Physical Sciences and Mathematics Commons^™

Just-In-Time Biomass Yield Estimation With Multi-Modal Data And Variable Patch Training Size, Patricia O'Byrne, Patrick Jackman Dr., Damon Dr. Berry Dr., Thomas Lee, Michael French, Robert J. Ross

Conference papers

The just-in-time estimation of farmland traits such as biomass yield can aid considerably in the optimisation of agricultural processes. Data in domains such as precision farming is however notoriously expensive to collect and deep learning driven modelling approaches need to maximise performance but also acknowledge this reality. In this paper we present a study in which a platform was deployed to collect data from a heterogeneous collection of sensor types including visual, NIR, and LiDAR sources to estimate key pastureland traits. In addition to introducing the study itself we address two key research questions. The first of these was the …

Interactive Learning Approach For Arabic Target-Based Sentiment Analysis, Husamelddin Balla, Marisa Llorens, Sarah Jane Delany

Conference papers

Recently, the majority of sentiment analysis researchers focus on target-based sentiment analysis because it delivers in-depth analysis with more accurate results as compared to traditional sentiment analysis. In this paper, we propose an interactive learning approach to tackle a target-based sentiment analysis task for the Arabic language. The proposed IALSTM model uses an interactive attentionbased mechanism to force the model to focus on different parts (targets) of a sentence. We investigate the ability to use targets, right and left contexts, and model them separately to learn their own representations via interactive modeling. We evaluated our model on two different datasets: …

A Comparison Of Instructional Efficiency Models In Third Level Education, Murali Rajendran

Dissertations

This study investigates the validity and sensitivity of a novel model of instructional efficiency: the parabolic model. The novel model is compared against state-of-the-art models present in instructional design today; Likelihood model, Deviational model and Multidimensional model. This models is based on the assumption that optimal mental workload and high performance leads to high efficiency, while other models assume that low mental workload and high performance leads to high efficiency. The investigation makes use of two instructional design conditions: a direct instructions approach to learning and its extension with a collaborative activity. A control group received the former instructional design …

Stellar Classification Of Folded Spectra Using The Mk Classification Scheme And Convolutional Neural Networks, John Magee

Dissertations

The year 1943 saw the introduction of the Morgan-Keenan (MK) classification scheme and this replaced the existing Harvard Classification scheme. Both stellar classification scheme are fundamentally grounded in the field of spectroscopy. The Harvard Classification scheme classified stars based on stellar surface temperature. The MK Classification scheme introduced the concept of a luminosity class that is intrinsically linked to the surface gravity of a star. Temperature and luminosity class values are estimated directly from the stellar spectrum.

Machine learning is a well-established technique in astronomy. Traditionally, a spectrum is treated as a one-dimensional sequence of data. Techniques such as artificial …

Human Age And Gender Classification Using Convolutional Neural Networks, Eamon Kelliher

Dissertations

In a world relying ever more on human classification, this papers aims to improve on age and gender image classification through the use of Convolutional Neural Networks (CNN). Age and gender classification has become a popular area of study in the past number of years however there are still improvements to be made, particularly in the area of age classification. This research paper aims to test the currently accepted fact that CNN models are the superior model type for image classification by comparing CNN performance against Support Vector Machine performance on the same dataset. Using the Adience image classification dataset, …

Pothole Detection Under Diverse Conditions Using Object Detection Model, Ibrahim Hassan Syed, Dympna O'Sullivan, Susan Mckeever

Datasets

One of the most important tasks in road maintenance is the detection of potholes. This process is usually done through manual visual inspection, where certified engineers assess recorded images of pavements acquired using cameras or professional road assessment vehicles. Machine learning techniques are now being applied to this problem, with models trained to automatically identify road conditions. However, approaching this real-world problem with machine learning techniques presents the classic problem of how to produce generalizable models. Images and videos may be captured in different illumination conditions, with different camera types, camera angles and resolutions. In this paper we present our …

You Can't Lose A Game If You Don't Play The Game: Exploring The Ethics Of Gamification In Education, Dympna O'Sullivan, Ioannis Stavrakakis, Damian Gordon, Andrea Curley, Brendan Tierney, Emma Murphy, Michael Collins, Anna Becevel

Articles

Gamification has been hailed as a meaningful solution to the perennial challenge of sustaining student attention in class. It uses facets of gameplay in an educational context, including things such as points, leaderboards and badges. These are clearly efforts to make the student experience more entertaining and engaging, but nonetheless, they are also clearly digital nudges and attempts to change the students’ behaviours and attitudes to a specific set of concepts, and in which case they must, and should, be subject to the same ethical scrutiny as any other form of persuasion technique, as they may be unintentionally eroding the …

