1,721,019 research outputs found
Distributed Interactive Real-time Multimedia Applications: A Sampling and Analysis Framework
No full textThe advancements in distributed computing have driven the emergence of service-based infrastructures that allow for on-demand provision of IT assets. However, the complexity of characterizing an application’s behavior, and as a result the potential offered level of Quality of Service (QoS), introduces a number of challenges in the data collection and analysis process on the Service Providers’ side, especially for real time applications. The aforementioned complexity is increased due to additional factors that influence the application’s behavior, such as real time scheduling decisions, percentage of a node assigned to the application or application-generated workload. In this paper, we present a framework developed under the IRMOS EU-funded project that enables the sampling and gathering of the necessary dataset in order to analyze an application’s behavior. Processing of the resulting dataset is also conducted in order to extract useful conclusions regarding CPU allocation and scheduling decisions effect on the QoS. We demonstrate the operation of the proposed framework and evaluate its performance and effectiveness using an interactive real-time multimedia application, namely a webbased eLearning scenario
Big Data and Artificial Intelligence in Digital Finance
Full text linkThis open access book presents how cutting-edge digital technologies like Big Data, Machine Learning, Artificial Intelligence (AI), and Blockchain are set to disrupt the financial sector. The book illustrates how recent advances in these technologies facilitate banks, FinTech, and financial institutions to collect, process, analyze, and fully leverage the very large amounts of data that are nowadays produced and exchanged in the sector. To this end, the book also describes some more the most popular Big Data, AI and Blockchain applications in the sector, including novel applications in the areas of Know Your Customer (KYC), Personalized Wealth Management and Asset Management, Portfolio Risk Assessment, as well as variety of novel Usage-based Insurance applications based on Internet-of-Things data. Most of the presented applications have been developed, deployed and validated in real-life digital finance settings in the context of the European Commission funded INFINITECH project, which is a flagship innovation initiative for Big Data and AI in digital finance. This book is ideal for researchers and practitioners in Big Data, AI, banking and digital finance
Human in the Loop of AI Systems in Manufacturing
No full textArtificial Intelligence (AI) in manufacturing is typically looked upon from the view-point of its contribution to automation. Additionally, the role of AI in augmenting human activities has been the subject of a wide range of studies with impact on practical applications in manufacturing environments. Recently, the empowering effect of human and AI actors working in synergy has attracted increased atten-tion. After outlining relevant work, this chapter considers the potential emergent outcomes of such a synergy in a way that goes beyond automation or augmenta-tion. Aimed at both developers and work designers, the present work proposes a model of human-AI interaction along with an outline of key concepts and success criteria towards making human-AI interaction more effective
Trusted Artificial Intelligence in Manufacturing; Trusted Artificial Intelligence in Manufacturing
No full textThe successful deployment of AI solutions in manufacturing environments hinges on their security, safety and reliability which becomes more challenging in settings where multiple AI systems (e.g., industrial robots, robotic cells, Deep Neural Networks (DNNs)) interact as atomic systems and with humans. To guarantee the safe and reliable operation of AI systems in the shopfloor, there is a need to address many challenges in the scope of complex, heterogeneous, dynamic and unpredictable environments. Specifically, data reliability, human machine interaction, security, transparency and explainability challenges need to be addressed at the same time. Recent advances in AI research (e.g., in deep neural networks security and explainable AI (XAI) systems), coupled with novel research outcomes in the formal specification and verification of AI systems provide a sound basis for safe and reliable AI deployments in production lines. Moreover, the legal and regulatory dimension of safe and reliable AI solutions in production lines must be considered as well. To address some of the above listed challenges, fifteen European Organizations collaborate in the scope of the STAR project, a research initiative funded by the European Commission in the scope of its H2020 program (Grant Agreement Number: 956573). STAR researches, develops, and validates novel technologies that enable AI systems to acquire knowledge in order to take timely and safe decisions in dynamic and unpredictable environments. Moreover, the project researches and delivers approaches that enable AI systems to confront sophisticated adversaries and to remain robust against security attacks. This book is co-authored by the STAR consortium members and provides a review of technologies, techniques and systems for trusted, ethical, and secure AI in manufacturing. The different chapters of the book cover systems and technologies for industrial data reliability, responsible and transparent artificial intelligence systems, human centered manufacturing systems such as human-centred digital twins, cyber-defence