1,721,034 research outputs found
A visual ontology management system for handling, integrating and enriching semantic repositories
No full textThis paper presents a prototype system for managing ontological data from RDF semantic repositories, via an intuitive, graph-based visual interface. The core of the system provides basic editing functionalities for the managed ontologies, while at the same time allowing for more advanced operations to be plugged-in and applied on them, including the execution of ontology integration algorithms or the enrichment of the ontological knowledge bases via conceptualization mechanisms. The system is able to handle and visualize any ontology accessible from a SPARQL endpoint, and as such could be used to visualize portions of Linked Open Data repositories as well. The prototype has been applied on a case study revolving around a learning application for lawyers within the context of a larger software framework
Experimentation of a smart learning system for law based on knowledge discovery and cognitive computing
No full textThis work presents a Smart Learning system based on Knowledge Discovery and Cognitive Computing techniques aimed at citizens, legal students and experts alike, providing them with the possibility of submitting legal cases expressed in natural language and obtaining legal insight and advice in return. Advanced features implemented within the system include the automatic conceptualization and classification of textual legal cases via natural language processing, the generation of learning paths by relying upon legal ontologies, and additional features for managing legal knowledge bases, including editing, versioning, integration and enrichment. The system has been experimented on a diversified user-base and succeeded in obtaining a positive evaluation with respect to the aspects that were subject of the investigation, including effectiveness, efficiency and usability, thus paving the way to make the system a successful cognitive learning platform for future law professionals and knowledgeable citizens
A Neural Network-Based Approximation of Model Predictive Control for a Lithium-Ion Battery with Electro-Thermal Dynamics
No full textLithium-ion batteries are complex systems that require suitable management strategies to work properly, achieve fast charging, mitigate ageing mechanisms and guarantee safety. Among the different model-based charging strategies, the use of predictive control has shown promising results, due to its ability to deal with nonlinear systems subject to safety constraints. However, although many implementations have been proposed in the literature, little attention has been paid to their practical feasibility, which is limited by the high computational cost required online. In this paper, we exploit, for the first time in the batteries field, an approximation of predictive control obtained through the use of a deep neural network. The proposed solution is suitable for real-time battery charging, due to the fact that most of the computational burden is addressed offline. The results highlight the effectiveness of the presented methodology in approximating a standard model predictive control solution
Semi-automatic generation of an Object-Oriented API framework over semantic repositories
No full textThis paper presents a system able to generate an abstraction framework over a RDF-based, semantic triplestore, offering Object-Oriented Application Programming Interfaces to be made available for external applications. The system only requires a well-defined RDF schema and a minimal supervision by the user, and is able to produce all of the components of the API framework at their different layers, ranging from data source classes up to higher-level modules in terms of web service interfaces, in order to provide CRUD operations over the underlying semantic data. The system is sufficiently generic to accept any RDF repository with its schema as input, and can be easily configured to fine-tune the automatic generation of the API components to suit the needs of specific applications. The system has been deployed and tested on top of a large semantic repository featuring a schema where multiple real-world conceptualizations are defined, including one representing a learning model specifically designed for advanced e-learning management platforms
NETHIC: A system for automatic text classification using neural networks and hierarchical taxonomies
No full textThis paper presents NETHIC, a software system for the automatic classification of textual documents based on hierarchical taxonomies and artificial neural networks. This approach combines the advantages of highly-structured hierarchies of textual labels with the versatility and scalability of neural networks, thus bringing about a textual classifier that displays high levels of performance in terms of both effectiveness and efficiency. The system has first been tested as a general-purpose classifier on a generic document corpus, and then applied to the specific domain tackled by DANTE, a European project that is meant to address criminal and terrorist-related online contents, showing consistent results across both application domains
An Automatic Identification and Resolution System for Protein-Related Abbreviations in Scientific Papers
No full textA framework for semi-automatic identification, disambiguation and storage of protein-related abbreviations in scientific literature
No full textA Knowledge Discovery Methodology for Semantic Categorization of Unstructured Textual Sources
No full text
Experimentation of an automatic resolution method for protein abbreviations in full-text papers
No full text- …
