Driver State Accident Risk Prediction for Early Vehicle Warning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to predict the risk of traffic accidents, particularly those that do not occur frequently, as they focus on specific driving operations rather than infrequent events.
Innovation Solution
An operation support method and system that uses machine learning to predict the risk of traffic accidents by inputting biological data of a driver and traveling state data into accident risk definition and prediction models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If prediction focuses on specific driving operations, then prediction accuracy for common events is improved, but ability to predict infrequent events deteriorates
Solution Approach 1:
The prediction system is designed to handle multiple types of events simultaneously - both frequent driving operations and infrequent accidents. By using a unified machine learning model that processes biological data, traveling state data, and hazard occurrence data together, the system achieves both specific prediction accuracy and broad event coverage without requiring separate prediction mechanisms for different event types.
2Device complexity
If only driving operation data is used for prediction, then model simplicity is maintained, but prediction reliability for traffic accidents deteriorates
Solution Approach 1:
The system merges multiple data sources - biological data from drivers, traveling state data from vehicle sensors, and hazard occurrence data - into a unified prediction model. This combination of diverse data types enhances prediction reliability for traffic accidents while the use of machine learning automatically manages the complexity of processing these multiple data streams together.
3Speed
If prediction is made for immediate risk only, then response time is reduced, but early warning capability for future risks deteriorates
Solution Approach 1:
The system performs preliminary prediction of accident risk for future time points rather than only immediate risk assessment. By using machine learning to analyze current biological and traveling state data in the context of historical hazard occurrence patterns, the system can predict future accident risk and provide early warnings before the actual risk materializes, giving advance notice while maintaining rapid response capability.
Data Source
AI summary
A computer generates an accident risk definition model to estimate a probability of hazard occurrence as an accident risk by inputting first in-vehicle sensor data collected in the past and hazard occurrence data having information on hazard occurrence from the first in-vehicle sensor data preset therein, generates accident risk estimation data by inputting second in-vehicle sensor data collected in the past to the accident risk definition model and estimating the probability of the hazard occurrence, generates an accident risk prediction model to predict the accident risk after a predetermined time by inputting first biological index data corresponding to the second in-vehicle sensor data and the accident risk estimation data, calculates second biological index data from second biological sensor data by acquiring the second biological sensor data of a driver, and predicts the accident risk after the predetermined time by inputting second biological index data to the accident risk prediction model.