in AI systems, simulated reality systems, human robot collaboration systems, as well as automated mobile robots for manufacturing environments. A variety of cutting-edge AI technologies are employed by these systems including deep neural networks, reinforcement learning systems, and explainable artificial intelligence systems. Furthermore, relevant standards and applicable regulations are discussed. Beyond reviewing state of the art standards and technologies, the book illustrates how the STAR research goes beyond the state of the art, towards enabling and showcasing human-centred technologies in production lines. Emphasis is put on dynamic human in the loop scenarios, where ethical, transparent, and trusted AI systems co-exist with human workers. The book is made available as an open access publication, which could make it broadly and freely available to the AI and smart manufacturing communities
Next-Generation Personalized Investment Recommendations
Full text linkRecent advances in Big Data and Artificial Intelligence have created new opportunities for AI-based agents, referred to as Robo-Advisors, to provide financial advice and recommendations to investors. In this chapter, we will introduce the concept of investment recommendation and describe how automated services for this task can be developed and tested. In particular, this chapter covers the following core topics: (1) the legal landscape for investment recommendation systems, (2) what financial asset recommendation is and what data it needs to function, (3) how to clean and curate that data, (4) approaches to build/train asset recommendation models and (5) how to evaluate such systems prior to putting them into production
Big Data and Artificial Intelligence in Digital Finance
Full text linkThis open access book presents how cutting-edge digital technologies like Big Data, Machine Learning, Artificial Intelligence (AI), and Blockchain are set to disrupt the financial sector. The book illustrates how recent advances in these technologies facilitate banks, FinTech, and financial institutions to collect, process, analyze, and fully leverage the very large amounts of data that are nowadays produced and exchanged in the sector. To this end, the book also describes some more the most popular Big Data, AI and Blockchain applications in the sector, including novel applications in the areas of Know Your Customer (KYC), Personalized Wealth Management and Asset Management, Portfolio Risk Assessment, as well as variety of novel Usage-based Insurance applications based on Internet-of-Things data. Most of the presented applications have been developed, deployed and validated in real-life digital finance settings in the context of the European Commission funded INFINITECH project, which is a flagship innovation initiative for Big Data and AI in digital finance. This book is ideal for researchers and practitioners in Big Data, AI, banking and digital finance
Stream qualitative reasoning in sensor data sensemaking
No full textMaking sense is an everyday activity whenever you face the unknown, something you cannot grasp immediately, or when you observe a set of potentially conflicting information origins. It is similar to the proverb “There is no smoke without fire”; there are signs that something must be true, so it must be at least partly true. This is the key motivation behind this thesis. Keeping the human in the loop is still necessary for the AI era, which focuses on providing and sometimes making decisions based on informational results. We still lack systems that “connect the dots” and accomplish utterly general tasks. Iterative conceptualisations of situations with further deploying this model to the same environment to recognise this situation are what we currently have. The moment the concept “drifts”, the model might be insufficient to answer the same question.
The thesis addresses the problem of keeping the human in the loop in a machine-based “sensemaking” process and revisiting approaches from classical AI, which tend to be revived in hybrid architectures, making the best of both worlds. The main challenge is selecting appropriate abstractions relatable to humans that qualitatively express their reasoning, using, for example, words such as “increasing”, “decreasing”, “flat”, or their synonyms. Since the early origins of AI, the commonsense knowledge and reasoning innate in this sensemaking process have used some form of a logical language, and the reasoning is characterised as a logical inference in this language. I know it cannot be accomplished in any other known formalism.
To this end, the thesis proposes a holistic approach to transferring raw data from various sources containing information about the unobserved phenomenon, using a set of qualitative linguistic abstractions instead of the raw numerical data. Additionally, it alleviates probabilistic uncertainty on expressing domain knowledge about these abstract happenings in complex patterns that gasp the intention to give them meaning with several possible explanations drawn by the different hypotheses.
The key contribution is the concept, validated as a prototypical stream processing/ reasoning artefact. It is implemented on top of a unified programming model for batch and streaming processing, indicating advantages when using a declarative sensor fusion model over observing single sources, where multivariate sources will increase the probability of the unobserved phenomenon holding partially true. Every step in the framework is interpretable and endorses fault tolerance via the various knowledge composition alternatives.
