Digital Commons Network^™

The Effectiveness Of Local Updates For Decentralized Learning Under Data Heterogeneity, Tongle Wu, Zhize Li, Ying Sun

Research Collection School Of Computing and Information Systems

We revisit two fundamental decentralized optimization methods, Decentralized Gradient Tracking (DGT) and Decentralized Gradient Descent (DGD), with multiple local updates. We consider two settings and demonstrate that incorporating local update steps can reduce communication complexity. Specifically, for  $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT  achieves communication complexity {}{$\tilde{\mathcal{O}} \Big(\frac{L}{\mu(K+1)} + \frac{\delta + {}{\mu}}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$}, where $K$ is the number of additional local update}, $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local losses. Our results reveal the tradeoff between communication and …

Therapeutic Potential Of Brassica Carinata Microgreens Extract In Alleviating Symptoms Of Type 2 Diabetes In Wistar Rats, Lilian Nakakaawa, Ifeoluwa D. Gbala, Joel L. Bargul, Xavier Cheseto, John M. Wesonga

All Peer-Reviewed Publications

Microgreens of Brassica plants have attracted increasing research interest in the management of the prevailing epidemic of Type 2 diabetes mellitus (T2DM) because of their high nutritional value. This study evaluated the antidiabetic effects of Brassica carinata Microgreens Ethanolic Extract (BMEE) in type-2 diabetic rats. For the normoglycemic assay, rats were divided into five groups and received a single oral dose of 100, 250, and 500 mg/kg of BMEE while the control groups received distilled water and Glibenclamide. Fasting blood glucose (FBG) levels were determined on a weekly basis for 28 days in diabetic rats after treatment with BMEE at …

Governing Intelligence: Singapore’S Evolving Ai Governance Framework, Jason G. Allen, Jane Loo, Jose Luna

Research Collection Yong Pung How School Of Law

This paper provides an outline analysis of the evolving governance framework for Artificial Intelligence (AI) in Singapore. Across the Singapore government, AI solutions are being adopted in line with Singapore’s “Smart Nation Initiative” to leverage technology to make impactful changes to the nation and the economy. In tandem, Singaporean authorities have been assiduous to release a growing number of governance documents, which we analyse together to chart the city-state’s approach to AI governance in international comparison. Characteristics of Singapore’s AI governance approach include an emphasis on consensusbuilding between stakeholders (particularly government and industry but also citizens) andvoluntary or “quasi” regulation, …

Andrew Phang (Gen. Ed.), Pioneer, Polymath And Mentor: The Life And Legacy Of Yong Pung How, Kwan Ho Lau, Bryan Leow

Research Collection Yong Pung How School Of Law

Many know the story of modern Singapore in broad outline. When the country attained independence in 1965, it was not industrialised and fishing villages still dotted the landscape. By 1990, GDP per capita had risen to around US$13,000, far exceeding its neighbours and on par with Hong Kong and New Zealand. A further three decades on, Singapore today boasts gleaming skyscrapers, well-developed infrastructure and a high degree of trust by residents and investors alike in its government.

Human Rights At Sea: Analyzing States' Responses To Cruise Ships During The Covid-19 Pandemic, Lixin Chen

Research Collection Yong Pung How School Of Law

In the early stages of the COVID-19 pandemic, the treatment of cruise ships by coastal states was inconsistent, with some ships being allowed to dock while others were not. To that end, this Note focuses on the obligations that a coastal state owes to the individuals onboard the cruise ships in the context of the COVID-19 pandemic, including the rights to life and health. It further considers whether and how such rights are to be balanced with other countervailing considerations of such states, such as the risk of transmission to the local communities. This author concludes with the view that …

She Speaks: Amplifying Women's Voices For Wellbeing, Narelle Lemon

Reports accepted as research outputs

Executive Summary

The SheSpeaks project successfully transformed how 223 Western Australian women understand and practice self-care, demonstrating  that targeted wellbeing literacy interventions can create lasting change  in women’s relationship with their own wellbeing. Funded by the Women’s Grants for a Stronger Future program, this innovative initiative combined evidence-based workshops with authentic podcasting to challenge the pervasive cultural narrative that positions women’s self-care as selfish  or impossible.

