CORA
Cork Open Research Archive (CORA) is UCC’s Open Access institutional repository which enables UCC researchers to make their research outputs freely available and accessible.
UCC Research Communities
Recent Submissions
The role of remote monitoring sensors in health and well-being. Release 1.0
(Alliance for AI, IoT and Edge Continuum Innovation, 2025-07-23) Gyrard, Amelie; Krukowski, Artur; Dionisio, Pietro; Tedesco, Salvatore; Dionisio, Pietro; Filipovic, Damir; Reviewer
In a world where healthcare is evolving from reactive treatment to proactive prevention, remote monitoring sensors are quietly revolutionising how we care for ourselves and others. These small, often wearable devices, equipped with cutting-edge sensors and enhanced by artificial intelligence (AI), are enabling a new era of health and well-being—one defined by continuous, personalised, and data-driven care. From monitoring chronic conditions at home to predicting falls in elderly patients, these technologies offer real-time insights that empower individuals and caregivers alike. They are reshaping healthcare delivery, making it more accessible, adaptive, and intelligent. Elderly individuals can live more independently, patients recovering from surgery can be monitored from the comfort of home, and healthcare professionals can make better-informed decisions with real-time data at their fingertips. This transformation is not happening in isolation. Across Europe, a tapestry of collaborative initiatives—such as ACTIVAGE, SHAPES, StrokeBack, and ENACT—are weaving together technology, clinical expertise, and user-centred design to ensure that these innovations are not only effective but also equitable and scalable. Meanwhile, European regulatory frameworks like the GDPR and the upcoming AI Act are setting the stage for responsible and ethical deployment of these systems. However, this bright future comes with challenges. Questions of data privacy, technological readiness, and equitable access must be answered with as much ingenuity and urgency as the technologies themselves. But the promise is clear: remote monitoring sensors are not just tools—they are enablers of a healthier, more connected society where health and well-being are continuously supported, regardless of place, age, or ability.
Artificial Intelligence at the Edge - A joint European roadmap for Edge AI
(European Association on Smart Systems Integration, 2025-10) Azzoni, Paolo; Bierzynski, Kay; Daaldero, Gerardo; Dallemagne, Philippe; Diaznava, Mario; Duranton, Marc; Ecker, Wolfgang; Flak, Jacek; Hausrotter, Andreas; Katkoria, Deepak V.; Langer, Jan; Lindgren, Anders; Magno, Michele; Mathis, Harald; Pau, Danilo; Peischl, Bernhard; Perlo, Pietro; Sawyer, Davis; Seifert, Inessa; Solanti, Petri; Taube, Markus; Tedesco, Salvatore; Vögel, Hans-Jörg; Weimer, Lars
In recent years, digitalisation, the availability of data and the possibilities for applying Artificial Intelligence (AI) have become important business drivers for Europe’s key industrial sectors. In our understanding, AI is a technical system that has the ability to mimic human intelligence, which is characterised by behaviours such as sensing, learning, understanding, decision-making and acting. Due to the availability of powerful computing hardware (graphics processing units (GPUs) and specialised architectures) and large amounts of data, AI solutions – in particular Machine Learning (ML), and more specifically Deep Learning (DL) – have found numerous and widespread applications over the last two decades (including image recognition, fault detection and automated driving functions). Low latency, privacy, connectivity limits and distributed applications have driven research in Edge AI, which enables processing and decision-making near data sources – across cloud, edge, and Internet of Things (IoT) devices. It involves training AI models in the cloud and deploying them on edge devices. In 2021, the EPoSS Edge AI Working Group published a white paper called “AI at the Edge” [1], which provided a broad overview of AI methods and techniques, together with technological milestones to guide the research and innovation over the next few years. Following the publication of this white paper, two industry associations – EPoSS and INSIDE – joined forces. The joint Edge AI Working Group is a community of hardware and software experts from industry and academia who drive research and innovation for both national and EU-funded projects, and contribute their insights and views concerning the future of Edge AI. Recent breakthroughs, and in particular in the domain of Generative AI (GenAI), have driven a clear need to revise our roadmap, including the technology milestones, to better understand and exploit the potential of GenAI in
the computing continuum, including at the edge. Figure 1.1 shows how to read our refined and updated Vision.
