Engineering Commons^™

Sustainable Mobility: Machine Learning-Driven Deployment Of Ev Charging Points In Dublin, Ruairí De Fréin, Alexander Mutiso Mutua Mr

Articles

Electric vehicle (EV) drivers in urban areas face range anxiety due to the fear of running out of charge without timely access to charging points (CPs). The lack of sufficient numbers of CPs has hindered EV adoption and negatively impacted the progress of sustainable mobility. We propose a CP distribution algorithm that is machine learning-based and leverages population density, points of interest (POIs), and the most used roads as input parameters to determine the best locations for deploying CPs. The objects of the following research are as follows: (1) to allocate weights to the three parameters in a $6$ km …

Reducing Carbon Footprint In Ai: A Framework For Sustainable Training Of Large Language Models, Sunbal Iftikhar, Steven Davy

Conference papers

In the world of artificial intelligence (AI), large language models (LLMs) are leading the way, transforming how people understand and use language. These models have significantly impacted various domains, from natural language processing (NLP) to content generation, sparking a wave of innovation and exploration. However, this rapid progress brings to light the environmental implications of LLMs, particularly the significant energy consumption and carbon emissions during their training and operational phases. This requires a shift towards more energy-efficient practices in training and deploying LLMs, balancing AI innovation with environmental responsibility. This paper emphasizes the need for improving the energy efficiency of …

Building Services Engineering November/December 2024

Building Services Engineering

No abstract provided.

Interpreting Black-Box Time Series Classifiers Using Parameterised Event Primitives, Ephrem Tibebe Mekonnen, Luca Longo, Pierpaolo Dondio

Conference papers

Amidst the remarkable performance of deep learning models in time series classification, there is a pressing demand for methods that unveil their prediction rationale. Existing feature importance techniques often neglect the temporal nature of time series data, focusing solely on segment importance. Addressing this gap, this paper introduces a local model-agnostic method akin to LIME, which generates neighbouring samples by randomly perturbing segments of the original instance. Subsequently, weights are computed for each neighbouring instance based on its distance from the original, elucidating its influence. Parameterised event primitives (PEPs) are then extracted from these perturbed samples, encompassing increasing and decreasing …

Towards An Iot-Enabled Digital Earth For Sdgs: The Data Quality Challenge, Msb Syed, Paula Kelly, Paul Stacey, Damon Berry

Articles

Digital Earth (DE), a technology offering real-time visualisation of Earth's processes, has shown promising results in aiding decision-making for a sustainable world, raising awareness about individual impacts on our planet, and supporting the United Nations Sustainable Development Goals (UN SDGs) agenda. However, both DE and SDGs face a common obstacle: Data Quality (DQ). This review investigates the challenge of DQ in the context of DE for SDGs and explores how IoT can address this challenge and extend the reach of DE to support SDGs. Furthermore, the study discusses three core aspects; first, the potential of IoT as a data source …

Investigating Gender Bias In Large Language Models Through Text Generation, Shweta Soundararajan, Sarah Jane Delany

Conference papers

Large Language Models (LLMs) have swiftly become essential tools across diverse text generation applications. However, LLMs also raise significant ethical and societal concerns, particularly regarding potential gender biases in the text they produce. This study investigates the presence of gender bias in four LLMs: ChatGPT 3.5, ChatGPT 4, Llama 2 7B, and Llama 2 13B. By generating a gendered language dataset using these LLMs, focusing on sentences about men and women, we analyze the extent of gender bias in their outputs. Our evaluation is two-fold: we use the generated dataset to train a gender stereotype detection task and measure gender …

A Global Model-Agnostic Rule-Based Xai Method Based On Parameterized Event Primitives For Time Series Classifiers, Ephrem T. Mekonnen, Luca Longo, Pierpaolo Dondio

Articles

Time series classification is a challenging research area where machine learning and deep learning techniques have shown remarkable performance. However, often, these are seen as black boxes due to their minimal interpretability. On the one hand, there is a plethora of eXplainable AI (XAI) methods designed to elucidate the functioning of models trained on image and tabular data. On the other hand, adapting these methods to explain deep learning-based time series classifiers may not be straightforward due to the temporal nature of time series data. This research proposes a novel global post-hoc explainable method for unearthing the key time steps …