Hublinked: A Curriculum Mapping Framework For Industry, Paul Doyle, Cathy Ennis, Anna Becevel, Stephane Maag, Radu Dobrin, Mojca Ciglarič, Yunia Choi, Alan Fahey, Deirdre Lillis

Conference Papers

A key aim of HubLinked is to improve the effectiveness of University-Industry linkages between CS faculties and ICT companies. One of the problems identified as core to the Project was to match Learning Outcomes from different curricula with the requirements dictated by the ICT industry with the final aim to enhance students Graduate Skills and employability. Based on agreed core U-I linkage attributes, lower-level curriculum L0s have been designed and reviewed by industry partners. To enable the replication of this process, a tool was designed to make the comparison of graduates' skills from different institutions easily accessible. Using this tool …

Sustainable International Engagement Using A Partner Co-Hosted Teaching Model, Brian Gillespie, Paul Doyle, Zy Jiang, Darryl Humble

Conference Papers

Internationalisation is a significant activity of Higher Education Institutions (HEIs) worldwide and is typically embedded within the aims, ambitions, vision, and strategy of the institution. It incorporates the policies and procedures required to facilitate participation within a global academic environment, and is often considered to be a transformative process that impacts practices in teaching and learning, research, and administration. With formal protocols to establish partnerships, such as memoranda of understanding and articulation agreements, the business of formally creating international partnerships is well defined. However, the motivations, corresponding metrics and key performance indicators (KPIs) of successful partnerships are not as well …

Configurations To Superior Environmental Innovation Strategy: A Both–And Approach, Tiziana Russo-Spena, Nadia Di Paola, Aidan O'Driscoll

Articles

An effective climate change action involves the critical role that companies must play in assuring the long-term human and social well-being of future generations. In our study, we offer a more holistic, inclusive, both–and approach to the challenge of environmental innovation (EI) that uses a novel methodology to identify relevant configurations for firms engaging in a superior EI strategy. A conceptual framework is proposed that identifies six sets of driving characteristics of EI and two sets of beneficial outcomes, all inherently tensional. Our analysis utilizes a complementary rather than an oppositional point of view. A data set of 65 companies …

Virtual Tutor Personality In Computer Assisted Language Learning, Johanna Dobbriner, Cathy Ennis, Robert J. Ross

Conference papers

The use of intelligent virtual agents in language learning has increased in recent years. Studies into several aspects of personalisation aiming to increase user engagement are an ongoing research topic with avatar personality being one such aspect. As a step towards our development of intelligent virtual avatars, we present two of our initial experiments to explore differences in user interaction with two contrasting avatar personalities -- P1: open-minded, friendly and sociable and P2: closed-off, curt and distant. Each user interacted with a single personality in a video-call setting and gave feedback on the interaction. Our expectations, that P1 would be …

Zero-Shot Action Recognition With Knowledge Enhanced Generative Adversarial Networks, Kaiqiang Huang, Luis Miralles-Pechuán, Susan Mckeever

Conference papers

Zero-Shot Action Recognition (ZSAR) aims to recognise action classes in videos that have never been seen during model training. In some approaches, ZSAR has been achieved by generating visual features for unseen classes based on the semantic information of the unseen class labels using generative adversarial networks (GANs). Therefore, the problem is converted to standard supervised learning since the unseen visual features are accessible. This approach alleviates the lack of labelled samples of unseen classes. In addition, objects appearing in the action instances could be used to create enriched semantics of action classes and therefore, increase the accuracy of ZSAR. …

K-Nearest Neighbour Classifiers - A Tutorial, Padraig Cunningham, Sarah Jane Delany

Conference papers

Perhaps the most straightforward classifier in the arsenal or Machine Learning techniques is the Nearest Neighbour Classifier – classification is achieved by identifying the nearest neighbours to a query example and using those neighbours to determine the class of the query. This approach to classification is of particular importance because issues of poor run-time performance is not such a problem these days with the computational power that is available. This paper presents an overview of techniques for Nearest Neighbour classification focusing on; mechanisms for assessing similarity (distance), computational issues in identifying nearest neighbours and mechanisms for reducing the dimension of …

Big Data: Potential As An Ocular Epidemiology And Public Health Tool, Michael Moore

Doctoral

Refractive error is a significant cause of vision impairment both through the limited access to correction in some areas and the associated ocular diseases for which refractive errors are risk factors. Having timely, regular access to population level estimates of refractive error and vision impairment is necessary to adequately plan public health resources and resource appropriate interventions. A lack of access to current and regularly updated refractive error and vision impairment prevalence data has been identified as a significant limitation in predicting future population trends with many countries lacking any prevalence data or available data being outdated. This project addresses …

Data: The Good, The Bad And The Ethical, John D. Kelleher, Filipe Cabral Pinto, Luis M. Cortesao

