1,720,960 research outputs found
Ontology-enriched Graph Databases: an Interoperable Framework for Knowledge Integration and Management
Get PDFL'enorme quantità e varietà di dati oggi disponibili è in costante aumento, guidata dalle esigenze accademiche e industriali e dalla necessità di sviluppare sistemi intelligenti e sostenibili per la società. I ricercatori si adoperano per tenere il passo con questa espansione attraverso nuove soluzioni hardware e software, affrontando però anche la sfida di progettare soluzioni conformi alle nuove normative, sostenibili dal punto di vista ambientale e gestibili nel lungo termine. Dato il gran numero di ambiti in cui i dati vengono utilizzati, è naturale che essi si presentino in formati eterogenei e con vocabolari differenti. In questo contesto, i database a grafo si rivelano estremamente utili grazie alla loro struttura non rigida, che permette flessibilità e agevola attività complesse e dispendiose in termini di tempo, come l’integrazione dei dati. La ragione di questa flessibilità risiede nel fatto che i database a grafo non richiedono di memorizzare uno schema per le istanze, a differenza dei modelli logici dei database tradizionali. Tuttavia, questa peculiarità implica la mancanza di controllo sulle informazioni disponibili, il che porta frequentemente a problemi di disambiguazione, incompletezza o incoerenza dei dati. Si propone, pertanto, l’arricchimento dei database a grafo con degli schemi, combinando in un'unica soluzione i vantaggi dei grafi in termini di prestazioni e interoperabilità con gli aspetti di condivisione di un vocabolario comune che, in
quanto concettualizzazione ontologica, apre nuove possibilità per il ragionamento.
Il contributo della tesi consiste nella progettazione di un framework per l'integrazione degli schemi nelle strutture su grafo. Gli schemi consentono di risolvere o mitigare le problematiche sopra menzionate relative all'integrazione dei dati e propongono soluzioni innovative a problemi di Intelligenza Artificiale che coinvolgono database a grafo, o strutture a grafo in generale. Il contributo include una soluzione per l'interconnessione e la mappatura di dati e schemi sui linguaggi basati sul web semantico. Il framework proposto prevede una soluzione per la valutazione degli schemi basata esclusivamente sulle istanze, e integra il framework in linguaggi logici (prevalentemente su logica del primo ordine) per compiti di ragionamento automatico. Il framework proposto è una soluzione generale che trova molteplici possibili applicazioni; nelle nostre sperimentazioni ci siamo principalmente concentrati sul campo delle biblioteche digitali, del patrimonio culturale e della linguistica.The amount and variety of data available nowadays are constantly increasing due to academic and industrial needs, as well as for building intelligent and sustainable network systems for society. Researchers endeavour to keep pace with this expansion with new hardware and software solutions, but they also struggle to design solutions that are compliant with new regulations, environmentally sustainable, and manageable in the long term. Given the extraordinary quantity of domains in which data are employed, the natural consequence is they come under diverse formats and with different vocabularies. In this context, graph databases are extremely valuable given their unfixed structure, which allows flexibility and permits facilitating time-consuming tasks like data integration. The cause of this flexibility is that graph databases do not hold schema information about instances, which is in contrast with traditional database logical models. The natural downside of this peculiarity is the lack of any control over the available information. In this scenario, problems related to data disambiguation, incompleteness, or inconsistency are frequent. Here we propose the enrichment of graphs with schema information, combining in a single solution the advantages of
graphs in terms of performance and interoperability and the aspects of sharing a common vocabulary that, seen as an ontological conceptualization, opens scenarios for reasoning
capabilities.
