UE Data analysis, data web and semantic web



This course concerns analysis of data, the data web, and the semantic web.

It is articulated in two major parts.

The first deals with approaches at the confluence of statistics, artificial intelligence, and machine learning, the objective of which is the analysis of large datasets for knowledge extraction and decision support. Data analysis is becoming increasingly relevant in emerging applications (social media and networks, smart-grid, Internet of Things, smart-cities, human mobility, etc.), requiring the use of fine and advanced methods for analysis and prediction based on complex data (massive, structured, connected, and dynamic). These methodologies are at the heart of much data mining software used at both the industrial and academic levels. This course explains the main methods and techniques of data analysis leading to the development of an exploratory analysis and decision-making project: the preparation of data and coding for the basis of analysis, analysis of objectives, and choice of models, validation, and interpretation of results. This course is supported by practice assignments, a decision analysis project, and the use of data analysis methods under R.

 The second part of the course focus essentially on the semantic web and web of data, the aim of which is to provide a general framework for the exchange, sharing, and re-use of data between applications across enterprises and user communities. It is the result of a collaborative effort by the World Wide Web Consortium (W3C) with the participation of many partners from the world of research and industry. The semantic web seeks to structure new knowledge by relying on the web of data (Linked data). The web of data seeks to integrate and publish structured data by linking them and sharing and distributing this information. This course will focus on some of the technologies standardized by the W3C and which are at the heart of the semantic web: RDF and SPARQL allow the exchange and interrogation of the data, RDFS and OWL offer the expressivity necessary for the modelling of ontologies. The presentation of these different languages ​​in the course will be complemented by practical computer exercises (with the Java Jena framework and the Protected-OWL ontology editor), which will enable students to directly and concretely interact with the implementation of the semantic web.


skin.odf-2017:SKIN_ODF_CONTENT_COURSE_INFOS_LIEUX_TITLEGrenoble - Domaine universitaire