Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues

Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues

This paper presents a hybrid model for early onset prediction of driver fatigue, which is the major reason of severe traffic accidents. The proposed method divides the prediction problem into three stages, that is, SVM-based model for predicting the early onset driver fatigue state, GA-based model f...

Full description

Bibliographic Details
Main Authors: Mingheng Zhang, Gang Longhui, Zhe Wang, Xiaoming Xu, Baozhen Yao, Liping Zhou
Format: Article
Language:English
Published: Hindawi Limited 2014-01-01
Series:Mathematical Problems in Engineering
Online Access:http://dx.doi.org/10.1155/2014/385716
id doaj-1b723d239e2a43c897021a68e01d0433
record_format Article
spelling doaj-1b723d239e2a43c897021a68e01d04332020-11-24T22:13:37ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472014-01-01201410.1155/2014/385716385716Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable CuesMingheng Zhang0Gang Longhui1Zhe Wang2Xiaoming Xu3Baozhen Yao4Liping Zhou5State Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian 116024, ChinaSchool of Navigation, Dalian Maritime University, Dalian 116026, ChinaSchool of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaSchool of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaState Key Laboratory of Structural Analysis for Industrial Equipment, Dalian University of Technology, Dalian 116024, ChinaWuxi Mingda Traffic & Technology Consulted Co., Ltd., Wuxi 214125, ChinaThis paper presents a hybrid model for early onset prediction of driver fatigue, which is the major reason of severe traffic accidents. The proposed method divides the prediction problem into three stages, that is, SVM-based model for predicting the early onset driver fatigue state, GA-based model for optimizing the parameters in the SVM, and PCA-based model for reducing the dimensionality of the complex features datasets. The model and algorithm are illustrated with driving experiment data and comparison results also show that the hybrid method can generally provide a better performance for driver fatigue state prediction.http://dx.doi.org/10.1155/2014/385716
collection DOAJ
language English
format Article
sources DOAJ
author Mingheng Zhang
Gang Longhui
Zhe Wang
Xiaoming Xu
Baozhen Yao
Liping Zhou
spellingShingle Mingheng Zhang
Gang Longhui
Zhe Wang
Xiaoming Xu
Baozhen Yao
Liping Zhou
Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
Mathematical Problems in Engineering
author_facet Mingheng Zhang
Gang Longhui
Zhe Wang
Xiaoming Xu
Baozhen Yao
Liping Zhou
author_sort Mingheng Zhang
title Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
title_short Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
title_full Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
title_fullStr Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
title_full_unstemmed Hybrid Model for Early Onset Prediction of Driver Fatigue with Observable Cues
title_sort hybrid model for early onset prediction of driver fatigue with observable cues
publisher Hindawi Limited
series Mathematical Problems in Engineering
issn 1024-123X
1563-5147
publishDate 2014-01-01
description This paper presents a hybrid model for early onset prediction of driver fatigue, which is the major reason of severe traffic accidents. The proposed method divides the prediction problem into three stages, that is, SVM-based model for predicting the early onset driver fatigue state, GA-based model for optimizing the parameters in the SVM, and PCA-based model for reducing the dimensionality of the complex features datasets. The model and algorithm are illustrated with driving experiment data and comparison results also show that the hybrid method can generally provide a better performance for driver fatigue state prediction.
url http://dx.doi.org/10.1155/2014/385716
work_keys_str_mv AT minghengzhang hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
AT ganglonghui hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
AT zhewang hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
AT xiaomingxu hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
AT baozhenyao hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
AT lipingzhou hybridmodelforearlyonsetpredictionofdriverfatiguewithobservablecues
_version_ 1725800420281942016

Similar Items