![Page 1: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/1.jpg)
Spatial DBMS and Intelligent Transportation
SystemShashi Shekhar
Intelligent Transportation Instituteand Computer Science Department
University of Minnesota
[email protected](612) 624-8307
http://www.cs.umn.edu/~shekharhttp://www.cs.umn.edu/research/shashi-group/
![Page 2: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/2.jpg)
Biography Highlights
7/01-now : Professor, Dept. of CS, U. of MN 12/89-6/01 : Asst./Asso. Prof. of CS, U of MN Ph.D. (CS), M.B.A., U of California, Berkeley (1989) Member: CTS(since 1990),Army Center, CURA Author: “A Tour of Spatial Database” (Prentice Hall,
2002) and 100+ papers in Journals, Conferences Editor: Geo-Information(2002-onwards), IEEE
Transactions on Knowledge and Data Eng.(96-00) Program chair: ACM Intl Conf. on GIS (1996) Tech. Advisor: UNDP(1997-98), ESRI(1995), MNDOT
GuideStar(1993-95 on Genesis Travlink) Grants: FHWA, MNDOT, NASA, ARMY, NSF, ... Supervised 7+ Ph.D Thesis (placed at Oracle, IBM
TJ Watson Research Center etc.), 30+ MS. Thesis
![Page 3: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/3.jpg)
Research Interests
Knowledge and Data Engineering Spatial Database Management Spatial Data Mining(SDM) and
Visualization Geographic Information System Application Domains : Transportation,
Climatology, Defence Computations
![Page 4: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/4.jpg)
Spatial Data Mining, SDBMS
Historical Examples London Cholera (1854) Dental health in Colorado
Current Examples Environmental justice Crime mapping - hot spots (NIJ) Cancer clusters (CDC) Habitat location prediction (Ecology) Site selection, assest tracking, spatial
outliers
![Page 5: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/5.jpg)
Road Maps
City Maps
Construction Schedule
Business Directory
Home, office Shopping mall
Information center, PCS
Highway Based Sensor
ITS Database Systems
ITSDatabase
Drivers
Traffic Reports
Transportation Planners,
Policy Maker
![Page 6: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/6.jpg)
SDBMS & SDM in ITS
Operational Routing, Guidance, Navigation for travelers and Commuters Asset tracking in APTS, CVO for security, and customer service Emergency services Ramp meter control (freeway operation) Incident management
Tactical Event planning (maintenance, sports connection) Infrastructure security - patrol routes Snow cleaning routes and schedules Impact analysis (e.g. Mall of America)
Strategic Travel demand forecasting for capacity planning Public transportation route selection Policy decision(e.g. HOV lanes, ramp meter study) Research: Driving Simulation and Safety
![Page 7: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/7.jpg)
SDBMS and SDM in ITS Transportation Manager
How the freeway system performed yesterday? Which locations are worst performers?
Traffic Engineering Where are the congestion (in time and space)? Which of these recurrent congestion? Which loop detection are not working properly? How congestion start and spread?
Traveler, Commuter What is the travel time on a route? Will I make to destination in time for a meeting? Where are the incident and events?
Planner and Research How much can information technique to reduce congestion? What is an appropriate ramp meter strategy given specific
evolution of congestion phenomenon?
