Visual Exploration of Shanghai Subway Data Report By Xinshuang Wang - PowerPoint PPT Presentation

Visual Exploration of Shanghai Subway Data Report By Xinshuang Wang

01 Introduction and Related work Outline 02 Three views 03 Explore the influence of weather on passenger flow

Introduction and Related Work

Introduction of Visualization 4

Interactive Visual Discovering of Movement Patterns from Sparsely Sampled Geo-tagged Social Media Data Track people’s movements with social media data with geotags. [2] Chen S, Yuan X, Wang Z, et al. Interactive Visual Discovering of Movement Patterns from Sparsely Sampled Geo-tagged Social Media Data[J]. IEEE Transactions on Visualization and Computer Graphics, 2016, 22(1): 270-279. 5

Visualizing Mobility of Public Transportation System Visualize and explore passenger mobility in a public transportation system with subway system data and bus network data. [1] Zeng W, Fu C W, Arisona S M, et al. Visualizing mobility of public transportation system[J]. IEEE Transactions 6 on Visualization and Computer Graphics, 2014, 20(12): 1833-1842.

Visual Exploration of Big Spatio-Temporal Urban Data A Study of New York City Taxi Trips Propose a model that allows users to visually query taxi trips. [3] Ferreira N, Poco J, Vo H T, et al. Visual exploration of big spatio-temporal urban data: A study of new york city 7 taxi trips[J]. IEEE Transactions on Visualization and Computer Graphics, 2013, 19(12): 2149-2158.

Three views  Passenger Flow Volume View  Running View  Lines & Stations View 8

Passenger Flow Volume View Passenger Flow Volume in particular time (mouse hover) Passenger Flow Volume 9 Time: Apr 1 – Apr 30 2015 14 Subway Lines

Visual analytics Line 2 Three Hot Lines: Line 1 Line 8 10 Qingming Festival: 3 days’ holiday on Apr 4 - 6 2015 Weekly periodic variation

Visual analytics Two Peaks: Line 16 Morning Peak (07:00 – 09:00) & Evening Peak (16:00 – 18:00) Morning peak comes earlier 11 Morning Peak is more agminated; Evening Peak is more dispersive Evening peak comes later

Running View Time Apr 16 2015 Time Line 1 12

Lines & Stations View Lines 14 Lines (Line 1 – Line 12, Line 16) Stations 366 Stations Length 617km 13

Explore the influence of weather on passenger flow

Explore the influence of weather on passenger flow 3 datasets: Shanghai subway smartcard data weather data AQI (air quality index) Sunny: --- Sunny: --- Sunny: --- Sunny: --- Raining and windy: --- Raining and windy: Raining and windy: --- Raining and windy: Fog and haze: --- Fog and haze: --- Fog and haze: Fog and haze: Residential district Business district Scenic resign Entertainment district 15

Explore the influence of weather on passenger flow Simply validate the influence of weather Station Apr 7 (Tues) Apr 8 (Wed) Apr 8 – Apr 7 (Apr 8 – Apr 7) / Apr 8 豫园 36547 41615 5068 12.1783% 人民广场 193788 216861 23073 10.6395% 上海动物园 12152 13327 1175 8.8167% 徐家汇 148406 159163 10757 6.7585% 南京西路 96842 101707 6865 6.7498% 金科路 66335 69324 2989 4.3116% 张江高科 68070 70769 2699 3.8138% 唐镇 27334 28220 886 3.1396% 浦东国际机场 17738 17262 -476 -2.7575% 上海火车站 200811 189518 -11293 -5.9588% 16

THANK YOU 2016.04.20 17