Inhaltszusammenfassung

This paper addresses the determination of geospatial key factors, which are relevant for bike sharing stations in the city of Hamburg. They serve as an application case for limited service offers in smart cities. Our approach combines real-world empirical data with open-source data on points of interest for the determination. We apply linear regression methods in combination with an established metric for calculating the geospatial impact. On top of the determination of the geospatial key fac...This paper addresses the determination of geospatial key factors, which are relevant for bike sharing stations in the city of Hamburg. They serve as an application case for limited service offers in smart cities. Our approach combines real-world empirical data with open-source data on points of interest for the determination. We apply linear regression methods in combination with an established metric for calculating the geospatial impact. On top of the determination of the geospatial key factors, our paper seeks for machine learning based approaches to predict the bike sharing activity. In our results of the analysis, we identify correlations between bike activity and geospatial factors. Moreover, our neural network provides a solid basis for predicting the activity of bike stations.» weiterlesen» einklappen

Autoren

Klassifikation

DDC Sachgruppe:
Informatik