![Page 8: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/8.jpg)
Transportation Projects
Traffic Database System Traffic Data Visualization Spatial Outlier Detection Roadmap storage and Routing Algorithms Road Map Accuracy Assessment Other:
Driving Simulation In-vehicle headup display evaluation
![Page 9: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/9.jpg)
Project: Traffic Database
System Sponsor and time-period: MNDOT, 1998-1999 Students: Xinhong Tan, Anuradha Thota Contributions to Transportation Domain
Reduce response of queries from hours to minutesPerformance tuning (table design, index selection)
Contributions to Computer ScienceGUI design for extracting relevant summaries Evaluate technologies with large dataset
![Page 10: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/10.jpg)
Map of Station in Mpls
![Page 11: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/11.jpg)
Gui Design
http://www.cs.umn.edu/research/shashi-group/TMC/html/gui.html
![Page 12: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/12.jpg)
Flow of Data From TMC
TMC Server
Binary ASCII
PC Conversion programs
Storage at University of Minnesota
FTP link Data made available for researchers
FTPlink
Convert binary to 5min data
FTP link
FTP link
![Page 13: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/13.jpg)
Existing Table
Fivemin
DetectorReadDateTimeDayofweekVolumeOccupancyValiditySpeed
![Page 14: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/14.jpg)
Table Designs
Detector ReadDate Time Volume occupancy validity speed Day_week
ReadDate Detector Vol_Occ_ValidtyFivemn_day
FiveminCurrent
Proposed-1
Proposed-2 Five_min Detector Time_id Volume occupancy validity
DateTime Time_id ReadDate Time
MN/Dot Five_min Detector ReadDate Hour Day_week time Vol_5_ min
Occl_5_ min
Validity_5_ min
15mn 1hr
Binary Five_min Detector ReadDate Time Volume occupancy validity
![Page 15: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/15.jpg)
Benchmark Queries1. Get 5-min Volume, occupancy for detector ID = 10 on Oct. 1st, 1997 from 7am to 8am2. Get 5-min volume, Occupancy for detector ‘5’ on
Aug1 1997.3. Get 5-min volume, Occupancy for detector ‘5’ on
Aug1 1997 from 6.30am to 7.30am.4. Get average 5-min volume, occupancy, for
Monday in Aug1997 between 8.00 - 8.05,8.05-8.10 …… 9.00
5. Get maximum volume, Occupancy for detector ‘5’ on Aug1 1997 from 6am to 7am
6. Get the average of AM rushhour hourly volume for a set of stations on highway I35W-NB with milepoint between 0.0 and 4.0 from Oct. 1st, 1997 to Oct. 5th , 1997
Conclusion
![Page 16: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/16.jpg)
Examples of the Query
Example1: Query description:
Get 5-min Volume, occupancy for detector ID = 10 on Oct. 1st, 1997 from 7am to 8am
SQL statement: SELECT readdate, time, xtan.fivemin.detector, occupancy,
volume FROM xtan.fivemin, xtan.datetime WHERE ReadDate = to_date('01-OCT-97', 'DD-MON-YYYY') AND time BETWEEN '0705' AND '0800' AND xtan.fivemin.Detector = '10' AND xtan.fivemin.
![Page 17: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/17.jpg)
Examples of the Query
Query result 1:
![Page 18: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/18.jpg)
Examples of the Query Example2:
Query description: Get the average of AM rushhour hourly volume for a set of
stations on highway I35W-NB with milepoint between 0.0 and 4.0 from Oct. 1st, 1997 to Oct. 5th , 1997
SQL statement: SELECT hour, xtan.v_stat_hour.station, avg(volume) FROM tan.v_stat_hour, xtan.statrdwy WHERE ReadDate BETWEEN to_date('01-OCT-97','DD-
MON-YYYY') AND to_date('05-OCT-97','DD-MON-YYYY') AND hour BETWEEN '06' AND '09' AND statrdwy.route = 'I35W-I' AND statrdwy.mp >= 0.0 AND statrdwy.mp <= 4.0 AND xtan.v_stat_hour.station = statrdwy.station GROUP BY xtan.v_stat_hour.station, hour
![Page 19: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/19.jpg)
Examples of the Query
Query result 2:
![Page 20: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/20.jpg)
Conclusions
MN/Dot model and Proposed-II(Normalized) are the two recommended models for the final structure
Little modification on existing loading process
Conversioneffort
Needs new loading program
Future Compatibility
Same format remains
Effort needed for derived data
Fifteenmin & hourly data exist, station data needs to be derived
Proposed-II
Number of columns increases
MN/Dot
Derived data
Query More flexible Less flexible
![Page 21: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/21.jpg)
Project: Traffic Data Visualization
Sponsor and time-period: USDOT/ITS Inst., 2000-2001 Students: Alan Liu, CT Lu Contributions to Transportation Domain
Allow intuitive browsing of loop detector data Highlight patterns in data for further study
Contributions to Computer Science Mapcube - Organize visualization using a dimension lattice Visual data mining, e.g. for clustering
![Page 22: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/22.jpg)
Motivation for Traffic Visualization
Transportation Manager How the freeway system performed yesterday? Which locations are worst performers?
