Pedestrian Injury Case Reconstruction Through Data Fusion and Machine Learning

Authors: Xiaoyang Song, Wenbo Sun, Jingwen Hu, Carol Flannagan, Jared Karlow, Patrick Bowman, University of Michigan; Iskander Farooq, Anil Kalra, Ford Motor Company

Abstract

The proportion of pedestrian injuries in motor-vehicle-crash-induced injuries in the U.S. has been increasing in recent years. Although extensive police-reported data on pedestrian injuries is available, the incomplete nature of the crash and injury information in these datasets presents a significant challenge for statistical injury analysis and pedestrian protection research. This study aims to address this issue by combining simulation data and field data to impute critical missing crash information in pedestrian crash cases through machine learning techniques. A total of 9,000 MADYMO simulations were generated using maximal projection design, incorporating variables such as pedestrian demographics, crash conditions, and vehicle impact parameters. Gaussian process (GP) surrogate models were trained to predict injury risks with simulation parameters calibrated using the complete crash information in the Pedestrian Crash Data Study (PCDS) dataset. Maximum likelihood estimations were then employed to impute the missing vehicle speed in Linked Michigan Trauma dataset. Validation involved comparing the imputed vehicle speed distribution with that of the PCDS dataset and verifying four CIREN cases reconstructed by both the proposed method and a physics-based approach. The histogram of the reconstructed vehicle speeds in Linked Michigan Trauma dataset highly correlated with that from the PCDS dataset. In the four CIREN cases, the absolute deviation between the reconstruction vehicle speeds from the proposed method and physics-based approach was 9 kph on average, with the predicted injury risks matched the observed AIS levels. These results support the use of machine learning for reconstructing missing crash data and enhancing pedestrian injury risk modeling. 

Type: Full Paper, Research

Keywords: Gaussian Process, Crash case reconstruction, speed imputation, pedestrian safety

© Stapp Association, 2025

Access Additional Papers from This Volume

View additional Full Papers from the Stapp Car Crash Journal, Volume 69.

• Assessment of the Skull Fracture Prediction Capability of Finite Element Head Models
  Authors: Clément Pozzi, Marc Gardegaront, Lucille Allegre, Philippe Beillas—Univ Lyon, Univ Lyon 1, Univ Eiffel, LBMC UMR_T9406, 69622 Lyon, France…
• Development of a Generic Nearside Impact Test Fixture for Evaluating In-Vehicle Crashworthiness of Wheelchairs
  Authors: Kyle Boyle, Jingwen Hu, Miriam Manary, Nichole R. Orton, Kathleen D. Klinich—University of Michigan Transportation Research Institute Abstract Current…
• Integration of Muscle Pre-tension and Activation to Evaluate Neck Muscle Strain Injury Risk during Simulated Rear Impacts Using a Finite Element Neck Model
  Authors: Matheus A. Correia, Stewart D. McLachlin, Duane S. Cronin—Department of Mechanical and Mechatronics Engineering, University of Waterloo Abstract Prevention…
• Investigation of Injury Risk Functions of THOR-AV 50th Percentile Male Dummy
  Author: Z. Jerry Wang and George Hu—Humanetics Innovative Solutions, Inc. Abstract This research investigated injury risk functions (IRF) for the…
• Proposed Reformulation of Brain Injury Criteria (BrIC) Using Head Rotation-Induced Brain Injury Thresholds Simulated and Derived Directly from a Subhuman Primate Finite Element Model
  Authors: Dominic R. Demma, Ying Tao, Liying Zhang—Wayne State University; Priya Prasad—Prasad Engineering, LLC Abstract Recent studies have found that…
• Traumatic Head and Brain Injuries in Helmeted Motorcycle Crashes
  Author: John Lloyd—BRAINS, Inc Abstract This study presents an analysis of 364 motorcycle helmet impact tests, including standard certified full-face,…

Looking for Something Else?