In recent years, the widespread availability of smartphones provided with sensors has enabled the possibility of harvesting large quantities of data in urban areas exploiting user devices, thus enabling so-called mobile crowd sensing (MCS). While many efforts have been made to improve specific techniques for MCS - spanning from signal processing to the assignment of data collection campaigns to users, and to the entire data processing spectrum - to the best of our knowledge, thus far there have been no active experiments of MCS that involve all these techniques in a large-scale real-world experiment. Based on these considerations, we started the ParticipAct Living Lab testbed, an ongoing experiment at the University of Bologna involving 300 students for one year in crowd sensing campaigns that can passively access smartphone sensors and also require active user collaboration. In this article we describe the guidelines behind the design of ParticipAct, as well as its features and architecture. Moreover, we report some of the seminal results gathered during the first three months of its deployment, including accuracy of the classifier provided by ParticipAct client and user inclination to successfully complete tasks depending on the level of active collaboration required to executing them.
The participact mobile crowd sensing living lab: The testbed for smart cities
CARDONE, GIUSEPPE;CIRRI, ANDREA;CORRADI, ANTONIO;FOSCHINI, LUCA
2014
Abstract
In recent years, the widespread availability of smartphones provided with sensors has enabled the possibility of harvesting large quantities of data in urban areas exploiting user devices, thus enabling so-called mobile crowd sensing (MCS). While many efforts have been made to improve specific techniques for MCS - spanning from signal processing to the assignment of data collection campaigns to users, and to the entire data processing spectrum - to the best of our knowledge, thus far there have been no active experiments of MCS that involve all these techniques in a large-scale real-world experiment. Based on these considerations, we started the ParticipAct Living Lab testbed, an ongoing experiment at the University of Bologna involving 300 students for one year in crowd sensing campaigns that can passively access smartphone sensors and also require active user collaboration. In this article we describe the guidelines behind the design of ParticipAct, as well as its features and architecture. Moreover, we report some of the seminal results gathered during the first three months of its deployment, including accuracy of the classifier provided by ParticipAct client and user inclination to successfully complete tasks depending on the level of active collaboration required to executing them.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
