Digital Commons Network^™

Learning Comprehensive Global Features In Person Re-Identification: Ensuring Discriminativeness Of More Local Regions, Jiali Xia, Jianqiang Huang, Shibao Zheng, Qin Zhou, Bernt Schiele, Xian-Sheng Hua, Qianru Sun

Research Collection School Of Computing and Information Systems

Person re-identification (Re-ID) aims to retrieve person images from a large gallery given a query image of a person of interest. Global information and fine-grained local features are both essential for the representation. However, global embedding learned by naive classification model tends to be trapped in the most discriminative local region, leading to poor evaluation performance. To address the issue, we propose a novel baseline network that learns strong global feature termed as Comprehensive Global Embedding (CGE), ensuring more local regions of global feature maps to be discriminative. In this work, two key modules are proposed including Non-parameterized Local Classifier …

Online Hyperparameter Optimization For Class-Incremental Learning, Yaoyao Liu, Yingying Li, Bernt Schiele, Qianru Sun

Research Collection School Of Computing and Information Systems

Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. However, none of the existing CIL models can achieve the optimal tradeoff in different data-receiving settings—where typically the training-from-half (TFH) setting needs more stability, but the training-from-scratch (TFS) needs more plasticity. To this end, we design an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori. Specifically, we first introduce the …

Real-Time Hierarchical Map Segmentation For Coordinating Multi-Robot Exploration, Tianze Luo, Zichen Chen, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Coordinating a team of autonomous agents to explore an environment can be done by partitioning the map of the environment into segments and allocating the segments as targets for the individual agents to visit. However, given an unknown environment, map segmentation must be conducted in a continuous and incremental manner. In this paper, we propose a novel real-time hierarchical map segmentation method for supporting multi-agent exploration of indoor environments, wherein clusters of regions of segments are formed hierarchically from randomly sampled points in the environment. Each cluster is then assigned with a cost-utility value based on the minimum cost possible …

Safe Delivery Of Critical Services In Areas With Volatile Security Situation Via A Stackelberg Game Approach, Tien Mai, Arunesh Sinha

Research Collection School Of Computing and Information Systems

Vaccine delivery in under-resourced locations with security risks is not just challenging but also life threatening. The COVID pandemic and the need to vaccinate added even more urgency to this issue. Motivated by this problem, we propose a general framework to set-up limited temporary (vaccination) centers that balance physical security and desired (vaccine) service coverage with limited resources. We set-up the problem as a Stackelberg game between the centers operator (defender) and an adversary, where the set of centers is not fixed a priori but is part of the decision output. This results in a mixed combinatorial and continuous optimization …

A Fair Incentive Scheme For Community Health Workers, Avinandan Bose, Tracey Li, Arunesh Sinha, Tien Mai

Research Collection School Of Computing and Information Systems

Community health workers (CHWs) play a crucial role in the last mile delivery of essential health services to under-served populations in low-income countries. Many non-governmental organizations (NGOs) provide training and support to enable CHWs to deliver health services to their communities, with no charge to the recipients of the services. This includes monetary compensation for the work that CHWs perform, which is broken down into a series of well-defined tasks. In this work, we partner with a NGO D-Tree International to design a fair monetary compensation scheme for tasks performed by CHWs in the semi-autonomous region of Zanzibar in Tanzania, …

Scalable And Globally Optimal Generalized L1 K-Center Clustering Via Constraint Generation In Mixed Integer Linear Programming, Aravinth Chembu, Scott Sanner, Hassan Khurram, Akshat Kumar

Research Collection School Of Computing and Information Systems

The k-center clustering algorithm, introduced over 35 years ago, is known to be robust to class imbalance prevalent in many clustering problems and has various applications such as data summarization, document clustering, and facility location determination. Unfortunately, existing k-center algorithms provide highly suboptimal solutions that can limit their practical application, reproducibility, and clustering quality. In this paper, we provide a novel scalable and globally optimal solution to a popular variant of the k-center problem known as generalized L1 k-center clustering that uses L1 distance and allows the selection of arbitrary vectors as cluster centers. We show that this clustering objective …

Human-Centered Ai For Software Engineering: Requirements, Reflection, And Road Ahead, David Lo

