Study on the Analysis Method for Multivariate Time Series Based on the PCA

摘要：

The feature of multivariate time series was researched in this paper. The principle component analysis principle was introduced. Two approaches based on kernel function classification were used for character selection of multivariate time series. The advantages and disadvantages of the method were discussed. The results of experiment with target showed that the arithmetic is effective and feasible.

关键词： multivariate time series principle component analysis kernel function classification

作者: Zhao An-xing Zhou Xiao-cheng Ma xiang-ling

作者单位: School of Information & Electrical Engineering, Shandong Jianzhu University, Jinan, Shandong, 250101 Department of Ordnance Science and Technology, Naval Aeronautical and Astronautical University, Yant

会议类型: 国际会议

会议名称: 第八届国际测试技术研讨会(8th International Symposium on Test and Measurement)

会议地点: 重庆

会议语种:英文

页码: 299-302

在线出版日期: 2009-08-01（万方平台首次上网日期，不代表论文的发表时间）