Method for predicting subdural hematoma injury based on KNN-ANN

Abstract

The invention relates to a method for predicting subdural hematoma injury based on KNN-ANN, and the method comprises the steps: taking vehicle collision test data in a database as the basis, and carrying out the Spearman rank correlation analysis of the correlation between each motion parameter or injury evaluation criterion and the brain injury amount; combining KNN and a regression method for data diagnosis, eliminating abnormal data, enhancing the correlation between motion parameters and the damage amount, obtaining the optimal weight of the motion parameters through an optimization strategy, and constructing a new craniocerebral injury evaluation index; adopting maximum-minimum standardization to preprocess training test data, and constructing a brain injury prediction model through neural network learning. According to the method, the influence of the horizontal momentum and the rotation amount on the craniocerebral injury is comprehensively analyzed; compared with a traditionaltraumatic craniocerebral injury evaluation criterion, the established injury criterion is higher in precision, quantitative prediction of the craniocerebral injury can be achieved, and the defect thatthe traditional injury evaluation criterion can only conduct qualitative analysis is overcome.

Description

technical field [0001] The invention relates to the field of craniocerebral injury prediction, in particular to a KNN-ANN-based subdural hematoma injury prediction method and an injury prediction method. Background technique [0002] With the continuous increase of car ownership and the frequent occurrence of road traffic accidents, the research on human injury and protection has attracted extensive attention in the fields of vehicle safety and injury biomechanics. As the evaluation standard of vehicle safety performance and human injury degree, damage evaluation criterion is of great significance to human body protection and vehicle performance improvement. However, due to the complexity of road traffic accidents and the limitation of crash data, traditional damage evaluation criteria cannot accurately evaluate and predict the degree of craniocerebral injury of occupants in accidents, which restricts the improvement of vehicle protection performance. Therefore, constructin...

AI Technical Summary

Problems solved by technology

However, due to the complexity of road traffic accidents and the limitations of collision data, traditional damage evaluation criteria cannot accurately evaluate and predict the degree of craniocerebral injury of occupants in accidents, which in turn restricts the improvement of vehicle protection performance.

Images