Research Collection School Of Computing and Information Systems

Since its inception in the 2000s, AI for Software Engineering (AI4SE) has grown rapidly. AI in its different forms, e.g., data mining, information retrieval, machine learning, natural language processing, etc., has been demonstrated to be able to produce good results for automating many tasks, including specification mining, bug and vulnerability discovery, bug localization, duplicate bug report identification, failure detection, program repair, technical question answering, code search, and many more. AI4SE has much potential to improve software engineers’ productivity and software quality. Due to its potential, it is currently one of the most popular research areas in the software engineering field.To …

An Empirical Study Of Package Management Issues Via Stack Overflow, Syful Islam, Raula Kula, Christoph Treude, Bodin Chinthanet, Takashi Ishio, Kenichi Matsumoto

Research Collection School Of Computing and Information Systems

The package manager (PM) is crucial to most technology stacks, acting as a broker to ensure that a verified dependency package is correctly installed, configured, or removed from an application. Diversity in technology stacks has led to dozens of PMs with various features. While our recent study indicates that package management features of PM are related to end-user experiences, it is unclear what those issues are and what information is required to resolve them. In this paper, we have investigated PM issues faced by end-users through an empirical study of content on Stack Overflow (SO). We carried out a qualitative …

Quantization-Aware Interval Bound Propagation For Training Certifiably Robust Quantized Neural Networks, Mathias Lechner, Dorde Zikelic, Krishnendu Chatterjee, A. Thomas Henzinger, Daniela Rus

Research Collection School Of Computing and Information Systems

We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training …

Oria Stage Ii Expansion: Keep River Post-Development Aquatic Fauna And Targeted Sawfish Survey - 2022, Indopacific Environmental, Department Of Primary Industries And Regional Development, Western Australia

Irrigated Agricultural Development in the North

This report presents the results of the 2022 Keep River Aquatic Fauna and Targeted Sawfish Survey which represents the final post-development survey required as per the project conditions of the Goomig Irrigation Development. Unlike the 2021 survey, which was affected by pandemic related travel restrictions that prohibited some sites from being surveyed, all regular monitoring sites were able to be sampled in 2022. Field work was undertaken September 2022 and sampling and analyses undertaken during the current study aligned with standardised methodologies set forth in the Ord River Irrigation Area – Weaber Plain Development Project Aquatic Fauna Management Plan.

Building Resilience In Graduate Nurses Through Online Virtual Simulation, Robert Grant Harmon

Electronic Theses and Dissertations

Resilience has become a popular topic in nursing research. Nurses experience enormous stress throughout their training process that extends into their first employment as they transition into practice. Simulation training is a standard for training nurses and for continuing professional education within academia. Most simulation training for nurses is focused on building critical thinking skills. While critical thinking is an essential quality equipping nurses to meet professional demands, resilience is a crucial quality to overcome the stress of both training and practice. Resilience is believed to play an essential role in the retention of new graduate nurses and preventing burnout …

Smartphone Use And Daily Cognitive Failures: A Critical Examination Using A Daily Diary Approach With Objective Smartphone Measures, Andree Hartanto, Kristine Y. X. Lee, Yi Jing Chua, Frosch Y. X. Quek, Nadyannam M. Majeed

Research Collection School of Social Sciences

While smartphones have brought many benefits and conveniences to users, there is continuing debate regarding their potential negative consequences on everyday cognition such as daily cognitive failures. A few cross-sectional studies have found positive associations between smartphone use and cognitive failures. However, several research gaps remain, such as the use of cross-sectional designs, confounds related to stable individual differences, the lack of validity in self-report measures of smartphone use, memory biases in retrospective self-reports, and the lack of differentiation between smartphone checking and smartphone screen time. To simultaneously address the aforementioned shortcomings, the current study examined the within-person associations between …

Executive Function Deficits And Borderline Personality Disorder Symptomatology In A Nonclinical Adult Sample: A Latent Variable Analysis, Keisha D. Veerapandian, Gabriel X. D. Tan, Nadyanna M. Majeed, Andree Hartanto

