Department of Information Science
Recent Deposits
-
Towards supporting long-term physical activity with information systems: A self-determination theory perspective
Physical activity apps and devices offer manifold opportunities for users to increase their activity levels and have gained growing popularity. However, people worldwide still struggle to reach sufficient levels of physical ... -
Novel machine learning approaches for wildfire prediction to overcome the drawbacks of equation-based forecasting
Predicting wildfires using Machine Learning (ML) models is relevant and essential to minimize wildfire threats to protect human lives and reduce significant property damages. Mixed results have been found in this domain, ... -
Standardisation and Data Augmentation in Genetic Programming
Genetic programming (GP) is a common method for performing symbolic regression that relies on the use of ephemeral random constants in order to adequately scale predictions. Suitable values for these constants must be drawn ... -
Data transformation and knowledge retrieval for humanitarian crisis response
Humanitarian crises are unpredictable and complex environments, in which access to basic services and infrastructures is not adequately available. Computing in a humanitarian crisis environment is different from any other ... -
Error decomposition of evolutionary machine learning
Algorithms or models are often measured using a fitness function that calculates total prediction error. While reducing total error is typically the overall objective, examining error as an aggregate value does not provide ... -
Graph-structured populations and the Hill–Robertson effect
The Hill–Robertson effect describes how, in a finite panmictic diploid population, selection at one diallelic locus reduces the fixation probability of a selectively favoured allele at a second, linked diallelic locus. ... -
Deep generative models for transductive transfer learning
To achieve satisfactory generalization abilities, machine learning models usually require large amounts of labelled data. However, data labelling is very costly, even in the era of big data. Transductive transfer learning ... -
Ensemble learning through cooperative evolutionary computation
Building ensembles of classifiers is an active area of research for machine learning, with the fundamental goal of combining the predictions of multiple classifiers to improve prediction accuracy over an individual classifier. ... -
ECG Classification with Patient-Dependent Normalization and Multi-step Classifier.
Electrocardiogram (ECG) is an important tool for monitoring abnormal heartbeats. Machine learning has been used to facilitate the process of identifying the beats from the ECG data. In this research, we undertook the ... -
People and processes during decision-making in open source software communities: A case study of Python
Open Source Software Development (OSSD) communities are often able to produce high quality software comparable to proprietary software. The success of an OSSD community is often attributed to the underlying governance ... -
Prioritisation of requests, bugs and enhancements pertaining to apps for remedial actions. Towards solving the problem of which app concerns to address initially for app developers
Useful app reviews contain information related to the bugs reported by the app’s end-users along with the requests or enhancements (i.e., suggestions for improvement) pertaining to the app. App developers expend exhaustive ... -
Optimal coalition structure generation on large-scale renewable energy smart grids
Most renewable energy sources are dependent on unpredictable weather conditions, which have considerable variation over space and time. The intermittent nature of this production means that any renewable energy prosumer ... -
Investigating Cultural Dimensions via Developers Artefacts: The Utility of Repository Mining
A growing body of research is using artefacts from online development communities to explore the impact of developers’ behaviours on the software development process. Although this research has produced many insights, ... -
Agent-based models of long-distance trading societies
Studying historical trading societies helps us to identify the institutions (e.g. rules) and characteristics that lead to their success or failure. Historically, long-distance trading societies, as a more particular example ... -
Removing spatial boundaries in immersive mobile communications
Despite a worldwide trend towards mobile computing, current telepresence experiences focus on stationary desktop computers, limiting how, when, and where researched solutions can be used. In this thesis I demonstrate that ... -
Investigating value propositions in social media: studies of brand and customer exchanges on Twitter
Social media presents one of the richest forums to investigate publicly explicit brand value propositions and its corresponding customer engagement. Seldom have researchers investigated the nature of value propositions ... -
Interaction and Emotional Response in Immersive Virtual Reality Learning Environments
Virtual Reality (VR) is seen as a promising tool for effective education. The flexibility, controllability, and interactive capabilities of VR allow for a range of immersive experiences. This presents an opportunity for ... -
Energy efficiency: modelling and performance analysis of self-powered sensors
The idea of employing harvested energy from human motion to run electronic devices such as self-powered sensors in fitness gadgets is attracting increased attention of many researchers. However, there is still limited ... -
Closing Price Manipulation and Market Quality
This thesis examines the impact of closing price manipulation (“marking the close”) on several dimensions of equity market quality, including both the efficiency and integrity of equity markets. Marking the close is an ... -
Human Activity Recognition in Smart Homes
There is an increasing interest in activity recognition analysis due to the tremendous growth of sensors and devices that have recently brought significant attention to smart homes research which promotes inhabitants' ...