A5052671966- Semantic Web and Ontologies
- Web Data Mining and Analysis
- Natural Language Processing Techniques
- Topic Modeling
- Service-Oriented Architecture and Web Services
- Data Quality and Management
- Advanced Database Systems and Queries
- Advanced Text Analysis Techniques
- Complex Network Analysis Techniques
- Biomedical Text Mining and Ontologies
- Geographic Information Systems Studies
- Text and Document Classification Technologies
- Data Visualization and Analytics
- Context-Aware Activity Recognition Systems
- Mobile Crowdsensing and Crowdsourcing
- Advanced Image and Video Retrieval Techniques
- Human Mobility and Location-Based Analysis
- Public Relations and Crisis Communication
- Video Analysis and Summarization
- Image Retrieval and Classification Techniques
- Misinformation and Its Impacts
- Data Management and Algorithms
- Image Processing and 3D Reconstruction
- Software Engineering Research
- Scientific Computing and Data Management
University of Sheffield
2015-2024
University of Turin
2023
Insigneo
2021-2023
Istituto Centrale per la Ricerca Scientifica e Tecnologica Applicata al Mare
1995-2000
Centro Ricerche FIAT
1992-1993
In this paper, we present a Bluetooth Low Energy (BLE) based indoor positioning system developed for monitoring the daily living pattern of old people (e.g. with dementia) or individuals disabilities. The proposed sensing is composed multiple sensors that are installed in different locations home environment. specific location user building has been pre-recorded into captures raw Received Signal Strength Indicator (RSSI) from BLE beacon attached on user. Two methods to determine and tracking...
Miles Osborne, Sean Moran, Richard McCreadie, Alexander Von Lunen, Martin Sykora, Elizabeth Cano, Neil Ireson, Craig Macdonald, Iadh Ounis, Yulan He, Tom Jackson, Fabio Ciravegna, Ann O’Brien. Proceedings of 52nd Annual Meeting the Association for Computational Linguistics: System Demonstrations. 2014.
Existing mobility endpoints based on functional performance, physical assessments and patient self-reporting are often affected by lack of sensitivity, limiting their utility in clinical practice. Wearable devices including inertial measurement units (IMUs) can overcome these limitations quantifying digital outcomes (DMOs) both during supervised structured real-world conditions. The validity IMU-based methods the real-world, however, is still limited populations. Rigorous validation...
Parkinson's disease (PD) is a neurodegenerative disorder which requires complex medication regimens to mitigate motor symptoms. The use of digital health technology systems (DHTSs) collect mobility and data provides an opportunity objectively quantify the effect on performance during day-to-day activities. This insight could inform clinical decision-making, personalise care, aid self-management. study investigates feasibility usability multi-component DHTS remotely assess self-reported...
Too few young people engage in behaviours that reduce the risk of morbidity and premature mortality, such as eating healthily, being physically active, drinking sensibly not smoking. This study sought to assess efficacy cost-effectiveness a theory-based online health behaviour intervention (based on self-affirmation theory, Theory Planned Behaviour implementation intentions) targeting these new university students, comparison measurement-only control. Two-weeks before starting all incoming...
Abstract Measuring lexical semantic relatedness is an important task in Natural Language Processing (NLP). It often a prerequisite to many complex NLP tasks. Despite extensive amount of work dedicated this area research, there lack up-to-date survey the field. This paper aims address issue with study that focused on four perspectives: (i) comparative analysis background information resources are essential for measuring relatedness; (ii) review literature focus recent methods not covered...
Human activity recognition (HAR) using smartphone sensors have been recently studied in various applications including healthcare, fitness, and smart home. Their accuracy often depends on high-quality feature design effectiveness of classification algorithms, where existing work mostly replies laborious hand-crafted shallow learning architecture. Recent deep techniques demonstrate outstanding performing automatic outperform traditional models terms accuracy. But their performance is limited...
This paper describes 'Archaeotools', a major e-Science project in archaeology. The aim of the is to use faceted classification and natural language processing create an advanced infrastructure for archaeological research. aims integrate over 1 x 10(6) structured database records referring sites monuments UK, with information extracted from semi-structured grey literature reports, unstructured antiquarian journal accounts, single browser interface. has illuminated variable level vocabulary...
Extracting information from Web pages for populating large, cross-domain knowledge bases requires methods which are suitable across domains, do not require manual effort to adapt new able deal with noise, and integrate extracted different pages.Recent approaches have used existing learn extract promising results, one of those being distant supervision.Distant supervision is an unsupervised method uses background the Linking Open Data cloud automatically label sentences relations create...
Automatic Term Extraction (ATE) deals with the extraction of terminology from a domain specific corpus, and has long been an established research area in data knowledge acquisition. ATE remains challenging task as it is known that there no existing methods can consistently outperform others any domain. This work adopts refreshed perspective to this problem: instead searching for such ‘one-size-fit-all’ solution may never exist, we propose develop generic ‘enhance’ methods. We introduce...