Presentations
Templates
Features
Teams
Pricing
Log in
Sign up
Log in
Sign up
Menu
Optimize ambulance placement
Roy Hyunjin Han
March 27, 2014
Mountain View Spatiotemporal Analysis Working Group Meetup
Overview
Goal
Methods
Techniques
Discussion
Press the right arrow key to skip to the next topic
Press the down arrow key to explore a topic
Goal
Reduce emergency response time
Place ambulances close to where emergencies might happen
From
Benjamin Dean
of the
NYC's Mayor's Office of Data Analytics
Reduce emergency response time
Estimate where emergencies might happen
using past 911 calls
Optimize ambulance placement
Optimize ambulance placement
Generate ranked list
of
recommended ambulance locations
to maximize number of past calls
within 800m of an ambulance
and minimize summed distance of past calls
to nearest ambulance
Method
Random
Single
Split
Rank
Place five ambulances at random
Place one ambulance
Divide and conquer
Survival of the fittest
Method comparison
Technique
K-D tree
Brute force gradient descent
K-D tree
kdtree = KDTree(points)
kdtree.query(
x,
maximum_count,
maximum_distance)
Brute force gradient descent
scipy.optimize.fmin_bfgs(f, x0)
Discussion
Form groups of three
Think of your approach
Present approach
Optimize ambulance placement
By Roy Hyunjin Han
Made with Slides.com
Optimize ambulance placement
2,077
Roy Hyunjin Han
Create and Run Tools for Analyzing Open Data
crosscompute.com
crosscompute
More from
Roy Hyunjin Han