Digital Commons Network^™

A Comparative Analysis Of Shap, Lime, Anchors, And Dice For Interpreting A Dense Neural Network In Credit Card Fraud Detection, Bujar Raufi, Ciaran Finnegan, Luca Longo

Conference papers

Financial institutions heavily rely on advanced Machine Learning algorithms to screen transactions. However, they face increasing pressure from regulators and the public to ensure AI accountability and transparency, particularly in credit card fraud detection. While ML technology has effectively detected fraudulent activity, the opacity of Artificial Neural Networks (ANN) can make it challenging to explain decisions. This has prompted a recent push for more explainable fraud prevention tools. Although vendors claim to improve detection rates, integrating explanation data is still early. Data scientists recognize the potential of Explainable AI (XAI) techniques in fraud prevention, but comparative research on their effectiveness …

Human Centered Approaches And Taxonomies For Explainable Artificial Intelligence, Helen Sheridan, Emma Murphy, Dympna O'Sullivan

Conference papers

Recent interest within the research community related to explainable artificial intelligence (XAI) has led to a profuse amount of literature on the subject. Those who wish to tackle the domain from an HCI focus may be presented with overwhelming material, most of which does not pertain to human aspects of XAI. Taxonomies can serve to categorize a subject into topic areas and distill content into an overview of the field. This late breaking work intends to help those within the HCI community with a focus on XAI to understand relevant aspects of human centered XAI. We also present a taxonomy …

Using Chatgpt To Generate Gendered Language, Shweta Soundararajan, Manuela Nayantara Jeyaraj, Sarah Jane Delany

Conference papers

Gendered language is the use of words that denote an individual's gender. This can be explicit where the gender is evident in the actual word used, e.g. mother, she, man, but it can also be implicit where social roles or behaviours can signal an individual's gender - for example, expectations that women display communal traits (e.g., affectionate, caring, gentle) and men display agentic traits (e.g., assertive, competitive, decisive). The use of gendered language in NLP systems can perpetuate gender stereotypes and bias. This paper proposes an approach to generating gendered language datasets using ChatGPT which will provide data for data-driven …

Exploring The Design Of Low-End Technology To Increase Patient Connectivity To Electronic Health Records, Rens Kievit, Abdullahi Abubakar Kawu, Mirjam Van Reisen, Dympna O'Sullivan, Lucy Hederman

Conference papers

The tracking of the vitals of patients with long term health problems is essential for clinicians to determine proper care. Using Patient Generated Health Data (PGHD) communicated remotely allows patients to be monitored without requiring frequent hospital visits. Issues might arise when the communication of data digitally is difficult or impossible due to a lack of access to internet or a low level of digital literacy as is the case in many African countries. The VODAN-Africa project (van Reisen et al., 2021) started in 2020 and has greatly increased the capabilities of clinics in different countries in both Africa and …

An Investigation Of The Physical And Thermal Properties Of Irish Hemp Fibres As A Loose-Fill Insulation Product, Killian Markey, Sameer Mehra Dr., David Palmer, David Knight, Timothy O'Leary

Conference papers

Construction and built environment sectors account for approximately 37% of Ireland’s carbon emissions. Of this 37%, 14% of the emissions consist of embodied carbon emissions from the construction materials from the production to the end-of-disposal of buildings. The construction industry can reduce its embodied carbon by using materials with a lower embodied carbon. Hemp fibre batt insulation is an example of a bio-based material and a lower embodied carbon alternative to conventional insulations. The existing hemp fibre batt insulation is typically composed of hemp fibres with a polyester binder. These polyester binders have higher embodied carbon while also being a …

Exploring The Impact Of Design Professionals On The Energy Retrofit Of Dwellings In Ireland: A Qualitative Methodology, Olivia Golden

