The purpose of this tutorial is to provide an brief introduction of semantic explainability and to make the audience familiar to the use of an end-to-end platform supporting the generation of natural language recommendations concerning the self-monitoring of people behaviors.
The content of this tutorial can be applied to many domains but for making this event feasible to be performed during a half day timespan, we will focus on the healthcare one. In particular, we will show how to set up a semantic explainability platform for supporting the generation of food advises.
The tutorial purpose is to teach how to use the services provided by the HORUS.AI platform. This is an AI-based system built upon the integration of semantic web technologies and persuasive techniques for motivating people to adopt healthy lifestyle or for supporting them to cope with the self-management of chronic diseases. The system collects data from users’ devices, explicit users’ inputs, or from the external environment and interacts with users by using a goal-based metaphor. The attendants will master all the Web APIs provided by the platform in order to build healthcare applications based on HORUS.AI.
1. Introduction to Semantic Explainability (30 minutes [Slides here])
- What is the Semantic Explainability?
- Brief review of the Semantic Explainability literature.
- Active challenges in Semantic Explainability.
- Domains and scenarios requiring a proper use of Semantic Explainability strategies.
2. Presentation of the HORUS.AI platform (20 minutes [Slides here])
- Introduction to the HORUS.AI platform.
- Scientific aspects integrated into this state-of-the-art Semantic Explainable system.
- Description of the technological layers of the system.
- Facilities for the domain experts.
- How to configure the HORUS.AI platform.
3. Presentation of underlying ontology and the reasoner (20 minutes [Slides here])
- Introduction to the HeLiS ontology.
- The underlying conceptual model.
- The main entities involved in the semantic explanation process.
- How the ontology is populated with user data.
- The reasoning process.
- How to interpret the output of the reasoning process
4. Description of the HORUS.AI APIs (30 minutes [Slides here])
- Introduction to the HORUS.AI APIs.
- Overview of the implemented services.
- Methods for accessing to the HORUS.AI platform from third-party applications.
- Sample data packages.
- Methods for invoking the reasoning process.
The aim of the tutorial is to bring together a multidisciplinary spectrum of researchers, industrialists, entrepreneurs and healthcare practitioners. The audience experts coming from the following digital health areas will mainly benefit the tutorial:
- Computer science;
- national and international public health organizations;
- epidemic intelligence systems providers.
- NGOs and Agencies;
- industry and startups;
The only requirement is that the attendees should be equipped with a notebook in order to participate actively during the hands-on session.
Mauro Dragoni is a Research Scientist at Fondazione Bruno Kessler in Trento since 2011. He received his Ph.D. degree in Computer Science from the Università degli Studi di Milano in 2010 and his major research interests concern the Computational Intelligence and Knowledge Management fields applied to the Information Retrieval, e-Health, and Sentiment Analysis topics. In particular, he focuses on applying state of the art research paradigms to the implementation of real-world knowledge management systems. He co-organized two editions of the Cognitive Computing Special Track at ACM-SAC 2017 and 2018 and several editions of the ESWC Challenge and Workshops on Sentiment Analysis. He was program co-chair of OWLED 2015 and general chair of OWLED 2016.
Ivan Donadello is a Post Doctoral Researcher at Fondazione Bruno Kessler in Trento since 2018. He received his Ph.D. degree in Computer Science from Università degli Studi di Trento and Fondazione Bruno Kessler in 2018 with a thesis on the integration of logics and machine learning (Neural-Symbolic integration) for Semantic Image Interpretation. His current research interest mainly focuses on virtual agents (or softbots) able to recognize the health state of a person and give suggestions to improve it. His expertise encompasses the fields of Knowledge Representation (ontologies and Fuzzy Logic), Machine/Deep Learning, Computer Vision, eHealth and Explainable Artificial Intelligence.