Physical Sciences and Mathematics Commons^™

A Hybrid Neural Network For Stock Price Direction Forecasting, Daniel Devine

Dissertations

The volatility of stock markets makes them notoriously difficult to predict and is the reason that many investors sell out at the wrong time. Contrary to the efficient market hypothesis (EMH) and the random walk theory, contribution to the study of machine learning models for stock price forecasting has shown evidence of stock markets predictability with varying degrees of success. Contemporary approaches have sought to use a hybrid of convolutional neural network (CNN) for its feature extraction capabilities and long short-term memory (LSTM) neural network for its time series prediction. This comparative study aims to determine the predictability of stock …

Identifying Significant Features For Player Evaluation In Nfl Comparing Anns And Traditional Models, Ronan Walsh

Dissertations

The evaluation of player performance in sports is popular and important in modern sports, enabling teams to use real data in the construction of their rosters. This dissertation proposes to apply machine learning algorithms to predicting the player evaluations from a leading NFL analytics company who use a combination of statistics and expert evaluation. In addition, it will investigate what features are significant in the evaluation of a position. Data for the dissertation is obtained from multiple online sources - Pro Football Reference and Pro Football Focus (the the NFL analytics company). These data sets are combined and analysed before …

Identifying Roles Of Software Developers From Their Answers On Stack Overflow, Dean Power

Dissertations

Stack Overflow is the world’s largest community of software developers. Users ask and answer questions on various tagged topics of software development. The set of questions a site user answers is representative of their knowledge base, or “wheelhouse”. It is proposed that clustering users by their wheelhouse yields communities of similar software developers by skill-set. These communities represent the different roles within software development and could be used as the basis to define roles at any point in time in an ever-evolving landscape of software development. A network graph of site users, linked if they answered questions on the same …

Can Generative Adversarial Networks Help Us Fight Financial Fraud?, Sean Mciver

Dissertations

Transactional fraud datasets exhibit extreme class imbalance. Learners cannot make accurate generalizations without sufficient data. Researchers can account for imbalance at the data level, algorithmic level or both. This paper focuses on techniques at the data level. We evaluate the evidence of the optimal technique and potential enhancements. Global fraud losses totalled more than 80 % of the UK’s GDP in 2019. The improvement of preprocessing is inherently valuable in fighting these losses. Synthetic minority oversampling technique (SMOTE) and extensions of SMOTE are currently the most common preprocessing strategies. SMOTE oversamples the minority classes by randomly generating a point between …

Performance Comparison Between A Distributed Particle Swarm Algorithm And A Centralised Algorithm, Ciarán O’Loughlin

Dissertations

Particle Swarm optimisation (PSO) is a particular form of swarm intelligence, which itself is an innovative intelligent paradigm for solving optimization problems. PSO is generally used to find a global optimum in a single optimisation function. This typically occurs on one node(machine) but there has been a significant body of research into creating distributed implementations of the PSO algorithm. Such research has often focused on the creation and performance of the distributed implementation in an isolated manner or compared to different distributed algorithms.

This research piece aims to bridge a gap in the existing literature, by testing a distributed implementation …

Comparing Passenger Satisfaction, Employees’ Perspective And Performance On Quality And Safety Indicators: A Field Study, Luca D’Alonzo, Maria Chiara Leva, Edgardo Bucciarelli

Articles

This paper aims to analyze the impact that different attributes related to a Regional Airport service and the socio-economic factors of the passengers have on the passenger’s overall satisfaction. The study also compared passenger and employee satisfaction in relation to the service offered by the airport, to identify possible critical areas of improvement. An Ordinal Logistic Regression (OLR) approach was used to model how the attributes considered for qualifying airport services and the socio-economic variables impact the predicted variable (i.e., passenger satisfaction). Furthermore, the results were triangulated to include quality and safety performance indicators as an objective anchor point for …

Food Contact Surfaces: Challenges, Legislation And Solutions, Shubham Sharma, Amit Jaiswal, Brendan Duffy, Swarna Jaiswal

Articles

Food contact surfaces (FCSs) include all surfaces that may come in contact with the food during production, processing, and packaging. Food processing industries encounter several challenges due to its microbial interaction with the FCSs, such as cross-contamination of pathogenic microorganisms or allergens in food, formation of biofilm, biodeterioration of food contact surface leads to food with reduced shelf-life and quality. A legal EU framework provides the fundamental postulates for the safety and inertness of all Food Contact Materials (FCMs). Legislations have an important role in providing regulatory guidance on the quality assurance systems and verifying their implementation as a means …

