Computer Sciences Commons^™

Synthetic Heart Sound Dataset, Davoud Shariat Panah, Andrew Hines, Susan Mckeever

Datasets

The repository contains synthetic heart sound recordings. The publication related to this dataset is "Exploring the impact of noise and degradations on heart sound classification models", Biomedical Signal Processing and Control journal.

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 …

Investigation, Detection And Prevention Of Online Child Sexual Abuse Material: A Comprehensive Survey, Vuong Ngo, Christina Thorpe, Cach N. Dang, Susan Mckeever

Conference papers

Child sexual abuse inflicts lifelong devastating consequences for victims and is a growing social concern. In most countries, child sexual abuse material (CSAM) distribution is illegal. As a result, there are many research papers in the literature which proposed technologies to detect and investigate CSAM. In this survey, a comprehensive search of the peer reviewed journal and conference paper databases (including preprints) is conducted to identify high-quality literature. We use the PRISMA methodology to refine our search space to 2,761 papers published by Springer, Elsevier, IEEE and ACM. After iterative reviews of title, abstract and full text for relevance to …

Transfer Of Personality Through Text Style, Michael O'Mahony, Robert Ross

Other resources

The style of generated text is how something is said rather than what is said. We hypothesize that changing the style of generated text can change the perceived personality of the text generation agent. Dialogue systems that aim to imitate a human agent can appear to have a consistent personality through a consistent, controllable style of conversation. Some recent work on the style of generated text [1] performs impressively in the small number of domains selected for their experiments using transformer and LSTM-based models. Lin et al. [1] used weak supervised learning as their data set lacks parallel data. The …

The Interaction Of Normalisation And Clustering In Sub-Domain Definition For Multi-Source Transfer Learning Based Time Series Anomaly Detection, Matthew Nicholson, Rahul Agrahari, Clare Conran, Haythem Assem, John D. Kelleher

Articles

This paper examines how data normalisation and clustering interact in the definition of sub-domains within multi-source transfer learning systems for time series anomaly detection. The paper introduces a distinction between (i) clustering as a primary/direct method for anomaly detection, and (ii) clustering as a method for identifying sub-domains within the source or target datasets. Reporting the results of three sets of experiments, we find that normalisation after feature extraction and before clustering results in the best performance for anomaly detection. Interestingly, we find that in the multi-source transfer learning scenario clustering on the target dataset and identifying subdomains in the …

Algorithms For Compression Of Electrocardiogram Signals, Yuliyan Velchev

Books

The study is dedicated to modern methods and algorithms for compression of electrocardiogram (ECG) signals. In its original part, two lossy compression algorithms based on a combination of linear transforms are proposed. These algorithms are with relatively low computational complexity, making them applicable for implementation in low power designs such as mobile devices or embedded systems. Since the algorithms do not provide perfect signal reconstruction, they would find application in ECG monitoring systems rather than those intended for precision medical diagnosis.

This monograph consists of abstract, preface, five chapters and conclusion. The chapters are as follows: Chapter 1 — Introduction …

Identity Term Sampling For Measuring Gender Bias In Training Data, Nasim Sobhani, Sarah Jane Delany

Conference Papers

Predictions from machine learning models can reflect biases in the data on which they are trained. Gender bias has been identified in natural language processing systems such as those used for recruitment. The development of approaches to mitigate gender bias in training data typically need to be able to isolate the effect of gender on the output to see the impact of gender. While it is possible to isolate and identify gender for some types of training data, e.g. CVs in recruitment, for most textual corpora there is no obvious gender label. This paper proposes a general approach to measure …

A Review Of Risk Concepts And Models For Predicting The Risk Of Primary Stroke, Elizabeth Hunter, John D. Kelleher

Articles

Predicting an individual's risk of primary stroke is an important tool that can help to lower the burden of stroke for both the individual and society. There are a number of risk models and risk scores in existence but no review or classification designed to help the reader better understand how models differ and the reasoning behind these differences. In this paper we review the existing literature on primary stroke risk prediction models. From our literature review we identify key similarities and differences in the existing models. We find that models can differ in a number of ways, including the …

The Smart Dementia Care Project, Dympna O'Sullivan, Jonathan Turner, Ciaran Nugent, Damon Berry, Michael Wilson, Julie Doyle

Articles

No abstract provided.

