SIMILARITY SEARCH OVER DATA STREAM USING LPC-DTW

摘要：

Effective similarity search over data stream is of importance for applications like network monitoring, information retrieval and financial service, etc.Linear Predictive Coding (LPC) is a tool using the information of a linear predictive model.In this paper, we propose similarity search over data stream based on LPC cepstral coefficients using Dynamic Time Warping (DTW).Compared with traditional approaches, such as similarity search based on Discrete Fourier Transform (DFT) and Discrete Wavelet Transform (DWT), the proposed method LPC-DTW can use fewer coefficients to capture desired features from data stream for similarity search.In distance metric of similarity search, DTW that replaces the Euclidean distance metric could bring better performance.The relative experiment results demonstrate the proposed method is better than the traditional approaches.

关键词： Similarity search Data stream LPC DTW

作者: WEI-MIN LI FENG LI JIAN-WEI LIU JIA-JIN LE

作者单位: College of Computer Science and Technology of Donghua University, 1882 West Yanan Road, Shanghai, C College of Mechanical and Electronic Engineering, China University of Petroleum, Beijing, 102249

会议类型: 国际会议

会议名称: 2007 International Conference on Machine Learning and Cybernetics(IEEE第六届机器学习与控制论国际会议)

会议地点: 香港

会议语种:英文

页码: 1631-1634

在线出版日期: 2007-08-19（万方平台首次上网日期，不代表论文的发表时间）