Aim of this paper is to present an innovative personal dosimeter for ionizing radiations obtained using a multilevel approach based on smartphone, artificial intelligence (AI) and data fusion. Nowadays, ionizing radiations are gaining ever more attention by the scientific community due to their severe impact on human health. In particular, it is difficult to measure long lasting exposure to low doses of ionizing radiations and to assess their impact on human health. The proposed system measures the actual users' exposition level by means of a data fusion technique of personal data (logs of their positions using smartphone's GPS, flight hours, X-rays, etc.) and those sampled by public and open sensor networks measuring radon gas concentration. Furthermore, the system proposes a forecasting analysis of users' annual exposition level using a binary neural network to identify "exposition risk profiles". In this way, the proposed system can be useful to influence users towards improving their lifestyles.
Smart App for Personal Dosimeter / Scarcelli, Alessandra; Amato, Alberto; Giove, Antonella; Dario, Rita; Soldo, Domenico; Quarto, Alessandro; Lecce, Vincenzo Di. - ELETTRONICO. - (2020). (Intervento presentato al convegno IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications, CIVEMSA 2020 tenutosi a Tunis, Tunisia nel June 22-24, 2020) [10.1109/CIVEMSA48639.2020.9132974].
Smart App for Personal Dosimeter
Scarcelli, Alessandra
;Lecce, Vincenzo Di
2020-01-01
Abstract
Aim of this paper is to present an innovative personal dosimeter for ionizing radiations obtained using a multilevel approach based on smartphone, artificial intelligence (AI) and data fusion. Nowadays, ionizing radiations are gaining ever more attention by the scientific community due to their severe impact on human health. In particular, it is difficult to measure long lasting exposure to low doses of ionizing radiations and to assess their impact on human health. The proposed system measures the actual users' exposition level by means of a data fusion technique of personal data (logs of their positions using smartphone's GPS, flight hours, X-rays, etc.) and those sampled by public and open sensor networks measuring radon gas concentration. Furthermore, the system proposes a forecasting analysis of users' annual exposition level using a binary neural network to identify "exposition risk profiles". In this way, the proposed system can be useful to influence users towards improving their lifestyles.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
