Engineering Commons^™

Fake News Detection In Online Platforms, Elena Shushkevich

Doctoral

This thesis presents research conducted during a Ph.D. program at Technological University Dublin from 2020 to 2024. The objective of this research is to develop and evaluate effective methods for detecting and classifying fake news in social media and press, addressing the critical issue of misinformation in the digital age. The relevance of this study is underscored by the increasing prevalence of fake news and its potential societal impact, emphasizing the importance of advanced tools for identifying and mitigating misinformation.

Multiple Sclerosis Diagnosis With Deep Learning And Explainable Ai, Nighat Bibi, Jane Courtney, Kathleen M. Curran

Conference papers

Diagnosing multiple sclerosis (MS) presents significant challenges due to its complex clinical presentation and the subjective interpretation of imaging findings. Machine learning (ML) and deep learning (DL) models, despite their potential, often exacerbate these challenges with their opaque decision-making processes, hindering clinical integration. This study addresses these limitations by employing eXplainable Artificial Intelligence (XAI) techniques, specifically integrating Grad-CAM within a Convolutional Neural Network (CNN) framework, EfficientNetB1, for the diagnosis of MS. The primary objective is to enhance the transparency and reliability of MS diagnosis by providing clear visual insights into the model’s decision-making process, while also identifying and mitigating potential …

Enhancing Multiple Sclerosis Diagnosis With Explainable Ai, Nighat Bibi, Jane Courtney, Kathleen M. Curran

Conference papers

Multiple sclerosis (MS) is a complex neurological disorder that requires precise diagnosis for effective treatment. This study aims to enhance MS diagnosis by integrating eXplainable Artificial Intelligence (XAI) techniques into a convolutional neural network (CNN) framework. The proposed model achieves high accuracy and provides visual explanations of its predictions. Using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, it highlights the most important regions in MRI images influencing the model’s decisions, adding transparency and trust to the diagnostic process. The CNN, trained on a dataset of FLAIR MRI images, demonstrates superior performance compared to existing models, with a final accuracy of …

Build Digital Annual Survey 2023 Results, Clare Eriksson, Robert Moore, Bilal Succar

Reports

The Build Digital Annual Survey 2023 examines the level of digital transformation across Ireland’s construction and built environment sector. Based on 252 responses from industry, academia, and government, the report shows that most participants were working in organisations already engaged in digital transformation, with key expected benefits including improved accuracy, operational efficiency, cost reduction, faster clash resolution, and improved scheduling. The findings indicate that many respondents had experience using digital tools and methods across common model uses, particularly capturing and representing, planning and designing, and simulating and quantifying. The report also highlights continued challenges, including limited formal training, uneven assessment …

Building Services Engineering January/February 2024

Building Services Engineering

No abstract provided.

A Fully Automated Global Post-Hoc Method Based On Abstract Argumentation For Explainable Artificial Intelligence And Its Application On Fully Connected Dense Deep Neural Networks, Giulia Vilone

Dissertations

Explainable Artificial Intelligence (XAI) has rapidly grown in the past decade due to the prevalence of machine learning, especially deep learning, in fields like healthcare and finance. While these models excel in accuracy, their complexity hampers transparency and interpretability. Ensuring understandable explanations for AI predictions fosters trust, prevents errors, complies with regulations, and enhances model refinement. The research project outlined in this thesis unfolds in phases. It commences with a comprehensive review of existing XAI studies, contributing to the field’s knowledge by proposing a taxonomy that organises theories and notions related to explainability, the evaluation approaches for XAI methods, and …

Towards Interpretable Propaganda Detection In News Text Through The Use Of Rhetorical Devices As Features, Kyle Hamilton

Doctoral

This doctoral thesis presents research undertaken towards interpretable propaganda detection in news text. Propaganda and mis/disinformation in the media have been identified in the social sciences literature as a major threat to the functioning of democratic society. While mis/disinformation is false by definition, propaganda is intended to modify the beliefs and behaviors of the information consumer but does not have to be false. Propagandistic text is often characterized by the use of rhetorical devices and linguistic style designed to exploit the reader’s cognitive and emotional biases. One way of counteracting this effect is by shifting the focus from “what” is …

Privacy-Preserving Pedestrian Movement Analysis In Complex Public Spaces, Kunchala Anil

Doctoral

Every journey starts and ends with a walking phase. As a fundamental mode of transportation, it plays a crucial role in the functioning of urban societies. Cities should strive to create public spaces that promote walking by designing pedestrian-friendly infrastructure that is accessible, safe, and convenient for all. An essential step in designing pedestrian-friendly infrastructure is understanding pedestrian usage patterns and behaviour in existing public spaces and infrastructure.