Traffic Engineering Where are the congestion (in time and space)? Which of these recurrent congestion? Which loop detection are not working properly? How congestion start and spread?
Traveler, Commuter What is the travel time on a route? Will I make to destination in time for a meeting? Where are the incident and events?
Planner and Research How much can information technique to reduce congestion? What is an appropriate ramp meter strategy given specific
evolution of congestion phenomenon?
![Page 23: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/23.jpg)
Dimensions
Available• TTD : Time of Day
• TDW : Day of Week
• TMY : Month of Year• S : Station, Highway, All Stations
Others• Scale, Weather, Seasons, Event types,
…
![Page 24: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/24.jpg)
Mapcube : Which Subset of Dimensions ?
TTDTDWS
TTDTDW TDWS STTD
TTD TDWS
TTDTDWTMYS
Next Project
![Page 25: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/25.jpg)
Singleton Subset : TTD
X-axis: time of day; Y-axis: Volume
For station sid 138, sid 139, sid 140, on 1/12/1997
Configuration:
Trends:
Station sid 139: rush hour all day long
Station sid 139 is an S-outlier
![Page 26: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/26.jpg)
Singleton Subset: TDW
Configuration: X axis: Day of week; Y axis: Avg. volume.For stations 4, 8, 577Avg. volume for Jan 1997
Trends:Friday is the busiest day of weekTuesday is the second busiest day of week
![Page 27: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/27.jpg)
Singleton Subset: S
Configuration:
X-axis: I-35W South; Y-axis: Avg. traffic volume
Avg. traffic volume for January 1997
Trends?:
High avg. traffic volume from Franklin Ave to Nicollet Ave
Two outliers: 35W/26S(sid 576) and 35W/TH55S(sid 585)
![Page 28: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/28.jpg)
Dimension Pair: TTD-TDW
Evening rush hour broader than morning rush hour Rush hour starts early on Friday. Wednesday - narrower evening rush hour
Configuration:
Trends:
X-axis: time of date; Y-axis: day of Week f(x,y): Avg. volume over all stations for Jan 1997, except Jan 1, 1997
![Page 29: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/29.jpg)
Dimension Pair: S-TTD
Configuration: X-axis: Time of Day Y-axis: Highway f(x,y): Avg. volume over all stations for
1/15, 1997
Trends: 3-Cluster
• North section:Evening rush hour• Downtown area: All day rush
hour• South section:Morning rush hour
S-Outliers • station ranked 9th
• Time: 2:35pm Missing Data
![Page 30: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/30.jpg)
Dimension Pair: TDW-S
Busiest segment of I-35 SW is b/w Downtown MPLS & I-62
Saturday has more traffic than Sunday Outliers – highway branch
Configuration: X-axis: stations; Y-axis: day of week
f(x,y): Avg. volume over all stations for Jan-Mar 1997
Trends:
![Page 31: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/31.jpg)
Post Processing of cluster patterns
Clustering Based Classification:
Class 1: Stations with Morning Rush Hour
Class 2: Stations Evening Rush Hour
Class 3: Stations with Morning + Evening Rush Hour
![Page 32: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/32.jpg)
Triplet: TTDTDWS: Compare Traffic Videos
Configuration: Traffic volume on Jan 9 (Th) and 10 (F), 1997
Trends: Evening rush hour starts earlier on Friday Congested segments: I-35W (downtown Mpls – I-62);
I-94 (Mpls – St. Paul); I-494 ( intersection I-35W)
![Page 33: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/33.jpg)
Size 4 Subset: TTDTDWTMYS(Album)
Configuration: Outer: X-axis (month of year); Y-axis (highway) Inner: X-axis (time of day); Y-axis (day of week)
Trends:
Morning rush hour: I-94 East longer than I-35 W North Evening rush hour: I-35W North longer than I-94 East Evening rush hour on I-94 East: Jan longer than Feb
![Page 34: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/34.jpg)
Project: Spatial Outlier
Detection
Sponsor and time-period: USDOT/ITS Inst. (2000-2002) Students: C T Lu, Pusheng Zhang Contributions to Transportation Domain
