The increasing availability of Big Data is changing the way data exploration for Business Intelligence is performed, due to the volume, velocity and uncontrolled variety of data on which exploration relies. In particular, data exploration is required in Data Lakes that have been proposed to host heterogeneous data sources, given their flexibility to cope with cumbersome properties of Big Data. However, as data grows, new methods and techniques are required for extracting value and knowledge from data stored within Data Lakes, aggregating data into indicators according to multiple analysis dimensions, to enable a large number of users with different roles and competencies to capitalise on available information. In this paper, we propose PERSEUS (PERSonalised Exploration by User Support), a computer-aided approach for data exploration on top of a Data Lake, structured over three phases: (1) the construction of a semantic metadata catalog on top of the Data Lake, leveraging tools and metrics to ease the annotation of the Data Lake metadata; (2) modelling of indicators and analysis dimensions, guided by an openly available Multi-Dimensional Ontology to enable conformance checking of indicators and let users explore Data Lake contents; (3) enrichment of the definition of indicators with personalisation aspects, based on users’ profiles and preferences, to make easier and more usable the exploration of data for a large number of users. Results of an experimental evaluation in the Smart City domain are presented with the aim of demonstrating the feasibility of the approach.

In Smart Manufacturing, the recent opportunities provided by the Information and Communication Technologies has paved the way to a seamless connection of the manufactured product throughout its entire lifecycle, leading to the diffusion of the concepts of Smart Product and Digital Thread, that leverages digital technologies to assure a continuous flow of data encompassing the design phase of a product, manufacturing, operation, maintenance and also its eventual disposal or recycling. This compelling need to obtain a unified view of information associated with Smart Products has stimulated the so-called Internet of Services (IoS) paradigm, allowing for the sharing of products data and the execution of functions among various participants in intertwined supply chains. In these contexts, service-oriented architectures are being more and more employed to meet the complex and ever-evolving data analysis requirements, particularly when implementing Digital Thread solutions for Smart Products, where several issues must be considered, ranging from the heterogeneity of (Big) data to data sovereignty and data access policies, as information may cross the borders of multiple actors participating in intertwined supply chains. This survey discusses about the technological solutions and challenges to implement Digital Threads for Smart Products in Smart Manufacturing contexts, providing insights on opportunities for future research directions. In addition, the survey proposes a comprehensive multi-tier service-oriented architectural model to jointly tackle (Big) data heterogeneity, data sovereignty and data access policies issues, as they are only partially addressed by the research efforts examined in the literature review.

In modern Smart Cities, the unpredictable growth and heterogeneity of the shared data is raising interest for data lakes repositories, due to their versatility and schema-on-read nature. Personalised data access methods are required to deal with the variety of users, their goals and preferences on available data, and need to be adapted to the unique characteristics of data lakes. Pay-as-you-go or on-demand solutions are advocated, where integration is progressively carried out, and methodologies to enable personalised data exploration are required. In this paper, we present a methodological approach to build users’ profiles, in terms of context, determining the roles and activities of users while acting in the Smart City, and preferences expressed on indicators semantically derived from data lake sources. The proposed methodology includes: (a) the definition of preference constructors based on the semantic representation of indicators from data lake sources; (b) the definition of users’ profiles, in terms of context and preferences; (c) the definition of a procedure to support domain experts and data analysts for enabling personalised exploration of indicators.