Monitoring Activities Of Daily Living For Maintaining Independent Living In Dementia, Jonathan Turner, Ciaran Nugent, Damon Berry, Dympna O'Sullivan, Michael Wilson, Julie Doyle

Articles

Our ability to live independent meaningful lives depends on our ability to perform various activities and to maintain our cognitive functions. Maintaining independent living is important for persons with dementia, it increases selfworth and allows to remain independent and in their own homes for longer. We describe the activities established as being important for the maintenance of independent living, and methods for monitoring these activities using technology.

Ideating Xai: An Exploration Of User’S Mental Models Of An Ai-Driven Recruitment System Using A Design Thinking Approach, Helen Sheridan, Dympna O'Sullivan, Emma Murphy

Conference Papers

Artificial Intelligence (AI) is playing an important role in society including how vital, often life changing decisions are made. For this reason, interest in Explainable Artificial Intelligence (XAI) has grown in recent years as a means of revealing the processes and operations contained within what is often described as a black box, an often-opaque system whose decisions are difficult to understand by the end user. This paper presents the results of a design thinking workshop with 20 participants (computer science and graphic design students) where we sought to investigate users' mental models when interacting with AI systems. Using two personas, …

An Investigation Of The Reconstruction Capacity Of Stacked Convolutional Autoencoders For Log-Mel-Spectrograms, Anastasia Natsiou, Luca Longo, Seán O'Leary

Conference Papers

In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. These representations can be used to manipulate the timbre and influence the synthesis of creative instrumental notes. Modern algorithms, such as neural networks, have inspired the development of expressive synthesizers based on musical instrument timbre compression. Unsupervised deep learning methods can achieve audio compression by training the network to learn a mapping from waveforms or spectrograms to low-dimensional representations. This study investigates the use of stacked convolutional autoencoders for the compression of time-frequency audio representations for a variety of instruments for a single …

Xai Analysis Of Online Activism To Capture Integration In Irish Society Through Twitter, Arjumand Younus, Muhammad Atif Qureshi, Mingyeong Jeon, Arefeh Kazemi, Simon Caton

Books/Book Chapters

Online activism over Twitter has assumed a multidimensional nature, especially in societies with abundant multicultural identities. In this paper, we pursue a case study of Ireland’s Twitter landscape and specifically migrant and native activists on this platform. We aim to capture the level to which immigrants are integrated into Irish society and study the similarities and differences between their characteristic patterns by delving into the features that play a significant role in classifying a Twitterer as a migrant or a native. A study such as ours can provide a window into the level of integration and harmony in society.

Exploring The Impact Of Gender Bias Mitigation Approaches On A Downstream Classification Task, Nasim Sobhani, Sarah Jane Delany

Conference Papers

Natural language models and systems have been shown to reflect gender bias existing in training data. This bias can impact on the downstream task that machine learning models, built on this training data, are to accomplish. A variety of techniques have been proposed to mitigate gender bias in training data. In this paper we compare different gender bias mitigation approaches on a classification task. We consider mitigation techniques that manipulate the training data itself, including data scrubbing, gender swapping and counterfactual data augmentation approaches. We also look at using de-biased word embeddings in the representation of the training data. We …

Morton-Ordered Gpu Lattice Boltzmann Cfd Simulations With Application To Blood Flow, Gerald Gallagher, Fergal J. Boyle

Conference Papers

Computational fluid dynamics (CFD) is routinely used for numerically predicting cardiovascular-system medical device fluid flows. Most CFD simulations ignore the suspended cellular phases of blood due to computational constraints, which negatively affects simulation accuracy. A graphics processing unit (GPU) lattice Boltzmann-immersed boundary (LB-IB) CFD software package capable of accurately modelling blood flow is in development by the authors, focusing on the behaviour of plasma and stomatocyte, discocyte and echinocyte red blood cells during flow. Optimised memory ordering and layout schemes yield significant efficiency improvements for LB GPU simulations. In this work, comparisons of row-major-ordered Structure of Arrays (SoA) and Collected …

Minding The Gap: Computing Ethics And The Political Economy Of Big Tech, Ioannis Stavrakakis, Damian Gordon, Paul John Gibson, Dympna O'Sullivan, Anna Becevel

Articles

In 1988 Michael Mahoney wrote that “[w]hat is truly revolutionary about the computer will become clear only when computing acquires a proper history, one that ties it to other technologies and thus uncovers the precedents that make its innovations significant” (Mahoney, 1988). Today, over thirty years after this quote was written, we are living right in the middle of the information age and computing technology is constantly transforming modern living in revolutionary ways and in such a high degree that is giving rise to many ethical considerations, dilemmas, and social disruption. To explore the myriad of issues associated with the …

