State-Aware Unsafe Driving Action Detection and Defense

Tianqi Li; Rujun Hu; Lei Xue; Xiapu Luo

State-Aware Unsafe Driving Action Detection and Defense

Tianqi Li, Rujun Hu, Lei Xue, Xiapu Luo

Department of Computing

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

Considering most driving accidents are caused by unsafe driving actions, this paper focuses on improving driving safety by proposing a novel state-aware unsafe driving action detection and defense method. By combining three indicators of the vehicle's physical models using fuzzy logic, our approach improves the prediction stability and warning time without sacrificing false alarm rates. This research enhances vehicle cybersecurity and contributes to safer and more secure transportation systems.

Original language	English
Title of host publication	2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)
Publication status	Published - Jul 2023

Cite this

@inproceedings{b448e5fb7cc143508662b6786bcb46b4,

title = "State-Aware Unsafe Driving Action Detection and Defense",

abstract = "Considering most driving accidents are caused by unsafe driving actions, this paper focuses on improving driving safety by proposing a novel state-aware unsafe driving action detection and defense method. By combining three indicators of the vehicle's physical models using fuzzy logic, our approach improves the prediction stability and warning time without sacrificing false alarm rates. This research enhances vehicle cybersecurity and contributes to safer and more secure transportation systems.",

author = "Tianqi Li and Rujun Hu and Lei Xue and Xiapu Luo",

year = "2023",

month = jul,

language = "English",

booktitle = "2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)",

}

TY - GEN

T1 - State-Aware Unsafe Driving Action Detection and Defense

AU - Li, Tianqi

AU - Hu, Rujun

AU - Xue, Lei

AU - Luo, Xiapu

PY - 2023/7

Y1 - 2023/7

N2 - Considering most driving accidents are caused by unsafe driving actions, this paper focuses on improving driving safety by proposing a novel state-aware unsafe driving action detection and defense method. By combining three indicators of the vehicle's physical models using fuzzy logic, our approach improves the prediction stability and warning time without sacrificing false alarm rates. This research enhances vehicle cybersecurity and contributes to safer and more secure transportation systems.

AB - Considering most driving accidents are caused by unsafe driving actions, this paper focuses on improving driving safety by proposing a novel state-aware unsafe driving action detection and defense method. By combining three indicators of the vehicle's physical models using fuzzy logic, our approach improves the prediction stability and warning time without sacrificing false alarm rates. This research enhances vehicle cybersecurity and contributes to safer and more secure transportation systems.

M3 - Conference article published in proceeding or book

BT - 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)

ER -

State-Aware Unsafe Driving Action Detection and Defense

Abstract

Fingerprint

Cite this