Research Collection School of Social Sciences

While borderline personality disorder (BPD) symptomatology has been studied extensively in clinical populations, the mechanisms underlying its manifestation in nonclinical populations remain largely understudied. One aspect of BPD symptomatology in nonclinical populations that has not been well studied is cognitive mechanisms, especially in relation to executive functions. To explore the cognitive mechanisms underlying BPD symptomatology in nonclinical populations, we analysed a large-scale dataset of 233 young adults that were administered with nine executive function tasks and BPD symptomatology assessments. Our structural equation modelling did not find any significant relations between latent factors of executive functions and the severity of BPD …

A Narrative Review Of Screen Time And Wellbeing Among Adolescents Before And During The Covid-19 Pandemic: Implications For The Future, Verity Yu Qing Lua, Terence B. K. Chua, Michael Y. H. Chia

Research Collection School of Social Sciences

The COVID-19 pandemic has disrupted the lives of many. In particular, during the height of the pandemic, many experienced lockdowns, which in turn increased screen time drastically. While the pandemic has been declared an endemic and most activities have been reinstated, there appears to still be elevated screen time among adolescents due to poor habits formed during the pandemic lockdowns. This paper explores the factors by which screen time affects well-being among adolescents and how the pandemic may have influenced some of these factors. For example, beyond having greater screen time, many adolescents have also reduced their physical activities and …

The Study Of Followers In Leadership Research: A Systematic And Critical Review, Burak Oc, Kraivin Chintakananda, Michael R. Bashshur, David V. Day

Research Collection Lee Kong Chian School Of Business

Despite the significant amount of existing research examining the relationship of follower-related factors with leadership outcomes, there is no systematic, critical review that integrates and helps leadership scholars make sense of this rapidly growing body of research. To address this gap in the literature, we first briefly discuss the leading perspectives explaining the role of followers in leadership. Next, we identify and discuss the most frequently studied theoretical narratives explaining the relationship between follower-related predictors and leadership outcomes. Because theoretical arguments generally make causal claims, we identify and examine how methodological concerns including power analysis, multicollinearity, and endogeneity might prevent …

Deep Feature Meta-Learners Ensemble Models For Covid-19 Ct Scan Classification, Jibin B. Thomas, K. V. Shihabudheen, Sheik Mohammed Sulthan, Adel Al-Jumaily

Research outputs 2022 to 2026

The infectious nature of the COVID-19 virus demands rapid detection to quarantine the infected to isolate the spread or provide the necessary treatment if required. Analysis of COVID-19-infected chest Computed Tomography Scans (CT scans) have been shown to be successful in detecting the disease, making them essential in radiology assessment and screening of infected patients. Single-model Deep CNN models have been used to extract complex information pertaining to the CT scan images, allowing for in-depth analysis and thereby aiding in the diagnosis of the infection by automatically classifying the chest CT scan images as infected or non-infected. The feature maps …

Using Nanomaterials As Excellent Immobilisation Layer For Biosensor Design, Azeez Olayiwola Idris, Seyi Philemon Akanji, Benjamin O. Orimolade, Foluke Omobola Grace Olorundare, Shohreh Azizi, Bhekie Mamba, Malik Maaza

Research outputs 2022 to 2026

The endless development in nanotechnology has introduced new vitality in device fabrication including biosensor design for biomedical applications. With outstanding features like suitable biocompatibility, good electrical and thermal conductivity, wide surface area and catalytic activity, nanomaterials have been considered excellent and promising immobilisation candidates for the development of high-impact biosensors after they emerged. Owing to these reasons, the present review deals with the efficient use of nanomaterials as immobilisation candidates for biosensor fabrication. These include the implementation of carbon nanomaterials—graphene and its derivatives, carbon nanotubes, carbon nanoparticles, carbon nanodots—and MXenes, likewise their synergistic impact when merged with metal oxide nanomaterials. …

Transeuntis Mundi, A Nomadic Artistic Practice, Cândida Luiza Borges Da Silva

School of Law, Humanities and Social Sciences Theses

In this practice-led Ph.D. research, I investigate how an artistic practice can respond to the migration phenomena performed by human beings across the planet over millennia ¬– what I refer to as the millennial global human journey. Based on the idea of mobility, I chose to frame this research in the articulation of concepts deriving from the prefix trans: transculture, transhumance and transmediality. This research contributes to studies in art composition by developing the processes and concept of transmedial composition, mainly contributing to the field of New Media Art. This investigation resulted in the work Transeuntis Mundi (TM) Project – …