Hybrid DCNN-enabled depolarizing chipless RFID: improving tag detection across varying lossy surfaces and shapes
(Institute of Electrical and Electronics Engineers (IEEE), 2025-09-10) Rather, Nadeem; Simorangkir, Roy B. V. B.; Gawade, Dinesh R.; Buckley, John L.; O’Flynn, Brendan; Tedesco, Salvatore; Research Ireland; Department of Agriculture, Food and the Marine, Ireland; European Regional Development Fund; Enterprise Ireland
This paper presents a comprehensive design and implementation approach for robust detection of depolarizing chipless RFID (CRFID) tags. Depolarizing tags are advantageous compared to co-polar CRFID tags due to their improved performance on RF-lossy materials. This work introduces the application of deep learning (DL) regression modelling to a specialised dataset of depolarised Radar Cross Section (RCS) measurements of a custom 3-bit CRFID tag, acquired through an extensive robot-based data acquisition method. A dataset of 12,600 depolarised Electromagnetic (EM) RCS signatures were collected using an automated data acquisition system to train and validate a 1-dimensional Convolutional Neural Network (1D CNN) architecture. A novel hybrid 1D CNN with Bi-LSTM and attention mechanism architecture was also implemented to visualize the model attention and improve detection performance. We present, for the first time reported in literature, a comprehensive design and AI implementation approach for reliably detecting identification (ID) information from depolarized signals. Also, we report the first instance of describing the impact of surface permittivity variations, tag deformations, tilt angles, and read ranges, all integrated into model training for enhanced robustness in detecting ID information. The developed models facilitate real-time identification and recording of objects, enhancing IoT applications in varied environments. It was observed that both models were able to generalize well to given data, with Model-1 achieving a low RMSE of 0.040 (0.66%) on an unseen test dataset. However, the hybrid model reduced the error further by 27.5% with a test RMSE of 0.029 (0.48%).
Volunteering as a pathway to integration and belonging: migrant experiences in Ireland
(Springer Nature, 2025) Martin, Shirley; Scanlon, Margaret; Irish Research Council
This article explores how volunteering functions as a multidimensional pathway to migrant integration and belonging in Ireland, drawing on a mixed-methods study conducted in Cork city and county. Grounded in Heckmann’s integration model, Yuval-Davis’s concept of belonging, and Erel and Ryan’s theory of migrant capitals, the research investigates migrants’ motivations, experiences, and perceived outcomes across formal, informal, and migrant-led forms of volunteering. Findings reveal that volunteering supports integration across structural, cultural, social, and identificational domains, enabling migrants to build networks, improve language skills, maintain professional expertise, and gain recognition. Volunteering also fosters emotional and symbolic belonging, particularly through peer support and civic engagement. However, access remains uneven, with barriers such as language limitations and residence in Direct Provision constraining participation. Migrants emerge not only as beneficiaries but as active agents of integration, contributing to Irish society through advocacy, informal support, and community leadership. The study calls for inclusive policies that recognise and resource both formal and informal volunteering, and that value the civic agency of migrants in shaping integration outcomes.
Estimating perceived fatigue using machine learning and biomechanical features from wearable sensors
(Institute of Electrical and Electronics Engineers (IEEE), 2025-07-03) Qirtas, Malik Muhammad; Yasar, Merve Nur; Sica, Marco; Tedesco, Salvatore; Visentin, Andrea; Science Foundation Ireland; European Regional Development Fund; HORIZON EUROPE Digital, Industry and Space
Physical fatigue is a state of reduced physical ability caused by prolonged activity or repetitive tasks. It can affect performance in tasks that require effort, focus or precision and can lead to reduced strength and increased risk of injuries. Detecting physical fatigue is important for timely interventions and enhancing safety, efficiency and overall well-being in workplaces, sports and rehabilitation. In this study, we propose a robust and generalizable framework for fatigue detection using wearable sensor data, specifically using Inertial Measurement Unit and Electromyography sensors. A comprehensive set of biomechanical features was extracted from raw sensor data to capture both kinematic and neuromuscular aspects of fatigue progression. These features were evaluated across shoulder internal rotation and external rotation movements under different resistance levels. We trained and compared multiple regression models for fatigue estimation using subjective fatigue ratings based on the Borg Rating of Perceived Exertion scale and performed feature importance analysis to get model interpretability. The extracted feature set showed strong generalizability specifically for IR movements, as proved by leave one task out cross-validation, where models maintained robust performance across unseen movement-resistance task settings. This work highlights the potential of combining IMU and EMG data, along with biomechanical features extracted from these two sensor modalities for accurate and interpretable fatigue estimation. It opens the way for real-world applications in dynamic and diverse environments for effective fatigue estimation.