因子分析与多层神经网络组合的酒驾辨识模型研究

doi:10.16265/j.cnki.issn1003-3033.2017.07.023

中国安全科学学报 ›› 2017, Vol. 27 ›› Issue (7): 127-132.doi: 10.16265/j.cnki.issn1003-3033.2017.07.023

因子分析与多层神经网络组合的酒驾辨识模型研究

孙一帆, 张敬磊^** 副教授, 王丝丝

山东理工大学交通与车辆工程学院,山东淄博 255000

收稿日期:2017-04-20 修回日期:2017-06-17 发布日期:2020-11-26
通讯作者: ^**张敬磊(1979—),男,山东高密人,硕士,副教授,主要从事智能交通、驾驶行为及安全方面的研究。E-mail:jinglei@sdut.edu.cn。
作者简介:孙一帆 (1991—),男,山东青岛人,硕士研究生,研究方向为驾驶行为及交通安全。E-mail:18705423520@163.com。
基金资助:
国家自然科学基金资助(61573009);山东省自然科学基金资助(ZR2014FM027); 山东省高等学校科技计划(J15LB07); 汽车安全与节能国家重点实验室开放基金资助(KF16232)。

Study of drunk driving identification model based on factor analysis and multilayer neural network

SUN Yifan, ZHANG Jinglei, WANG Sisi

School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo Shandong 255000, China

Received:2017-04-20 Revised:2017-06-17 Published:2020-11-26

摘要/Abstract

摘要： 为准确辨识驾驶员酒驾行为以及酒驾状态水平,提高酒驾治理效率,通过人因工程试验和驾驶模拟试验,采集并预处理驾驶员在正常、饮酒、醉酒3种驾驶状态下的驾驶行为数据(包括驾驶员的人、车、环境数据);对原始参数进行因子分析,提取特征参数并将其作为多层神经网络的输入向量,训练多层神经网络,建立基于因子分析和多层神经网络的酒驾行为辨识模型;选取75组测试样本数据输入模型,将模型的输出结果与实际情况比较,验证模型的有效性。研究表明:该模型的训练时间为0.905 s,最优验证均方误差(MSE)为0.034,识别准确率达92.41%,用该模型能较为快速、准确地识别酒后驾驶行为。

关键词: 酒后驾驶, 驾驶行为, 特征参数, 因子分析, 多层神经网络

Abstract: In order to recognize drunk driving and identify the level of drunk driving states accurately, and improve the efficiencies of drunk driving governances, all drivers' driving behavior data (including the data on human, vehicle and environment) of three driving states including normal, tipsy and intoxicated were gathered by human factors engineering experiments and driving simulation experiments, the experimental data were pretreated. The original parameters were analyzed by factor analysis and the characteristic parameters were extracted as the vectors to be input in a multilayer neural network. The multilayer neural network was trained, and an identification model was built for drunk driving behaviors based on factor analysis and multi-layer neural network. The research shows that the training time of the model is 0.905 seconds, the optimal validation mean square error(MSE) of the model is 0.034, and recognition accuracy is 92.41%, and the model could be used to identify drunk driving behaviors quickly and accurately .

Key words: drunk driving, driving behavior, characteristic parameter, factor analysis, multilayer neural network

中图分类号:

X951

孙一帆, 张敬磊, 王丝丝. 因子分析与多层神经网络组合的酒驾辨识模型研究[J]. 中国安全科学学报, 2017, 27(7): 127-132.

SUN Yifan, ZHANG Jinglei, WANG Sisi. Study of drunk driving identification model based on factor analysis and multilayer neural network[J]. China Safety Science Journal, 2017, 27(7): 127-132.