A Review On Machine Learning Methods For Customer Churn Prediction And Recommendations For Business Practitioners, Awais Manzoor, M. Atif Qureshi, Etain Kidney, Luca Longo

Articles

Due to market deregulation and globalisation, competitive environments in various sectors continuously evolve, leading to increased customer churn. Effectively anticipating and mitigating customer churn is vital for businesses to retain their customer base and sustain business growth. This research scrutinizes 212 published articles from 2015 to 2023, delving into customer churn prediction using machine learning methods. Distinctive in its scope, this work covers key stages of churn prediction models comprehensively, contrary to published reviews, which focus on some aspects of churn prediction, such as model development, feature engineering and model evaluation using traditional machine learning-based evaluation metrics. The review emphasises …

Disaggregating Longer-Term Trends From Seasonal Variations In Measured Pv System Performance, Chibuisi Chinasaokwu Okorieimoh, Brian Norton, Michael Conlon

Articles

Photovoltaic (PV) systems are widely adopted for renewable energy generation, but their performance is influenced by complex interactions between longer-term trends and seasonal variations. This study aims to remove these factors and provide valuable insights for optimising PV system operation. We employ comprehensive datasets of measured PV system performance over five years, focusing on identifying the distinct contributions of longer-term trends and seasonal effects. To achieve this, we develop a novel analytical framework that combines time series and statistical analytical techniques. By applying this framework to the extensive performance data, we successfully break down the overall PV system output into …

Information Management Plan - Organisational, Robert Moore

Tools

Information Management Plan – Organisational, is a support in a spreadsheet format that contains a number of client templates that ISO 19650 recommend the Employer/Client/Sanctioning authority should consider before starting a delivery project for an Asset.

Build Digital has created Industry templates to allow organisations work in accordance with ISO 19650. These templates start to address the information requirements in the ISO 19650 series of standards. The templates are also in accordance with CEN-TR17654-2021” Guideline for the implementation of Exchange Information Requirements (EIR)and BIM Execution Plans (BEP) on European level based on EN ISO 19650-1 and -2”. Aspects of the …

Information Management Plan – Appointing Party, Robert Moore

Tools

Information Management Plan – Appointing Party is a support in a spreadsheet format that contains a number of client templates that ISO 19650 recommend the Employer/Client/Sanctioning authority should consider when appointing a delivery team to a delivery project for an Asset.

Build Digital has created Industry templates to allow organisations work in accordance with ISO 19650. These templates start to address the information requirements in the ISO 19650 series of standards. The templates are also in accordance with CEN-TR17654-2021” Guideline for the implementation of Exchange Information Requirements (EIR)and BIM Execution Plans (BEP) on European level based on EN ISO 19650-1 …

Project Information Standard – File Naming, Robert Moore

Tools

Project Information Standard – File Naming is a support in a spreadsheet format that contains a number of templates that give guidance on file naming in accordance with the Irish National Annexe to ISO 19650-2.

Build Digital has created Industry templates to allow organisations work in accordance with ISO 19650. These templates start to address the information requirements in the ISO 19650 series of standards. The templates are also in accordance with CEN-TR17654-2021” Guideline for the implementation of Exchange Information Requirements (EIR)and BIM Execution Plans (BEP) on European level based on EN ISO 19650-1 and -2”. Aspects of the Templates …

Energy Efficiency And Fault Tolerance In Open Ran And Future Internet, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open Radio Access Networks (Open RAN) repre- sent a promising technological advancement within the realm of the future internet. Research efforts are currently directed towards enhancing energy efficiency and fault tolerance, which are critical aspects for both Open RAN and the future internet landscape. In the context of energy saving in Open RAN, there exists a spectrum of methods for achieving energy efficiency. These methods include the toggling of on/off states for different hardware resources such as base station units, distributed units, and radio units. Conversely, for enhancing fault tolerance in Open RAN, Software-Defined Networking (SDN) and OpenFlow based techniques …

Improving Energy Efficiency In Open Ran Through Dynamic Cpu Scheduling, Saish Urumkar, Byrav Ramamurthy, Sachin Sharma

Conference papers

Open RAN is a promising cellular technology that is currently undergoing extensive research for future wireless radio access networks. Achieving optimal energy efficiency in Open RAN poses a significant challenge. This paper introduces a CPU scheduling algorithm that specifically targets this chal- lenge by optimizing energy consumption at the base station while maintaining optimal performance levels. With the goal of minimizing energy consumption, the proposed algorithm dynamically adjusts the CPU core states, seamlessly switching between active and sleep modes based on the load conditions. To evaluate the algorithm’s effectiveness in terms of energy saving and performance, experimental testing is conducted …

