Large-scale data collection by means of wireless sensor network andinternet-of-things technology poses various challenges in view of thelimitations in transmission, computation, and energy resources of theassociated wireless devices. Compressive data gathering based on compressedsensing has been proven a well-suited solution to the problem. Existing designsexploit the spatiotemporal correlations among data collected by a specificsensing modality. However, many applications, such as environmental monitoring,involve collecting heterogeneous data that are intrinsically correlated. Inthis study, we propose to leverage the correlation from multiple heterogeneoussignals when recovering the data from compressive measurements. To this end, wepropose a novel recovery algorithm---built upon belief-propagationprinciples---that leverages correlated information from multiple heterogeneoussignals. To efficiently capture the statistical dependencies among diversesensor data, the proposed algorithm uses the statistical model of copulafunctions. Experiments with heterogeneous air-pollution sensor measurementsshow that the proposed design provides significant performance improvementsagainst state-of-the-art compressive data gathering and recovery schemes thatuse classical compressed sensing, compressed sensing with side information, anddistributed compressed sensing.
展开▼
