The accurate estimation of human activity in cities is one of the first steps towards understanding the structure of the urban environment. Human activities are highly granular and dynamic in both the spatial and temporal dimensions and having a clear idea about the whereabouts of these activities is crucial for decision-making in numerous applications, such as urban management, retail, transport planning and emergency management. Detecting general trends in the flow of people between spatial locations is neither obvious nor an easy task due to the high cost of capturing these movements without compromising the privacy of those involved. This research intends to address this problem by examining the movement of people in a SmartStreetSensors network at a fine spatial and temporal resolution. A novel methodology to the field of Big Data using mathematical models from information theory is introduced.
