Fatigue driving judgment method based on unsupervised extreme learning machine multi-clustering algorithm

Abstract

The invention discloses a fatigue driving judgment method based on an unsupervised extreme learning machine multi-clustering algorithm, belongs to the technical field of driving safety, and determinesan optimal classification cluster number and a probability density distribution function under each class through a Gaussian mixture model and a Bayesian information criterion, and determines an optimal identification model in a fatigue identification data set. Through a feature extraction non-iterative algorithm of an unsupervised extreme learning machine, a minimum value converged to the wholeenvironment is obtained, and an output matrix is obtained; the advantages of four clustering algorithms under unsupervised extreme learning machine feature extraction under different feature divisionlearning are fully utilized through a PCA algorithm; and component score coefficient matrix calculation is performed on the fatigue identification point identification accuracy matrix, and a normalized score coefficient is converted into a weight coefficient for balancing four clustering algorithms in the field of fatigue identification, so that the precision of training set data clustering tendsto be balanced.

Description

technical field [0001] The invention belongs to the technical field of driving safety, and in particular relates to a method for obtaining driver fatigue characteristic signals in traffic engineering by using an unsupervised extreme learning machine through a Gaussian mixture model and a Bayesian information criterion algorithm. Background technique [0002] Using the traditional unsupervised clustering method to divide driver fatigue feature areas can overcome the shortcomings of supervised clustering division and subjective evaluation, which are highly subjective, and a large amount of data still needs to be manually calibrated under big data, and it is helpful to find multi-features of driver fatigue The classification rules can be used to improve the accuracy of driver state monitoring and driving behavior prediction. However, the traditional single unsupervised classification algorithm has a low accuracy rate for learning and classifying unbalanced data features, and th...

AI Technical Summary

Problems solved by technology

However, the improved fatigue feature clustering recognition algorithm has the problem of increased time complexity; in unsupervised learning, there is still a defect that a large amount of manual intervention is required to determine the number of clusters

Images