1 / 7

Temporal Applications for Big Data

Discover the power of temporal analysis in big data, with before and after studies, seasonal modeling, and short-term forecasts. Explore how this approach can revolutionize traditional data collection methods and provide valuable insights for various industries.

emilym
Télécharger la présentation

Temporal Applications for Big Data

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Temporal Applications for Big Data Realizing new uses for Big Data Jonathan Avner, WRA Greg Giaimo, ODOT

  2. Time and Big Data 1 • Traditional data collection has been what we “knew” at a given time. • The temporal nature of big data provides insights into additional time periods: • Before and after studies • Seasonal modeling • Short term forecasts 1500 years ago everybody “knew” that the Earth was the center of the universe. 500 years ago, everybody “knew” that the Earth was flat. And 15 minutes ago, you “knew” that humans were alone on this plant. Imagine what you’ll “know” tomorrow. - Kay, MiB

  3. Travel Demand Model Application • Temporal use of big data • Changes in travel patterns on key corridors because of roadway projects impacting validation • Hampton Roads Model Development • Use of Big Data for External-External and External-Internal Modeling • Testing of model to a 2017 validation year (calibration to 2015)

  4. Estimation of Design Hour Traffic • Design hour traffic (30th Hour) required for highway design • Currently estimated based on limited permanent traffic recorders • ODOT worked with Streetlight to test producing location specific data • Permanent traffic count vs Streetlight by hour of the week – averaged across the year

  5. Estimation of Design Hour Traffic • Significant sampling variance: challenge for identifying Nth highest hour • Observations when looking at 200 highest hours • Streetlight is distributed around the count • Sorted by Streetlight highest hours, the count volume is much lower

  6. Seasonal / Day of Week AADT Factors • Adjustment of a single or multiple day count to average weekday or season • Typically use the permanent count data • Initial analysis showed significant variation of count vs Streetlight for a given day – linked to adjustment to annual count • Since Streetlight adjusts to monthly sample rate

  7. Conclusions Jonathan Avner, WRA javner@wrallp.com Greg Giaimo, ODOT Greg.Giaimo@dot.state.oh.us • Model Application • Opportunity to expand the predictive horizon of the model • Design Hour Traffic • Streetlight based K30 were about 26% higher • Improvement with greater market penetration • Seasonal / Day of Week AADT • Improved with control to seasonal / monthly totals (part of software)

More Related