Filter/reduce data for manual browsing Identify days with spatial outliers Identify sensors with anamolous behaviour
Contributions to Computer Science Unified definition of spatial outliers using algebraic aggregates Spatial outlier detection algorithm = scan spatial join
![Page 35: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/35.jpg)
Algorithms for Spatial outlier detection
Spatial outlier A data point that is extreme
relative to it neighbors
Given A spatial graph G={V,E} A neighbor relationship (K
neighbors) An attribute function f: V -> R Test T for spatial outliers
Find O = {vi | vi V, vi is a spatial outlier}
Objective Correctness, Computational
efficiency
Constraints Computation cost dominated by I/O
op. Test T is an algebraic aggregate
function
![Page 36: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/36.jpg)
Spatial outlier detection
Example Outlier Detection Test
1. Choice of Spatial Statistic S(x) = [f(x)–E y N(x)(f(y))]
Theorem: S(x) is normally distributed
if f(x) is normally distributed
2. Test for Outlier Detection | (S(x) - s) / s | >
HypothesisI/O cost = f( clustering efficiency )
f(x) S(x)
Spatial outlier and its neighbors
![Page 37: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/37.jpg)
Spatial outlier detection
Results 1. CCAM achieves higher
clustering efficiency (CE)
2. CCAM has lower I/O cost
3. Higher CE leads to lower
I/O cost 4. Page size improves CE
for all methods
Z-orderCCAM
I/O costCE value
Cell-Tree
![Page 38: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/38.jpg)
Project: Roadmap storage and
Routing Algorithms
Sponsor and time-period: FHWA/MNDOT, 1993-1997 Students: Prof. Du-Ren Liu, Dr. Mark Coyle,
Andrew Fetterer, Ashim Kohli, Brajesh Goyal Contributions to Transportation Domain
CRR = measure of storage methods for roadmaps In-vehicle navigation devices, routing servers on web
Contributions to Computer Science CCAM - Better storage method for roadmaps Hierarchical routing - optimal routes
even when map-size > memory size
![Page 39: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/39.jpg)
Road Map Storage - Problem Statement
Given roadmaps Find efficient data-structure to store
roadmap on disk blocks Goal - Minimize I/O-cost of
operations Find(), Insert(), Delete(), Create() Get-A-Successor(), Get-Successors()
Constraint Roadmaps larger than main memories
![Page 40: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/40.jpg)
Mpls map partitioning 1
Another way that we may partition the street network for Minneapolis
among disk blocks for improving performance of network computations.
![Page 41: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/41.jpg)
Mpls map partitioning:CCAM
This is one way that we may partition the street network for Minneapolis
among disk blocks for improving performance of network computations.
![Page 42: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/42.jpg)
Road Map Storage
Insight: I/O cost of network operations is minimized by maximizing CRR = Pr. ( road-intersection nodes connected
by a road-segment edge are together in a disk page)
WCRR = weighted CRR (edges have weights) Commercial database support geometric
storage methods even though CRR is a graph property
![Page 43: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/43.jpg)
Measurements of CRR
![Page 44: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/44.jpg)
Shortest Path Problem
Route computation Find a rout from current location to destination Criteria: Shortest travel distance or smallest
travel time Useful for
Travel during rush hour Travel in an unfamiliar area Travel to an unfamiliar destination
![Page 45: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/45.jpg)
Problem definition
Given Graph G=(N,E,C)
Each edge (u,v) in E has a cost C(u,v) Path from source to destination is a
sequence of nodes Cost of path=C(vi-1,vi) A path cost estimation is a function
f(u,v) that computes estimated cost of an optional path between the two nodes
![Page 46: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/46.jpg)
Smallest Paths
Blue: Smallest travel time path between two points.
