Edward Curry

University of Galway | NUI Galway · INSIGHT Centre for Data Analytics

Training of object detection models using less data is currently the focus of existing N-shot learning models in computer vision. Such methods use object-level labels and takes hours to train on unseen classes. There are many cases where we have large amount of image-level labels available for training and cannot be utilized by few shot object dete...

In this book chapter, recent advances in the development and implementation of open-source software technologies and information management systems to support the progression of the data economy by means of data operations and data offering descriptions are introduced. The management of controlled registries, mapping of information using metadata a...

This chapter presents a maturity model for Data Spaces, which provides a management system with associated improvement roadmaps that guide strategies to continuously improve, develop, and manage the data space capability within their organization. It highlights the challenges with data sharing and motivates the benefit of maturity models. This chap...

Common European data sharing spaces are essential for the implementation of the European digital market. This chapter addresses the challenges and opportunities of Data Spaces identified by the Big Data Value Association community. It brings forward five independent goals, convergence, experimentation, standardization, deployment, and awareness, ea...

This chapter focuses on data interoperability best practices related to semantic technologies and data management systems. It introduces a particular view on how relevant data interoperability is achieved and its effects on developing technologies for the financial and insurance sectors. Financial technology (FinTech) and insurance technology (Insu...

In our societies, there is a growing demand for the production and use of more data. Data is reaching the point that is driving all the social and economic activities in every industry sector. Technology is not going to be a barrier anymore; however, where there is large deployment of technology, the production of data creates a growing demand for...

Digital transformation, data ecosystems, and Data Spaces are inevitable parts of our future. The book aims to educate the reader on data sharing and exchange techniques using Data Spaces. It will address and explore the cutting-edge theory, technologies, methodologies, and best practices for Data Spaces for both industrial and personal data. The bo...

Using data and Artificial Intelligence, it is possible to answer the big questions, how sustainable the planet is or what impact industry has on climate. The Big Data Value Association (BDVA) believes that Data Sharing Spaces will be a key enabler to this vision. The BDVA community has created a unified perspective on the value of data sharing spac...

Scene graph generation aims to capture the semantic elements in images by modelling objects and their relationships in a structured manner, which are essential for visual understanding and reasoning tasks including image captioning, visual question answering, multimedia event processing, visual storytelling and image retrieval. The existing scene g...

Visual understanding involves detecting objects in a scene and investigating rich semantic relationships between the objects, which is required for downstream visual reasoning tasks. Scene graph is widely used for structured scene representation, however, the performance of scene graph generation for visual reasoning is limited due to challenges po...

Scene graph generation aims to capture the semantic elements in images by modelling objects and their relationships in a structured manner, which are essential for visual understanding and reasoning tasks including image captioning, visual question answering, multimedia event processing, visual storytelling and image retrieval. The existing scene g...

Training of object detection models using less data is currently the focus of existing N-shot learning models in computer vision. Such methods use object-level labels and takes hours to train on unseen classes. There are many cases where we have large amount of image-level labels available for training but cannot be utilized by few shot object dete...

Modern distributed computing infrastructure need to process vast quantities of data streams generated by a growing number of participants with information generated in multiple formats. With the Internet of Multimedia Things (IoMT) becoming a reality, new approaches are needed to process realtime multimodal event data streams. Existing approaches t...

The continuous and significant growth of data, together with improved access to data and the availability of powerful computing infrastructure, has led to intensified activities around Big Data Value (BDV) and data-driven Artificial Intelligence (AI). Powerful data techniques and tools allow collecting, storing, analysing, processing and visualisin...

This paper presents GNOSIS, an event processing engine to detectcomplex event patterns over multimodal data streams. GNOSISfollows a query-driven approach where users can write complexevent queries using Multimodal Event Processing Language (MEPL).The system models incoming multimodal data into an evolvingMultimodal Event Knowledge Graph (MEKG) usi...

The smart city concept has now become one of the key enablers in urban city management. The adoption and permeation of ICT and AI-driven techniques have enabled the authorities to resolve poor urban planning issues with improved delivery of citizen services. Major urban problem is addressing the accessibility issue across cities road crossing and f...

Advances in Deep Neural Network (DNN) techniques have revolutionized video analytics and unlocked the potential for querying and mining video event patterns. This paper details GNOSIS, an event processing platform to perform near-real-time video event detection in a distributed setting. GNOSIS follows a serverless approach where its component acts...

