1,721,032 research outputs found
Symbolic Regression for Transparent Clinical Decision Support: A Data-Centric Framework for Scoring System Development
Full text linkSemantic Web Service Composition in the NeP4B Project: Challenges and Architectural Issues
No full textSemantic Web service discovery and composition frameworks proposed so far assume for the most part a centralized registry that holds information of all the Web services available at any given time. This solution does not well cope with the scalability and flexibility requirements of dynamic, fast changing contexts. As part of the NeP4B project, in this paper we propose an alternative peer to peer architecture based on the Goal concept
A weak KAM approach to the periodic stationary Hartree equation
Full text linkWe present, through weak KAM theory, an investigation of the stationary Hartree equation in the periodic setting. More in details, we study the Mean Field asymptotics of quantum many body operators thanks to various integral identities providing the energy of the ground state and the minimum value of the Hartree functional. Finally, the ground state of the multiple-well case is studied in the semiclassical asymptotics thanks to the Agmon metric
Multi-Objective Symbolic Regression for Data-Driven Scoring System Management
No full textScores are mathematical combinations of elementary indicators (EIs) widely used to measure complex phenomena. Upon the theoretical framework definition, score construction requires a method to aggregate EIs. Aggregation is usually chosen among known methodologies fixing its shape through a try and error approach. Only then are the predictive power, the distribution of the index, and its ability to stratify the population measured. In this paper, we propose a novel data-driven approach that generates analytic aggregation methods relying on multi-objective symbolic regression. We translate the properties that the index must exhibit into optimization goals so that optimal index candidates replicate target variables, data balancing, and stratification. We run experiments on real data sets to solve three main score management problems: data-driven score simplification, generation, and combination. The results obtained show the effectiveness and robustness of the proposed approach
Dealing With Data Heterogeneity in a Data Fusion Perspective: Models, Methodologies, and Algorithms
No full textDealing with multiple manifestations of the same real-world entity across several data sources is a very common challenge for many modern applications, including life science applications. This challenge is referenced as data heterogeneity in the data management research field where the final aim is often to get a unified or integrated view of the real-world entities represented in the data sources. Data heterogeneity is a long-standing challenge that has attracted much interest in different computer science disciplines. The main aim of the chapter is to show how data heterogeneity problems that are typical of life science application contexts can be afforded by adopting systematic solutions stemming from the computer science field. To this end, it focusses on the main sources of heterogeneity in the life science context, presents the main problems that arise when dealing with heterogeneity, and provides a review of the solutions proposed in the computer science literature
Combining large language models with enterprise knowledge graphs: a perspective on enhanced natural language understanding
Full text linkKnowledge Graphs (KGs) have revolutionized knowledge representation, enabling a graph-structured framework where entities and their interrelations are systematically organized. Since their inception, KGs have significantly enhanced various knowledge-aware applications, including recommendation systems and question-answering systems. Sensigrafo, an enterprise KG developed by Expert.AI, exemplifies this advancement by focusing on Natural Language Understanding through a machine-oriented lexicon representation. Despite the progress, maintaining and enriching KGs remains a challenge, often requiring manual efforts. Recent developments in Large Language Models (LLMs) offer promising solutions for KG enrichment (KGE) by leveraging their ability to understand natural language. In this article, we discuss the state-of-the-art LLM-based techniques for KGE and show the challenges associated with automating and deploying these processes in an industrial setup. We then propose our perspective on overcoming problems associated with data quality and scarcity, economic viability, privacy issues, language evolution, and the need to automate the KGE process while maintaining high accuracy
Autonomous, context-aware, adaptive Digital Twins—State of the art and roadmap
No full textDigital Twins are an important concept in the comprehensive digital representation of manufacturing assets, products, and other resources, comprising their design and configuration, state, and behaviour. Digital Twins provide information about and services based on their physical counterpart's current condition, history and predicted future. They are the building blocks of a vision of future Digital Factories where stakeholders collaborate via the information Digital Twins provide about physical assets in the factory and throughout the product lifecycle. Digital Twins may also contribute to more flexible and resilient Digital Factories. To achieve this, Digital Twins will need to evolve from today's expert-centric tools towards active entities which extend the capabilities of their physical counterparts. Required features include sensing and processing their environment and situation, pro-actively communicating with each other, taking decisions towards their own or cooperative goals, and adapting themselves and their physical counterparts to achieve those goals. Future Digital Twins will need to be context-aware, autonomous, and adaptive. This paper aims to establish a roadmap for this evolution. It sets the scene by proposing a working definition of Digital Twins and examines the state-of-the-art in the three topics in their relation to DTs. It then elaborates potentials for each topic mapped against the working definition, to finally identify research gaps allowing for the definition of a roadmap towards the full realisation of autonomous, context-aware, adaptive Digital Twins as building blocks of tomorrow's Digital Factories
Dynamic digital factories for agile supply chains: An architectural approach
Full text linkDigital factories comprise a multi-layered integration of various activities along the factories and product lifecycles. A central aspect of a digital factory is that of enabling the product lifecycle stakeholders to collaborate through the use of software solutions. The digital factory thus expands outside the company boundaries and offers the opportunity to collaborate on business processes affecting the whole supply chain. This paper discusses an interoperability architecture for digital factories. To this end, it delves into the issue by analysing the key requirements for enabling a scalable factory architecture characterized by access to services, aggregation of data, and orchestration of production processes. Then, the paper revises the state-of-the-art w.r.t. these requirements and proposes an architectural framework conjugating features of both service-oriented and data-sharing architectures. The framework is exemplified through a case study
SUNRISE: Exploring PDMS Networks with Semantic Routing Indexes
No full textWe demonstrate SUNRISE (System for Unified Network Routing, Indexing and Semantic Exploration), a complete infrastructure supporting the construction of a PDMS semantic layer and providing a series of techniques that can be used for an effective and efficient exploration of a semantic network, for instance in a query answering setting
- …