It follows a freeway (I-94) which is faster but not shorter in distance.
Red: Shortest distance path between the same two points
![Page 47: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/47.jpg)
Routing around incidents
![Page 48: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/48.jpg)
Algorithm for Single pair Path Computation
Road Map Size<<Main Memory Size Iterative Algorithm Dijkstra’s Algorithm A* algorithm
A* with euclidean distance heuristic A* with manhattan distance heuristic
Road Map Size >> Main Memory Size Traditional algorithm run into difficulties! Hierarchical Algorithm
![Page 49: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/49.jpg)
Motivation for Hierarchical Algorithms
Road Map Size >> Main Memory Size Traditional algorithms yield sub-optimal
path Heuristics - bounding box (source,
destination) or Freeway first then sideroads Example: Microsoft Expedia
route(Tampa FL to Miami, FL via Canada)
Need an algorithm to give optimal route A piece of roadmap in memory at a time Intuition - travelling from island to island
![Page 50: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/50.jpg)
Hierarchical Routing : Step 1
Step 1: Choose Boundary Node Pair Minimize COST(S,Ba)+COST(Ba,Bd)+COST(Bd,D) Determining Cost May Be Non-Travial
![Page 51: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/51.jpg)
Hierarchical Routing : Step 2
Step 2: Examine Alternative Boundary Paths Between Chosen Pair (Ba,Bd)
![Page 52: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/52.jpg)
Hierarchical Routing : Step 2 result
Step 2 Result: Shortest Boundary Path
![Page 53: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/53.jpg)
Hierarchical Routing : Step 3
Step 3: Expand Boundary Path: (Ba1,Bd) -> Ba1 Bda2 Ba3 Bda4…Bd
Boundary Edge (Bij,Bj) ->fragment path (Bi1,N1N2N3…….Nk,Bj)
![Page 54: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/54.jpg)
Project: Road Map Accuracy
Assessment
Sponsor and time-period: 10+ State DOTs, 2001-2003 Co-investigators: Prof. Max Donath, Dr. Pi-Ming Chen Students: Weili Wu, Hui Xiong, Zhihong YaoContributions to Transportation Domain
Defining map accuracy for navigable roadmaps Site selection for evaluating GPS and roadmap accuracy
Contributions to Computer Science Definition of Co-location patterns with linear features Efficient algorithms for finding those
![Page 55: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/55.jpg)
Motivation: Identify road given
GPS GPS accuracy and roadmap accuracy
Garmin error circle USA topo
![Page 56: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/56.jpg)
Road Map Accuracy
Evaluation of digital road map databases road user charge system needs: accuracy,
coverage Goals
Recommend a cost-effective approach Develop the content and quality requirements
Rationale Each GIS dataset can contain various errors
From different sources E.g. Map Scale, Area Cover, Density of Observations
Failure to control and manage error Limit or invalidate GIS applications
![Page 57: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/57.jpg)
Map analysis questions Site Selection:
Which road segments are vulnerable for mis-classification given GPS accuracy? Feasibility Issue:
What fraction of highway miles are vulnerable?
