Abstract
Investigation of the state-of-the-art in Cyber-Physical-Social System (CPSS) reveals that significant work has been done in interpreting data from different sources in isolation, performing correlations for numerical observations across one or two domains, or to provide simple textual explanations from social networks content for analysed physical world data. Existing works also work with ideal sets or already cleaned data that does not provide the same real-world insight into working with big data in cities. Thus, there is a need for integrated solutions that address the complete data flow; from data acquisition to processing and knowledge representation. This thesis presents a data-centric framework for CPSS that contains management and processing capabilities for knowledge discovery from mobile sensing data and social networks content, by mainly addressing challenges from mobile sensing scenarios in CPSS, including: 1) interoperability issues caused by the vast amount of heterogeneous data sources; 2) thematic-spatial-temporal information retrieval of opportunistic mobile sensing; 3) incomplete datasets generated from noisy data sources of mobile sensing techniques; 4) different scales/types of data and information, which cannot be correlated directly. The contributions of the thesis include 1) a data retrieval method that addresses the issue of searching for both current and historical sensor measurement values from the heterogeneous data sources; 2) a novel spatio-temporal model for regression analysis that can perform missing data estimation in the incomplete datasets; 3) a knowledge discovery mechanism that merges and correlates physical and social sensing data, enabling links between different scales/types of data: numeric values of sensor observation data and textual content of social networks’ messages. The above contributions were evaluated through experimentation on real smart city datasets and data collected from the Twitter social network to prove their accuracy and reliability, as well as to show the applicability of the proposed approaches to existing smart cities.