Articles

It is often the case with new technologies that it is very hard to predict their long-term impacts and as a result, although new technology may be beneficial in the short term, it can still cause problems in the longer term. This is what happened with oil by-products in different areas: the use of plastic as a disposable material did not take into account the hundreds of years necessary for its decomposition and its related long-term environmental damage. Data is said to be the new oil. The message to be conveyed is associated with its intrinsic value. But as in …

A Comparative Analysis Of Rule-Based, Model-Agnostic Methods For Explainable Artificial Intelligence, Giulia Vilone, Lucas Rizzo, Luca Longo

Articles

The ultimate goal of Explainable Artificial Intelligence is to build models that possess both high accuracy and degree of explainability. Understanding the inferences of such models can be seen as a process that discloses the relationships between their input and output. These relationships can be represented as a set of inference rules which are usually not explicit within a model. Scholars have proposed several methods for extracting rules from data-driven machine-learned models. However, limited work exists on their comparison. This study proposes a novel comparative approach to evaluate and compare the rulesets produced by four post-hoc rule extractors by employing …

Exploring The Potential Of Defeasible Argumentation For Quantitative Inferences In Real-World Contexts: An Assessment Of Computational Trust, Lucas Rizzo, Pierpaolo Dondio, Luca Longo

Articles

Argumentation has recently shown appealing properties for inference under uncertainty and conflicting knowledge. However, there is a lack of studies focused on the examination of its capacity of exploiting real-world knowledge bases for performing quantitative, case-by-case inferences. This study performs an analysis of the inferential capacity of a set of argument-based models, designed by a human reasoner, for the problem of trust assessment. Precisely, these models are exploited using data from Wikipedia, and are aimed at inferring the trustworthiness of its editors. A comparison against non-deductive approaches revealed that these models were superior according to values inferred to recognised trustworthy …

Lightgwas: A Novel Machine Learning Procedure For Genome-Wide Association Study, Ambrozio Bruno, Luca Longo, Lucas Rizzo

Articles

This paper proposes a novel machine learning procedure for genome-wide association study (GWAS), named LightGWAS. It is based on the LightGBM framework, in addition to being a single, resilient, autonomous and scalable solution to address common limitations of GWAS implementations found in the literature. These include reliance on massive manual quality control steps and specific GWAS methods for each type of dataset morphology and size. Through this research, LightGWAS has been contrasted against PLINK2, one of the current state-of-the-art for GWAS implementations based on general linear model with support to firth regularisation. The mean differences measured upon standard classification metrics, …

A Conceptual Model To Explain Dark Matter And Dark Energy, Jonathan Blackledge

Articles

This paper considers a conceptual model that attempts to explain ‘Dark Matter’ and‘Dark Energy’. The model is based on considering a gravitational field to be the result of a mass (aHiggs field) scattering pre-existing cosmic background space-time waves or ‘Uber-waves’. The term‘Uber’ is used to denote an outstanding or supreme example of a particular kind of gravitationalwave with cosmic-scale wavelengths that are far in excess of those associated with the gravitationalwaves generated by accelerating masses. Such waves are taken to be the very lowest frequencycomponents associated with the spectrum of space-time waves generated by the ‘Big Bang’ andare supported by …

Neurophysiological Correlates Of Dual Tasking In People With Parkinson's Disease And Freezing Of Gait, Conor Fearon, John Butler, Saskia Waechter, Isabelle Killane, Simon Kelly, Richard B Reilly, Timothy Lynch

Articles

Freezing of gait in people with Parkinson's disease (PwP) is associated with executive dysfunction and motor preparation deficits. We have recently shown that electrophysiological markers of motor preparation, rather than decision-making, differentiate PwP with freezing of gait (FOG +) and without (FOG -) while sitting. To examine the effect of locomotion on these results, we measured behavioural and electrophysiological responses in PwP with and without FOG during a target response time task while sitting (single-task) and stepping-in-place (dual-task). Behavioural and electroencephalographic data were acquired from 18 PwP (eight FOG +) and seven young controls performing the task while sitting and …

Detecting Hacker Threats: Performance Of Word And Sentence Embedding Models In Identifying Hacker Communications, Susan Mckeever, Brian Keegan, Andrei Quieroz

Conference papers

Abstract—Cyber security is striving to find new forms of protection against hacker attacks. An emerging approach nowadays is the investigation of security-related messages exchanged on deep/dark web and even surface web channels. This approach can be supported by the use of supervised machine learning models and text mining techniques. In our work, we compare a variety of machine learning algorithms, text representations and dimension reduction approaches for the detection accuracies of software-vulnerability-related communications. Given the imbalanced nature of the three public datasets used, we investigate appropriate sampling approaches to boost detection accuracies of our models. In addition, we examine how …

