Search

In the framework of indoor air monitoring, this paper proposes an Internet of Things ready solution to detect and classify contaminants. It is based on a compact and low-power integrated system including both sensing and processing capabilities. The sensing is composed of a sensor array on which electrical impedance measurements are performed through a microchip, named SENSIPLUS, while the processing phase is mainly based on Machine Learning techniques, embedded in a low power and low resources micro controller unit, for classification purposes. An extensive experimental campaign on different contaminants has been carried out and raw sensor data have been processed through a lightweight Multi Layer Perceptron for embedded implementation. More complex and computationally costly Deep Learning techniques, as Convolutional Neural Network and Long Short Term Memory, have been adopted as a reference for the validation of Multi Layer Perceptron performance. Results prove good classification capabilities, obtaining an accuracy greater than 75% in average. The obtained results, jointly with the reduced computational costs of the solution, highlight that this proposal is a proof of concept for a pervasive IoT air monitoring system.

The work deals with a technique adopted to calibrate in laboratory chemiresistor gas sensing film based on graphene that work at room temperature installed on a micro sensor board for applications in open air and IOT scenario. From the study in controlled environment the beginning of poisoning due to chemisorption can be estimated for the sensing layer and is possible to avoid harmful exposure to the analite during the calibration.

The Electrical Impedance Spectroscopy (EIS) measurements, in addition to being used for research purposes, are increasingly spreading in clinical setting. Thanks to the improvement of electronic and information technology, the necessary equipment is becoming increasingly simple and small, suitable for example for home care applications. In this work, the characteristics of a smartphone based system for impedance measurements are described. Besides, it is tested its reliability by measuring resistors of known values which fall in the range of bioimpedance. The proof demonstrator, here assessed, consists of a prototypal analogic, low-power chip capable of performing impedance measurements at different frequencies, a hardware support for the connection with a standard smartphone and an application properly developed. After its final validation, the proof demonstrator could be useful to design wearable devices for sport and consumer electronic.