Sensing and Mining Urban Qualities in Smart Cities

The emergence of the Internet of Things in Smart Cities questions how the future citizens will perceive their predominant living and working environments and what quality of living they can experience within it, for instance the level of everyday stress. However, perception and experienced stress levels are challenging metrics to measure and are even more challenging to correlate with an underlying causal-effectual relationship in such stimulus abundant environments. The Internet of Things, enabled by several pervasive and ubiquitous devices such as smart phones and smart sensors, can provide real-time contextual information that can be used by advanced data science methodologies to generate new insights about urban qualities in Smart Cities and how they can be improved. The goal of this study is to show the predominant factors, which influence perceptual qualities of inhabitants in a Smart City equipped with sensing capabilities by the Internet of Things. To serve this goal, a novel data collection process for Smart Cities is introduced that involves (i) environmental data, such noise, dust, illuminance, temperature, relative humidity, (ii) location/mobility data, such as GNSS and citizens density detected via WiFi, and (iii) perceptual social data collected by citizens' responses in smart phones. These fine-grained real-time data can provide invaluable insights about the spatial correlations of the sensor measurements as well as the spatial and citizens' similarity illustrated. The data analysis illustrated reveals significant links between stress level and environmental changes observed.