基于PCA和SVM的交通事件自动检测算法

支持向量机分类在处理高维的小样本学习问题上具有优异的表现,特别是具有很好的范化能力。然而其在处理一些高维的原始数据时维数会有冗余,那么样本的主要特征必须被首先选出来以改善支持向量机的性能。将主成分分析技术引入以减少原始样本的特征维数,并且预先有效地预选取主要的特征。在所选取的特征空间中构建支持向量机改善学习速度和检测性能。在对I-880高速公路事件数据的仿真结果表明,所提出的基于主成分分析的支持向量机减少了误警率和平均检测时间。

Automatic Incident Detection Algorithm based on PCA and SVM

Support vector machine (SVM) has the good performance on small sample learning problems with high dimensions,with especially better generalization ability.However there is a little redundancy among the high dimensions of the original samples and the major feature of the samples can be firstly selected to improve the performance of SVM.A principal component analysis (PCA) is employed to reduce the feature dimensions of the original samples and the pre -selected major features efficiently,and an SVM is constr...