The thesis provides the following contributions: (i) linguistic abstractions from data-driven patterns, based on a symbolic time series representation method and maintaining interpretability end-to-end, (ii) an expressive high-level meta-reasoning component, employing probabilistic graphical models to handle the logical uncertainty on creating the various hypothesis during the sensemaking process, and (iii) an integrated framework for sensor data sensemaking, build on robust foundations to execute on streaming engines
Big Data and Artificial Intelligence in Digital Finance
No full textThis open access book presents how cutting-edge digital technologies like Big Data, Machine Learning, Artificial Intelligence (AI), and Blockchain are set to disrupt the financial sector. The book illustrates how recent advances in these technologies facilitate banks, FinTech, and financial institutions to collect, process, analyze, and fully leverage the very large amounts of data that are nowadays produced and exchanged in the sector. To this end, the book also describes some more the most popular Big Data, AI and Blockchain applications in the sector, including novel applications in the areas of Know Your Customer (KYC), Personalized Wealth Management and Asset Management, Portfolio Risk Assessment, as well as variety of novel Usage-based Insurance applications based on Internet-of-Things data. Most of the presented applications have been developed, deployed and validated in real-life digital finance settings in the context of the European Commission funded INFINITECH project, which is a flagship innovation initiative for Big Data and AI in digital finance. This book is ideal for researchers and practitioners in Big Data, AI, banking and digital finance
Trusted Artificial Intelligence in Manufacturing; Trusted Artificial Intelligence in Manufacturing
Full text linkThe successful deployment of AI solutions in manufacturing environments hinges on their security, safety and reliability which becomes more challenging in settings where multiple AI systems (e.g., industrial robots, robotic cells, Deep Neural Networks (DNNs)) interact as atomic systems and with humans. To guarantee the safe and reliable operation of AI systems in the shopfloor, there is a need to address many challenges in the scope of complex, heterogeneous, dynamic and unpredictable environments. Specifically, data reliability, human machine interaction, security, transparency and explainability challenges need to be addressed at the same time. Recent advances in AI research (e.g., in deep neural networks security and explainable AI (XAI) systems), coupled with novel research outcomes in the formal specification and verification of AI systems provide a sound basis for safe and reliable AI deployments in production lines. Moreover, the legal and regulatory dimension of safe and reliable AI solutions in production lines must be considered as well. To address some of the above listed challenges, fifteen European Organizations collaborate in the scope of the STAR project, a research initiative funded by the European Commission in the scope of its H2020 program (Grant Agreement Number: 956573). STAR researches, develops, and validates novel technologies that enable AI systems to acquire knowledge in order to take timely and safe decisions in dynamic and unpredictable environments. Moreover, the project researches and delivers approaches that enable AI systems to confront sophisticated adversaries and to remain robust against security attacks. This book is co-authored by the STAR consortium members and provides a review of technologies, techniques and systems for trusted, ethical, and secure AI in manufacturing. The different chapters of the book cover systems and technologies for industrial data reliability, responsible and transparent artificial intelligence systems, human centered manufacturing systems such as human-centred digital twins, cyber-defence in AI systems, simulated reality systems, human robot collaboration systems, as well as automated mobile robots for manufacturing environments. A variety of cutting-edge AI technologies are employed by these systems including deep neural networks, reinforcement learning systems, and explainable artificial intelligence systems. Furthermore, relevant standards and applicable regulations are discussed. Beyond reviewing state of the art standards and technologies, the book illustrates how the STAR research goes beyond the state of the art, towards enabling and showcasing human-centred technologies in production lines. Emphasis is put on dynamic human in the loop scenarios, where ethical, transparent, and trusted AI systems co-exist with human workers. The book is made available as an open access publication, which could make it broadly and freely available to the AI and smart manufacturing communities
Workflow management systems in distributed environments
No full textWith the advent of Service Oriented Architectures, more applications are built in a distributed manner based on loose coupled services. In this context, Workflow Management Systems play an important role as they are the means to both define the processes that realize the application goals as well as implement the orchestration of the different services. The purpose of the chapter is to give an overview of various solutions regarding workflow semantics and languages, as well as their enactment within the scope of distributed systems. To this end, major focus is given to solutions that are aimed at Grid environments. Scheduling algorithms and advance reservation techniques are also discussed as these are among the hottest research topics in Workflow Management Systems
- …