The Need For Energy Storage On Renewable Energy Generator Outputs To Lessen The Geeth Effect, I.E. Short-Term Variations Mainly Associated With Wind Turbine Active Power Output, Tony Kealy

Articles

Many studies investigating the short-term variations associated with the power output from wind turbine generators utilise simulated or modelled data in the analysis. This current study uses short-term empirical data downloaded directly from operational wind turbines via electrical power quality meters. The empirical data shows that the short-term variations (one-second or sub-one-second timeframe) occur continuously over most of the power output range. A novel name is proposed, the Geeth Effect, for this variability phenomenon. The Geeth Effect is measured using the coefficient of variation mathematical expression and is likely contributing to (i) lower-than-expected financial and environmental benefits associated with …

Revising Policy And Process: A Collaborative Project Between The Society Of Chartered Surveyors Ireland (Scsi) And Tu Dublin, Roisin Murphy Dr, James Lonergan

Conference Papers

No abstract provided.

Are We Day-Dreaming Our Way To The Future?, John O'Connor

Presentations

This paper explores the transformative impact of technology on society, drawing on Marshall McLuhan’s insights. It scrutinizes the consequences of profit-driven technological progress, particularly in VR, brain-computer interfaces, and AI hallucinations. Critiquing the dominance of industry leaders in AI safety discussions, the paper advocates a balanced, inclusive approach.

Philosophical perspectives on AI and VR prompt questions about their impact on human experience. The paper proposes an educational shift to cultivate human attributes alongside technological skills. Examining AI hallucinations and gaming glitches, it raises concerns about the potential blurring of reality and virtuality.

Connecting technological advancements with environmental challenges, the paper …

A Comprehensive Review On Metal Oxide-Nanocellulose Composites In Sustainable Active And Intelligent Food Packaging, Kalpani Y. Perera, Amit Jaiswal, Swarma Jaiswal, Dileswar Pradhan

Articles

The aim of this article is to provide an overview of the potential advantages and drawbacks of nanocellulose and metal oxide-based composites in food packaging. These materials offer improved mechanical and barrier properties, as well as antioxidant and antimicrobial benefits that extend the shelf life of food products. Nanocomposite structures protect food from various physiological factors and immobilize enzymes, while metal oxide nanoparticles provide antibacterial effects against Gram-positive and Gram-negative bacteria. However, there are concerns regarding the safety of nanoparticles and their potential migration into packaged food during processing and storage. This article explores these issues and highlights the need …

Making Tradable White Certificates Trustworthy, Anonymous, And Efficient Using Blockchains, Nouman Ashraf, Sachin Sharma, Sheraz Aslam, Khursheed Aurangzeb

Articles

Fossil fuel pollution has contributed to dramatic changes in the Earth’s climate, and this trend will continue as fossil fuels are burned at an ever-increasing rate. Many countries around the world are currently making efforts to reduce greenhouse gas emissions, and one of the methods is the Tradable White Certificate (TWC) mechanism. The mechanism allows organizations to reduce their energy consumption to generate energy savings certificates, and those that achieve greater energy savings can sell their certificates to those that fall short. However, there are some challenges to implementing this mechanism, such as the centralized and costly verification and control …

Synergising Bim And Real-Time Data For Improved Efficiency: An Irish Case Study, Ahmed Hassan, Ankur Mitra, Alan Hore, Mark Mulville

Conference Papers

The evolution of 3D visualisation and the Internet of Things (IoT) presents a substantial opportunity for integrating real-time data with Building Information Models (BIM) to improve its functionality and construction workflow efficiency. Integrating real-time data with BIM can enhance the digital representation of construction buildings’ physical and functional characteristics and provide recordable status of on-site operations. Nevertheless, the integration between Visualisation and IoT technologies with BIM remains in its preliminary stages and faces a myriad of technical and operational challenges. Furthermore, developing advanced solutions to facilitate this complex integration requires a considerable understanding of the viability and feasibility of merging …

Digital Construction Annual Survey 2022 Report, Davitt Lamon, Ted Mckenna

Reports

The Annual Survey 2022 was conducted to assess the state of digital transformation in the Irish construction and built environment sector. This report presents the analysis of survey data, with a focus on implications for the Build Digital project and Build Digital’s five pillars: Digital Leadership & Cultural Change, Digital Standards, Digital Education & Training, Digital Procurement, and Sustainability & Circular Economy. Key findings from the survey indicated that a significant number of organisations have started their digital transformation journey, with many identifying themselves as proactive and possessing a clear business-focused strategy. However, a considerable cohort of respondents are keen …

