IRIT-SMAC/University of Palermo (Italy)

Context presentation

The development of sustainable smart cities requires the deployment of information and communication technology to ensure better services and available information at any time and everywhere. As IoT devices become more powerful and low-cost, the implementation of an extensive sensor network for an urban context can be expensive. This project proposes a technique for estimating missing environmental information in large-scale environments named HybridIoT. Our proposal enables providing information whereas devices are not available for an area of the environment not sufficiently covered by sensing devices. The contribution of our proposal is summarized in the following points:

-    limiting the number of sensing devices to be deployed in an urban environment;

-    the exploitation of heterogeneous data acquired from intermittent devices;

-    real-time processing of information;

-    self-calibration of the system.

HybridIoT exploits both homogeneous (information of the same type) and heterogeneous information (information of different types or units) acquired from the available sensing device to provide accurate estimates in the point of the environment where sensing devices are not available.


Figure 1 HybridIoT uses information from intermittent and mobile devices to provide accurate estimates.


Smart City, Missing Data Estimation, Heterogeneous Data Integration

Scientific goal

HybridIoT enables estimating accurate environmental information under conditions of uncertainty arising from the urban application context in which the project is situated, and which have not been explored by the state-of-the-art solutions :

-    openness: sensors can enter or leave the system at any time without the need for any reconfiguration;

-    large scale: the system can be deployed in a large, urban context and ensure correct operation with a significant number of devices;

-    heterogeneity: the system handles different types of information without any a priori configuration.


Davide Guastella, Valérie Camps, Marie-Pierre Gleizes {davide.guastella, valerie.camps,