Automated Methods For Estimating Blood Alcohol Concentration Level From Facial Cues, Ensiyeh Keshtkaran

Theses: Doctorates and Masters

This thesis investigates different approaches for detecting alcohol intoxication in drivers by analysing facial video data. Tackling this issue necessitates the creation of a novel dataset to overcome the limitations of existing datasets. The dataset constructed in this study is the first to include RGB video recordings of individual faces at varying levels of alcohol intoxication during simulated driving, featuring 60 participants with BAC levels ranging from 0 to 0.165 g/100ml. The constructed dataset not only supports this thesis, but also offers the broader scientific community a valuable resource for further study and development.

Building on this, this thesis presents …

A Tale Of Two Publishing Houses, Linda Martin

Theses: Doctorates and Masters

This research explores the use of creative nonfiction in writing an account of two publishing houses established decades apart, and demonstrates how a hybrid approach that incorporates multiple voices can contribute to the field of biographies and memoirs on publishing. Using practice-led research as its primary methodology, ‘A tale of two publishing houses’ is a creative nonfiction work that focusses on the publishing experiences of Fremantle Arts Centre Press (now Fremantle Press) in its first decade of publishing from 1975, alongside present publishing experiences of Night Parrot Press in its formative years of publishing from 2019. The accompanying reflexive exegesis …

Toward Embodied Navigation Through Vision And Language, Muraleekrishna Gopinathan

Theses: Doctorates and Masters

Embodied AI is a challenging but exciting field in which a robot learns to interact with human-living spaces to perform various tasks. This thesis studies the embodied navigation problem in which a robotic agent navigates in a previously unseen indoor environment based on a challenging task. In particular, the Vision-and-Language Navigation (VLN) task requires a robot to navigate based on a descriptive human-language instruction. This thesis aims to improve VLN agents on four key aspects - their understanding of the environment, training via additional data, correcting navigational errors, and predicting the layout of the environment for better planning.

First, we …

Investigation Of Under-Frequency Load Shedding Prevention Of Isolated Medium-Sized Power Systems Using Energy Storage, Dilan Indoopa Manamperi

Theses: Doctorates and Masters

Due to the rapid uptake of distributed photovoltaic generation, the visible load to transmission operators in distribution feeders is reducing. Traditional load-shedding schemes are facing challenges due to this low-load situation. The required amount of load reduction cannot be achieved with the same load-shedding scheme as before. In some situations, with reverse power flows, load shedding can further increase the generation reduction. On the other hand, increased Rate of Change of Frequency (RoCoF) due to low inertia can result in false activation of under-frequency load shedding (UFLS) relays. These challenges can cause a serious problem with the power system security. …

Machine Learning For Computer-Aided Diagnostics From Complex Medical Images, Afsah Saleem

Theses: Doctorates and Masters

Machine learning has significantly transformed medical image analysis in the current age of artificial intelligence offering vast potential in improving disease diagnosis and management. Cardiovascular diseases (CVDs) are among the leading cause of global mortality, emphasizing the need for early detection for effective intervention and prevention. Abdominal Aortic Calcification (AAC) is an early indicator and contributor to Atherosclerotic Cardiovascular Diseases (ASCVDs) and is commonly assessed through imaging modalities such as computed tomography (CT), X-rays, and Dual-energy X-ray Absorptiometry (DXA). Among these, lateral spine DXA scans, commonly used for osteoporosis screening, offer a cost-effective and low-radiation opportunity for opportunistic CVD risk …

Enhancing Energy Efficiency In Solar Thermal Systems: The Role Of Hybrid Nanofluids In Sustainable Energy Harvesting And Storage, Seyedehzahra Haeri

Theses: Doctorates and Masters

Global energy demand continues to grow, making the reliance on fossil fuels increasingly unsustainable due to dwindling reserves and environmental impacts. Among these, solar thermal systems have emerged as a practical and environmentally friendly solution, with applications ranging from industrial heating and solar water heating to concentrated solar power (CSP) plants and solar desalination units. Solar-based thermal systems offer a promising alternative, with nanofluids (NFs) emerging as a transformative solution. Engineered by dispersing nanoparticles into base fluids, NFs enhance thermal conductivity, heat absorption, and efficiency. Notably, nanoparticles such as titanium nitride also act as nano-catalysts, improving chemical reactions and reducing …

Family Members’ Experiences Of Post-Cardiac Surgery Delirium In The Intensive Care Unit: A Narrative Inquiry, Amber Coral Mclean

Theses: Doctorates and Masters

Aim: This study explores delirium in the intensive care unit (ICU) following cardiac surgery from the perspective of family members.