Conference papers

A qualitative approach was taken to investigate the role of design professionals in the energy retrofit of external wall insulation to dwellings in Ireland. The research method combines document analysis with semi structured interviews. Document analysis is used to both inform the questions for the interviews and for validation. The SEAI One Stop Shop grant scheme and PAS 2035 framework were selected for detailed document analysis to gain an understanding of the context in which design professionals are working in Ireland and compare it to the energy retrofit framework in the United Kingdom. This was investigated by mapping the data …

Chatting For Change: Insights Into And Directions For Using Online Peer Support Groups To Interrupt Prolonged Workplace Sitting, Ekaterina Uetova, Lucy Hederman, Dympna O'Sullivan, Robert J. Ross, Marily Oppezzo

Conference papers

Prolonged sedentary behavior and insufficient physical activity increase the risk for non-communicable diseases. Online peer support groups, driven by the widespread use of mobile phones and social media, have gained popularity among people seeking health condition management advice. This position paper examines the role of online peer support groups within a behaviour change intervention, MOV’D (Move Often eVery Day), which promotes physical activity and reduces sedentary behavior in the workplace. We conducted a thematic analysis of post-study interviews from two randomized control trials to identify the benefits and limitations of online peer support groups and provide recommendations for improvement. We …

Meeting The Sustainability Challenges: An Assessment Of Entrepreneurial Education, Anna Zherdeva, Intesar Madi, Abrar Alzankawi, Lucia Morales Dr, L. Pop, A. Soler-Dominguez, J.C. Saez

Conference papers

The importance of sustainability and entrepreneurship education is highlighted in this study. The world economies are facing significant challenges as they try to enable the transition towards more sustainable economic and business models. Therefore, at the centre of the transition process, it is critical to consider the role that business education can play and, more specifically, the role of business schools in integrating and supporting the development of skills and competencies that align with our contemporary society's needs. In this paper, we initially assess the need to connect entrepreneurial and sustainability education by exploring the educational offerings at Technological University …

An Exploration Into How Print And Online News Journalists Manage Political Fake News In Ireland, John William Hogan

Conference papers

This paper examines how a number of Irish political journalists, working for both traditional newspapers and an online news website, deal with the problem of fake news. The aim is to gain an understanding of what the journalists’ perception of political fake news is and the methods they employ to manage it - a sorely under researched topic. Our findings show that the journalists we spoke with feel there are a range of forms that fake news assumes, many of them insidious and challenging to overcome with facts. The paper highlights the important role journalists play in confronting political fake …

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 …

Exploring Wav2vec 2.0 Model For Heart Murmur Detection, Davoud Shariat Panah, Andrew Hines, Susan Mckeever

Conference papers

The lack of access to cardiology resources in many regions of the world has motivated the development of automatic diagnostic systems based on cardiac signals. In recent years, a wide range of supervised learning models have been proposed that can make an initial diagnosis of heart disease from heart sounds. To achieve high accuracy, however, such supervised learning models generally require a large amount of labeled data, which can be costly to obtain. In this regard, self-supervised learning has been recently employed to reduce the over-reliance on annotated data. Wav2vec 2.0 is an audio self-supervised learning model that has shown …

Developing Research Culture Among Staff Under Conditions Of Organizational Change, Mariia Perelygina, Denise O'Leary

Conference papers

This paper focuses on encouraging the growth of a research culture within a school of hospitality and tourism in one third-level institution in Ireland. The aim of the initiative is to increase engagement of staff members in impactful research, leading to benefits for individual staff members and a greater research profile for the school. Taking an action research approach, a plan of initiatives was designed and implemented to develop research culture. The paper examines the phenomenon of changing the organizational culture at the department level in a higher education institution undergoing a large amount of organisational change. The initiative is …

Leadership For The Future: Towards The Challenge Of Understanding Leadership In The Aec Sector, Roisin Murphy Dr, Rory Concannon, Oluwasegun Seriki Dr