The contribution of the thesis is the design of a framework for integrating schemas into graph-based structures. Schemas solve or mitigate the above-mentioned issues in data integration, and help in solving current Artificial Intelligence tasks involving graph structures efficiently. The contribution includes a solution for interconnecting and mapping graph database models and the SW-based graph model. The proposed framework covers a solution for schema evaluation that is purely instance-based and demonstrates the capability of this solution to be integrated into first-order logic frameworks for reasoning tasks. The proposed framework is a general solution and, among its possible uses, we mainly experimented with the framework in the field of digital libraries, cultural heritage, and linguistics
NutriWell: An Explainable Ontology-Based FoodAI Service for Nutrition and Health Management
No full textNon-communicable diseases (NCDs) like hypertension, diabetes, osteoporosis, and cancer constitute 80% of the disease burden in European countries, affecting a significant portion of the working-age population. Addressing these numbers requires a strong effort in prevention and management. Nutrition is crucial not only for chronic conditions but also for non-chronic medical needs such as pregnancy, allergies, and intolerances. Artificial Intelligence (AI), especially when integrated with chatbots or social robots, now plays a pivotal role in assisting users with NCD prevention and management, as well as dietary needs. This manuscript introduces NutriWell, a framework leveraging AI and the GraphBRAIN technology for intelligent knowledge retrieval in nutrition and health management. NutriWell informs users about meal suitability based on their nutritional requirements, utilizing explanations that combine feature data and user preferences. Italian websites such as GialloZafferano and AlimentiNUTrizione provide extensive catalogs of European meals, including ingredients, allergens, and dietary specifics. The contribution of this work is the construction of a personalized diet assistant by utilizing datasets extracted from these websites that, as far as we know, have never been used for these tasks. A key contribution is an API that retrieves graph-based information integrated with an ontology specifying relational constraints. The ontology design, derived from existing frameworks and enhanced to integrate food impacts on disorders, allows for the calculation of meal impact scores tailored to user needs and preferences
Functionality and~Architecture for~a~Platform for~Independent Learners: KEPLAIR
No full textThe state-of-the-art in Artificial Intelligence, the Internet, and the computational power reached by the current technologies, allow to think of Intelligent Tutoring Systems much more advanced than their original definition. The KEPLAIR project envisages an online platform, designed to help all players involved in the educational endeavors, especially learners, in improving performance and effectiveness of their activities. Using leading edge AI solutions, KEPLAIR will act as a personalized assistant, helping its users in the entire educational experience, from goal elicitation, to learning path definition, to selection of materials, to performance/attainment testing, to analytics and report building. This paper introduces KEPLAIR’s architecture and functionality, and the role played by AI technologies
TestGraphia, a Software System for the Early Diagnosis of Dysgraphia
Get PDFDysgraphia, which is known as a writing disorder, is a specific disorder of writing regarding the reproduction of alphabetical and numerical signs. Dysgraphia may be related to dyspraxia, which is secondary to incomplete lateralization and characterized by a difficulty to reproduce alphabetical and numerical signs. Since the causes of dysgraphia are unknown, the rapid detection of symptoms is very important. In academic and clinical uses, the most common tool for detecting dysgraphia is an evaluation of the quality of writing on paper sheets. A writing analysis is based on rules for scoring the writing quality. In this paper, we discuss TestGraphia, which is a software system that can support doctors in making diagnoses and monitoring patients with dysgraphia in an objective manner. The system is based on known document analysis algorithms and modified or specially designed algorithms. Based on this software, a forms analysis requires considerably less time than that needed by traditional methods, enabling large screening activities and reducing time and cost. Potential dynamic changes in dysgraphia screening can be assessed by monitoring the quality of writing in a non-invasive way with reduced costs, both in the laboratory and the patient's home, and the appropriate frequency. In the system that we will describe, the mean time to execute a diagnosis is nearly ten times faster with trustworthy results
A Smartphone-Based Cell Segmentation to Support Nasal Cytology
Get PDFRhinology studies the anatomy, physiology, and diseases affecting the nasal region—one of the most modern techniques to diagnose these diseases is nasal cytology, which involves microscopic analysis of the cells contained in the nasal mucosa. The standard clinical protocol regulates the compilation of the rhino-cytogram by observing, for each slide, at least 50 fields under an optical microscope to evaluate the cell population and search for cells important for diagnosis. The time and effort required for the specialist to analyze a slide are significant. In this paper, we present a smartphones-based system to support cell segmentation on images acquired directly from the microscope. Then, the specialist can analyze the cells and the other elements extracted directly or, alternatively, he can send them to Rhino-cyt, a server system recently presented in the literature, that also performs the automatic cell classification, giving back the final rhinocytogram. This way he significantly reduces the time for diagnosing. The system crops cells with sensitivity = 0.96, which is satisfactory because it shows that cells are not overlooked as false negatives are few, and therefore largely sufficient to support the specialist effectively. The use of traditional image processing techniques to preprocess the images also makes the process sustainable from the computational point of view for medium–low end architectures and is battery-efficient on a mobile phone
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
