A5057747620- Semantic Web and Ontologies
- Data Quality and Management
- Biomedical Text Mining and Ontologies
- Data Mining Algorithms and Applications
- Advanced Database Systems and Queries
- Library Science and Information Systems
- Data Management and Algorithms
- Sports Performance and Training
- Sports Analytics and Performance
- Context-Aware Activity Recognition Systems
- Service-Oriented Architecture and Web Services
- Personal Information Management and User Behavior
- Gambling Behavior and Treatments
- Topic Modeling
- Advanced Graph Neural Networks
- Computational Drug Discovery Methods
- Scientific Computing and Data Management
- Privacy, Security, and Data Protection
- Pharmaceutical Practices and Patient Outcomes
- Machine Learning in Healthcare
- FinTech, Crowdfunding, Digital Finance
- Human Mobility and Location-Based Analysis
- Data Visualization and Analytics
- Video Analysis and Summarization
- Traffic Prediction and Management Techniques
University of Malta
2024
Trinity College Dublin
2018-2019
University of Bonn
2014-2017
Fraunhofer Institute for Intelligent Analysis and Information Systems
2015
National University of Ireland
2013
Ollscoil na Gaillimhe – University of Galway
2012-2013
The increasing variety of Linked Data on the Web makes it challenging to determine quality this data and, subsequently, make information explicit consumers. Despite availability a number tools and frameworks assess Quality, output such is not suitable for machine consumption, thus consumers can hardly compare rank datasets in order fitness use . This article describes conceptual methodology assessing Datasets, Luzzu; framework Quality Assessment. Luzzu based four major components: (1) an...
The increasing adoption of the Linked Data principles brought with it an unprecedented dimension to Web, transforming traditional Web Documents a vibrant information ecosystem, also known as Data. This transformation, however, does not come without any pain points. Similar Documents, is heterogenous in terms various domains covers. diversity reflected its quality. quality impacts fitness for use data application at hand, and choosing right dataset often challenge consumers. In this...
The increasing variety of Linked Data on the Web makes it challenging to determine quality this data, and subsequently make information explicit data consumers. Despite availability a number tools frameworks assess Quality, output such is not suitable for machine consumption, thus consumers can hardly compare rank datasets in order fitness use. This paper describes Luzzu, framework Quality Assessment. Luzzu based four major components: (1) an extensible interface defining new metrics, (2)...
The Web of Data is an increasingly rich source information, which makes it useful for Big analysis. However, there no guarantee that this will provide the consumer with truthful and valuable information. Most research has focused on Data's Volume, Velocity, Variety dimensions. Unfortunately, Veracity Value, often regarded as fourth fifth dimensions, have been largely overlooked. In paper we discuss potential Linked methods to tackle all five V's, particularly propose addressing last two We...
Data quality is commonly defined as fitness for use. The problem of identifying data faced by many consumers. publishers often do not have the means to identify problems in their data. To make task both stakeholders easier, we developed Dataset Quality Ontology (daQ). daQ a core vocabulary representing results benchmarking linked dataset. It represents metadata multi-dimensional and statistical observations using Cube vocabulary. are organised self-contained graph, which can, e.g., be...
The current decade is a witness to an enormous explosion of data being published on the Web as Linked Data maximise its reusability. Answering questions that users speak or write in natural language increasingly popular application scenario for Data, especially when domain not limited where dedicated curated datasets exist, like medicine. increasing use this and other settings has highlighted importance assessing quality. While quite some work been done with regard quality only few efforts...
This paper presents an approach for metadata reconciliation, curation and linking Open Governamental Data Portals (ODPs). ODPs have been lately the standard solution governments willing to put their public data available society. Portal managers use several types of organize datasets, one most important ones being tags. However, tagging process is subject many problems, such as synonyms, ambiguity or incoherence, among others. As our empiric analysis shows, these issues are currently...
<title>Abstract</title> In the last decades, people have been consuming and combining more drugsthan before, increasing number of Drug-Drug Interactions (DDIs). To pre-dict unknown DDIs, recently, studies started incorporating Knowledge Graphs(KGs) since they are able to capture relationships among entities provid-ing better drug representations than using a single property. this paper,we propose an end-to-end framework that integrates several features frompublic repositories into KG embeds...
Quality is a complicated and multifarious topic in contemporary Linked Data research. The aspect of literal quality particular has not yet been rigorously studied. Nevertheless, analyzing improving the literals important since form substantial (one seven statement s) crucial part Semantic Web. Specifically, allow infinite value spaces to be expressed they provide linguistic entry point LOD Cloud. We present toolchain that builds on Laundromat data cleaning republishing infrastructure allows...
The amount of video content available on the Web is constantly growing, especially due to increasing popularity Video Demand (VoD) platforms such as Netflix, Hulu and Youtube. This has made it harder for viewers discover right visual them. Recommender systems are being offered by VoD services in order automatically suggest potentially interesting videos users. However, recommendations typically based on: (i) limited metadata fields, genre, title actors; (ii) that other users liked; (iii)...
The steadily growing number of linked open datasets brought about a reservations amongst data consumers with regard to the datasets' quality. Quality assessment requires significant effort and consideration, including definition quality metrics process assess based on these definitions. Luzzu is framework for that allows domain-specific be plugged in. LQML offers notations, abstractions expressive power, focusing representation metrics. It provides power defining sophisticated Its...
In this position paper we describe a conceptual model for intelligent Big Data analytics based on both semantic and machine learning AI techniques (called ensembles). These processes are linked to business outcomes by explicitly modelling data value using technologies as the underlying mode communication between diverse organisations creating ensembles. Furthermore, show how governance can direct enhance these ensembles providing recommendations insights that ensure output generated produces...
Although a number of initiatives provide personalized context‐aware guidance for niche use cases, standard framework context awareness remains lacking. This article explains how semantic technology has been exploited to generate centralized repository personal activity context. data drives advanced features such as situation recognition and customizable rules the context‐sensitive management devices sharing. As proof concept, we demonstrate an innovative system successfully adopted infrastructure.