Noel E. O’Connor
YOU?
Author Swipe
View article: Accelerating Workflows in Video Game Translation: A Recommender System for Review and Post-Edit Assignments
Accelerating Workflows in Video Game Translation: A Recommender System for Review and Post-Edit Assignments Open
The advancement in Neural Machine Translation (NMT) has significantly improved the localisation of content across multiple languages, offering fluency and efficiency. However, in complex applications, such as the translation of video games…
View article: DCU Campus Explorer: Engaging Staff and Students to Use Campus Facilities
DCU Campus Explorer: Engaging Staff and Students to Use Campus Facilities Open
CE ( Citizen engagement) is an activity that aims to provide a way to link citizens and organizations. As such it has a bidirectional channel of communication, from citizens to organization and from organization to citizens. These channels…
View article: Brain Tumor Classification in MRI Scans Using Edge Computing and a Shallow Attention-Guided CNN
Brain Tumor Classification in MRI Scans Using Edge Computing and a Shallow Attention-Guided CNN Open
Background/Objectives: Brain tumors arise from abnormal, uncontrolled cell growth due to changes in the DNA. Magnetic Resonance Imaging (MRI) is vital for early diagnosis and treatment planning. Artificial intelligence (AI), especially dee…
View article: New Imaging Method of Mobile Phone-Based Colorimetric Sensor for Iron Quantification
New Imaging Method of Mobile Phone-Based Colorimetric Sensor for Iron Quantification Open
Blood iron levels are related to many health conditions, affecting hundreds of millions of individuals worldwide. To aid in the prevention and treatment of iron-related disorders, previous research has developed a low-cost, accurate, point…
View article: New Imaging Method of Mobile Phone-Based Colorimetric Sensor for Iron Quantification
New Imaging Method of Mobile Phone-Based Colorimetric Sensor for Iron Quantification Open
Blood iron levels are related to many health conditions, affecting hundreds of millions of individuals worldwide. To aid in the prevention and treatment of iron-related disorders, previous research has developed a low-cost, accurate point-…
View article: An investigation of pre-stimulus eeg for prediction of driver reaction time
An investigation of pre-stimulus eeg for prediction of driver reaction time Open
Driver drowsiness significantly contributes to road accidents worldwide, and timely prediction of driver reaction time is crucial for developing effective advanced driver assistance systems. In this paper, we present an EEG-based predictio…
View article: Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset
Towards Investigating Residual Hearing Loss: Quantification of Fibrosis in a Novel Cochlear OCT Dataset Open
For the first time, we have successfully applied computer vision techniques to an OCT dataset of implanted cochleae with fibrosis. Using this deep learning model, the cochlear fibrotic burden calculation can be reliably carried out as we v…
View article: Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation Open
Foundation models trained on web-scraped datasets propagate societal biases to downstream tasks. While counterfactual generation enables bias analysis, existing methods introduce artifacts by modifying contextual elements like clothing and…
View article: The impact of sex differences on perceived pain intensity in pain protocol standardization
The impact of sex differences on perceived pain intensity in pain protocol standardization Open
Background Sex differences have been widely demonstrated in both acute and chronic pain. Sex differences may have wider impact on research design and analysis than already established. This study addresses an important methodological aspec…
View article: LLMasMMKG: LLM Assisted Synthetic Multi-Modal Knowledge Graph Creation For Smart City Cognitive Digital Twins
LLMasMMKG: LLM Assisted Synthetic Multi-Modal Knowledge Graph Creation For Smart City Cognitive Digital Twins Open
The concept of a Smart City (SC) Cognitive Digital Twin (CDT) presents significant potential for optimizing urban environments through sophisticated simulations, predictions, and informed decision-making. Comprehensive Knowledge Representa…
View article: Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment
Harnessing Frozen Unimodal Encoders for Flexible Multimodal Alignment Open
Recent contrastive multimodal vision-language models like CLIP have demonstrated robust open-world semantic understanding, becoming the standard image backbones for vision-language applications. However, recent findings suggest high semant…
View article: Evaluating Image-Based Face and Eye Tracking with Event Cameras
Evaluating Image-Based Face and Eye Tracking with Event Cameras Open
Event Cameras, also known as Neuromorphic sensors, capture changes in local light intensity at the pixel level, producing asynchronously generated data termed ``events''. This distinct data format mitigates common issues observed in conven…
