Experimental Learning in Engineering
- Innovative Teaching and Learning Methods
- Technology-Enhanced Education Studies
- Advanced Database Systems and Queries
- Learning Styles and Cognitive Differences
- Model-Driven Software Engineering Techniques
- Web Applications and Data Management
Multimedia University
2012-2023
The University of Melbourne
2011
University of Kansas
1992-1993
An unorganized deployment of grid applications with a large amount fine-grain jobs would let the communication overhead dominate overall processing time, resulting in low computation-communication ratio. Grid's dynamic nature complicates planning job scheduling activity for minimizing application time. This paper presents algorithm, based on parameterized grouping strategy, which is adaptive to runtime environment. Jobs are grouped requirements, resource policies, network conditions and...
A Feedforward Deep Neural Network (FDNN) model contains densely connected layers where backpropagation is applied to calculate the loss function gradients.Optimising network weights important minimise value, hence decreasing prediction errors and increasing accuracy rate.Optimisers are used update weight values or learning rate for each weight.Recent studies show that, although Adaptive Moment Estimation (Adam) produces better results in terms of optimising parameters FDNN model, it might...
This research proposed an algorithm to enhance the software requirements prioritization activity, called multiple perspective technique. technique (algorithm) attempts represent three perspectives: customer, business and technical perspectives. In addition, this is designed for a medium large number of requirements. The effectiveness efficiency were investigated empirically, in order show whether it worthy be adopted real working environment. For reason, controlled experiment was conducted...
<ns4:p><ns4:bold>Background</ns4:bold> – Recently, there have been attempts to develop mHealth applications for asthma self-management. However, is a lack of that can offer accurate predictions exacerbation using the weather triggers and demographic characteristics give tailored response users. This paper proposes an optimised Deep Neural Network Regression (DNNR) model predict based on personalised triggers.</ns4:p><ns4:p> <ns4:bold>Methods</ns4:bold> With aim integrating weather,...
The overhead of processing fine-grain tasks on a grid induces the need for batch or task group deployment in order to minimise overall application turnaround time. When deciding granularity batch, requirements each should be considered as well utilisation constraints interconnecting network and designated resources. However, dynamic nature requires size adaptable latest status. In this paper, we describe policies specific techniques involved resizing process. We explain nuts bolts these...
The recent surge in the number of commercial open-source software (COSS) companies shows growing importance COSS industry. As knowledge-based firms, companies' success depends heavily on interplay among intangible resources such as human capital, relational structural and quality. To observe these relationships, we conducted a hypothesis-testing questionnaire-type survey involving 200 development experts professionals working at 60 multinational companies. Accordingly, study unearthed two...
The significant growth of the Massive Open Online Course (MOCC) over last decade has promoted rise educational data mining era in online education domain. This situation created an opportunity for educator to utilize available from MOOCs facilitate student learning and performance. Therefore, this research study aims introduce three types ensemble methods, which are stacking, boosting, bagging, predict performance on that contain 480 students with 17 features. These techniques have include...
Textboxes are minimum size rectangles enclosing blocks of text in engineering drawings. Their separation from the graphics surrounding them is a first step character recognition, and part Machine Drawing Understanding System, currently under development. Textbox extraction preceded by orthogonal zig-zag vectorization, arc segmentation, arrowhead recognition. It done clustering remaining short bars that located close to each other through region growing process. Further refinements follow...
A key exchange protocol enables two parties to share a common for encrypting large amount of data.Authentication is an essential requirement prior the process in order prevent man-in-the-middle attack.It important understand capabilities and performance existing protocols before employing our applications.In this paper, we compare Secure Socket Layer, Shell, Identity-based by quantifying performance, complexity, level security each protocol.Detailed experiments observations are conducted...
An e-learning system provides a platform for communication between educators and students. It facilitates the sharing of information learning content in form which can be easily accessed by users. The scope research revolves around idea that an automated assessment would able to help programming learners understand defects their program independently learn how program. This investigate effects on college or university analyzes effectiveness various ways language. is believed tools monitor...
With the wide availability of chip multi-processing (CMP), software developers are now facing task effectively parallelizing their code. Once they have identified areas parallelization, will need to know level code granularity needed ensure profitable execution. Furthermore, this problem multiplies itself with different hardware available. In paper, we present a novel approach for fair comparison configuration by simulation through configuring pair quad-core processors. The simulated...