Background: Delirium is a common complication affecting 28-52% of people following cardiac surgery in the ICU, which can lead to distress for both the person and their family members. While research has been conducted on clinical outcomes of family involvement in delirium care, there is a lack of understanding of how delirium impacts the family members themselves. This study seeks to provide detailed narrative accounts of families’ experience of witnessing delirium in their loved one following cardiac surgery in the …

The Rise Of Women In Mining - How To Improve Inclusion And Diversity Through Organisational Programs, Ashley Mcgrath

Theses: Doctorates and Masters

The inclusion and diversity (I&D) of women has become a priority for organisations due to the positive association with business performance and rising expectations of employees and shareholders for fair outcomes for all genders. Improving the I&D of women is also being driven by the evolving Australian legal framework which has heightened the responsibility of organisations regarding psychological safety and the prevention of sexual harassment and sex-based discrimination. Companies operating in male dominated industries in Western Australia (WA) are under particular pressure due to lagging performance in addressing equity issues at a state level. Existing research correlates the I&D of …

Optimal Bag Valve Mask Ventilation Efficacy Of Smart Bag Ventilation Compared To Traditional Adult And Paediatric Bag Valve Ventilation During Cardiopulmonary Resuscitation, Ian Dawson

Theses: Doctorates and Masters

Background: Out-of-Hospital Cardiac Arrest (OHCA) is one of the world’s leading causes of mortality. Survival rates are low, ranging from 3.1–20.4% internationally. The most effective oxygenation method for patients during pre-hospital cardiac arrest is ventilating using a self- inflating Bag-Valve-Mask (BVM). Yet, extensive research has identified a lack of compliance with ventilator guidelines during OHCA cardiopulmonary resuscitation (CPR). As a result, clinicians often ventilate patients too aggressively using the BVM, delivering breaths excessively higher than the International Liaison Committee on Resuscitation (ILCOR) recommended rate of 10 breaths per minute (BPM). Hyperventilation can lead to complications such as aspiration, barotrauma, and …

Modified Constraint-Induced Movement Therapy After Stroke: A Process Evaluation Of Implementation In An Early-Supported Discharge Rehabilitation Service, Ashan Bimalka Weerakkody

Theses: Doctorates and Masters

Background

Modified constraint-induced movement therapy (mCIMT) improves upper limb (UL) function after stroke, but its routine delivery in rehabilitation settings remains limited.

Aims

The objectives were to determine the feasibility, acceptability, and sustainability of implementing mCIMT within an early-supported discharge (ESD) rehabilitation service, using existing resources and staffing.

Aims were to:

• Develop and deliver a multi-modal behaviour change intervention to clinicians to increase mCIMT delivery.
• Explore the acceptability of mCIMT among stroke survivors, carers, therapists, and allied health managers.
• Identify program adaptations to better suit stakeholder needs.
• Evaluate the process of implementing mCIMT in the ESD service.

Methods

This thesis …

Embodied Ai For Challenging Rearrangement Tasks In The Context Of Service And Assistive Robots, Mariia Khan

Theses: Doctorates and Masters

Embodied AI explores intelligent agents that learn through interaction with their environment, aiming to replicate human-like learning processes. Achieving this requires agents capable of understanding a scene via various sensors, reasoning about their actions, and reacting accordingly. These abilities are necessary for service domestic robots to assist humans in their day-to-day activities. Embodied AI tasks can include but are not limited to: visual exploration, visual navigation, instruction following and embodied question answering, which typically consider static (unchanging) environments, where objects do not move over time. This thesis addresses one of the most challenging Embodied AI tasks – visual room rearrangement, …

Anomaly Detection Of Seasonal Vessel Activity, Travis Rybicki

Theses: Doctorates and Masters

Monitoring maritime traffic is essential for ensuring the safety of vessels, safeguarding transported goods or persons, and preventing illicit or hazardous activity at sea. Increasingly, researchers have explored data-driven approaches to model expected vessel behaviour and detect deviations or anomalies. These anomalies—such as course deviations, unauthorised area entries, or unexpected operational patterns—can indicate emergencies, regulatory breaches, or unlawful intent. Data broadcast by vessels provides a valuable resource for such analyses; however, the inherent complexity and context-dependency of maritime behaviour present persistent modelling challenges. One critical yet underutilised factor in this context is seasonality. For certain vessel types, for example, fishing …