“Be A Pattern For The World”: The Development Of A Dark Patterns Detection Tool To Prevent Online User Loss, Jordan Donnelly, Alan Dowley, Yunpeng Liu, Yufei Su, Quanwei Sun, Lan Zeng, Andrea Curley, Damian Gordon, Paul Kelly, Dympna O'Sullivan, Anna Becevel

Articles

Dark Patterns are designed to trick users into sharing more information or spending more money than they had intended to do, by configuring online interactions to confuse or add pressure to the users. They are highly varied in their form, and are therefore difficult to classify and detect. Therefore, this research is designed to develop a framework for the automated detection of potential instances of web-based dark patterns, and from there to develop a software tool that will provide a highly useful defensive tool that helps detect and highlight these patterns.

Technical Debt Is An Ethical Issue, Paul John Gibson, Yannis Stavrakakis, Massamaesso Narouwa, Damian Gordon, Dympna O'Sullivan, Jonathan Turner, Michael Collins

Conference Papers

We introduce the problem of technical debt, with particular focus on critical infrastructure, and put forward our view that this is a digital ethics issue. We propose that the software engineering process must adapt its current notion of technical debt – focusing on technical costs – to include the potential cost to society if the technical debt is not addressed, and the cost of analysing, modelling and understanding this ethical debt. Finally, we provide an overview of the development of educational material – based on a collection of technical debt case studies - in order to teach about technical debt …

Self-Supervised Learning For Invariant Representations From Multi-Spectral And Sar Images, Pallavi Jain, Bianca Schoen Phelan, Robert J. Ross

Articles

Self-Supervised learning (SSL) has become the new state of the art in several domain classification and segmentation tasks. One popular category of SSL are distillation networks such as Bootstrap Your Own Latent (BYOL). This work proposes RS-BYOL, which builds on BYOL in the remote sensing (RS) domain where data are non-trivially different from natural RGB images. Since multi-spectral (MS) and synthetic aperture radar (SAR) sensors provide varied spectral and spatial resolution information, we utilise them as an implicit augmentation to learn invariant feature embeddings. In order to learn RS based invariant features with SSL, we trained RS-BYOL in two ways, …

Understanding The Assumptions Of An Seir Compartmental Model Using Agentization And A Complexity Hierarchy, Elizabeth Hunter, John D. Kelleher

Articles

Equation-based and agent-based models are popular methods in understanding disease dynamics. Although there are many types of equation-based models, the most common is the SIR compartmental model that assumes homogeneous mixing and populations. One way to understand the effects of these assumptions is by agentization. Equation-based models can be agentized by creating a simple agent-based model that replicates the results of the equationbased model, then by adding complexity to these agentized models it is possible to break the assumptions of homogeneous mixing and populations and test how breaking these assumptions results in different outputs. We report a set of experiments …

The Ukicer 2022 Conference Poster: Techmate: A Best Practice Toolkit For Driving Sustainable Acceleration Towards Gender Equality In Technology Disciplines In Heis., Alina Berry

Conference papers

TechMate is a research project that is being developed to enhance gender balance in technology disciplines, in particular computing higher education in Ireland and beyond. Gender imbalance in computing education is a well-known issue: in Ireland, less than 15% of the student population in computer science, ICT and related disciplines are women. Despite a significant amount of research and practical work conducted in the recent decades, the problem still persists and this research initiative aims to improve the situation.

Among the main aims of this project, there is a development of a toolkit to drive sustainable acceleration towards gender equality …

Accessdesign: An Inclusive Co-Design Toolkit For The Creation Of Accessible Digital Tools., Claudia Fernandez-Rivera, Sarah Boland, Eamon Aswad, John Gilligan, Dympna O'Sullivan, Emma Murphy

Articles

Existing toolkits and resources to support co-design are not always accessible to designers and co-designers with disabilities. In this paper we present a study based on an innovative co-design programme, in collaboration with St John of God Community Services, where 3rd year computer science students work with service users with intellectual disabilities to create digital applications together. We conducted a series of co-design focus group sessions involving the service users who were previously involved in the co-design collaboration with SJOG Services and TU Dublin. The data collected during these design sessions has been integrated to form an accessible design toolkit …

Addressing Ethical Issues In The Design Of Smart Home Technology For Older Adults And People With Disabilities., Jonathan Turner, Dympna O'Sullivan, Damian Gordon, Yannis Stavrakakis, Brian Keegan, Emma Murphy

Articles

Unique ethical, privacy and safety implications arise for people who are reliant on home-based smart technology due to health conditions or disabilities. In this paper we highlight a need for a reflective, inclusive ethical framework that encompasses the life cycle of smart home technology. We present key ethical considerations for smart home technology for older adults and people with disabilities and argue for ethical frameworks which combine these key considerations with existing models of design and development.

