Nowadays, smart city paradigm plays a primary role in the fulfillment of sustainable solutions in the field of urban mobility, both public and private. At the same time, the Internet of Things (IoT) is allowing the development of increasingly advanced solutions for real-time management of collected information related to the management and coexistence of vehicles (i.e., buses, cars, trains, bicycles, etc.) immersed in urban and sub-urban traffic. The Social IoT (SIoT) paradigm adds a relational connotation between objects typical of human relationships. Objects operate as equals and request/provide information among them in the perspective of providing IoT services to users while maintaining their individuality. Social object relationship enables the design of solutions aiming to improve the exchange of information among network nodes in terms of security from malicious attacks external to the so-called social network of objects. In this context, a new SIoT smart city solution is presented in this article: private and public vehicles together with pedestrians are involved in a real-time collection of data to improve the viability of the city in order to suggest new directions and information to citizens to better organize how to live the city. The developed architecture presented in this article is equipped with an artificial intelligence that process collected traffic data and, thanks to machine learning techniques, evaluate the directions and flows undertaken by vehicles and pedestrians on a daily basis. The authors are also presenting an application that allow both citizens to live the city in a better way and municipal authorities to promptly manage traffic flows. The proposed system was installed in a specific area of Cagliari (Italy) and the traffic flows have been compared with daily traffic data monitored before the installation, observing an average gain of up to 35 percent in daily traffic reduction.
A social smart city for public and private mobility: A real case study / Anedda, M.; Fadda, M.; Girau, R.; Pau, G.; Giusto, D.. - In: COMPUTER NETWORKS. - ISSN 1389-1286. - 220:(2023). [10.1016/j.comnet.2022.109464]
A social smart city for public and private mobility: A real case study
Anedda M.;Fadda M.;Pau G.;Giusto D.
2023-01-01
Abstract
Nowadays, smart city paradigm plays a primary role in the fulfillment of sustainable solutions in the field of urban mobility, both public and private. At the same time, the Internet of Things (IoT) is allowing the development of increasingly advanced solutions for real-time management of collected information related to the management and coexistence of vehicles (i.e., buses, cars, trains, bicycles, etc.) immersed in urban and sub-urban traffic. The Social IoT (SIoT) paradigm adds a relational connotation between objects typical of human relationships. Objects operate as equals and request/provide information among them in the perspective of providing IoT services to users while maintaining their individuality. Social object relationship enables the design of solutions aiming to improve the exchange of information among network nodes in terms of security from malicious attacks external to the so-called social network of objects. In this context, a new SIoT smart city solution is presented in this article: private and public vehicles together with pedestrians are involved in a real-time collection of data to improve the viability of the city in order to suggest new directions and information to citizens to better organize how to live the city. The developed architecture presented in this article is equipped with an artificial intelligence that process collected traffic data and, thanks to machine learning techniques, evaluate the directions and flows undertaken by vehicles and pedestrians on a daily basis. The authors are also presenting an application that allow both citizens to live the city in a better way and municipal authorities to promptly manage traffic flows. The proposed system was installed in a specific area of Cagliari (Italy) and the traffic flows have been compared with daily traffic data monitored before the installation, observing an average gain of up to 35 percent in daily traffic reduction.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.