Précis Of The Edge Of Sentience: Risk And Precaution In Humans, Other Animals, And Ai, Jonathan Birch

Animal Sentience

We often face grave practical decisions that seem to hinge on whether a system is sentient. This family of cases includes invertebrate animals, people who are unresponsive after brain injury, fetuses, neural organoids, and now AI technologies. We must decide what to do despite ongoing disagreement about the nature of sentience. In our state of uncertainty, we should pragmatically transform the question from “Is it sentient?” to “Is it a sentience candidate, an investigation priority, or neither?”. When a system is a sentience candidate, it is negligent to fail to consider precautions. We should instead evaluate precautions for their proportionality …

The Role Of Game-Based Learning Simulation To Enhance Leadership In Pandemic Preparedness For Nursing Students, Scott James Andrews

Theses: Doctorates and Masters

During the COVID-19 pandemic, nurses around the world suffered with the impact of resource scarcity on the provision of quality nursing care to patients. Nursing staff were at higher risk of infection than all other healthcare workers, with working conditions during the pandemic resulting in significant staffing pressures. The challenges faced by staff during the pandemic inevitably influenced the quality and delivery of clinical education, highlighting the need for innovative solutions such as digital learning to address emerging training needs. Further, the impact of COVID-19 restrictions on clinical education has highlighted the benefits of digital learning environments as alternatives to …

Financial Named Entity Recognition: How Far Can Llm Go?, Yi-Te Lu, Yintong Huo

Research Collection School Of Computing and Information Systems

The surge of large language models (LLMs) has revolutionized the extraction and analysis of crucial information from a growing volume of financial statements, announcements, and business news. Recognition for named entities to construct structured data poses a significant challenge in analyzing financial documents and is a foundational task for intelligent financial analytics. However, how effective are these generic LLMs and their performance under various prompts are yet need a better understanding. To fill in the blank, we present a systematic evaluation of state-of-the-art LLMs and prompting methods in the financial Named Entity Recognition (NER) problem. Specifically, our experimental results highlight …

Processed Amaranth And Finger Millet Enriched With Cricket Flour Influence The Functionality, Microbial Quality, Shelf Life, And Consumer Preference Of The Porridge Products, Nelly Maiyo, Michael Okoth, George Abong, Brian O. Ochieng, Fathiya Khamis, Margaret Kababu, Chrysantus M. Tanga

All Peer-Reviewed Publications

Exploration of nutritious, cheap, and easy-to-prepare locally available complementary foods using different processing techniques is gaining traction globally. This study evaluated the impact of three processing techniques (roasting, germination, and fermentation) on finger millet and amaranth quality. The implications of blending processed products with 10% cricket flour on the functional properties, microbial safety, and shelf life of the porridge products were tested. Thereafter, consumer preference and acceptability of the cooked porridge products were assessed with randomly enrolled panelist of mothers (20–66 years), as primary caregivers. Our results showed that powder from germinated cereal products had higher swelling power, water absorption …

An Assessment Of Vegetable Production Constraints, Trait Preferences And Willingness To Adopt Sustainable Intensification Options In Kenya And Uganda, Rose N. Okoma, Evanson R. Omuse, Daniel M. Mutyambai, Dennis Beesigamukama, Marius F. Murongo, Sevgan Subramanian, Frank Chidawanyika

All Peer-Reviewed Publications

Global food production systems are under pressure due to population increase, limited farmland, biotic and abiotic constrains, and ongoing climate change. Sustainable intensification is needed to increase agricultural productivity with minimal adverse environmental and social impacts. Vegetable-integrated push pull (VIPP) technology coupled with black soldier fly (BSF) frass offer such opportunities to smallholder farmers. However, farmers’ vegetable preferences and willingness to adopt these innovations remain unknown and are variable across various geographic scales. Focus group discussions (FGDs) and in-person interviews with smallholder farmers were conducted to assess vegetable production constraints and select vegetables to be integrated into VIPP coupled with …

The Genomic Landscape Of Hermetia Illucens: Exploring The Potential Of The Black Soldier Fly Through Molecular Insights, Peter Muchina, Johnson Kinyua, Fathiya Khamis, Chrysantus M. Tanga, Grum Gebreyesus, Zexi Cai, Goutam Sahana

