Multivariate Time Series Classification by Combining Trend-Based and Value-Based Approximations

Abstract

Abstract. Multivariate time series data often have a very high dimensionality. Classifying such high dimensional data poses a challenge because a vast number of features can be extracted. Furthermore, the meaning of the normally intuitive term "similar to" needs to be precisely defined. Representing the time series data effectively is an essential task for decision-making activities such as prediction, clustering and classification. In this paper we propose a featurebased classification approach to classify real-world multivariate time series generated by drilling rig sensors in the oil and gas industry. Our approach encompasses two main phases: representation and classification.For the representation phase, we propose a novel representation of time series which combines trend-based and value-based approximations (we abbreviate it as TVA). It produces a compact representation of the time series which consists of symbolic strings that represent the trends and the values of each variable in the series. The TVA representation improves both the accuracy and the running time of the classification process by extracting a set of informative features suitable for common classifiers.For the classification phase, we propose a memory-based classifier which takes into account the antecedent results of the classification process. The inputs of the proposed classifier are the TVA features computed from the current segment, as well as the predicted class of the previous segment.Our experimental results on real-world multivariate time series show that our approach enables highly accurate and fast classification of multivariate time series.

Stacking for multivariate time series classification

“…In Esmael et al [29], a compact representation of time series is proposed that combine trend values and valuebased approximations. This approach extends SAX [51,52] adding new strings symbols.…”

Large-Scale Indexing, Discovery, and Ranking for the Internet of Things (IoT)

“…Therefore, [Esmael et al 2012] extend the plain SAX approach by adding symbols (U, D, S) for up, down and straight, receptively to de ne the direction of time-series data. Overall representing data using SAX shows better result than using the raw data due to dimensionality reduction approach [Lin et al 2003].…”

Improving time series classification using Hidden Markov Models

“…We collected real time datasets from different drilling scenarios. The collected datasets were classified using the classifier described in [9]. The collected datasets and the classification accuracies are described in table 2.…”

“…Window-based representation is a common representation in machine learning. Some examples of such techniques are Piecewise Aggregate Approximation (PLA) [10], Trend-based and Value-based Approximation (TVA) [9], and Symbolic Aggregate Approximation (SAX) [4]. In window-based representation, the whole time series data are divided into a sequence of equal sized windows (segments).…”

“…Thus, classifying such data poses a challenge because a vast number of features can be extracted [4] [9]. That means, applying classification techniques directly on raw time series data is often not practical.…”