Built Environment, Pedestrian Injuries, and Deep Learning - BEPIDL-Notes

Summarizing Street-specific SES Level from Block-level Data

One of the goals in the project is to assess the relationship of socioeconomic status (SES) with pedestrian collisions at the street level. While the street-level collision…

Diagnostic Evaluation of an AI Model for Built Environment Features

Part 2: Comparing GIS, AI training data and predictions with CANVAS data

As another post to document the process of the (preliminary) assessments of the reliability of the AI model for built environment (BE) features, here, we are comparing the…

Diagnostic Evaluation of an AI Model for Built Environment Features

Part 1: Comparing annotators’ reports, AI training data and predictions with GIS data

This post is to document the process of the (preliminary) assessments of the reliability of the AI model for built environment (BE) features, by comparing different data…

Hierarchical Clustering with Spatial Constraint

with ZAT- and calle-level indicators in Bogotá

First, we’ll aggregate a few calle level indicators to ZAT level for clustering. Here, for the calles matching to multiple ZAT units, we are making replicates of the calles…

Hierarchical Clustering with Spatial Constraint

with ZAT indicators in Bogotá

Previously we have used finite mixture modeling to cluster the neighborhoods (ZATs) across all the ZAT-level indicators on road infrastructures. In this post, we’ll explore…

Expanding the Neighborhood-Level Database

Aggregating street-level data to neighborhood (ZAT) level

To include more indicators at the ZAT level for our neighborhood built environment profiling, we’ll describe the process of aggregating some of street-level variables to the…

Traffic Sign Data Cleaning

Grouping by individual types of traffic signs

Check out the updated shiny dashboard of ZAT-level indicators!

Neighborhood Built Environment Profiles in Bogotá

Spatial visualization | Assess variable influence

After using finite mixture modeling to cluster the neighborhoods (ZATs) across all the ZAT-level indicators on road infrastructures, we’ll visualize the resulting…

Neighborhood Built Environment Profiles in Bogotá

Finite mixture modeling with ZAT-level data

After visualizing ZAT-level variable distributions spatially on maps and statistically through histograms, we’ll now try using finite mixture modeling to fit our data to…

Street Level Variables

Part 1: Road Infrastructure

From the first look, the street-level variables names in Calles_datos/ seemed a bit confusing, but after cross-referencing the codebook with CRUCES_DATOS.xlsx and variables…

Exploratory Data Analysis of BEPIDL Data

Geo-referenced ZAT-level Indicators

Building on the initial exploratory data analysis on variable distribution, I’d like to join the spatial information from ZAT folder with the variables from ZAT_INDICADORES.x…

Initial Look into BEPIDL Data

ZAT and Street Level

In this report, my goal is to get familiar with the variables (indicators), what they represent (according to codebook), how complete the datasets are, and potentially…