Predicting Pedestrian Counts per Street Segment in Urban Environments
Abstract: Cities are continuously growing all over the world and the complexity of designingurban environments increases. Therefore, there is a need to build a better understandingin how our cities work today. One of the essential parts of this is understandingthe pedestrian movement. Using pedestrian count data from Amsterdam, Londonand Stockholm, this thesis explore new variables to further explain pedestrian countsusing negative binomial and random forest. The models explored includes variablesthat represent street centrality, built density, land division, attractions and the roadnetwork. The result of the thesis suggests ways for variables to be represented orcreated to increase the explanatory value in regards to pedestrian counts. Thesesuggestions include: including street centrality measurements at multiple scales, attractioncounts within the surrounding area instead of counts on the street segment,counting attractions instead of calculating the distance to the nearest attraction,using network reach to constrain the network at different scales instead of boundingbox, and counting intersections in the road network instead of computing the networklength.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)