View article: Quantifying physical activity, physical education and active travel in children and adolescents with visual Impairments
Quantifying physical activity, physical education and active travel in children and adolescents with visual Impairments Open
This study provides a valuable insight into the low levels of PA that prevail amongst BVI children. Increasing PA levels would provide individual benefits (including physical and mental health benefits) as well as population benefits (incl…
View article: Synthetic Time Series for Anomaly Detection in Cloud Microservices
Synthetic Time Series for Anomaly Detection in Cloud Microservices Open
This paper proposes a framework for time series generation built to investigate anomaly detection in cloud microservices. In the field of cloud computing, ensuring the reliability of microservices is of paramount concern and yet a remarkab…
View article: An accurate detection is not all you need to combat label noise in web-noisy datasets
An accurate detection is not all you need to combat label noise in web-noisy datasets Open
Training a classifier on web-crawled data demands learning algorithms that are robust to annotation errors and irrelevant examples. This paper builds upon the recent empirical observation that applying unsupervised contrastive learning to …
View article: Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach
Accelerating Cardiac MRI Reconstruction with CMRatt: An Attention-Driven Approach Open
Cine cardiac magnetic resonance (CMR) imaging is recognised as the benchmark modality for the comprehensive assessment of cardiac function. Nevertheless, the acquisition process of cine CMR is considered as an impediment due to its prolong…
View article: Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation
Test-Time Adaptation with SaLIP: A Cascade of SAM and CLIP for Zero shot Medical Image Segmentation Open
The Segment Anything Model (SAM) and CLIP are remarkable vision foundation models (VFMs). SAM, a prompt driven segmentation model, excels in segmentation tasks across diverse domains, while CLIP is renowned for its zero shot recognition ca…
View article: An Innovative Adaptive Web-Based Solution for Improved Remote Co-Creation and Delivery of Artistic Performances
An Innovative Adaptive Web-Based Solution for Improved Remote Co-Creation and Delivery of Artistic Performances Open
Due to the COVID-19 pandemic, most arts and cultural activities have moved online. This has contributed to the surge in development of artistic tools that enable professional artists to produce engaging and immersive shows remotely. This a…
View article: A  Meta-Learning Approach for Adaptive Model Selection in Hydrological Time Series Forecasting
A  Meta-Learning Approach for Adaptive Model Selection in Hydrological Time Series Forecasting Open
Accurate hydrological prediction faces challenges due to diverse datasets and the absence of universally applicable models. This study investigates meta-learning's role in identifying optimal models for hydrological time series forecasting…
View article: Investigating physical activity levels in adults who are blind and vision impaired
Investigating physical activity levels in adults who are blind and vision impaired Open
This study provides a valuable insight into the low levels of PA that persist amongst adults with BVI. Future research should seek to gain a deeper understanding of the PA barriers, motivators and facilitators in this cohort.
View article: HECA Research Conference 2023: Sharing an Open Research Landscape
HECA Research Conference 2023: Sharing an Open Research Landscape Open
No abstract provided.
View article: Dataset Clustering for Improved Offline Policy Learning
Dataset Clustering for Improved Offline Policy Learning Open
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment. As the training dataset is fixed, its quality becomes a crucial determining f…
View article: Do Vision and Language Encoders Represent the World Similarly?
Do Vision and Language Encoders Represent the World Similarly? Open
Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an…
View article: Event Camera-Based Eye Motion Analysis: A Survey
Event Camera-Based Eye Motion Analysis: A Survey Open
Neuromorphic vision sensors, commonly referred to as Event Cameras (ECs), have gained prominence as a field of research in Computer Vision. This popularity stems from the numerous unique characteristics including High Dynamic Range, High T…
View article: Sensitivity analysis of the Substance Emission Model v2.1.2 component of the Greenhouse Emission Model
Sensitivity analysis of the Substance Emission Model v2.1.2 component of the Greenhouse Emission Model Open
The substance emission model (SEM) simulates fate of plant protection products applied to crops grown in soilless cultures in greenhouses. It is part of the Greenhouse Emission Model used for regulatory risk assessment. This report present…