A data-driven, kinematic feature-based, near real-time algorithm for injury severity prediction of vehicle occupants

Wang, Qingfan; Gan, Shun; Chen, Wentao; Li, Quan; Nie, Bingbing

doi:10.1016/j.aap.2021.106149

Cited by 22 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, to obtain the rear-seat occupant injury prediction model, the AIS 3+ probability of the body region (P body ) can be defined as follows: P body = max(P head 3+ , P neck3+ , P chest 3+ ) (11) where P head3+ , P neck3+ , and P chest3+ can be obtained using Equations ( 8), (9), and (10), respectively. Equations ( 8) and (10) indicate that when Δv < 35 km/h, no rear-seat occupants were injured fatally, whereas a high probability of serious-to-fatal injury was observed when Δv > 58 km/h.…”

Section: Regression Modelmentioning

confidence: 99%

“…To verify the reliability and accuracy of the regression model and the proposed AACN system terminal, we collected actual acci- The Δv of these cases were input to the algorithms, and the values of P head3+ , P neck3+ , and P chest3+ of a rear-seat occupant were obtained using Equations ( 8), (9), and (10), respectively. Additionally, we calculated the value of P body and determined whether the terminal was triggered.…”

Section: Case Verificationmentioning

confidence: 99%

“…If the acceleration is less than the discrimination threshold of −2 g, the AACN system terminal determines the impact. Subsequently, the algorithm calculates Δv using Equation (7), which is then substituted in Equations ( 8), (9), and (10) to obtain P head3+ , P neck3+ , P chest3+ , and P body . If P body is greater than 50%, the AACN system terminal sends information to the EMS.…”

Section: Design Of the Rear-seat Injury Prediction Algorithmmentioning

confidence: 99%

“…Several researchers used the inbuilt finite element (FE) model of the occupant-vehicle system directly in the simulation software [16] or an FE model verified by an authorized institution [9]. Alternatively, rear-seat occupant simulation models were developed based on actual vehicle data [9,17,18]; however, these models should be validated by considering actual crashes before the FE model can be generated for more cases with various parameters. Gavelin et al [19] explored the influence of seat configurations on the pelvis and torso responses of occupants.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Injury prediction algorithm for rear‐seat occupants in advanced automatic crash notification systems

Lü

Liu

Shu

et al. 2021

IET Intelligent Trans Sys

View full text Add to dashboard Cite

An advanced automatic crash notification (AACN) system can predict the injuries of a vehicle's occupants when the vehicle is involved in a collision accident. The rear‐seat occupants are at significant risk in collision accidents owing to an inferior protection system and the absence of mandatory seat belt laws. However, only a few studies have focused on the injury prediction for rear‐seat occupants, which can be used in AACN system. Therefore, an injury prediction algorithm is proposed for rear‐seat occupants. Initially, a rear‐seat occupant simulation model is established and verified and the relationship between the head, neck, and chest injury levels and velocity variation is examined. Then, a rear‐seat occupant injury prediction algorithm is developed and AACN terminal is constructed to analyse the effects of the algorithm. The comparison of the obtained results with actual accident data validated that the proposed algorithm can effectively evaluate the injury levels of rear‐seat occupants. The study findings can enhance the prediction accuracy of all occupants’ injury levels based on their positions inside the vehicle and improve the efficiency of rescue operations, particularly in the case of rear‐seat occupants.

show abstract

Section: Regression Modelmentioning

confidence: 99%

Section: Case Verificationmentioning

confidence: 99%

Section: Design Of the Rear-seat Injury Prediction Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Injury prediction algorithm for rear‐seat occupants in advanced automatic crash notification systems

Lü

Liu

Shu

et al. 2021

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…The equations for this model include a function considering systems that limit the passenger's movement. The paper [18] proposes the model for injury evaluation based on the database of passengers' kinematics, their injuries and the kinematics of the vehicle itself. It is assumed that the model can be applied in real-time in the vehicle providing information to the passengers' safety systems before and after the collision.…”

Section: Introductionmentioning

confidence: 99%

Experimental and Numerical Assessment of Supporting Road Signs Masts Family for Compliance with the Standard EN 12767

Stopel

Cichański

Yague³

et al. 2021

Materials

View full text Add to dashboard Cite

The analysis aimed to assess the passive safety of supporting masts for road signs in accordance with EN 12767. Experimental tests were carried out based on the requirements of the standard for the smallest and the largest constructions within the product family. Numerical models of crash tests were prepared for whole product family using the Finite Element Method in the LS-Dyna environment. Based on the comparison of the experimental tests and the numerical calculations, the usefulness of the numerical model for estimating the actual value of the Acceleration Severity Index (ASI) and the Theoretical Head Impact Velocity (THIV) was assessed. With the use of these relationships the values of ASI and THIV for masts not tested experimentally were estimated. It was confirmed that the analyzed masts met the requirements for the passive safety of structures set out in the standard EN 12767. It was possible since as a result of the impact, the mast column detached from the base, allowing the vehicle to continue moving. The behavior of the masts was primarily influenced by the destruction of the safety connectors. The paper presents the most important elements from the point of view of designing such solutions.

show abstract

Research on occupant injury severity prediction of autonomous vehicles based on transfer learning

Yang,

Liu,

Liu

et al. 2024

Journal of Forecasting

View full text Add to dashboard Cite

The focus of the future of autonomous vehicles has shifted from feasibility to safety and comfort. The seat of an autonomous vehicle may be equipped with a rotational function, and the occupant's sitting position would be diverse. This poses a higher challenge to occupant injury protection during vehicle collisions. The main objective of the current study is to develop occupant injury prediction models for autonomous vehicles that can be used to predict the injury severity of occupants in different seat orientations and sitting positions. The first step is to establish an occupant crash model database with different seat orientations. It is used to simulate the occupant crash injury database of an autonomous vehicle, considering seat rotation and the back inclination angle. The second step is to establish a pre‐training occupant injury prediction model based on the existing database and then train the autonomous vehicle occupant injury prediction model using an in‐house database based on the transfer learning method. Occupant injury prediction models achieve good accuracy (82.8% on the numerical database and 62.9% on the real verification database) and shorter computational time (4.86 ± 0.33 ms) on the prediction tasks. Finally, the influence of the model input variables is analyzed. This study demonstrates the feasibility of using a small‐sample database based on transfer learning for occupant injury prediction in autonomous vehicles.

show abstract

A data-driven, kinematic feature-based, near real-time algorithm for injury severity prediction of vehicle occupants

Cited by 22 publications

References 19 publications

Injury prediction algorithm for rear‐seat occupants in advanced automatic crash notification systems

Injury prediction algorithm for rear‐seat occupants in advanced automatic crash notification systems

Experimental and Numerical Assessment of Supporting Road Signs Masts Family for Compliance with the Standard EN 12767

Research on occupant injury severity prediction of autonomous vehicles based on transfer learning

Contact Info

Product

Resources

About