Abstract
The recent advancements in sensing technologies and the ubiquitous nature of sensory devices have paved the way to the popular paradigm called Smart City. In smart cities, data from a multitude of sources are collected and analyzed to understand the different aspects of the population, which helps in future urban planning activities. This process is called the Knowledge Discovery in smart cities. Gathering proper insights is a paramount task to understand the needs of people and to improve the quality of living conditions that cater to the requirements of people. Data Fusion and Segmentation analysis are key components in knowledge discovery as it leads to identifying different groups (segments) of people, and the popular places of visit among those groups. The work presented in this thesis focuses on data fusion and segmentation techniques to identify points of interest (POI), mobility patterns, and user segments using three case studies with real-world data collected from smartphone-based applications and a survey questionnaire. In each case study, we present the challenges in data fusion and knowledge discovery and propose novel segmentation analysis techniques to understand meaningful insights in different aspects of the smart city domain.