Monitoring the citizens' perception on urban security in Smart City environments

Sensing the perception of citizens on urban security is a key point in Smart City management. To address non-emergency issues municipalities commonly acquire citizens' reports and then analyze them offline to perform targeted actions. However, since non-emergency data potentially scale towards Big Data there is a need for open standards and technologies to enable data mining and Business Intelligence analyses. The paper presents an integrated data mining and Business Intelligence architecture, relying on open technologies, for the analysis of non-emergency open data acquired in a Smart City context. Non-emergency data are first enriched with additional information related to the context of the warning reports and then analyzed offline to generate (i) informative dashboards based on a selection of Key Performance Indicators (KPIs), and (iii) association rules representing implications between warning categories and contextual information (e.g., city areas, districts, time slots). KPIs and rules are exploited to selectively notify to municipality actors (assessors, area operators) potentially critical situations, according to their role and authority. The experiments demonstrate the effectiveness of the proposed approach in a real Smart City context