Skip to Main Content
Several pervasive and mobile computing systems would benefit from being notified about special events happening in the city. In this paper we present a methodology to discover events from human mobility patterns as recorded by cell network usage. Experiments conducted over an extensive dataset from the main Italian telecom operator show that the proposed approach is effective and can be applied to a number of different scenarios. These results can have a strong impact on pervasive applications including online map services, automatic gazetteers, urban planning, and disaster response.