Urban Computing with Taxicabs Yu Zheng Microsoft Research Asia
Preview:
Citation preview
- Slide 1
- Urban Computing with Taxicabs Yu Zheng Microsoft Research
Asia
- Slide 2
- Motivation Urban computing for Urban planning Developing
countries: Urbanization and city planning Developed countries:
Urban reconstruction, city renewal, and sub- urbanization Questions
Whats wrong with the city configurations? Does a carried out urban
planning really works?
- Slide 3
- GPS-equipped taxis are mobile sensors
- Slide 4
- RankCitiesCountry/RegionTaxicabs 1The Mexico cityMexico103,000+
2BangkokThailand80,000+ 3SeoulSouth Korea73,000+
4BeijingChina67,000 5TokyoJapan60,000 6ShanghaiChina50,000+ 7New
York CityUSA48,300 8buenos airesArgentina45,000 9MoscowRussia40,000
(1000,000) 10St.PaulBrazil37,000 11TianjinChina35,000
12TaipeiTaiwan31,000+ 13New Taipei CityTaiwan23,500 14Singapore
23,000 15OsakaJapan20,000 16Hong KongChina18,000+
17WuhanChina18,000 18LondonEngland17,000 19HarbinChina17,000
20GuangzhouChina16,000+ 21ShenyangChina15,000+
22ParisFrance15,000
- Slide 5
- What We Do Detect flawed urban planning using taxi trajectories
Evaluate the carried out city configurations Reminder city planners
with the unrecognized problems Challenges City-wide traffic
modeling Embodying flaws and reveal their relationship
- Slide 6
- Methodology Partition a city into regions with major roads
- Slide 7
- Methodology Partition the trajectory dataset into some portions
TimeWork dayRest day Slot 17:00am-10:30am9:00am-12:30pm Slot
210:30am-4:00pm12:30pm-7:30pm Slot 34:00pm-7:30pm7:30pm-9:00am Slot
47:30pm-7:00am WorkdayRest day
- Slide 8
- Methodology Project taxi trajectories onto these regions
Building a region graph for each time slot
- Slide 9
- Methodology
- Slide 10
- Slide 11
- Formulate skyline graphs Mining frequent patterns To avoid
false alert Deep understanding
- Slide 12
- Evaluations Datasets2009. 3-52010.3-6 Number of
taxis29,28630,121 Effective days89116 Number of points
Total679M1,730M Per taxi/day306528 Distance (KM) Total310M600M Per
taxi/day128171 Average sampling rate (s)10074 Ave. dist. between
two points (m)457349
- Slide 13
- WorkdaysRest Days 2009 2010
- Slide 14
- Some flaws occurring in 2009 disappeared Example 1: Two roads
launched in late 2009 Results
- Slide 15
- Some flaws occurring in 2009 still exist in 2010 Example 1:
Subway line 14 and 15 Results
- Slide 16
- Conclusion Video
- Slide 17
- Thanks! Yu Zheng
http://research.microsoft.com/en-us/people/yuzheng/ The Released
Dataset: T-Drive taxi trajectories A demo in the demo session on
Sept. 20.