All Peer-Reviewed Publications

Abstract The black soldier fly (BSF), Hermetia illucens, has garnered significant attention recently due to its potential applications in waste management, animal feed production, frass fertilizer production, and biotechnology. Despite its numerous advantages, genomic resources for BSF remain limited, underscoring the necessity for continued genomic exploration. This review provides a comprehensive overview of the genomic landscape of BSF, emphasizing the critical role of genomics in understanding its biology and optimizing its applications. We highlighted recent advancements in BSF genome sequencing, transcriptomic and proteomic studies, and the characterization of the gut microbiome, revealing its implications for BSF health and production efficiency. …

Young Women In Cities: Urbanization And Gender-Biased Migration, Yumi Koh, Jing Li, Yifan Wu, Junjian Yi, Hanzhe Zhang

Research Collection School Of Economics

Young women outnumber young men in cities in many countries during periods of economic growth and urbanization. This gender imbalance among young urbanites is more pronounced in larger cities. We use the gradual rollout of Special Economic Zones across China as a quasi-experiment to establish the causal impact of urbanization on gender-differentiated incentives to migrate. We highlight the role of the marriage market in increasing rural women’s chance of marrying and marrying up in urban areas during rapid urbanization.

Redesigning Home Reversion Products To Empower Retirement For Singapore's Public Flat Owners, Koon Shing Kwong, Jing Rong Goh, Jordan Jie Xin Lee, Ting Lin Collin Chua

Research Collection School Of Economics

This paper introduces an innovative sell-type home reversion product aimed at monetizing Singapore’s public flats, serving as a new alternative to the existing Singapore Lease Buyback Scheme (LBS). This new product not only retains the LBS’s guaranteed period of residence in the property along with life annuity incomes but also enhances the product features to meet specific homeowner needs, including the ability to age in place, flexibility in retaining part of the property, options for bequests, and guaranteed principal return. By incorporating these additional features, the new product seeks to stimulate greater demand for monetizing public flats among asset-rich but …

Gauging Growth Risk In An International Financial Centre: Some Evidence From Singapore, Hwee Kwan Chow

Research Collection School Of Economics

This paper applies the growth-at-risk framework proposed by Adrian et al. (2019) to Singapore, an international financial centre whereby financial shocks are intermediated away quickly. We gauge near-term risks around growth projections taken from the survey of professional forecasters by accounting for financial stress in both local and global financial markets, as well as worldwide economic uncertainty. The conditioning variables are first linked to future growth through quantile regressions, and the estimated quantiles are fitted with skew t-distributions to produce full predictive distributions. Scenario analysis reveals that greater local financial strain tends to widen the uncertainty of growth outlook, higher …

Your Cursor Reveals: On Analyzing Workers’ Browsing Behavior And Annotation Quality In Crowdsourcing Tasks, Pei-Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

In this work, we investigate the connection between browsing behavior and task quality of crowdsourcing workers performing annotation tasks that require information judgements. Such information judgements are often required to derive ground truth answers to information retrieval queries. We explore the use of workers’ browsing behavior to directly determine their annotation result quality. We hypothesize user attention to be the main factor contributing to a worker’s annotation quality. To predict annotation quality at the task level, we model two aspects of task-specific user attention, also known as general and semantic user attentions . Both aspects of user attention can be …

The Gender Wage Gap In An Online Labor Market: The Cost Of Interruptions, Abi Adams, Kotaro Hara, Kristy Milland, Chris Callison-Burch

Research Collection School Of Computing and Information Systems

This paper analyses gender differences in working patterns and wages on Amazon Mechanical Turk, a popular online labour platform. Using information on 2 million tasks, we find no gender differences in task selection nor experience. Nonetheless, women earn 20% less per hour on average. Gender differences in working patterns are a significant driver of this wage gap. Women are more likely to interrupt their working time on the platform with consequences for their task completion speed. A follow-up survey shows that the gender differences in working patterns and hourly wages are concentrated amongst workers with children.

Deep Reinforcement Learning With Explicit Context Representation, Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji

Research Collection School Of Computing and Information Systems

Though reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems, most RL algorithms lack an explicit method that would allow learning from contextual information. On the other hand, humans often use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. However, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This article proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state …