Near-Field Propagation Analysis For Vivaldi Antenna Design: Insight Into The Propagation Process For Optimizing The Directivity, Integrity Of Signal Transmission, And Efficiency, Ha Hoang, Matthias John, Patrick Mcevoy, Max Ammann

Articles

Refined optimization of complex curve–linear-shaped radiators, such as traveling-wave Vivaldi antennas, can be achieved by considering simulated near fields to interpret in detail the structural influences of a design. The relationships between the space and time distributions of electromagnetic (EM) energy clusters and the geometric features are revealed with appropriate use of impulse response analysis combined with the multiple signal classification (MUSIC) algorithm. This article reports a deeper approach when applied to the adjustment of the geometric features of a traveling-wave antenna based on an analysis of near-field propagation features.

Effect Of Mutation And Vaccination On Spread, Severity, And Mortality Of Covid-19 Disease, Dr Hossam Zawbaa, Hasnaa Osama, Ahmed El‐Gendy, Haitham Saeed, Hadeer S. Harb, Yasmin M. Madney, Mona Abdelrahman, Marwa Mohsen, Ahmed M.A. Ali, Mina Nicola, Marwa O. Elgendy, Ihab A. Ibrahim, Mohamed E.A. Abdelrahim

Articles

Coronavirus disease 2019 (COVID-19) has had different waves within the same country. The spread rate and severity showed different properties within the COVID-19 different waves. The present work aims to compare the spread and the severity of the different waves using the available data of confirmed COVID-19 cases and death cases. Real-data sets collected from the Johns Hopkins University Center for Systems Science were used to perform a comparative study between COVID-19 different waves in 12 countries with the highest total performed tests for severe acute respiratory syndrome coronavirus 2 detection in the world (Italy, Brazil, Japan, Germany, Spain, India, …

Event-Driven Servers Using Asynchronous, Non-Blocking Network I/O: Performance Evaluation Of Kqueue And Epoll, Lorcan Leonard

Dissertations

This research project evaluates the performance of kqueue and epoll in the context of event-driven servers. The evaluation is done through benchmarking and tracing which are used to measure throughput and execution time respectively. The experiment is repeated for both a virtualised and native server environment. The results from the experiment are statistically analysed and compared. These results show significant differences between kqueue and epoll, and a profound impact of virtualisation as a variable.

Evaluation Of Postoperative Refractive Error Correction After Cataract Surgery, Ellen Konadu Antwi-Adjei, Emmanuel Owusu, Emmanuel Kobia-Acquah, Emmanuella Esi Dadzie, Emmanuel Anarfi, Seth Wanye

Articles

Suboptimal cataract surgery outcomes remain a challenge in most developing countries. In Ghana, about 2 million people have been reported to be blind due to cataract with about 20% new cases being recorded yearly. The aim of this study was to evaluate postoperative correction of refractive errors after cataract surgery in a selected eye hospital in Ashanti Region, Ghana. This was a retrospective study where medical records of patients (aged 40–100) who reported to an eye hospital in Ghana from 2013–2018 were reviewed. Included in the study were patients aged ≥40 years and patients with complete records. Data on patient …

The Design And Evaluation Of An Educational Software Development Process For First Year Computing Undergraduates, Catherine Higgins

Doctoral

First year, undergraduate computing students experience a series of well-known challenges when learning how to design and develop software solutions. These challenges, which include a failure to engage effectively with planning solutions prior to implementation ultimately impact upon the students’ competency and their retention beyond the first year of their studies. In the software industry, software development processes systematically guide the development of software solutions through iterations of analysis, design, implementation and testing. Industry-standard processes are, however, unsuitable for novice programmers as they require prior programming knowledge. This study investigates how a researcher-designed educational software development process could be created …

Just-In-Time Pastureland Trait Estimation For Silage Optimization, Under Limited Data Constraints, Patricia O'Byrne

Doctoral

To ensure that pasture-based farming meets production and environmental targets for a growing population under increasing resource constraints, producers need to know pastureland traits. Current proximal pastureland trait prediction methods largely rely on vegetation indices to determine biomass and moisture content. The development of new techniques relies on the challenging task of collecting labelled pastureland data, leading to small datasets. Classical computer vision has already been applied to weed identification and recognition of fruit blemishes using morphological features, but machine learning algorithms can parameterise models without the provision of explicit features, and deep learning can extract even more abstract knowledge …