Design Considerations For Self-Management Technologies For People Living With Dementia And Informal Carers - Perspectives Of Healthcare Professionals And Charity Workers, Dympna O'Sullivan, Julie Doyle, Orla Moran, Michael Wilson, Siobhan Oneill, Jonathan Turner, Suzanne Smith

Conference papers

Dementia is a neurodegenerative disorder that leads to decline in memory, language, reasoning, and the ability to perform daily activities. It is linked to poorer quality of life for the person with dementia and their informal (unpaid) carers. While early intervention and access to adequate care are critical in slowing dementia's progression and better managing associated symptoms, dementia is frequently only diagnosed at an advanced stage and care is often fragmented. To better understand how to meet the complex needs of persons living with dementia and their informal carers, 10 healthcare professionals and 10 charity workers from relevant community and …

Design Considerations For Self-Management Technologies For People Living With Dementia And Informal Carers – Perspectives Of Healthcare Professionals And Charity Workers, Dympna O'Sullivan

Conference papers

Dementia is a neurodegenerative disorder that leads to decline in memory, language, reasoning, and the ability to perform daily activities. It is linked to poorer quality of life for the person with dementia and their informal (unpaid) carers. While early intervention and access to adequate care are critical in slowing dementia's progression and better managing associated symptoms, dementia is frequently only diagnosed at an advanced stage and care is often fragmented. To better understand how to meet the complex needs of persons living with dementia and their informal carers, 10 healthcare professionals and 10 charity workers from relevant community and …

Materiality And The Machine. Maximising Material Experiences In The Age Of Ai, Ceri Almrott, Keith Colton, Mark Ennis, Ina O'Connor

Conference Papers

Artificial Intelligence (AI) and related technologies are expected to significantly impact the future of design, but traditional design methods are still important. Material Intelligence (MI) is crucial for product designers, and a structured four-year approach to undergraduate design education centred around experiential learning through MI is presented. The approach emphasises hands-on experimentation, integrates MI into the core curriculum, and prioritises interdisciplinary collaboration to produce innovative, functional, and sustainable design solutions.

Building Services Engineering September/October 2024

Building Services Engineering

No abstract provided.

Empirical Investigation Of Withdrawal Capacity Of Staple For Experimental Design Of Irish Timber, Afnan Nafees, Patrick Mcgetrick, Aimee Byrne

Conference papers

Sitka spruce is the main tree species grown in Ireland, covering over 50% of the forest area. Despite this, Ireland imported €1.8 billion worth of wood products in 2020 mostly from UK, China, US and Sweden. One of the factors that currently limits the specifying of Irish grown timber in construction applications is the lack of data relating to its structural performance. Expanding the use of this locally available material in construction will add economic and environmental benefits, creating new opportunities for employment. In order to effectively use Irish timber for structural purposes, a comprehensive analysis of its inherent properties …

A Hierarchical Framework For Interpretable, Safe, And Specialised Deep Reinforcement Learning, Ammar Abbas

Doctoral

Safety-critical systems, which are crucial for human safety and the environment, are difficult to control and operate. Traditional controllers need precise models of these complex systems, which is hard to develop. \acrfull{drl} offers a potential solution by learning from interactions rather than detailed models, but it faces limitations such as non-transparent decision-making and an expensive, unsafe learning process. Additionally, a key challenge in DRL is ensuring effective decision-making in rare situations.

This thesis proposes a novel approach called the \acrfull{prop_frame} that enables safe and reliable control of critical systems. SRLA combines probabilistic modelling with reinforcement learning to create an interpretable …

Road To Sustainability: Developing A Sustainability Performance Measurement Framework For City Logistics From A Multi-Stakeholder Perspective, Xu Zhang

Doctoral

Sustainability assessment in city logistics has been a perpetual and salient agenda among city managers and logistics industry practitioners, especially in light of the promotion of the new Corporate Sustainability Reporting Directive (CSRD) and European Sustainability Reporting Standards (ESRS). Research studies to date have tried to assess city logistics operations’ sustainability performance and their impact, but most endeavours have ended in vain due to elusive sustainability goals, inconsistent indicator quality, ambiguous stakeholder responsibility, and poor data availability on city levels.