Conference papers

The Irish Architecture, Engineering, and Construction (AEC) sector faces ongoing challenges relating to low productivity, digital adoption, sustainability, and innovation. Effective leadership is required to transform the sector to address these challenges and meet the future needs of society. However, there remains a lack of empirical evidence relating to leadership requirements, assessment, and development, in the context of the Irish AEC sector. As part of an ongoing study with the aim of developing resources to support leadership development, this research, conducted through a review of literature, examines how leadership is being assessed and explored in the AEC sector. The findings …

Exploring Factors That Influence Web Technology Adoption In A Time Of Crisis: A Ukraine Sme Perspective, Olena Kublitska, Róisín Vize Dr, Isobel O'Reilly Dr

Conference papers

This paper aims to investigate factors that influence web technologies adoption among small and medium enterprises in Ukraine and understand how volatile conditions influence managerial decisions about the operation of small retailers' businesses. This research takes a case study approach and uses qualitative semi-structured interviews. This study contributes to the existing literature on web technologies adoption among SMEs in developing countries, improves the understanding of the role of web technologies within SMEs operating in volatile conditions, and explores key-decision makers’ attitudes towards web technologies adoption within SMEs. The proposed framework based on Technology-Organization-Environment (TOE) is enriched with individual decision maker …

An Investigation Into The Application Of The Meijering Filter For Document Recapture Detection, John Magee, Stephen Sheridan Phd, Christina Thorpe Phd

Conference papers

The proliferation of mobile devices allows financial institutions to offer remote customer services, such as remote account opening. Manipulation of identity documents using image processing software is a low-cost, high-risk threat to modern financial systems, opening these institutions to fraud through crimes related to identity theft. In this paper we describe our exploratory research into the application of biomedical image algorithms to the domain of document recapture detection. We perform a statistical analysis to compare different types of recaptured documents and train a support vector machine classifier on the raw histogram data generated using the Meijering filter. The results show …

Interpretable Timbre Synthesis Using Variational Autoencoders Regularized On Timbre Descriptors, Anastasia Natsiou, Luca Longo, Sean O'Leary

Conference papers

Controllable timbre synthesis has been a subject of research for several decades, and deep neural networks have been the most successful in this area. Deep generative models such as Variational Autoencoders (VAEs) have the ability to generate a high-level representation of audio while providing a structured latent space. Despite their advantages, the interpretability of these latent spaces in terms of human perception is often limited. To address this limitation and enhance the control over timbre generation, we propose a regularized VAE-based latent space that incorporates timbre descriptors. Moreover, we suggest a more concise representation of sound by utilizing its harmonic …

Digital Challenges And Opportunities Of Addressing On-Site Productivity And Safety On Construction Job Sites: An International Perspective, Ahmed Hassan, Ankur Mitra, Mark Mulville, Alan Hore

Conference papers

The slow pace of digital transformation in construction remains an impediment to the industry’s evolution. Despite rapid developments in digital technologies, the vast bulk of data generated on construction job sites remains underutilised due to the limited use of real-time data capture. The diffusion of digital solutions in construction depends on successfully capturing critical real-time data that can inform and contribute to more productive work patterns and safer job sites. Nevertheless, the construction industry’s fragmented nature has segregated the digital solutions offered by technology providers from the volatile challenges facing on-site construction practitioners.

This paper will present the early development …

Poster: Round Trip Time Measurement Over Microgrid Power Network, Yasin Emir Kutlu, Ruairí De Fréin, Malabika Basu, Ali Malik

Conference papers

A focus of the Power Systems and Networking communities is the design and deployment of Microgrid (MG) integration systems that ensure that quality of service targets are met for load sharing systems at different endpoints. This paper presents an integrated Microgrid testbed that allows Microgrids endpoints to share their current, voltage and power values using a Network Published Shared Variable (NPSV) approach. We present Round Trip Time (RTT) measurements for time sensitive Microgrid control traffic in the presence of varying background traffic as an example quality of service measurement. Numerical results are presented using a range of different background traffic …

