摘要
通过收集大数据对汽车驾驶员的疲劳特征和疲劳参数进行学习,根据学习的参数将驾驶员的疲劳程度进行分类,提出了蚁群优化的模糊C均值聚类算法。在初步聚类中运用蚁群聚类产生聚类中心和簇的个数,提供给模糊C均值聚类;利用模糊C均值聚类再次进行聚类,克服了单个聚类算法的缺点。仿真结果表明:文中方法比一般方法具有更好的性能和聚类效果。利用BP神经网络模式识别功能可以识别疲劳驾驶类别。
The fatigue characteristics and fatigue parameters of automobile drivers were learned by col? lecting big data. According to the parameters of learning, the driver’s fatigue degree was classified. An ant colony optimization fuzzy C-means clustering algorithm was proposed. The cluster centers and clusters were generated by using ant colony clustering in preliminary clustering for fuzzy C-means clustering. The fuzzy C-means clustering was used to cluster again, which solved the shortcomings of the clus? tering algorithm. The simulation results show that the proposed method has better performance and clus? tering effect than the general method. The BP neural network pattern recognition function can be used to identify the fatigue driving category.
作者
鲁明
王彬
刘东儒
胡颖雁
Lu Ming;Wang Bin;Liu Dongru;Hu Yingyan(Dept. of Mechanical and Electrical Technology,Chizhou Vocational and Technical College,Chizhou 247000,China)
出处
《湖北汽车工业学院学报》
2019年第2期23-28,共6页
Journal of Hubei University Of Automotive Technology
基金
池州职业技术学院院级重点项目(2017jyxm07)
池州职业技术学院省级教学项目(2017jyxm0686)
安徽省高校省级质量工程校企合作实践教育基地项目(2017sjjd052)
关键词
驾驶行为
模糊C均值聚类
蚁群聚类算法
模式识别
driving behavior
fuzzy C-means clustering
ant colony clustering
pattern recognition