The adoption of big data technology within industrial sectors facilitates organizations to gain competitive advantage. The impacts of big data go beyond the commercial world, creating significant societal impact, from improving healthcare systems to the energy-efficient operation of cities and transportation infrastructure, to increasing the transp...

To drive innovation and competitiveness, organisations need to foster the development and broad adoption of data technologies, value-adding use cases and sustainable business models. Enabling an effective data ecosystem requires overcoming several technical challenges associated with the cost and complexity of management, processing, analysis and u...

This chapter presents a best practice framework for the operation of Big Data and Artificial Intelligence Centres of Excellence (BDAI CoE). The goal of the framework is to foster collaboration and share best practices among existing centres and support the establishment of new Centres of Excellence (CoEs) within Europe. The framework was developed...

The fields of Big Data, Data Analytics and Data Science, which are key areas of current and future industrial demand, are quickly growing and evolving. Within Europe, there is a significant skills gap which needs to be addressed. A key activity is to ensure we meet future needs for skills and align the supply of educational offerings with the deman...

The European contractual Public-Private Partnership on Big Data Value (BDV PPP) has played a central role in the implementation of the revised Digital Single Market strategy, contributing to multiple pillars, including “Digitising European Industry”, “Digital Skills”, “Building the European Data Economy” and “Developing a European Data Infrastructu...

To support the adoption of big data value, it is essential to foster, strengthen, and support the development of big data value technologies, successful use cases and data-driven business models. At the same time, it is necessary to deal with many different aspects of an increasingly complex data ecosystem. Creating a productive ecosystem for big d...

Artificial intelligence (AI) has a tremendous potential to benefit European citizens, economy, environment and society and already demonstrated its potential to generate value in various applications and domains. From a data economy point of view, AI means algorithm-based and data-driven systems that enable machines with digital capabilities such a...

The Big Data Value (BDV) Reference Model has been developed with input from technical experts and stakeholders along the whole big data value chain. The BDV Reference Model may serve as a common reference framework to locate big data technologies on the overall IT stack. It addresses the main technical concerns and aspects to be considered for big...

Stakeholder analysis and management have received significant attention in management literature primarily due to the role played by key stakeholders in the success or failure of projects and programmes. Consequently, it becomes important to collect and analyse information on relevant stakeholders to develop an understanding of their interest and i...

Efficient video processing is a critical component in many IoMT applications to detect events of interest. Presently, many window optimization techniques have been proposed in event processing with an underlying assumption that the incoming stream has a structured data model. Videos are highly complex due to the lack of any underlying structured da...

Efficient video processing is a critical component in many IoMT applications to detect events of interest. Presently, many window optimization techniques have been proposed in event processing with an underlying assumption that the incoming stream has a structured data model. Videos are highly complex due to the lack of any underlying structured da...

The enormous growth of multimedia content in the field of the Internet of Things (IoT) leads to the challenge of processing multimedia streams in real-time. Event-based systems are constructed to process event streams. They cannot natively consume multimedia event types produced by the Internet of Multimedia Things (IoMT) generated data to answer m...

This open access book presents the foundations of the Big Data research and innovation ecosystem and the associated enablers that facilitate delivering value from data for business and society. It provides insights into the key elements for research and innovation, technical architectures, business models, skills, and best practices to support the...

The original version of the chapter was inadvertently published with an error. The affiliation of the author Davide Dalle Carbonare has now been corrected to “Engineering Ingegneria Informatica, Rome, Italy”.

An enormous amount of sensing devices (scalar or multimedia) collect and generate information (in the form of events) over the Internet of Things (IoT). Present research on IoT mainly focus on the processing of scalar sensor data events and barely considers the challenges posed by multimedia based events. In this paper, we systematically review the...

Efficient multimedia event processing is a key enabler for real-time and complex decision making in streaming media. The need for expressive queries to detect high-level human-understandable spatial and temporal events in multimedia streams is inevitable due to the explosive growth of multimedia data in smart cities and internet. The recent work in...

Multimedia data is highly expressive and has traditionally been very difficult for a machine to interpret. Middleware systems such as complex event processing (CEP) mine patterns from data streams and send notifications to users in a timely fashion. Presently, CEP systems have inherent limitations to process multimedia streams due to its data compl...

Complex Event Processing (CEP) is an event processing paradigm to perform real-time analytics over streaming data and match high-level event patterns. Presently, CEP is limited to process structured data stream. Video streams are complicated due to their unstructured data model and limit CEP systems to perform matching over them. This work introduc...