参考文献

[1] 王文博, 陈红, 韦凌翔. 交通事故时间序列预测模型研究[J]. 中国安全科学学报, 2016, 26(6):52-56.
WANG Wenbo, CHEN Hong, WEI Lingxiang. Study on method for prediction of traffic accident time series[J]. China Safety Science Journal, 2016, 26(6):52-56.
[2] 吕能超, 旷权, 谭青山,等. 基于车路协同的行人车辆碰撞风险识别与决策方法[J]. 中国安全科学学报, 2015,25(1):60-66.
LYU Nengchao, KUANG Quan, TAN Qingshan, et al.Pedestrian-vehicle collision avoidance approach based on cooperative vehicle infrastructure system [J]. China Safety Science Journal, 2015,25(1):60-66.
[3] 张丽霞, 刘涛, 潘福全,等. 驾驶员因素对道路交通事故指标的影响分析[J]. 中国安全科学学报, 2014,24(5):79-84.
ZHANG Lixia, LIU Tao, PAN Fuquan, et al. Analysis of effects of driver factors on road traffic accident indexes[J]. China Safety Science Journal, 2014,24(5):79-84.
[4] 董葵, 陆宇. 酒后驾驶检测技术及设备应用现状和发展[J]. 中国公共安全:学术版,2014(3):65-69.
DONG Kui, LU Yu. Present situation and development of detection technology and devices for drunk driving [J]. China Public Security: Academic Edition, 2014(3): 65-69.
[5] 秦佳, 马卫东, 杨伊林,等. 应用红外检测技术防酒驾系统的研究与开发[J]. 包装工程, 2013,34(16):63-65,74.
QIN Jia, MA Weidong, YANG Yilin, et al. Research and development of the integrated anti-drunk-driving system using infrared detection technology [J]. Packaging Engineering, 2013,34(16): 63-65,74.
[6] ZHAO Xiaohua, ZHANG Xingjian, RONG Jian, et al. Identifying method of drunk driving based on driving behavior [J]. International Journal of Computational Intelligence Systems, 2011,4(3):361-369.
[7] LIN Xiaohong, WANG Xiangwen, HAO Zhanjun. Supervised learning in multilayer spiking neural networks with inner products of spike trains[J]. Neurocomputing, 2017, 237:59-70.
[8] AMINUDIN N, MARSADEK M,RAMLI N M,et al. Risk of voltage collapse using multi-layer feed-forward neural network and generalized regression neural network [J]. Applied Mechanics & Materials, 2015,793:483-488.
[9] EBRAHIMNEJAD S, RAMEEH V. Correlation and factor analysis of grain yield and some important component characters in spring bread wheat genotypes [J]. Cercetari Agronomice in Moldova, 2016,49(1):5-15.
[10] GHANEM S A M. Mutual information and minimum mean-square error in multiuser Gaussian channels[J]. IEEE, 2016, 10:18-21.

[1]	秦雅琴, 李秋谷, 赵鹏燕, 宝发旺, 谢济铭. 基于多分类Adaboost算法的驾驶人风险感知倾向研究[J]. 中国安全科学学报, 2022, 32(4): 141-147.
[2]	张新生, 常潆戈. 基于FA-BAS-ELM的海洋油气管道外腐蚀速率预测^*[J]. 中国安全科学学报, 2022, 32(2): 99-106.
[3]	赵小平, 马有才, 万平, 莫振龙. 情绪对新手驾驶员视觉特性的影响研究^*[J]. 中国安全科学学报, 2022, 32(1): 34-40.
[4]	郭子慧, 郭伟伟, 谭墍元. 驾驶员接管自动驾驶车辆的眼动特性和行为分析^*[J]. 中国安全科学学报, 2022, 32(1): 65-71.
[5]	刘继川, 桂蕾. 城市公共安全风险评估与控制对策研究:以武汉市为例^*[J]. 中国安全科学学报, 2022, 32(1): 164-171.
[6]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测^*[J]. 中国安全科学学报, 2021, 31(8): 69-74.
[7]	杨三军, 荆亚茹, 姜润发. 矿山救援队应急救援能力评价指标体系构建^*[J]. 中国安全科学学报, 2021, 31(8): 180-188.
[8]	尚婷, 吴鹏, 唐伯明, 白婧荣, 周亮宇. 隧道至互通小间距路段车辆换道博弈行为研究^*[J]. 中国安全科学学报, 2021, 31(10): 68-75.
[9]	杨慧敏, 石琴, 陈一锴, 骆仁佳. 基于混合聚类的农村公路单车事故影响因素分析[J]. 中国安全科学学报, 2020, 30(8): 129-136.
[10]	张志宇, 朱能. 16个高温高湿环境工况等级划分[J]. 中国安全科学学报, 2020, 30(5): 184-190.
[11]	史雪莹, 孙智诚, 朱彤. 基于异质性驾驶行为与碰撞的中观交通流仿真[J]. 中国安全科学学报, 2019, 29(9): 64-69.
[12]	王永刚, 张迪, 刘晓璐. 航空安全员安全保障能力评价研究[J]. 中国安全科学学报, 2019, 29(8): 10-16.
[13]	温廷新, 李洋子. 基于预处理的AFOA-ELM冲击地压危险预测模型[J]. 中国安全科学学报, 2019, 29(8): 29-34.
[14]	魏志杰, 殷腾飞, 王立杰. 煤矿安全诚信测量模型[J]. 中国安全科学学报, 2019, 29(3): 149-154.
[15]	毕娟, 李希建, 陈刘瑜. 预测冲击地压危险性等级R型因子Fisher判别[J]. 中国安全科学学报, 2019, 29(12): 103-109.

因子分析与多层神经网络组合的酒驾辨识模型研究

Study of drunk driving identification model based on factor analysis and multilayer neural network

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价