Road Traffic Management Using Vehicle-To- Everything (V2x) Communication, Azzeddine Ben Khadra

Theses

Traffic congestion is the primary concern in dense cities; while the increased number of automobiles is becoming uncontrollable in some cities, it is more challenging to manage or change how people use cars. To contribute to solving traffic congestion in cities, this project examines the study of transferring vehicles to be competent in a way that can help the government entities analyze the received vehicles’ data and for better decisions on reducing traffic congestion as well as the real-time monitoring of traffic wherever it is located using the Vehicle-to-Everything (V2X) communication methodology. This study proposes a hardware “system” that can …

Practical Led-Based Spectral Imaging For Cultural Heritage Studio Photography, Olivia R. Kuzio

Theses

"Wouldn't it be better if 99% of institutions were working toward 99% accuracy, rather than 1% of institutions working toward 100% accuracy?" — John Barrett (Senior Photographer, Bodleian Libraries) during the AHFAP panel discussion "The Practical Implementation of Imaging Standards" in February 2022. In an increasingly virtual world, cultural heritage collections are more frequently experienced on a screen than in person. For especially precious or ephemeral works, reproductions may serve as the primary means of interacting with them. Often, series of works or related pieces are held in different collections, and it may be logistically complicated to exhibit them together …

Empirical Investigations And Dataset Collection For American Sign Language-Aware Personal Assistants, Abraham Trout Glasser

Theses

Proliferation of voice-controlled personal-assistant devices poses accessibility barriers for Deaf and Hard of Hearing (DHH) users. It is estimated that 128 million people use a voice assistant in the United States, and 4.2 billion digital voice assistants being used around the world, e.g. through over 60,000 different smart home devices that support Amazon's Alexa, which is one instance of virtual assistants [97,134]. The ongoing (at the time of this dissertation) coronavirus pandemic has accelerated the uptake of home-based, voice-controlled devices. As artificial intelligence researchers and developers are working on American Sign Language (ASL) recognition technologies, Human-Computer Interaction (HCI) research is …

Smart Hvac System For A Residential House In Kerala, India And Study Of Green Building Regulations In Thrissur, Kerala, India And Dubai, Uae, Sariga Sunilkumar

Theses

The objective is to analyze the green building regulations in Dubai, UAE and Thrissur, Kerala. By comparing these regulations. An understanding of the factors that impact the residents of the building built using these green building regulations and what can be learned from each regulation, and if there is a common factor connecting these two cities with different climates. The rising temperatures in fact have reduced similarities between the two, as Thrissur is a tropical wet climate and Dubai is hot however the temperatures and humidity levels during the summer are similar. The comparative analysis will allow for the determination …

Pyrolysis Transports, And Transforms, Pfas From Biosolids To Py-Liquid, Patrick J. Mcnamara, Melvin S. Samuel, Sandeep Sathyamoorthy, Lynne Moss, Danny Valtierra, Hugo Cortes Lopez, Nicholas J. Nigro, Stephen Somerville, Zhongzhe Liu

Civil and Environmental Engineering Faculty Research and Publications

Per- and poly-fluoroalkyl substances (PFAS) in wastewater solids have resulted in bans on land application of biosolids, causing utilities to explore thermal treatment options. Pyrolysis is a thermal treatment process that converts wastewater solids to biochar, py-liquid (i.e., aqueous phase liquid and non-aqueous phase liquid), and py-gas. Research on the impact of pyrolysis on PFAS in biosolids has yielded mixed results, and no research has investigated if PFAS are present in the py-liquid. The goals of this research were to determine if pyrolysis releases PFAS with the effluent py-liquid and to distinguish “removal” from “transformation” of PFAS. Triplicate …

In Touch With Prairie Living, February 2023, Michael M. Miller

In Touch With Prairie Living Newsletter

February 2023 column for North Dakota and South Dakota newspapers.