Round Trip Time Measurement Over Microgrid Power Network, Yasin Emir Kutlu, Ruairí De Fréin, Malabika Basu, Ali Malik

Conference papers

A focus of the Power Systems and Networking communities is the design and deployment of Microgrid (MG) integration systems that ensure that quality of service targets are met for load sharing systems at different endpoints. This paper presents an integrated Microgrid testbed that allows Microgrids endpoints to share their current, voltage and power values using a Network Published Shared Variable (NPSV) approach. We present Round Trip Time (RTT) measurements for time sensitive Microgrid control traffic in the presence of varying background traffic as an example quality of service measurement. Numerical results are presented using a range of different background traffic …

Integrated Dc Microgrid Testbed For Qos Evaluation, Yasin Emir Kutlu, Ruairí De Fréin, Malabika Basu, Ali Malik

Conference papers

This poster describes the development of an integrated Direct Current (DC) Microgrid (MG) testbed, consisting of power system and computer networking hardware, e.g. Cisco 4331 Integrated Services Routers (ISR) and 500W AC/DC power supplies, to test the Quality of Service (QoS) of MG control packets which are delivered over Layer-2 and Layer-3 networking topologies. It facilitates an examination of control packets between MG end-points, that enable real-time power load sharing, in the presence of background computer network traffic such as video streaming. The effects of difference levels of background traffic on the round trip time of control packets are demonstrated.

Identifying Online Child Sexual Texts In Dark Web Through Machine Learning And Deep Learning Algorithms, Vuong Ngo, Susan Mckeever, Christina Thorpe

Conference papers

Predators often use the dark web to discuss and share Child Sexual Abuse Material (CSAM) because the dark web provides a degree of anonymity, making it more difficult for law enforcement to track the criminals involved. In most countries, CSAM is considered as forensic evidence of a crime in progress. Processing, identifying and investigating CSAM is often done manually. This is a time-consuming and emotionally challenging task. In this paper, we propose a novel model based on artificial intelligence algorithms to automatically detect CSA text messages in dark web forums. Our algorithms have achieved impressive results in detecting CSAM in …

Poster: Integrated Dc Microgrid Testbed For Quality Of Service Evaluation, Yasin Emir Kutlu, Ruairí De Fréin, Malabika Basu, Ali Malik

Conference papers

This study demonstrates a testbed for evaluating the effects of background network traffic on the Round-Trip Times (RTTs) of community-based integrated Direct Current (DC) Microgrid (MG) testbed using real hardware and different networking topologies.

The effects of difference levels of background traffic on the RTT of control packets are demonstrated.

An Exploration Of The Latent Space Of A Convolutional Variational Autoencoder For The Generation Of Musical Instrument Tones, Anastasia Natsiou, Sean O'Leary, Luca Longo

Conference papers

Variational Autoencoders (VAEs) constitute one of the most significant deep generative models for the creation of synthetic samples. In the field of audio synthesis, VAEs have been widely used for the generation of natural and expressive sounds, such as music or speech. However, VAEs are often considered black boxes and the attributes that contribute to the synthesis of a sound are yet unsolved. Existing research focused on the way input data can influence the generation of latent space, and how this latent space can create synthetic data, is still insufficient. In this manuscript, we investigate the interpretability of the latent …

Co-Designing Assistive Technology With And For Persons Living With Dementia, Dympna O'Sullivan, Jonathan Turner, Siobhan O'Neill, Micheal Wilson, Julie Doyle

Conference papers

Dementia is a chronic and progressive neurodegenerative illness, which can lead to significant difficulties in a person’s capacity to perform activities of daily living (ADLs) and engage in meaningful activities. There is an acute need, which digital health technologies can potentially fulfil, to provide proactive support for persons living with dementia (PLwD) and their caregivers. However, there is limited involvement of PLwD in the design of technology that could be used to support their personal plans for independent living at home. In this paper, we describe how we are employing a co-design methodology to support engagement in an assistive technology …

