Symbolic Aggregate approXimation (SAX) under interval uncertainty

Abstract

Abstract-In many practical situations, we monitor a system by continuously measuring the corresponding quantities, to make sure that an abnormal deviation is detected as early as possible. Often, we do not have ready algorithms to detect abnormality, so we need to use machine learning techniques. For these techniques to be efficient, we first need to compress the data. One of the most successful methods of data compression is the technique of Symbolic Aggregate approXimation (SAX). While this technique is motivated by measurement uncertainty, it does not explicitly take this uncertainty into account. In this paper, we show that we can further improve upon this techniques if we explicitly take measurement uncertainty into account.

BEATS: Blocks of Eigenvalues Algorithm for Time series Segmentation

“…SAX has been used to asses different problems such as finding time series discords [24], finding motifs in a database of shapes [25], and to compress data before finding abnormal deviations [26] and it has repeatedly been enhanced [27], [28], [29].…”

A New Time Series Similarity Measurement Method Based on the Morphological Pattern and Symbolic Aggregate Approximation

“…In modern industry, the dimensionality of time series is becoming higher gradually, and the rapid and accurate processing of time series is a new requirement in the data mining of time series [18]. Therefore, in order to improve the computational efficiency of similarity measurement, some methods which express the time series in a simple and feature-rich manner have been proposed, such as, describe time series from the following aspects of time series: symbolization [19], change trend [20] and shape [21]. For example, Tamura and Ichimura [22] proposed a hybrid symbolic aggregate approximation by combining the symbolic aggregate approximation strings of time series and moving average convergence divergence histogram.…”