International Information Management And Bim Best Practice Report, Ted Mckenna, Davitt Lamon

Reports

In order to inform the Digital Leadership and Cultural Change pillar of the Build Digital, a study of international best practice in digital adoption within the built environment sector globally was undertaken and is presented here-in. In order to identify key learnings for Ireland in the context of digital transformation, eight countries were included in this study, namely, Denmark, Finland, Netherlands, Germany, United Kingdom (UK), New Zealand, Australia and Singapore. These countries were selected for various reasons, including the level of digital maturity, the scale of the built environment sector and geographic spread. Key data for each country is included …

Sustainability And Circular Economy Horizon Scan And Needs Analysis, Sadaf Dalirazar, Mark Kelly, Derek Sinnott, James O'Donnell

Reports

The construction industry plays a crucial role in addressing the climate crisis as it is the largest global consumer of raw materials and contributes significantly to global energy consumption and emissions. Considering the world’s continuous population growth and the imperative to address infrastructure and housing demands the construction sector needs to adopt further sustainable strategies in its activities to reduce the pressure on natural resources. In addition, the Architecture, Engineering, and Construction (AEC) sector is responsible for generating substantial amount of waste known as Construction and Demolition Waste (CDW), which is projected to increase due to the future construction developments. …

Information Management And Bim Standards And Supports Inventory, Ryan Dempsey, Barry Mcauley, David Burke

Tools

The Digital Standards pillar consists of industry experts who champion the benefits of common rules, guidelines, and workflows that facilitate the improvement of information flow and information management across asset life cycles. Digital standards provide a common language that can be translated to technical specifications enabling clients, designers, contractors, and facilities managers, irrespective of their preferred tools, to communicate efficiently and reduce cost, rework, and disputes. Working closely with the Digital Procurement and Digital Education and Training pillars, this pillar is developing and delivering Irish Information Management/BIM (Digital Construction) guidelines for the sector.

This report summarises existing digital construction standards, …

Poster: Optimising Electric Vehicle Charging Infrastructure In Dublin Using Geecharge, Alexander Mutiso Mutua, Ruairí De Fréin, Ali Malik, Kibanza Eliel, Sahbane Marco, Pantel Maxime

Conference papers

Range anxiety is a significant challenge affecting electric vehicles use as drivers fear running out of charge without finding a charging point on time. We develop methods to optimise the distribution of charging points. EV portacharge and GEECharge solutions distribute charging points in a city by considering the population density and Points Of Interest (POI) or road traffic. This paper focuses on (1) developing and evaluating methods to distribute Charging Points (CPs) in Dublin city; (2) optimising CP allocation; (3) visualising paths in the graph network to show the most used roads and points of interest; (4) describing a way …

Profess 12: Project Report Pr4: The Profess 12 Summer School Toolkit, Una Beagon, Margaret Morgan, Ruchita Jani, Rosalind M Henry, Janet Mckennedy, Brian Bowe

Reports

This document forms part of the PROFESS 12 Summer School Toolkit for engineering educators as a component of Work Package 3 in the HEA funded PROFESS 12 (PROFessional skills for Engineering students - Summer School to achieve SDG 12) Project.

This handbook outlines the pedagogical background to the design of the Summer School and describes in detail the components of each session, outlining the aims and objectives, teaching and learning activities and links to resources or templates as required. Educators are encouraged to provide feedback or additional relevant resources to the project team for inclusion as alternative options.

A student …

Building Services Engineering November/December 2023

Building Services Engineering

No abstract provided.

Building Services Engineering September/October 2023

Building Services Engineering

No abstract provided.

Contemporary Landscape, Drivers And Developments In Engineering Education For Sustainability, Edmond Byrne

Plenary Presentations and Doctoral Symposium

The ‘landscape’ around sustainability education in engineering has continued to evolve. Engineering education for sustainability largely emerged originally out of environmental engineering imperatives, though more recent developments have considerably broadened the scope of ‘sustainability’ teaching in professional engineering programmes. This has implications for associated curriculum developments as well as having pedagogical implications. Principal drivers for these developments emanate from the evolving requirements of professional engineering bodies internationally. These drivers have been supported and supplemented by an enhanced sense of urgency in the wake of the impacts of an unsustainable societal construct (e.g. the consequences of accelerated climate change, biodiversity loss, …