Another Successful TRB for ABJ70
As usual, ABJ70 had a fruitful and successful kick-off for 2019 at the 98th TRB meeting. The committee sponsored and co-sponsored several sessions and workshops. Our TRB started with a co-sponsored workshop with ADB30 committee on Network Modeling in the Era of Automation Technologies, Big Data Analytics, and Advanced Computing: Identifying Challenges and Pathways to Future Breakthroughs, and another co-sponsored workshop with AHB20, AHB15, AHB10, and AHB25 committees on What Do Agencies Need to Assess, Plan, and Develop the Next Generation of Traffic Management Systems?.
Our signature workshop on Big Data Without Machine Learning Is Just Lots of Data: A Guided Tour to Big Data and Machine Learning was another great success during the TRB. The workshop was divided into two sections. The first section included three well-structured lectures that provided introduction to machine learning, a tour of machine learning methods, and a brief overview of required background and tools to successfully apply machine learning. The lectures provided a tour to audience from across the board of the academia (students, researchers, and professors) and the industry on what knowledge is needed to convert big data into useful information through application of machine learning techniques. The second lecture started with a lecture on smart transportation research at DiDi by Henry Liu, the VP and Chief Scientist of DiDi's Smart Transportation. Then, the five finalists in the TRANSFOR2019 Data competition, sponsored by DiDi, provided a summary of the important lessons learned from the competition.
The Data Competition at a Glance
Transportation Forecasting Competition 2019 (TRANSFOR19) was held at the Transportation Research Board (TRB) 98th Annual Meeting, for the second time since 2013. This year’s competition was organized by the Standing Committee on Artificial Intelligence and Advanced Computing Applications (ABJ70), supported by the IEEE ITSS Technical Activities Sub-Committee “Smart Cities and Smart Mobility” and sponsored by Didi Chuxing Gaia Open Data Initiative.
75 Teams have registered to this competition, 31 Teams submitted results, and 54 different models were evaluated.
The Organizing Committee selected the top 5 Teams to present their work during the TRB Annual Meeting Workshop 1058 on “Big Data Without Machine Learning Is Just Lots of Data: A Guided Tour to Big Data and Machine Learning” organized by ABJ70.
The results of TRANSFOR 19 are:
Winner - Traffic Flaw Theory Team, University of California, Irvine (USA)
2nd Place – IBM Team, IBM Ireland (Ireland)
3rd Place – Deusto Team, Deusto University (Spain)
4th Place – IUTSgo Team, University of Washington (USA)
5th Place - Iowa State Reactor, Iowa State University (USA)
The main lesson learned from the competition is that sometimes the simplest models and the least amount of data can help do the job!
To be continued!