A5017119349- Privacy, Security, and Data Protection
- Mobile Health and mHealth Applications
- COVID-19 Digital Contact Tracing
- Multimodal Machine Learning Applications
- Spam and Phishing Detection
- Advanced Image and Video Retrieval Techniques
- Human-Automation Interaction and Safety
- Domain Adaptation and Few-Shot Learning
- Internet Traffic Analysis and Secure E-voting
- Gaze Tracking and Assistive Technology
- Visual Attention and Saliency Detection
- Speech and dialogue systems
- Autonomous Vehicle Technology and Safety
- Persona Design and Applications
- User Authentication and Security Systems
- Advanced Malware Detection Techniques
University of Limerick
2020-2025
Science Foundation Ireland
2021
Blekinge Institute of Technology
2019
Jawaharlal Nehru Technological University, Hyderabad
2018
Digital Contact Tracing is seen as a key tool in reducing the propagation of Covid-19. But it requires high uptake and continued participation across population to be effective. To achieve sufficient uptake/participation, health authorities should address, thus aware of, user concerns.This work manually analyzes reviews Irish Heath Service Executive's (HSE) Tracker app, identify concerns lay foundations for subsequent, large-scale, automated analyses reviews. While this might seem tightly...
This paper presents DriVQA, a novel dataset that combines gaze plots and heatmaps with visual question-answering (VQA) data from participants who were presented driving scenarios. Visual Questioning Answering is proposed as part of the vehicle autonomy trustworthiness interpretability solution in decision-making by autonomous vehicles. Collected using Tobii Pro X3-120 eye-tracking device, DriVQA provides comprehensive mapping where direct their when images scenes, followed related questions...
Objective This study aims to gather public opinion on the Irish “COVID Tracker” digital contact tracing (DCT) App, with particular focus App usage, usability, usefulness, technological issues encountered, and potential changes App. Methods A 35-item online questionnaire was deployed for 10 days in October 2020, 3 months after launch of DCT Results total 2889 completed responses were recorded, 2553 (88%) respondents currently using Although four five users felt is easy download, use looks...
Abstract Digital Contact Tracing (DCT) is seen as a key tool in reducing the propagation of viruses such Covid-19, but it requires uptake and participation technology across large proportion population to be effective. While we observe pervasive mobile device usage our society, installation contact tracing apps developed by governments health services globally have faced difficulties. These difficulties range user-populations’ issues with apps, us-ability comprehension challenges, trust efficacy...
Contact Tracing (CT) is seen as a key tool in reducing the propagation of viruses, such Covid-19. Given near ubiquitous societal usage mobile devices, governments globally are choosing to augment manual CT with applications (CTAs) on smart phones. While plethora solutions have been spawned, their overall effectiveness based majority population uptake. Unfortunately, rapid deployment and nature information they gather has prompted variety user concerns privacy Data Protection (DP). Therefore...
This paper reports on the progress in project COVIGILANT, which is aimed at developing an evaluation taxonomy for Contact Tracing Applications (CTAs) COVID-19 Specifically, this article describes development of Usability, one pillar COVIGILANT taxonomy, discussing classification and decision-making processes, initial model validation The process was undertaken two stages First, we validated how Usability could be used to evaluate Irish Health Services Executive (HSE) CTA While supported many...
In the present article, authors investigate to what extent supervised binary classification can be used distinguish between legitimate and rogue privacy policies posted on web pages. 15 algorithms are evaluated using a data set that consists of 100 from websites (belonging companies top Fortune Global 500 list) as well 67 websites. A manual analysis all policy content was performed clear statistical differences in terms both length adherence seven general principles found. Privacy have 98%...
The development of vision and language transformer models has paved the way for Visual Question Answering (VQA) related research. There are metrics to assess general accuracy VQA but subjective assessment answers generated by is necessary gain an in-depth understanding a framework required. This work develops novel scoring system based on subjectivity question analyses provided model using multiple types natural processing (bert-base-uncased, nli-distilBERT-base, all-mpnet-base-v2 GPT-2)...
Visual Question Answering (VQA) models play a critical role in enhancing the perception capabilities of autonomous driving systems by allowing vehicles to analyze visual inputs alongside textual queries, fostering natural interaction and trust between vehicle its occupants or other road users. This study investigates attention patterns humans compared VQA model when answering driving-related questions, revealing disparities objects observed. We propose an approach integrating filters...
<sec> <title>BACKGROUND</title> Novel software applications (“Apps”) that can potentially simplify the laborious work of manual contact tracing during ongoing COVID-19 pandemic are a tempting prospect. Given this potential, many countries have designed, developed and deployed Apps before their efficacy has been established. The Irish health service launched “COVID Tracker” App on 7th July 2020 8 months later it is being used by 35% those over 16 in Ireland. </sec> <title>OBJECTIVE</title>...
This short paper presents a preliminary analysis of three popular Visual Question Answering (VQA) models, namely ViLBERT, ViLT, and LXMERT, in the context answering questions relating to driving scenarios. The performance these models is evaluated by comparing similarity responses reference answers provided computer vision experts. Model selection predicated on transformer utilization multimodal architectures. results indicate that incorporating cross-modal attention late fusion techniques...
<sec> <title>BACKGROUND</title> The silent transmission of COVID-19 has led to an exponential growth fatal infections. With over 4 million deaths worldwide, the need control and stem never been more critical. New vaccines offer hope. However, administration timelines, long-term protection, effectiveness against potential variants are still unknown. In this context, contact tracing digital apps (CTAs) continue a mechanism help contain transmission, keep people safe, kickstart economies. CTAs...