Combined Experimental And Modeling Analysis For Thedevelopment Of Optical Materials Suitable To Enhance Theimplementation Of Plasmonic-Enhanced Luminescent Down-Shifting Solutions On Existing Silicon-Based Photovoltaic Devices, James Walshe, Mihaela Girtan, Sarah Mccormack, John Doran, George Amarandei

Articles

The development of highly efficient solar collectors requires modulating the light interactions with the semiconducting materials. Incorporating luminescent species and metal nanoparticles within a semitransparent polymeric material (e.g., polymethyl methacrylate (PMMA)) leads to the formation of a plasmon-enhanced luminescent down-shifting (PLDS) layer, which offers a retrofittable approach toward expanding the wavelength range over which the conversion process can effectively occur. Adding antireflection coatings (ARCs) further controls the spectral response. However, with each additional component comes additional loss pathways. In this study, the losses related to light interactions with the PMMA and the ARCs have been investigated theoretically using a transfer …

Optimisation Of Retrofit Wall Insulation: An Irish Case Study, Rakshit D. Muddu, D M. Gowda, Anthony James Robinson, Aimee Byrne

Articles

Ireland has one of the highest rates of emissions per capita in the world and its residential sector is responsible for approximately 10% of total national CO2 emissions. Therefore, reducing the CO2 emissions in this sector will play a decisive role in achieving EU targets of reducing emissions by 40% by 2030. To better inform decisions regarding retrofit of the existing building stock, this study proposes Optimum Insulation Thicknesses (OIT) for typical walls in 25 regions in Ireland. The calculation of OIT includes annual heat energy expenditure, CO2 emissions, and material payback period. The approach taken is based on Heating …

An Investigation Into Employee Exposure To Environmental Tobacco Smoke Within Designated Smoking Areas In The Hospitality Industry, With An Analysis Of Legislative Compliance Of Said Designated Smoking Areas, Hannah Byrne

Masters

Background: Occupational exposure to environmental tobacco smoke (ETS) is still occurring in the hospitality industry and the instance of non-compliant smoking areas required investigation. A designated smoking area covered by a roof where more than 50% of the perimeter of that part is surrounded by one or more walls is deemed a non-compliant smoking area. This study aimed to gather evidence of non-compliances across Dublin, determine current employee exposure whilst also measuring PM2.5 concentrations within smoking areas as well as providing insight into possible immediate health effects of ETS exposure.

Methods: Seventy-five smoking areas (41 located in high, 27 in …

Acute Growth Inhibition & Toxicity Analysis Of Nano-Polystyrene Spheres On Raphidocelis Subcapitata, Anthony Reynolds, Michelle Giltrap, Gordon Chambers

Articles

Micro/nano-plastics (MNPs) have been found within many environments and organisms including humans, making them a significant and growing concern. Initial research into the potential detrimental effects these MNPs both from acute and chronic exposure has been ongoing but still requires substantially more data to clarify. This research presents the response of nano-polystyrene (NPS) on Raphidocelis subcapitata, a freshwater alga, under an existing acute toxicity test along with additional analytical techniques to try identifying possible sources of toxicity. R. subcapitata cells were exposed for 72 h to a concentration range of 0–100 mg/l NPS. Growth Inhibition (GI) testing showed the …

On The Mandelbrot Set For I**2 = ±1 And Imaginary Higgs Fields, Jonathan Blackledge

Articles

We consider the consequence of breaking with a fundamental result in complex analysisby lettingi2=±1wherei=√−1is the basic unit of all imaginary numbers. An analysis of theMandelbrot set for this case shows that a demarcation between a Fractal and a Euclidean object ispossible based oni2=−1andi2= +1, respectively. Further, we consider the transient behaviourassociated with the two cases to produce a range of non-standard sets in which a Fractal geometricstructure is transformed into a Euclidean object. In the case of the Mandelbrot set, the Euclideanobject is a square whose properties are investigate. Coupled with the associated Julia sets and othercomplex plane mappings, this …

Carbon Futures Trading And Short-Term Price Prediction:An Analysis Using The Fractal Market Hypothesis And Evolutionary Computing, Marc Lamphiere, Jonathan Blackledge, Derek Kearney

Articles

This paper presents trend prediction results based on backtesting of the European UnionEmissions Trading Scheme futures market. This is based on the Intercontinental Exchange from 2005to 2019. An alternative trend prediction strategy is taken that is predicated on an application of theFractal Market Hypothesis (FMH) in order to develop an indicator that is predictive of short termfuture behaviour. To achieve this, we consider that a change in the polarity of the Lyapunov-to-Volatility Ratio precedes an associated change in the trend of the European Union Allowances (EUAs)price signal. The application of the FMH in this case is demonstrated to provide a …