Co-Design To Support Engagement In Activities Of Daily Living And Meaningful Activities For People Living With Dementia, Michael Wilson, Julie Doyle, Ann Marron, Jonathan Turner, Ciaran Nugent, Dympna O'Sullivan

Articles

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 and engage in meaningful activities. The Smart Dementia Care project aims to establish an understanding of how best to design digital tools that persons with dementia and their carers will find useful and usable for care planning and goal setting. This paper discusses the first phase of this project and describes how co-design is being used to support engagement in activities of daily living and meaningful activities for people living with the early stages of dementia, …

An Ontological Approach For Recommending A Feature Selection Algorithm, Aparna Nayak, Bojan Bozic, Luca Longo

Conference papers

Feature selection plays an important role in machine learning or data mining problems. Removing irrelevant features increases model accuracy and reduces the computational cost. However, selecting important features is not a simple task as one feature selection algorithm does not perform well on all the datasets that are of interest. This paper tries to address the recommendation of a feature selection algorithm based on dataset characteristics and quality. The research uses three types of dataset characteristics along with data quality metrics. The main contribution of the work is the utilization of Semantic Web techniques to develop a novel system that …

Steps Towards Digital Transformation In The Pharmaceutical Manufacturing Landscape Knowledge-Enabled Technology Transfer, Anne Greene Professor, Martin Lipa Dr

Level 3

No abstract provided.

Machine Learning With Kay, Lasith Niroshan, James Carswell

Conference Papers

Computational power is very important when training Deep Learning (DL) models with large amounts of data (Wooldridge, 2021). Hence, High-Performance Computing (HPC) can be leveraged to reduce computational cost, and the Irish Centre for High-End Computing (ICHEC) provides significant infrastructure and services for research and development to both academia and industry. A portion of ICHEC's HPC system has been allocated for institutional access, and this paper presents a case study of how to use Kay (Ireland's national supercomputer) in the remote sensing domain. Specifically, this study uses clusters of Kay Graphics Processing Units (GPUs) for training DL models to extract …

Osm-Gan: Using Generative Adversarial Networks For Detecting Change In High-Resolution Spatial Images, Lasith Niroshan, James Carswell

Articles

Detecting changes to built environment objects such as buildings/roads/etc. in aerial/satellite (spatial) imagery is necessary to keep online maps and various value-added LBS applications up-to-date. However, recognising such changes automatically is not a trivial task, and there are many different approaches to this problem in the literature. This paper proposes an automated end-to-end workflow to address this problem by combining OpenStreetMap (OSM) vectors of building footprints with a machine learning Generative Adversarial Network (GAN) model - where two neural networks compete to become more accurate at predicting changes to building objects in spatial imagery. Notably, our proposed OSM-GAN architecture achieved …

Meaningful Activity Replacement Recommendations In Dementia, Jonathan Turner, Michael Wilson, Ciaran Nugent, Damon Berry, Julie Doyle, Dympna O'Sullivan

Articles

Exercise of meaningful activities is important for people living with dementia, both for quality of life and to maintain the necessary basic activities of daily living. A method is proposed for recommendation of replacements for lost meaningful activities that accounts for the need to maintain activities of daily living.

Post-Analysis Of Osm-Gan Spatial Change Detection, Lasith Niroshan Kottawa Hewa Manage, James Carswell

Conference Papers

Keeping crowdsourced maps up-to-date is important for a wide range of location-based applications (route planning, urban planning, navigation, tourism, etc.).We propose a novelmap updatingmechanism that combines the latest freely available remote sensing data with the current state of online vector map data to train a Deep Learning (DL) neural network. It uses a GenerativeAdversarial Network (GAN) to perform image-to-image translation, followed by segmentation and raster-vector comparison processes to identify changes to map features (e.g. buildings, roads, etc.) when compared to existing map data. This paper evaluates various GAN models trained with sixteen different datasets designed for use by our change …