Machine Learning in Vehicle Safety and Anomaly Detection

The field of vehicle safety and anomaly detection is rapidly advancing with the application of machine learning techniques. Researchers are exploring various approaches to improve the accuracy and reliability of safety inspections, anomaly detection, and maneuver recognition in vehicles. The use of time-series data, such as position, speed, and acceleration, is becoming increasingly popular in modeling and predicting vehicle behavior. Machine learning algorithms, including Long Short-Term Memory (LSTM) networks, Random Forest, and Artificial Neural Networks, are being employed to identify patterns and anomalies in vehicle data. These advancements have the potential to enhance road safety, reduce accidents, and support environmentally friendly driving practices.

Noteworthy papers in this area include:

  • A study on cybersecurity-focused anomaly detection in connected autonomous vehicles, which achieved high accuracy in detecting anomalies using stacked LSTM and Random Forest models.
  • A new machine learning framework for occupational accidents forecasting, which leveraged safety inspections and LSTM networks to predict high-risk periods with a balanced accuracy of 0.86.

Sources

Cybersecurity-Focused Anomaly Detection in Connected Autonomous Vehicles Using Machine Learning

maneuverRecognition -- A Python package for Timeseries Classification in the domain of Vehicle Telematics

A new machine learning framework for occupational accidents forecasting with safety inspections integration

Overtake Detection in Trucks Using CAN Bus Signals: A Comparative Study of Machine Learning Methods

Built with on top of