Recently servitization has been proposed as a strategic business innovation to enrich products offerings with the delivery of remote services (e.g. remote monitoring services), thus also improving the perception of the product quality. The increasing connections of systems that produce high volumes of real time data have raised the need for advanced Data Exploration techniques able to face the impact of Big Data, in order to make remote monitoring services sustainable. In this paper, the IDEAaS (Interactive Data Exploration As-a-Service) approach is presented, apt to support and ease exploration of real time data in a dynamic context of interconnected systems, where large amounts of data must be incrementally collected, organised and analysed on-the-fly. The proposed approach relies on three main pillars: (i) a multi-dimensional organisation of data, for data exploration according to different analysis dimensions; (ii) data summarisation, based on incremental clustering algorithm, to provide summarised representation of collected data streams; (iii) data relevance evaluation techniques, to attract the users attention on relevant data only during exploration. Finally, the approach has been tested in a Smart Factory context, applying the interactive data exploration techniques in order to assist anomaly detection in remote monitoring services.
IDEAaS: Interactive data exploration as-a service
Bagozi A.;Bianchini D.
2019-01-01
Abstract
Recently servitization has been proposed as a strategic business innovation to enrich products offerings with the delivery of remote services (e.g. remote monitoring services), thus also improving the perception of the product quality. The increasing connections of systems that produce high volumes of real time data have raised the need for advanced Data Exploration techniques able to face the impact of Big Data, in order to make remote monitoring services sustainable. In this paper, the IDEAaS (Interactive Data Exploration As-a-Service) approach is presented, apt to support and ease exploration of real time data in a dynamic context of interconnected systems, where large amounts of data must be incrementally collected, organised and analysed on-the-fly. The proposed approach relies on three main pillars: (i) a multi-dimensional organisation of data, for data exploration according to different analysis dimensions; (ii) data summarisation, based on incremental clustering algorithm, to provide summarised representation of collected data streams; (iii) data relevance evaluation techniques, to attract the users attention on relevant data only during exploration. Finally, the approach has been tested in a Smart Factory context, applying the interactive data exploration techniques in order to assist anomaly detection in remote monitoring services.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.