To address these challenges, this study is advocating for a collaborative sustainability reporting and assessment process among public and private …

Cyber Resilience, Risk Management, And Security Challenges In Enterprise-Scale Cloud Systems: Comprehensive Review, Abdiaziz Abdi, Hajar Bennouri, Anthony Keane

Conference Papers

The cyberthreat landscape is constantly evolving with the rapid development of cloud computing. Today, businesses and consumers rely heavily on cloud infrastructure, which provides high availability and resilient systems. However, cloud and IoT platforms contain vulnerabilities that can compromise data confidentiality, integrity, and availability, leading to disruptions in service operations. These significant challenges pose serious threats such as vulnerabilities, misconfigurations, data breaches, faulty hardware, and application failures with high costs. IBM reports that the average cost of a data breach worldwide is approximately US$4.5 million per incident. This highlights the need for adequately designed resilience systems with high availability and …

Emerging Cyber Risks & Threats In Healthcare Systems: A Case Study In Resilient Cybersecurity Solutions, Abdiaziz Abdi, Hajar Bennouri, Anthony Keane

Conference Papers

The exponential growth of digitalisation in healthcare and the ongoing threat of cybersecurity breaches are significant and cast a shadow over the industry’s progress. As the cost of data breaches reaches unprecedented levels, reaching an average of US$10.93 million in 2023 alone, and the frequency of attacks escalates, evidenced by a staggering 60% increase in phishing incidents between 2022 and 2023 reported by Smarttech247, Healthcare infrastructure is at a critical intersection. In this paper, we address the complex relationship between harnessing the potential of digital systems to improve and combating the escalating risks posed by cyber threats. The cyberattack on …

Building Sevices Engineering July/August 2024

Building Services Engineering

No abstract provided.

Title: List Of 132 Papers Citing One Or More Skin Lesion Image Datasets, Neda Alipour, Ted Butke, Jane Courtney

Other resources

This document is provided as a supplementary digital resource to accompany the article Skin Type Diversity in Skin Lesion Datasets: A Review. The following list contains 132 papers that were identified during a systematic review of papers that use one or more skin lesion image datasets. A partial list of these papers appears in Table 1 of the aforementioned article. The full list is provided here for reference.

Refining Transversal Skills Through Engineering Design Projects: A Case For Authentic Assessment, Gerald Gallagher, Kevin Delaney, David Salter, Mingzhu Chen

Conference Papers

Transversal skills were typically not the focus of traditional engineering education, where strong technical prowess by students tended to be emphasised in undergraduate and postgraduate study. However, the importance of developing these skills, having application across multiple career trajectories, is becoming a key area of development in engineering education. An engineering design module presented in this work has been refined to act as a vehicle to help students develop and practice these transversal skills while simultaneously reinforcing their abilities in mechanical design. This paper describes how the module has been structured and operationalised, through approximations of practice and authentic assessment, …

Early Age Assessment Of A New Course Of Irish Fly Ash As A Cement Replacement, Niall Holmes Dr., Nikki Shaji, Mark Tyrer

Articles

This paper explores the potential of a new source of fly ash, deposited on the site of a coalfired power plant in Ireland dating from 1985 to 1995, as a cement replacement material. A series of X-ray diffraction (XRD) analyses on binder samples with cement replacement levels of 0, 10, 25 and 35% was undertaken to determine the fly ash’s mineralogical composition and to determine its suitability as a supplemental cementitious material (SCM). The XRD results reveal a unique mineral composition with promising characteristics for enhancing the strength and durability of concrete. The experimental results were used to calibrate a …

Explainable Machine Learning For The Regulatory Environment: A Case Study In Micro-Droplet Printing, Elaine Harris, Darragh F. Ryan, Gerard M. O'Connor

Articles

Micro-droplet printing remains an invaluable tool for the additive manufacturing industry due to its versatility, efficiency and cost-effectiveness. The design and deployment of a disposable micro-droplet dispenser seeks to facilitate a quick and easy way to alternate between different printing materials (such as ink, metals, bio-materials, pharmaceuticals, etc.) without the need for thorough cleaning or separate delivery systems. While this works well in principle, in practice achieving consistent performance between dispensers can prove challenging. This paper aims to tackle this issue through the use of Machine Learning (ML) in order to (1) build a model that predicts dispenser performance from …

Building Services Engineering May/June 2024

Building Services Engineering

No abstract provided.

