Efficient discovery of emerging patternsin heterogeneous spatiotemporal data from mobile sensors

Heterogeneous sensor networks, including traffic monitoring systems and telemetry systems, produce massive spatiotemporal data. Geolocated time series data and timestamped trajectory data are generally produced from fixed and mobile sensors in these systems, offering the possibility to detect events of interest. Events of interest generally comprise emerging and gradual changes in the behavior of those systems, including patterns of congestion in road, utility and communication networks. However, the comprehensive discovery of these actionable events is challenged by the: i) inherently spatiotemporal and heterogeneous nature of data produced by different sensors; ii) difficulty of detecting emerging patterns not yet markedly noticeable at early stages; and iii) massive data size. This work proposes E2PAT, a scalable method to comprehensively detect emerging patterns from heterogoeneous sources of spatiotemporal data generated by large sensor networks. We combine simplistic time differencing and spatial intersection principles to identify all emerging patterns distributed along geographies of interest. We show that the use of these principles guarantee a linear-time efficiency of E2PAT on the size of the input data. In addition, we propose an integrative score to measure the relevance of emerging patterns and show its role to support pattern retrieval, promote usability, and guarantee the actionability of the found patterns. These contributions are comprehensively assessed in the context of the Lisbon’s road traffic monitoring system, a large-scale network of mobile and fixed sensors. The gathered results confirm the actionability of the found patterns and the scalability of E2PAT. E2PAT is provided as an open-source tool available at https://github.com/francisconeves97/emerging-patterns.