A5015174786- COVID-19 epidemiological studies
- COVID-19 Digital Contact Tracing
- Sports Performance and Training
- Anomaly Detection Techniques and Applications
- Data Mining Algorithms and Applications
- Sports Analytics and Performance
- Text Readability and Simplification
- Natural Language Processing Techniques
- Data-Driven Disease Surveillance
- Time Series Analysis and Forecasting
- Sports Dynamics and Biomechanics
- Data Visualization and Analytics
- Topic Modeling
Dublin City University
2024
Research in field sports often involves analysis of running performance profiles players during competitive games with individual, per-position, and time-related descriptive statistics. Data are acquired through wearable technologies, which generally capture simple data points, the case many team-based times, latitudes, longitudes. While is relatively high volumes, raw unsuited to any form or machine learning functions. The main goal this research develop a multistep feature engineering...
The global sports analytics industry has a market value of USD 3.78 billion in 2023. increase wearables such as GPS sensors provided analysts with large fine-grained datasets detailing player performance. Traditional analysis this data focuses on individual athletes measures internal and external loading distance covered speed zones or rate perceived exertion. However these metrics do not provide enough information to understand team dynamics within field sports. spatio-temporal nature match...
The practice of fine-tuning Pre-trained Language Models (PLMs) from general or domain-specific data to a specific task with limited resources, has gained popularity within the field natural language processing (NLP). In this work, we re-visit assumption and carry out an investigation in clinical NLP, specifically Named Entity Recognition on drugs their related attributes. We compare Transformer models that are trained scratch fine-tuned BERT-based LLMs namely BERT, BioBERT, ClinicalBERT....
With the outbreak of COVID-19 pandemic, a dire need to effectively identify individuals who may have come in close-contact others been infected with has risen. This process identifying individuals, also termed as 'Contact tracing', significant implications for containment and control spread this virus. However, manual tracing proven be ineffective calling automated contact approaches. As such, research presents an machine learning system using sensor data transmitted through handheld...