The 3d Printing Of Dielectric Elastomer Films Assisted By Electrostatic Force, Yuhao Wang, Yanfen Zhou, Wenyue Li, Zhanxu Liu, Bangzi Zhou, Shipeng Wen, Liang Jiang, Shaojuan Che, Jianwei Ma, Tony Betts, Stephen Jerrams, Fenglei Zhou

Articles

ompared with traditional methods for preparing dielectric elastomer (DE) films, electrohydrodynamic (EHD) 3D printing displays many advantages, notably full automation, computer control and flexible design. It also confers high printing resolution, high preparation efficiency with minimal probability of nozzle clogging. In this article, EHD 3D printing was employed to fabricate silicone rubber (SR) based DE films. In order to increase their dielectric constant, high dielectric copper phthalocyanine (CuPc) particles were added into the SR ink. Optimal printing conditions were determined by analyzing the effects of printing voltage and ink properties on the formation of liquid cone and the printed line …

Development And Testing Of A Dual‐Wavelength Sensitive Photopolymer Layer For Applications In Stacking Of Hoe Lense, Sanjay Keshri, Brian Rogers, Kevin Murphy, Kevin Reynolds, Izabela Naydenova, Suzanne Martin

Articles

Diffractive optical elements (DOEs) have been in development for many years and are an exciting technology with the capability to re‐direct light, using diffraction rather than refraction. Holographic Optical Elements (HOEs) are a subset of diffractive optical elements for which the pho‐ tonic structure is created holographically, i.e., by recording a specific interference pattern in a suit‐ able, photosensitive optical material. Volume HOEs are of particular interest for some applications because of their very high diffraction efficiency and single diffracted order; however, high disper‐ sion and angular wavelength selectivity still present significant challenges. This paper explores a method for producing …

In Depth Characterisation Of The Biomolecular Coronas Of Polymer Coated Inorganic Nanoparticles With Differential Centrifugal Sedimentation, André Perez-Potti, Hender Lopez, Beatriz Pelaz, Abuelmagd Abdelmonem, Mahmoud G. Soliman, Ingmar Schoen, Philip M. Kelly, Kenneth A. Dawson, Wolfgang J. Parak, Zeljka Krpetic, Marco P. Monopoli

Articles

Advances in nanofabrication methods have enabled the tailoring of new strategies towards the controlled production of nanoparticles with attractive applications in healthcare. In many cases, their characterisation remains a big challenge, particularly for small-sized functional nanoparticles of 5 nm diameter or smaller, where current particle sizing techniques struggle to provide the required sensitivity and accuracy. There is a clear need for the development of new reliable characterisation approaches for the physico-chemical characterisation of nanoparticles with significant accuracy, particularly for the analysis of the particles in the presence of complex biological fluids. Herein, we show that the Differential Centrifugal Sedimentation can …

Private Groundwater Management And Risk Awareness: A Cross-Sectional Analysis Of Two Age-Related Subsets In The Republic Of Ireland, Simon Mooney, J. O'Dwyer, Paul Hynds

Articles

Risk communication represents the optimal instrument for decreasing the incidence of private groundwater contamination and associated waterborne illnesses. However, despite attempts to promote voluntary well maintenance in high groundwater-reliant regions such as the Republic of Ireland, awareness levels of supply status (e.g. structural integrity) have remained low. As investigations of supply awareness are often thematically narrow and homogeneous with respect to sub-population, revised analyses of awareness among both current and future supply owners (i.e. adults of typical well owner and student age) are necessary. Accordingly, the current study utilised a national survey of well users and an age-based comparison of …

Towards An Improved Understanding Of Biogeochemical Processes Across Surface-Groundwater Interactions In Intermittent Rivers And Ephemeral Streams, Lluís Gómez-Gener

Articles

Surface-groundwater interactions in intermittent rivers and ephemeral streams (IRES), waterways which do not flow year-round, are spatially and temporally dynamic because of alternations between flowing, non-flowing and dry hydrological states. Interactions between surface and groundwater often create mixing zones with distinct redox gradients, potentially driving high rates of carbon and nutrient cycling. Yet a complete understanding of how underlying biogeochemical processes across surface-groundwater flowpaths in IRES differ among various hydrological states remains elusive. Here, we present a conceptual framework relating spatial and temporal hydrological variability in surface water-groundwater interactions to biogeochemical processing hotspots in IRES. We combine a review of …

