CityX Lab @UNSW

  • Home
  • Research
  • Publications
  • Teaching
  • Team
  • Blog
  • News
  • Contact
  • Home
  • Research
  • Publications
  • Teaching
  • Team
  • Blog
  • News
  • Contact

NEWS

CityX team at ARUP Open Data House, Melbourne Knowledge Week 2016

5/8/2016

0 Comments

 
CityX team participated at the ARUP Open Data House as part of the Melbourne Knowledge Week 2016. Arup and a select group of data providers opened up a curated set of rarely seen transport and urban data from Melbourne. Data scientists, city and transport planners, and designers were invited to analyse and help solve a critical urban problem using these exciting data sets.
Picture
Picture
We were invited to present some of our previous data visualizations to inspire participants for a productive afternoon. Later, we also participated in the competition with a project looking at "How do people use the city? Comparing temporal variation of pedestrian activities, on-street parking usage, traffic volumes, and tweets in Melbourne."

We put together an imperfect comparative analysis of time-series data from tens of pedestrian count sensors (1.1M+ rows), thousands of in-ground parking bay sensors (1M+ rows), traffic counts from several bluetooth detectors (2M+ rows), and thousands of tweets from Twitter (250K+). The map on the cover shows the spatial distribution of tweets in City of Melbourne.
The goal was to better understand how people use the city over time of day using available open data. We were specifically interested to find whether there is any correlation between the temporal variation of some of the data we had. In 2-3 hours, we put together a simple analysis and here are our findings.
Picture
Picture

​Pedestrian activities in the city do not seem to have a strong correlation with vehicle counts and on-street parking usage during the day. While distribution of vehicle counts is decreasing with a small slope from 7 am to 5 pm, pedestrian activities are increasing with three sharp peaks at 8 am, 12 pm, and 5 pm. This is probably due to the fact that a large fraction of people traveling to CBD use public transport. 
  • There is a relatively strong correlation between the number of on-street parking arrivals and vehicle counts as expected. However, there is an interesting sharp jump and drop at 6 am and 9 pm respectively and a peak around 10-11 am for on-street parking usage. In lame terms, the on-street parking usage distribution looks like a squeezed version of the vehicle counts distribution.
  • Distribution of tweets looks strange though. I guess this is perhaps due to the bias in the data as it was only a selective sample or maybe an error in our analysis. This whole practice was done in 2-3 hours. So, no surprise if we made a mistake somewhere working with millions of rows of data.
There are a number of limitations in this little work. We did not clean the data. We did not control the time window of the study. Each data set was covering a different time span over years. We did not also control the geographical coverage of the study. Each data set was from city of Melbourne but had a slightly different geographical coverage. We did not cross check our analysis. So, results are preliminary and not suitable for any serious/strong conclusion. 

​Special thanks to Bryan, Sajjad, Frank, and Domenico.
0 Comments



Leave a Reply.

    Author

    Dr. Meead Saberi, lecturer in transportation engineering, data guru, and urban scientist

    Archives

    May 2019
    August 2018
    March 2018
    February 2018
    September 2017
    August 2017
    July 2017
    June 2017
    May 2017
    March 2017
    January 2017
    December 2016
    November 2016
    October 2016
    September 2016
    August 2016
    July 2016
    June 2016
    May 2016
    April 2016

    Categories

    All

    RSS Feed

Location

Tell us what you think. Join us to innovate.

Whether you are a prospective student, a research fellow, or a professional working in public/private sector, you are more than welcome to work with us on exciting projects. We love innovative ideas and teamwork.

Contact Us