Similarity Matching over Uncertain Time Series
Yanfei Zuo, Guohua Liu, Xiaoli Yue, Wei Wang, Honghua Wu · 2011
Similarity matching is one of the most important operations for data mining over time series. But previous works mainly focus on certain data. With the development of the internet of things and sensor networks, uncertain time series are emerging from various sources, which is a new challenge for data processing. In this paper, a novel similarity matching algorithm over uncertain time series is proposed based on a simple model representing the uncertain time series. According to the certainty of the query time series and the database, similarity matching is classified to three types. Then a certain time series is extracted to represent the original uncertain time series. Finally, a similarity search algorithm for certain time series is adopted. Experimental evaluation shows that our algorithm has high efficiency for similarity matching over uncertain time series.