Recreational load as a driving variable for urban forests

Interpreting Sustainability for Urban Forests

Incisive interpretations of urban-forest sustainability are important in furthering our understanding of how to sustain the myriad values associated with urban forests. Our analysis of earlier interpretations reveals conceptual gaps. These interpretations are attached to restrictive definitions of a sustainable urban forest and limited to a rather mechanical view of maintaining the biophysical ...

Studies on the forest as a recreational resource for urban residents

Variable selection using random forests

This paper proposes, focusing on random forests, the increasingly used statistical method for classification and regression problems introduced by Leo Breiman in 2001, to investigate two classical issues of variable selection. The first one is to find important variables for interpretation and the second one is more restrictive and try to design a good prediction model. The main contribution is...

Short Range Safeguarding for Urban Driving

This report covers the development of a prototype low-cost collision warning system for short-range safeguarding (less than 5 meters) for driving in urban environments. Special interest is placed on using small, simple and cheap smart sensor modules that together, form a distributed sensing network whose overall performance exceeds the sum of the individual sensors. A “safety by the meter” appr...

Variable Selection Using Random Forests

One of the main topic in the development of predictive models is the identification of variables which are predictors of a given outcome. Automated model selection methods, such as backward or forward stepwise regression, are classical solutions to this problem, but are generally based on strong assumptions about the functional form of the model or the distribution of residuals. In this paper a...