Video data is highly expressive and has traditionally been very difficult for a machine to interpret. Querying event patterns from video streams is challenging due to its unstructured representation. Middleware systems such as Complex Event Processing (CEP) mine patterns from data streams and send notifications to users in a timely fashion. Current...

Complex Event Processing (CEP) is an event processing paradigm to perform real-time analytics over streaming data and match high-level event patterns. Presently, CEP is limited to process structured data stream. Video streams are complicated due to their unstructured data model and limit CEP systems to perform matching over them. This work introduc...

Displaying near-real-time traffic information is a useful feature of digital navigation maps. However, most commercial providers rely on privacy-compromising measures such as deriving location information from cellphones to estimate traffic. The lack of an open-source traffic estimation method using open data platforms is a bottleneck for building...

Land use land cover changes (LULCC) are generally modeled using multi-scale spatio-temporal variables. Recently, Markov Chain (MC) has been used to model LULCC. However, the model is derived from the proportion of LULCC observed over a given period and it does not account for temporal factors such as macro-economic, socio-economic, etc. In this pap...

Displaying near-real time traffic state information is an useful features of digital navigation maps. However, most commercial providers rely on privacy compromising measures such as deriving location information from cellphones to estimate traffic. The lack of an open source traffic estimation method using open data platforms is a bottleneck for b...

The heterogeneity of energy ontologies hinders the interoperability between ontology-based energy management applications to perform a large-scale energy management. Thus, there is the need for a global ontology that provides common vocabularies to represent the energy subdomains. A global energy ontology must provide a balance of reusability-usabi...

Complex Event Processing (CEP) systems is an event pro- cessing paradigm to perform real-time analytics over streaming data and match high-level event patterns. Presently, the CEP system is limited to process structured data stream. Video streams are complicated due to their unstructured data model and limit CEP systems to perform match- ing over...

In data ecosystems, vast amounts of data move among actors within complex information supply chains that can form in different ways around an organisation, community technology platforms, and within or across sectors. This chapter explores the role a data ecosystem can play in the design of intelligent systems to support data-rich Internet of Thing...

A fundamental requirement for intelligent decision-making within a smart environment is the availability of information about entities and their schemas across multiple data sources and intelligent systems. This chapter first discusses how this requirement is addressed with the help of catalogs in dataspaces; it then details how entity data can be...

As the volume and variety of data sources within a dataspace grow, it becomes a semantically heterogeneous and distributed environment; this presents a significant challenge to querying the dataspace. Approaches used for querying siloed databases fail within large dataspaces because users do not have an a priori understanding of all the available d...

The goal of Real-time Linked Dataspaces is to support a real-time response from intelligent systems to situations of interests within a smart environment by providing data processing support services that follow the data management philosophy of dataspaces and meet the requirements of real-time data processing. This part of the book details support...

A dataspace is an emerging data management approach used to tackle heterogeneous data integration in an incremental manner. Data sources that are participants in a dataspace can be of various types such as online services, open datasets, sensors, and smart devices. Given the dynamicity of dataspaces and the diversity of their data sources and user...

Smart environments have emerged in the form of smart cities, smart buildings, smart energy, smart water, and smart mobility. A key challenge in delivering smart environments is creating intelligent applications for end-users using the new digital infrastructures within the environment. In this chapter, we reflect on the experience of developing Int...

Within dataspaces, data sources are not necessarily fully integrated or homogeneous in their schematics and semantics. For dataspaces to support a real-time response to situations of interest when a set of events take place, for example from sensor readings, there is a need for a principled approach to tackling data heterogeneity within real-time d...

The objective of a Real-time Linked Dataspace is to support a real-time response from intelligent systems to situations of interest when a set of events take place within a smart environment. In addition to the obvious need for real-time data processing support services, there is also the need for the fundamental data support services one would exp...

The Internet of Things (IoT) envisions smart objects and intelligent systems collecting and sharing data on a global scale to enable smart environments. One challenging data management issue is how to disseminate data to relevant consumers efficiently. This chapter leverages semantic technologies, such as linked data, which can facilitate machine-t...

Real-time predictive data analytics is a very important tool for effective decision support within intelligent systems. When making decisions using data, it is critical to use the most appropriate data. When creating predictive analytics, the selection of data sources is important as the quality of the sources influences the accuracy of the predict...

