Difference between revisions of "Project Groups"

From Visual Analytics and Applications
Jump to navigation Jump to search
Line 41: Line 41:
 
|-
 
|-
 
||
 
||
[[S-MALL Overview|Group 3: Team S-MALL]]
+
[[Group01|Group 1: Team S-MALL]]
 
||
 
||
 
'''Understanding traffic patterns using network graph visualisations'''
 
'''Understanding traffic patterns using network graph visualisations'''

Revision as of 18:05, 30 October 2017

Vaa1.jpg ISSS608 Visual Analytics and Applications

About

Weekly Session

Assignments

Visual Analytics Project

Course Resources

 


Project Groups

Please change Your Team name to your project topic and change student name to your own name

Project Team Project Title/Description Project Artifacts Project Member

Group 1: Team S-MALL

Understanding traffic patterns using network graph visualisations

The project aims to illustrate the power of visual analytics in highlight patterns exhibited by vehicles when traversing through various traffic corridors. By linking the information captured in RFID tags when vehicles move through checkpoints, an interactive application is designed. This will help to unravel insights such as frequently travelled corridors, preferred routes amongst vehicles, traffic density, etc. The application will be primarily developed using R, and specifically the versatile ggraph package, which helps to develop powerful network visualisations. ggraph has been chosen as it is a recent release (Feb 2017), that exhibits the power of R and the ggplot architecture in incorporating network visualisations. Though ggplot tools have existed to visualise network patterns previously, the use of this package helps in making neater visualisations that help the user understand better. The motivation for this project stems from the traffic accumulation key problem found in most cities. Though the dataset pertains to a set of vehicles travelling through a wildlife preserve, the ideology can be applied to planning of roads and associated establishments. Urban planning needs to cater to robust planning of vehicle corridors to minimise disruptions in flow, and improve productivity. The interactive application helps the user understand linkages between various points in a predefined vicinity. The timestamp information of vehicle passages present in the data helps to understand various parameters such as traffic density, preferred corridors for vehicles and their speeds. The application devised here is also aimed to support the traffic authorities to identify what other alternative corridors might exist for reaching from Point A to point B. In addition, network measures such as the betweenness, the connectivity and closeness of various nodes, are also provided.

  • AAA
  • BBB
  • CCC
Team Members
Group 1 GE BIN LIM LIANG DANNY RYAN CHIA
Group 2 Rachel Tong Nurul Asyikeen Binte Azhar Matilda Tan Ying Xuan
Group 3 CHEN ZHENGJIAN XIAO ZHENYU ZHENG MIANYI
Group 4 Yau Hon Tak Deng Yuetong
Group 5 Wang Rui Wu Yuqing Xing Siyuan
Group 6 Wang Yizhou Zhou Chen Zhang Lidan
Group 7 Zhang Peng Wang Shang
Group 8 Fam Guo Teng Wang Yuchen Xu Yanru
Group 10 Ma Xiaoliu Deng Chunling AISHWARYA MOHAN