Stefano Tondini

Within the project named FIRST (artiFicial Intelligence for wiReless Sensor neTworks) supported by the Stiftung Südtiroler Sparkasse of Bolzano through the Fusion Grant, Eurac Research is developing drift compensation and adaptive learning methods to extend the calibration lifespan of low-cost sensors in time. The project aims at comparing several models (multivariate linear regression, random searches, feedforward neural networks, etc.) by exploiting training-set and data-set from real sensors for air quality deployed in a urban area.

A main focus of FIRST is to push the computational workload toward the network’s edge. In this sense, the talk is connected to the SFScon’s topic Intelligent Sensors/Networks of the IoT panel. The contribution is relevant to SFScon cause the entire process will be automatized by means of open-source software components. Moreover, the training-set is consumed via the API of the Open Data Hub, which exposes air-quality data from the certified monitoring stations located in the province of Bolzano.

The emergence of the cloud computing paradigm in combination with the latest technological developments is supporting the shaping of many existing solutions to tackle water management in agriculture. The talk aims to show how the novel approach of FIWARE, that moves beyond the data management, namely context information management, brings huge benefit when it comes to flexibility, scalability and interoperability of IoT solutions. The outcome is a complete context-aware system combined of the various Generic Enablers, capable of making autonomous irrigation decisions (using Complex Event Processing) which are not solely based on sensor-related measurements, but also on the integration of different sources of information such as weather forecast data. By doing so, optimal management of water resources according to the predicted weather conditions has been achieved.

A standalone low-cost mobile prototype with accurate localization capabilities and communicating environmental measurements in real-time can definitely expand the current picture of urban data characterized by limited spatio-temporal resolution. Sensor data enrichment with kinematics, high-frequency and robust positioning data plays a crucial role in IoT devices for mobile microclimatic monitoring application. Indeed, spatially enriched real time kinematic sensors lead directly to fast, reliable and accurate information over-time. This, in turn, allows to create added-value services (smart cities, transportation, e-health, smart home, social, etc.) for life quality improvement of urban communities. The design, prototyping and experimental activities have got funded the DPS4ESLAB project.