Wavelet decomposition algorithm for uncertain data streams

Abstract

Recently data mining over uncertain data streams has attracted a lot of attentions because of the widely existed imprecise data generated from a variety of streaming applications. Many applications have endless uncertain data streams which have a huge amount of data so that it is infeasible to reserve all data in memory to be visited. Therefore, we need a new technology to effectively compress uncertain data streams. Among different data compression technology, the Haar wavelet decomposition is the most popular one, but the traditional wavelet decomposition is no longer applicable on uncertain data streams. Although a significant amount of previous research explore various data reduction techniques on data streams, data reduction techniques on uncertain data streams have seldom been investigated. In this paper, we try to resolve the problem of the wavelet decomposition over uncertain data streams and propose U-HWT(Uncertain Haar Wavelet Transform),a new algorithm for compressing the uncertain data streams. U-HWT uses discrete Haar wavelet transform and emphasis on the impact of the tuple uncertainty on the decomposition. Experimental results show that U-HWT can effectively compress the uncertain data streams.Index Terms-uncertain data streams discrete wavelet transform Haar wavelet decomposition tuple uncertainty

Fast Online Similarity Search for Uncertain Time Series

“…Limited by the high dimension of the sequence, most current work just focuses on the uncertain offline data [7,11,17,18,19]. No efficient index has been proposed so far to support online query processing for uncertain time series.…”

Spatial Index for Uncertain Time Series

“…With massive time series data available, an efficient process for searching a specific pattern from the database is clearly becoming more and more essential. A lot of effort has been devoted to working with time series and some essential issues have been investigated, such as probabilistic range queries [13], [19], similarity match for uncertain time series [2], [7], [9], [11], pattern detection for uncertain data [18], and so on. Among these issues, one of the common requirements is to efficiently find probabilistically approximate matches from a collection of data items for a given query item.…”

“…Uncertainty extensively happens in the real world and has been studied in [1]- [4], [7], [9], [11], [12], [14], [15], [17], [18]. Instead of storing a single value at each timestamp in the classical time series, each timestamp can be modeled as a range of possible bucket or a variable with noise that is linked with a probability density function (pdf).…”