Language-Driven Region Pointer Advancement For Controllable Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher

Conference papers

Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the …

Dublin Smart City Data Integration, Analysis And Visualisation, Hammad Ul Ahad

Doctoral

Data is an important resource for any organisation, to understand the in-depth working and identifying the unseen trends with in the data. When this data is efficiently processed and analysed it helps the authorities to take appropriate decisions based on the derived insights and knowledge, through these decisions the service quality can be improved and enhance the customer experience. A massive growth in the data generation has been observed since two decades. The significant part of this generated data is generated from the dumb and smart sensors. If this raw data is processed in an efficient manner it could uplift …

Energy-Based Neural Modelling For Large-Scale Multiple Domain Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Scaling up dialogue state tracking to multiple domains is challenging due to the growth in the number of variables being tracked. Furthermore, dialog state tracking models do not yet explicitly make use of relationships between dialogue variables, such as slots across domains. We propose using energy-based structure prediction methods for large-scale dialogue state tracking task in two multiple domain dialogue datasets. Our results indicate that: (i) modelling variable dependencies yields better results; and (ii) the structured prediction output aligns with the dialogue slot-value constraint principles. This leads to promising directions to improve state-of-the-art models by incorporating variable dependencies into their …

Deep Learning In The Maintenance Industry, Paulo Cesar Ribeiro Silva

Doctoral

No abstract provided.

Enhancing The Visibility Of Vernier Effect In A Tri-Microfiber Coupler Fiber Loop Interferometer For Ultrasensitive Refractive Index And Temperature Sensing, Fangfang Wei, Dejun Liu, Zhe Wang, Zhuochen Wang, Gerald Farrell, Qiang Wu, Gang-Ding Peng, Yuliya Semenova

Articles

In this paper a Vernier effect based sensor is analyzed and demonstrated experimentally in a tri-microfiber coupler (Tri-MFC) and polarization-maintaining fiber (PMF) loop interferometer (Tri-MFC-PMF) to provide ultrasensitive refractive index and temperature sensing. The main novelty of this work is an analysis of parameters of the proposed Tri-MFC-PMF with the objective of determining the conditions leading to a strong Vernier effect. It has been identified by simulation that the Vernier effect is a primary factor in the design of Tri-MFC-PMF loop sensing structure for sensitivity enhancement. It is furthermore demonstrated experimentally that enhancing the visibility of the Vernier spectrum in …

Quotient-Transitivity And Cyclic Subgroup-Transitivity, Brendan Goldsmith, Ketao Gong

Articles

We introduce two new notions of transitivity for Abelian 𝑝-groups based on isomorphism of quotients rather than the classical use of equality of height sequences associated with Abelian 𝑝-group theory. Unlike the classical theory where “most” groups are transitive, these new notions lead to much smaller classes, but even these classes are sufficiently large to be interesting.

Chemical Effects Of Cold Atmospheric Plasma On Food Nutrients, Juan Manuel Pérez Andrés

Doctoral

A range of nonthermal techniques have demonstrated process efficacy in ensuring food product safety, extension of shelf-life and in general a retention of key quality attributes. However, various physical, chemical and biochemical effects of nonthermal techniques on both macro and micronutrients are evident, leading to both desirable and undesirable changes in food products. It is important to outline the effects of non-thermal techniques on food chemistry and the associated degradation mechanisms with the treatment of foods. Oxidation is one of the key mechanisms responsible for undesirable effects induced by non-thermal techniques. Degradation of key macromolecules largely depends on the processing …

A Hybrid Agent-Based And Equation Based Model For The Spread Of Infectious Diseases, Elizabeth Hunter, Brian Mac Namee, John D. Kelleher

Articles

Both agent-based models and equation-based models can be used to model the spread of an infectious disease. Equation-based models have been shown to capture the overall dynamics of a disease outbreak while agent-based models are able to capture heterogeneous characteristics of agents that drive the spread of an outbreak. However, agent-based models are computationally intensive. To capture the advantages of both the equation-based and agent-based models, we create a hybrid model where the disease component of the hybrid model switches between agent-based and equation-based. The switch is determined using the number of agents infected. We first test the model at …

Comparing Variable Importance In Prediction Of Silence Behaviours Between Random Forest And Conditional Inference Forest Models., Stephen Barrett Dr, Geraldine Gray Dr, Colm Mcguinness Dr, Michael Knoll Dr.

Articles

This paper explores variable importance metrics of Conditional Inference Trees (CIT) and classical Classification And Regression Trees (CART) based Random Forests. The paper compares both algorithms variable importance rankings and highlights why CIT should be used when dealing with data with different levels of aggregation. The models analysed explored the role of cultural factors at individual and societal level when predicting Organisational Silence behaviours.