As we move toward 2030, today’s computing paradigms such as data-intensive computing (Big Data), Open Data [380], Knowledge Graphs, Machine Learning, Large-Scale Distributed Systems [381], Internet of Things (IoT), Physical-Cyber-Social Computing [14], Service-Oriented [382], and Cloud/Edge Computing [383] will be the foundations to the realisation...

Global ontologies include common vocabularies to provide interoperability among different applications. These ontologies require a balance of reusability-usability to minimise the ontology reuse effort in different applications. To achieve such a balance, reusable and usable ontology design methodologies provide guidelines to design and develop lay...

Modelling complex events in unstructured data like videos not only requires detecting objects but also the spatiotemporal relationships among objects. Complex Event Processing (CEP) systems discretize continuous streams into fixed batches using windows and apply operators over these batches to detect patterns in real-time. To this end, we apply CEP...

Machine learning based applications that run on image datasets increasingly use local image feature descriptors. We can visualize images as objects and local features as parts. Typically, there are thousands of local features per image, resulting in an explosion of feature set size for already huge image datasets. In this paper, we present a featur...

Video data is highly expressive and has traditionally been very difficult for a machine to interpret. Querying event patterns from video streams is challenging due to its unstructured representation. Middleware systems such as Complex Event Processing (CEP) mine patterns from data streams and send notifications to users in a timely fashion. Current...

This work presents a data-driven adaptive windowing approach to accelerate video content extraction in DNN-based Complex Event Processing (CEP) systems. The CEP windows continuously monitor low-level content of incoming video frames and exploit interframe correlations to accelerate the overall DNN content extraction process. The two main contributi...

This work presents a data-driven adaptive windowing approach to accelerate video content extraction in DNN-based Complex Event Processing (CEP) systems. The CEP windows continuously monitor low-level content of incoming video frames and exploit interframe correlations to accelerate the overall DNN content extraction process. The two main contributi...

A dataspace is an emerging approach to data management which recognises that in large-scale integration scenarios, involving thousands of data sources, it is difficult and expensive to obtain an upfront unifying schema across all sources. Data is integrated on an “as-needed” basis with the labour-intensive aspects of data integration postponed unti...

Humans are playing critical roles in the management of data at large scales, through activities including schema building, matching data elements, resolving conflicts, and ranking results. The application of human-in-the-loop within intelligent systems in smart environments presents challenges in the areas of programming paradigms, execution method...

The proliferation of sensor devices and services along with the advances in event processing brings many new opportunities as well as challenges for intelligent systems. It is now possible to provide, analyse, and react upon real-time, complex events in smart environments. When existing event services do not provide such complex events directly, an...

The design of next-generation smart environments poses significant technical challenges with data management, data integration, and real-time processing of dynamic data, and non-technical challenges such as engaging end-users and supporting cultural and organisational changes. Real-time Linked Dataspaces (RLD) are data platforms designed explicitly...

Dataspaces can provide an approach to enable data management in smart environments that can help to overcome technical, conceptual, and social/organisational barriers to information sharing. However, there has been limited work on the use of dataspaces within smart environments and the necessary support services for real-time events and data stream...

Around 18,000 BCE, Paleolithic tribespeople marked notches into sticks, or bones, to keep track of trading activity or supplies. The tribespeople would compare the notches on their prehistoric data storage devices (their tally sticks) to make basic calculations that would allow them to make predictions such as how long their food supplies would las...

Smart environments have emerged in the form of smart cities, smart buildings, smart energy, smart water, and smart mobility [24], where the Internet of Things (IoT)-based infrastructure can support the efficient use of resources within the environment (e.g. water, energy, and waste) [289]. To this end, smart environments can engage a wide range of...

Complex Event Processing (CEP) is a paradigm to detect event patterns over streaming data in a timely manner. Presently, CEP systems have inherent limitations to detect event patterns over video streams due to their data complexity and lack of structured data model. Modelling complex events in unstructured data like videos not only requires detecti...

Global ontologies must provide a balance of reusabilityusability to minimize the ontology reuse effort in different applications. To achieve this balance, ontology design methods focus on designing layered ontologies that classify into abstraction layers the common domain knowledge (reused by most applications) and the variant domain knowledge (reu...

Statistical data account for a very large proportion of data published on open data platforms. This category of data are which are often of high quality, value and public interest; are gradually being published as 5-star linked open statistical data or data cubes (LOSD) for easy integration and cross-border comparability. However, publishing open d...