team advisor - georgia institute of...
TRANSCRIPT
![Page 1: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/1.jpg)
1
![Page 2: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/2.jpg)
TeamMatt Garvey
Nilaksh Das
Jiaxing Su
Bhanu Verma
Meghna Natraj
AdvisorDr. Polo Chau
2
CSE 6242 Fall ‘15 Capstone Project
![Page 3: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/3.jpg)
○ Atlanta is one of the
most crime-ridden cities
in U.S.A.
○ Pedestrians are highly
susceptible to crime,
especially at night.
PROBLEM
3
![Page 4: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/4.jpg)
4
![Page 5: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/5.jpg)
OBJECTIVES○ Enhance walking safety by providing routes with less crime risk
○ Provide risk-distance trade-off path choices to users
○ Enable safety alert to friends when user is in distress
5
![Page 6: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/6.jpg)
ANALYTICS BUILDING BLOCKS
6
Collection
Cleaning
Integration
Analysis
Visualization
Presentation
Dissemination
![Page 7: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/7.jpg)
7
Collection Cleaning Integration Analysis Visualization Presentation
![Page 8: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/8.jpg)
○ Atlanta Police Department website
○ 2009 → 2015
○ ~ 250k crimes
○ All crime data in CSV format
CRIME DATA
8
![Page 9: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/9.jpg)
Legend
Class Count (2009 - 2015)
LARCENY-FROM VEHICLE 64345
LARCENY-NON VEHICLE 55902
BURGLARY-RESIDENCE 38277
AUTO THEFT 33256
AGG ASSAULT 16388
ROBBERY-PEDESTRIAN 12483
BURGLARY-NONRES 7243
ROBBERY-RESIDENCE 1632
ROBBERY-COMMERCIAL 1575
RAPE 789
HOMICIDE 592
> 20,000
> 5,000 AND < 20,000
< 5,000
9
CLASSES OF CRIMES
![Page 10: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/10.jpg)
MAP DATA
○ OpenStreetMap of Atlanta
○ Downloaded using Mapzen metro extracts
10
![Page 11: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/11.jpg)
11
Collection Cleaning Integration Analysis Visualization Presentation
![Page 12: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/12.jpg)
Data is usually messy!
12
![Page 13: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/13.jpg)
13
Collection Cleaning Integration Analysis Visualization Presentation
![Page 14: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/14.jpg)
Integration of 2 datasets
14
City Crime Data - available by coordinates and time of day
City Map Data - in OpenStreetMap format
![Page 15: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/15.jpg)
MAP DATA○ Converted to a graph using osm4routing
○ Graph consists of nodes on every road segment in the city
○ Nodes on the same road segment are successively connected by edges
○ Nodes: 111,380
○ Edges: 141,656
15
![Page 16: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/16.jpg)
MAP DATA - EDGE LENGTHWalkable Distance
○ Skewed left with a mean of ~215m
○ Majority of edges being under 150m
○ Maximum 400m-500m
16
![Page 17: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/17.jpg)
RISK OF EDGES
17
Map NodeCrime Node
![Page 18: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/18.jpg)
RISK OF EDGES
18
Map NodeCrime Node
![Page 19: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/19.jpg)
RISK OF EDGES○ Assign risk values to nodes based on crime density
19
Map NodeCrime Node
![Page 20: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/20.jpg)
RISK OF EDGES○ Assign risk values to nodes based on crime density
○ Assign risk values to edges based on node values
20
Map NodeCrime Node
![Page 21: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/21.jpg)
RISK OF EDGES○ Assign risk values to nodes based on crime density
○ Assign risk values to edges based on node values
○ Each edge has a both a distance and risk value
21
Map NodeCrime Node
![Page 22: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/22.jpg)
22
Collection Cleaning Integration Analysis Visualization Presentation
![Page 23: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/23.jpg)
OPTIMAL PATHS Pulse algorithm
○ shortest distance, more risk → least risk, more distance
○ pruning algorithm
○ outputs all dominant paths
23
![Page 24: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/24.jpg)
TRADEOFF ANALYSIS● Left Plot:
○ Ratio of Least-Risk-Path’s distance to the Shortest-Distance-Path’s distance
○ mean: 1.13● Right Plot:
○ Ratio of Shortest-Distance-Path’s risk to the Least-Risk-Path’s risk
○ mean: 1.58● Takeaway
○ Going from SDP to LRP produces a larger proportional decrease in risk than the proportional increase in distance
24d(LRP) / d(SDP) r(SDP) / r(LRP)
![Page 25: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/25.jpg)
RUNTIME ANALYSIS400 recorded runtime instances
Statistics (seconds)
mean 1.22
SD 0.51
max 6.8 (not shown)
min 1.15
25
![Page 26: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/26.jpg)
TECHNOLOGY
26
- MongoDB
- Apache Spark
- Python 2.7
- Node.js
- Phonegap - HTML/JS
(Storing graph data, geospatial indexing)
(Preprocessing)
(Preprocessing / Back-end)
(Back-end)
(Front-end)
![Page 27: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/27.jpg)
27
Collection Cleaning Integration Analysis Visualization Presentation
![Page 28: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/28.jpg)
28
![Page 29: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/29.jpg)
29
Collection Cleaning Integration Analysis Visualization Presentation
![Page 30: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/30.jpg)
DEMO
![Page 31: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/31.jpg)
31
![Page 32: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/32.jpg)
32
![Page 33: Team Advisor - Georgia Institute of Technologypoloclub.gatech.edu/cse6242/2017fall/slides/passage-nilaksh.pdf · City Map Data - in OpenStreetMap format. MAP DATA Converted to a graph](https://reader031.vdocument.in/reader031/viewer/2022020417/5e03fa032a2d104d9655036c/html5/thumbnails/33.jpg)
Team Passage:
Matt GarveyNilaksh DasJiaxing SuMeghna Natraj Bhanu Verma
PASSAGE
Advisor:
Dr. Polo Chau