Design And Characterization Of An Aerosol Test Chamber For Emergency Response Patient Contamination Control Simulation And Research, Megan L. Steele, Emily M. Spatz, George P. Lemmer, Jacob M. Denney, Casey Cooper, Jeremy M. Slagley, Robert M. Eninger

Faculty Publications

Contaminated or infected patients present a risk of cross-contamination for emergency responders, attending medical personnel and medical facilities as they enter a treatment facility. The controlled conditions of an aerosol test chamber are required to examine factors of contamination, decontamination, and cross-contamination. This study presents the design, construction, and a method for characterizing an aerosol test chamber for a full-sized manikin on a standard North Atlantic Treaty Organization litter. The methodology combined air velocity measurements, aerosol particle counts and size distributions, and computational fluid dynamics modeling to describe the chamber’s performance in three dimensions. This detailed characterization facilitates future experimental …

House Price Prediction Using Machine Learning Model, Abdulla Alfalasi

Theses

Data Analytics and Machine Learning play an important role in extracting insights and patterns from datasets. The primary objective of using the above techniques for real world problems is to understand the intricacies of the problem, which is impossible with the help of manual human effort. The below chart shows the price trend (per sq. ft) over the past 10 years in Dubai, with a steady rise during the years from 2014. The 2020 pandemic plummeted the global prices due to the lack of demand and travel restrictions, which is clearly depicted in the chart. But at the very end …

Missed Opportunities In The Diagnosis Of Tuberculosis Meningitis, Niamh Simmons, Margaret A Olsen, Joanna Buss, Thomas C Bailey, Carlos Mejia-Chew

2020-Current year OA Pubs

BACKGROUND: Tuberculosis meningitis (TBM) has high mortality and morbidity. Diagnostic delays can impact TBM outcomes. We aimed to estimate the number of potentially missed opportunities (MOs) to diagnose TBM and determine its impact on 90-day mortality.

METHODS: This is a retrospective cohort of adult patients with a central nervous system (CNS) TB

RESULTS: Of 893 patients with TBM, median age at diagnosis was 50 years (interquartile range, 37-64), 61.3% were male, and 35.2% had Medicaid as primary payer. Overall, 407 (45.6%) had a prior hospital or ED visit with an MO code. In-hospital 90-day mortality was not different between those …

Broad Protective Vaccination Against Systemic Escherichia Coli With Autotransporter Antigens, Dylan M Chirman, Sabrina Green, Jacob J Zulk, Joseph Jelinski, Kathryn A Patras, Anthony W Maresso

Faculty, Staff and Students Publications

Extraintestinal pathogenic Escherichia coli (ExPEC) is the leading cause of adult life-threatening sepsis and urinary tract infections (UTI). The emergence and spread of multidrug-resistant (MDR) ExPEC strains result in a considerable amount of treatment failure and hospitalization costs, and contribute to the spread of drug resistance amongst the human microbiome. Thus, an effective vaccine against ExPEC would reduce morbidity and mortality and possibly decrease carriage in healthy or diseased populations. A comparative genomic analysis demonstrated a gene encoding an invasin-like protein, termed sinH, annotated as an autotransporter protein, shows high prevalence in various invasive ExPEC phylogroups, especially those associated with …

A Corpus-Driven Comparative Analysis Of Verb Phrase Based Bundles In L2 Malaysian Polytechnic Learners’ Writing, Subramaniam Radika

Student Works (2020-2029)

This study aims to explore the similarities and differences in the use of verb phrase-based (VP-based) bundles in the writing of L2 Malaysian Engineering learners via the Malaysian Polytechnic Electronic Engineering Learner Corpus (MyPolyEELC) in comparison to their native counterparts in the British Academic Written English (BAWE) sub-corpus and experts in the Electrical and Electronic Engineering Research Articles Corpus (3ERAC). The MyPolyEELC which consists of 891,919 words is developed from 231 Final Year Project reports written by Electronic Engineering Diploma learners from 14 Malaysian polytechnics. The 374,383-word BAWE sub-corpus is compiled from the existing BAWE corpus by selecting texts written …

The Perceptions Of Faculty And Instructional Designers Regarding The Impact Of Professional Development To Teach Online Courses, Scott Mitchell January

Electronic Theses and Dissertations

Leadership at a mid-sized 4-year university in the western region of Texas asserted a problem with the low amount of faculty training impacting online courses’ creation and quality. The purpose of this qualitative single case study was to investigate the elements needed to design quality online courses, determine how faculty and instructional designers perceived professional development provided by the university to develop online courses, and find out how faculty and instructional designers perceived professional development impacted faculty skills as an online instructor. Three research questions were created which generated two interview protocols. The following research questions were used and were …