Efficient Integration of Heterogeneous Mobility-Pollution Big Data for Joint Analytics at Scale with QoS Guarantees

• Published in: Future internet Vol. 15; no. 8; p. 263
• Main Authors: Al Jawarneh, Isam Mashhour, Foschini, Luca, Bellavista, Paolo
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.08.2023
• Subjects: Accuracy; Air pollution; air pollution control; Approximation; Big Data; climate strategies; Consortia; Correlation coefficients; Data management; Data processing; Design; Geographic information systems; Geospatial data; Internet of Things; Management systems; Mathematical analysis; Mean; Meteorological data; Middleware; Mobility; Outdoor air quality; Pollutants; Pollution; Prototyping; Queries; Sensors; Smart cities; Social networks; Spatial data; Urban planning; Vehicles; Weather
• ISSN: 1999-5903; 1999-5903
• DOI: 10.3390/fi15080263

Numerous real-life smart city application scenarios require joint analytics on unified views of georeferenced mobility data with environment contextual data including pollution and meteorological data. particularly, future urban planning requires restricting vehicle access to specific areas of a city to reduce the adverse effect of their engine combustion emissions on the health of dwellers and cyclers. Current editions of big spatial data management systems do not come with over-the-counter support for similar scenarios. To close this gap, in this paper, we show the design and prototyping of a novel system we term as EMDI for the enrichment of human and vehicle mobility data with pollution information, thus enabling integrated analytics on a unified view. Our system supports a variety of queries including single geo-statistics, such as ‘mean’, and Top-N queries, in addition to geo-visualization on the combined view. We have tested our system with real big georeferenced mobility and environmental data coming from the city of Bologna in Italy. Our testing results show that our system can be efficiently utilized for advanced combined pollution-mobility analytics at a scale with QoS guarantees. Specifically, a reduction in latency that equals roughly 65%, on average, is obtained by using EMDI as opposed to the plain baseline, we also obtain statistically significant accuracy results for Top-N queries ranging roughly from 0.84 to 1 for both Spearman and Pearson correlation coefficients depending on the geo-encoding configurations, in addition to significant single geo-statistics accuracy values expressed using Mean Absolute Percentage Error on the range from 0.00392 to 0.000195.