logo

SCIENCE CHINA Information Sciences, Volume 65 , Issue 6 : 169203(2022) https://doi.org/10.1007/s11432-020-3044-6

Car-following behavior modeling driven by small data sets based on mnemonic extreme gradient boosting framework

More info
  • ReceivedApr 17, 2020
  • AcceptedAug 1, 2020
  • PublishedMar 30, 2021

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by Opening Foundation of Key Laboratory of Advanced Manufacture Technology for Automobile Parts, Ministry of Education, China (Grant No. 2019KLMT05) and Natural Science Foundation of Chongqing (Grant No. cstc2019jcyj-msxmX0119).


Supplement

Appendixes A–C.


References

[1] Fleming J M, Allison C K, Yan X. Adaptive driver modelling in ADAS to improve user acceptance: A study using naturalistic data. Saf Sci, 2019, 119: 76-83 CrossRef Google Scholar

[2] B?rgman J, Boda C N, Dozza M. Counterfactual simulations applied to SHRP2 crashes: The effect of driver behavior models on safety benefit estimations of intelligent safety systems. Accident Anal Prevention, 2017, 102: 165-180 CrossRef Google Scholar

[3] Chen S, Jian Z, Huang Y. Autonomous driving: cognitive construction and situation understanding. Sci China Inf Sci, 2019, 62: 81101 CrossRef Google Scholar

[4] Chen T Q, Guestrin C, Yan X. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 2016. 785--794. Google Scholar

[5] Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation, 1997, 9: 1735-1780 CrossRef Google Scholar

  • Figure 1

    (Color online) (a) The test car and the experiment route; (b) the structure of XGBoost car-following model; (c) model training and parameter optimization; (d) M-XGBoost framework; (e) trajectory reconstruction.