Duplicate Report Detection in Urban Crowdsensing Applications for Smart City

Crowdsensing has become an emerging data collection paradigm for smart city applications. A new category of crowdsensing-based urban issue reporting systems have been developed to enable pervasive and real-time monitoring of urban infrastructure malfunctions. A key challenge exits in such systems is the duplicate report problem where uncoordinated users may submit redundant reports about the problem caused by the same underlying issue. The duplicate report problem has a significant economic impact on the municipal government. This paper develops a new duplicate report detection scheme that accurately detects the duplicate reports using an Expectation Maximization (EM) framework. The new duplicate report scheme has been evaluated on both synthetic and real world datasets collected from Chicago smart city applications. The results showed that our scheme significantly improves duplicate report detection accuracy compared to the state-of-the-arts.