Education And Training Networks, Ken Thomas, Robin Stubbs, Emily Shakespeare

Tools

Education And Training Networks Inventory is a review of relevant network in Ireland and the EU.

Processworkflows Cwmf To Iso 19650-2, Emma Hayes, Robert Moore

Tools

Process workflow that presents the Capital Works Management Framework (CWMF) according to ISO 19650-2, Government of Ireland.

doi:10.21427/nhzb-pp57

Circular Economy Eu Networks Inventory, Mark Kelly, James O’Donnell, Derek Sinnott, Azedine Derardja, Sadaf Dalirazar, Ioannis Markou

Tools

Circular Economy EU Networks Inventory is a review of complementary EU research projects in the area of Circular Economy

Comparative Assessment Of Gold Nanoparticle-Antibody Conjugates With Two Differently Shaped Particles For Multimodal Colorimetric Lateral Flow Assay, Vinayak Sharma, Bilal Javed, Furong Tian

Articles

Novel detection strategies that exploit the unique properties of gold nanoparticles (AuNPs) hold great potential for the advancement of point-of-care (POC) diagnostics, such as lateral flow and dipstick immunoassay [1–3]. Owing to its biocompatibility and convenient surface modifications, gold nanoparticles with enhanced sensitivity reduce the sample-to-answer times to less than 5 min (Figure 1). Methods like covalent conjugation and electrostatic adsorption are explored for antibody immobilization to develop a gold nanoparticle-based biosensor for fast and sensitive localized surface plasmon resonance (LSPR) for both basic research and clinical diagnostics. The mounting of antibodies on the gold nanoparticle surface requires selective binding …

Comparing Anova And Powershap Feature Selection Methods Via Shapley Additive Explanations Of Models Of Mental Workload Built With The Theta And Alpha Eeg Band Ratios, Bujar Raufi, Luca Longo

Articles

Background: Creating models to differentiate self-reported mental workload perceptions is challenging and requires machine learning to identify features from EEG signals. EEG band ratios quantify human activity, but limited research on mental workload assessment exists. This study evaluates the use of theta-to-alpha and alpha-to-theta EEG band ratio features to distinguish human self-reported perceptions of mental workload. Methods: In this study, EEG data from 48 participants were analyzed while engaged in resting and task-intensive activities. Multiple mental workload indices were developed using different EEG channel clusters and band ratios. ANOVA’s F-score and PowerSHAP were used to extract the statistical features. At …

Building Services Engineering March/April 2024

Building Services Engineering

No abstract provided.

Profess 12: Project Report 5: The Profess 12 Summer School - Evaluation, Una Beagon, Ruchita Jani, Janet Mckennedy, Brian Bowe, Margaret Morgan, Rosalind M Henry

Reports

This report outlines the evaluation of the summer school which was a key element of the PROFESS 12 project. The key steps involved in the 5-day summer school along with the method by which the feedback and the reflections of the participants of the summer school were collected is described here. Thereafter, the reflections received in the form of audio and text files are analysed and themes identified from the experience of the summer school participants are explained in detail.

The survey responses from the feedback on the summer school participation are also shown graphically. This analysis helped us identify …

Profess 12: Project Report 2: Priority Skills For Engineers On The Island Of Ireland: Key Stakeholder Perceptions, Rosalind M Henry, Margaret Morgan, Una Beagon, Ruchita Jani, Janet Mckennedy, Brian Bowe

Reports

Life on a shared island, in particular the island of Ireland (comprising Ireland and Northern Ireland), presents both challenges and opportunities, including for engineers tasked with addressing problems to help solve the SDGs that are indifferent to boundaries. Research demonstrates that (relative to current engineers) the engineer of the future will require a more diverse range of skills to navigate an increasingly complex work environment. Given this context, identification of relevant priority skills would therefore prove useful in focusing engineering educational initiatives.

Building on a European study (Beagon et al, 2022a) which identified at a European level the professional skills …