Direct Multiplexing Of Low Order Aberration Modes In A Photopolymerbased Holographic Element For Analog Holographic Wavefront Sensing, Emma Branigan, Suzanne Martin, Matthew Sheehan, Kevin Murphy

Conference Papers

The fabrication of an analog holographic wavefront sensor, capable of detecting the low order defocus aberration, was achieved in an acrylamide-based photopolymer. While other implementations of holographic wavefront sensors have been carried out digitally, this process utilises a recording setup consisting only of conventional refractive elements so the cost and complexity of holographic optical element (HOE) production could be much reduced. A pair of diffraction spots, corresponding to a maximum and minimum amount of defocus, were spatially separated in the detector plane by multiplexing two HOEs with different carrier spatial frequencies. For each wavefront with a known aberration that was …

Predictive Modeling Of Critical Temperatures In Superconducting Materials, Markus Hofmann, Natalia Sizochenko

Articles

n this study, we have investigated quantitative relationships between critical temperaturesof superconductive inorganic materials and the basic physicochemical attributes of these materials(also called quantitative structure-property relationships). We demonstrated that one of the mostrecent studies (titled "A data-driven statistical model for predicting the critical temperature of asuperconductor” and published in Computational Materials Science by K. Hamidieh in 2018) reportson models that were based on the dataset that contains 27% of duplicate entries. We aimed todeliver stable models for a properly cleaned dataset using the same modeling techniques (multiplelinear regression, MLR, and gradient boosting decision trees, XGBoost). The predictive ability ofour best …

Monitoring Stem Cell Differentiation Using Raman Microspectroscopy: Chondrogenic Differentiation, Towards Cartilage Formation, Francesca Ravera, Esen Efeoglu, Hugh Byrne

Articles

Mesenchymal Stem Cells (MSCs) have the ability to differentiate into chondrocytes, the only cellular components of cartilage and are therefore ideal candidates for cartilage and tissue repair technologies. Chondrocytes are surrounded by cartilage-like extracellular matrix (ECM), a complex network rich in glycosaminoglycans, proteoglycans, and collagen, which, together with a multitude of intracellular signalling molecules, trigger the chondrogenesis and allow the chondroprogenitor to acquire the spherical morphology of the chondrocytes. However, although the mechanisms of the differentiation of MSCs have been extensively explored, it has been difficult to provide a holistic picture of the process, in situ. Raman Micro Spectroscopy (RMS) …

Semiclassical Backreaction On Asymptotically Anti–De Sitter Black Holes, Peter Taylor, Cormac Breen

Articles

We consider a quantum scalar field on the classical background of an asymptotically anti–de Sitter black hole and the backreaction the field’s stress-energy tensor induces on the black hole geometry. The backreaction is computed by solving the reduced-order semiclassical Einstein field equations sourced by simple analytical approximations for the renormalized expectation value of the scalar field stress-energy tensor. When the field is massless and conformally coupled, we adopt Page’s approximation to the renormalized stress-energy tensor, while for massive fields we adopt a modified version of the DeWitt-Schwinger approximation. The latter approximation must be modified so that it possesses the correct …

Collaborations In Environmental Initiatives For An Effective Gover- Nance Of Social-Ecological Systems: What The Scientific Literature Suggests., Elena Andriollo, Alberto Caimo, Laura Secco, Elena Pisani

Articles

Moving from the scientific literature on evaluation of environmental projects and programs, this study identifies how and under which conditions collaborations are considered effective for adaptive gover- nance of SES. The method adopted is a systematic literature review based on the quantitative and qualitative analysis of 56 articles selected through specific queries on the SCOPUS database and published from 2004 to 2020. Results of the quantitative analysis underline conditions able to make collaborations effective for adaptive governance of SES: the importance of transdisciplinary research tackling both environmental and social sciences, the perceived urgency of stakeholders to tackle environmental challenges and …

Sure 2021 Undergraduate Science Conference Booklet, Sure Network

Group Reports

The SURE 2021 Conference was the fourth series of Science Undergraduate Research Experience (SURE) Conferences and second online conference, following earlier face to face series in 2018 (with three conferences in Dublin, Athlone and Waterford) and in 2019 (with three conferences in Dublin, Sligo and Carlow). The 2021 virtual online conference was hosted by Waterford Institute of Technology (WIT), TUS:MM (Athlone Institute of Technology) and Dundalk Institute of Technology (Dundalk IT) and featured 23 oral presentations and 48 poster presentations across three thematic streams/break out rooms on zoom. An interactive virtual poster session took place using …