This study proposes a method based on Dempster-Shafer theory (DST) and fuzzy neural network (FNN) to improve the reliability\nof recognizing fatigue driving. This methodmeasures driving states usingmultifeature fusion. First,FNNis introduced to obtain the\nbasic probability assignment (BPA) of each piece of evidence given the lack of a general solution to the definition of BPA function.\nSecond, a modified algorithm that revises conflict evidence is proposed to reduce unreasonable fusion results when unreliable\ninformation exists. Finally, the recognition result is given according to the combination of revised evidence based on Dempster�s\nrule. Experiment results demonstrate that the recognition method proposed in this paper can obtain reasonable results with the\ncombination of information given by multiple features. The proposed method can also effectively and accurately describe driving\nstates.
Loading....