Applying Positional Encoding To Enhance Vision-Language Transformers, Xuehao Liu, Sarah Jane Delany, Susan Mckeever

Conference papers

Positional encoding is used in both natural language and computer vision transformers. It provides information on sequence order and relative position of input tokens (such as of words in a sentence) for higher performance. Unlike the pure language and vision transformers, vision-language transformers do not currently exploit positional encoding schemes to enrich input information. We show that capturing location information of visual features can help vision-language transformers improve their performance. We take Oscar, one of the state-of-the-art (SOTA) vision-language transformers as an example transformer for implanting positional encoding. We use image captioning as a downstream task to test performance. We …

Towards A Framework For Privacy-Preserving Pedestrian Analysis, Anil Kunchala, Mélanie Bouroche, Bianca Schoen-Phelan

Conference papers

The design of pedestrian-friendly infrastructures plays a crucial role in creating sustainable transportation in urban environments. Analyzing pedestrian behaviour in response to existing infrastructure is pivotal to planning, maintaining, and creating more pedestrian-friendly facilities. Many approaches have been proposed to extract such behaviour by applying deep learning models to video data. Video data, however, includes an broad spectrum of privacy-sensitive information about individuals, such as their location at a given time or who they are with. Most of the existing models use privacy-invasive methodologies to track, detect, and analyse individual or group pedestrian behaviour patterns. As a step towards privacy-preserving …

Integrable Systems On Symmetric Spaces From A Quadratic Pencil Of Lax Operators, Rossen Ivanov

Conference papers

The article surveys the recent results on integrable systems arising from quadratic pencil of Lax operator L, with values in a Hermitian symmetric space. The counterpart operator M in the Lax pair defines positive, negative and rational flows. The results are illustrated with examples from the A.III symmetric space. The modeling aspect of the arising higher order nonlinear Schrödinger equations is briefly discussed.

Understanding And Quantifying Human Factors In Programming From Demonstration: A User Study Proposal, Shakra Mehak, Aayush Jain, John D. Kelleher, Philip Long, Michael Guilfoyle, Maria Chiara Leva

Conference papers

Programming by demonstration (PbD) is a promising method for robots to learn from direct, non-expert human interaction. This approach enables the interactive transfer of human skills to the robot. As the non-expert user is at the center of PbD, the efficacy of the learned skill is largely dependent on the demonstrations provided. Although PbD methods have been extensively developed and validated in the field of robotics, there has been inadequate confirmation of their effectiveness from the perspective of human teachability. To address this gap, we propose to experimentally investigate the impact of communicating robot learning process on the efficacy of …

The Suitability Of Demand-Controlled Sensor Based Ventilation Systems In Retrofit Dwellings - A Longitudinal Study., Seamus Harrington, Mark Mulville

Conference papers

A fabric-first approach to dwelling retrofit results in increased airtightness, therefore there is an obligation to ensure that the upgrades do not lead to poor indoor air quality (IAQ) resulting from inadequate ventilation. The sensor-based demand-controlled ventilation (SBDCV) under review seeks to provide fresh air for breathing and to dilute and exhaust pollutants and odours. This system modulates the ventilation rate over time based on relative humidity levels and/or presence detection and considers that the level of ventilation provided is sufficient to control the concentration of all other indoor air pollutants, including those that are not a result of human …

Determining Child Sexual Abuse Posts Based On Artificial Intelligence, Susan Mckeever, Christina Thorpe, Vuong Ngo

Conference papers

The volume of child sexual abuse materials (CSAM) created and shared daily both surface web platforms such as Twitter and dark web forums is very high. Based on volume, it is not viable for human experts to intercept or identify CSAM manually. However, automatically detecting and analysing child sexual abusive language in online text is challenging and time-intensive, mostly due to the variety of data formats and privacy constraints of hosting platforms. We propose a CSAM detection intelligence algorithm based on natural language processing and machine learning techniques. Our CSAM detection model is not only used to remove CSAM on …