摘要
为提高对驾驶倾向性的辨识准确率,进行驾驶倾向性问卷表调查、模拟驾驶、人因工程测试,考虑了驾驶员的心理、生理信息,以及环境、车辆和操作信息的基础上,提出用广义神经网络确定聚类中心,优化模糊c均值聚类算法,实现目标识别级信息融合的方法,对驾驶倾向性进行预测.利用实验数据对识别方法进行验证,结果表明,该算法对驾驶倾向性的预测准确率达到了85.83%,为进一步研究驾驶员倾向的动态特性提供了依据.
In order to improve the accuracy of the driving tendency,a driving tendency questionnaire survey,simulated driving,and human factors engineering tests were conducted.Based on the driver’s psychological and physiological information,as well as the environment,vehicle and operational information,a generalized neural network is used to determine the clustering center,and the fuzzy c-means clustering algorithm is optimized to achieve the target recognition level information fusion method.The driving tendency is predicted.The method was verified by experimental data and the prediction accuracy is 85.83%,which provides a basis for further study of the driver’s tendency dynamic characteristics.
作者
陈慈
张敬磊
于祥阁
王云
CHEN Ci;ZHANG Jing-lei;YU Xiang-ge;WANG Yun(School of Transportation and Vehicle Engineering,Shangdong University of Technology,Zibo 255000,China)
出处
《数学的实践与认识》
2021年第7期90-97,共8页
Mathematics in Practice and Theory
基金
国家自然科学基金(61573009)
山东省自然科学基金(ZR2017LF015)。
关键词
信息融合
驾驶倾向性
广义神经网络
模糊C均值聚类
information fusion
driving tendency generalized neural network fuzzy c-means clustering