A knowledge distillation-based training framework improves the accuracy of pre-crash occupant injury prediction models with high computation efficiency

Wang, Qingfan<sup>1</sup>; Xu, Dongyang<sup>1</sup>; Zhou, Qing<sup>1</sup>; Nie, Bingbing<sup>1</sup>

Wang, Qingfan¹; Xu, Dongyang¹; Zhou, Qing¹; Nie, Bingbing¹

Proceedings of the 2023 International IRCOBI Conference on the Biomechanics of Injury

Affiliations

¹School of Vehicle and Mobility at Tsinghua University and State Key Laboratory of Intelligent Green Vehicle and Mobility, China
Links

URL: http://www.ircobi.org/wordpress/downloads/irc23/pdf-files/23100.pdf

Cited Works (2)

Year	Entry
2020	Chen W, Zhou Q, Gan S, Nie B. Generating a large-scale numerical database of motor vehicle crashes for rapid injury severity prediction. In: Proceedings of the 2020 International IRCOBI Asia Conference on the Biomechanics of Injury. 2020; Beijing, China.25-28.
2019	Bance I, Nie B. A framework for near real-time occupant injury risk prediction using a sequence-to-sequence deep learning approach. In: Proceedings of the 2019 International IRCOBI Conference on the Biomechanics of Injury. September 11-13, 2019; Florence, Italy.86-87.