![Page 58: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/58.jpg)
Problem Definition
Given:
A digital roadmap and a Gold standard Find:
Spatial Accuracy of the given GIS dataset
Objective: Fair, reliable
Constrains: Gold-standard accuracy is better than GIS
dataset accuracy
![Page 59: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/59.jpg)
Framework to test positional accuracy
Compare with a reference of higher accuracy source find a larger scale map use the Global Positioning System (GPS) use raw survey data
Use internal evidence Indications of inaccuracy:
Unclosed polygons, lines which overshoot or undershoot junctions
A measure of positional accuracy: The sizes of gaps, overshoots and undershoots
Compute accuracy from knowledge of the errors By different sources, e.g 1 mm in source document 0.5 mm in map registration for digitizing 0.2 mm in digitizing
![Page 60: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/60.jpg)
Approach 1 : Visual Overlay of GPS Tracks Vs. Road Maps
Tiger-based Map
USGS Digital Map
![Page 61: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/61.jpg)
Pr. [ distance( P on map, real P) < D ] > 0.9 Tiger file in Windham County, VT (50025)
2: National Map Accuracy Standard
![Page 62: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/62.jpg)
Limitations of Related Work, Our Approach
Natl. map accuracy standard Based on land survey of a sample of
points Not aware of GPS accuracy Mixes lateral error and longitudal error
Our Approach Lateral vs. longitudal positional
accuracy Road classification accuracy Attribute accuracy
![Page 63: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/63.jpg)
Positional Accuracy Lateral accuracy
Perpendicular (RMS) distance from GPS reading to center line of road in road map.
Longitudinal accuracy Definition: horizontal distance from GPS reading to
corresponding Geodetic point.
Comment: Lateral error is more important when closest road is paralledLongitudinal error is important for other case
![Page 64: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/64.jpg)
Road Classification Accuracy
Probability of correctly classifying road for a given GPS Fraction of miles of roads correctly classified
at given confidence level (e.g. 90%)
![Page 65: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/65.jpg)
Attribute Accuracy & Completeness
Interesting Attributes: Economic attributes - administration zone(s), congestion
zones Route attribute - name, type, time restrictions Route segment - direction, type (e.g. bridge), restrictions Routing attributes - intersections, turn restrictions
Definition of Attribute Accuracy: Pr[Value of an attribute for given road segment is
correct] Definition of Completeness:
Pr[a road’s segment is in digital map] Pr[attribute value is not defined for a road segment]
Scope: Small sample
![Page 66: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/66.jpg)
Core Activities
1. Acquire digital road maps2. Select test sites3. Gather gold standard data for test site
GPS tracks, Surveys, etc.4. Complete subsets of road maps for test sites5. Compute accuracy measures6. Statistical analysis7. Visualization
![Page 67: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/67.jpg)
Map Acquisition Etak/Tele Atlas map data for 7
counties of metropolitan Twincities
![Page 68: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/68.jpg)
Site Selection
Red : another road within digen distance threshold (e.g. 30m) Blue: no other road withindistance threshold
![Page 69: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/69.jpg)
Site Selection - Zoom in
Around Hwy 100, 169,7 in SW metro
![Page 70: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/70.jpg)
Comparing GPS tracks and maps
Overlay of GPS tracks and digital road map (Hwy 7)
![Page 71: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/71.jpg)
Comparing GPS tracks and maps
Overlay of GPS tracks and digital road map (Hwy 7)
![Page 72: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/72.jpg)
Other Challenges
1. Center-line representation of roads2. Two-dimensional maps
Multi-level roads Altitude issues
3. Map matching
![Page 73: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/73.jpg)
Conclusions Spatial databases, data mining and
visualization Are useful for many ITS problems We have only scratched the surface so far
Many new exciting opportunities ATMS : visualize freeway operations for operations,
and planning, communicate impact of policies on freeway operations to public and lawmakers, new insights into congestion patterns,
APTS : track buses for customer service, sercurity; communicate impact of APTS in reducing congestion.
ATIS : understand traffic behaviour for route and transportation mode selection
![Page 74: Spatial DBMS and Intelligent Transportation System](https://reader030.vdocuments.site/reader030/viewer/2022013004/56813e65550346895da86fcb/html5/thumbnails/74.jpg)
Motivation for Traffic Visualization
Transportation Manager How the freeway system performed yesterday? Which locations are worst performers?
Traffic Engineering Where are the congestion (in time and space)? Which of these recurrent congestion? Which loop detection are not working properly? How congestion start and spread?
Traveler, Commuter What is the travel time on a route? Will I make to destination in time for a meeting? Where are the incident and events?
Planner and Research How much can information technique to reduce congestion? What is an appropriate ramp meter strategy given specific
evolution of congestion phenomenon?