TEMPORAL CLUSTERING OF MULTIVARIATE TIME SERIES

2022-2-07
Aslan, Sipan
Clustering of real-valued time series is a prevalent problem that frequently emerges in various fields and applications. While clustering of univariate time series is very much examined, clustering of multivariate time series has not been extensively addressed. This dissertation considers the clustering of real-valued multivariate time series data. When the data analyzed in the clustering task are time series, the time dependencies of the time series and the clusters to be formed should be considered together. In this thesis study, we propose a time series model-based clustering approach that can be used for the clustering of univariate and multivariate times series datasets. The proposed approach, rather than searching similar/dissimilar patterns within a given collection of time series, is mainly focused on clustering with respect to approximations to the generating mechanisms of time series by exploring and utilizing its temporal dependency, linear and non-linear behaviors. In addition, the proposed clustering approach is designed to capture time-dependent cluster changes. The efficiency of the proposed approach is demonstrated by using both synthetic and real data. Synthetic datasets are derived under different scenarios and real datasets obtained from several time series classification studies where the memberships of studied time series are already known. The clustering performances of the proposed approach are compared with other proposed clustering methods.

Suggestions

Temporal clustering of time series via threshold autoregressive models: application to commodity prices
Aslan, Sipan; Yozgatlıgil, Ceylan; İyigün, Cem (2018-01-01)
The primary aim in this study is grouping time series according to the similarity between their data generating mechanisms (DGMs) rather than comparing pattern similarities in the time series trajectories. The approximation to the DGM of each series is accomplished by fitting the linear autoregressive and the non-linear threshold autoregressive models, and outputs of the estimates are used for feature extraction. Threshold autoregressive models are recognized for their ability to represent nonlinear feature...
PROGRESSIVE CLUSTERING OF MANIFOLD-MODELED DATA BASED ON TANGENT SPACE VARIATIONS
Gokdogan, Gokhan; Vural, Elif (2017-09-28)
An important research topic of the recent years has been to understand and analyze manifold-modeled data for clustering and classification applications. Most clustering methods developed for data of non-linear and low-dimensional structure are based on local linearity assumptions. However, clustering algorithms based on locally linear representations can tolerate difficult sampling conditions only to some extent, and may fail for scarcely sampled data manifolds or at high-curvature regions. In this paper, w...
Time Series Forecasting Using Empirical Mode Decomposition and Hybrid Method
Büyükşahin, Ümit Çavuş; Ertekin Bolelli, Şeyda (2018-07-09)
Recently, various applications produce large amount of time series data. In these domains, accurately forecasting time series has been getting important for decision makers. autoregressive integrated moving average (ARIMA) as a linear method and Artificial Neural Networks (ANNs) as a nonlinear method have been widely used to forecast time series. However, many theoretical and empirical studies showed that assembling of those two approaches in hybrid methods can be efficient to improve forecasting performanc...
Time series classification with feature covariance matrices
Ergezer, Hamza; Leblebicioğlu, Mehmet Kemal (2018-06-01)
In this work, a novel approach utilizing feature covariance matrices is proposed for time series classification. In order to adapt the feature covariance matrices into time series classification problem, a feature vector is defined for each point in a time series. The feature vector comprises local and global information such as value, derivative, rank, deviation from the mean, the time index of the point and cumulative sum up to the point. Extracted feature vectors for the time instances are concatenated t...
Principal Coordinate Clustering
SEKMEN, ali; ALDROUBİ, Akram; HAMM, Keaton; Koku, Ahmet Buğra (2017-12-14)
This paper introduces a clustering algorithm, called principal coordinate clustering. It takes in a similarity matrix SW of a data matrix W and computes the singular value decomposition of SW to determine the principal coordinates to convert the clustering problem to a simpler domain. It is a relative of spectral clustering, however, principal coordinate clustering is easier to interpret, and gives a clear understanding of why it performs well. In a fashion, this gives intuition behind why spectral clusteri...
Citation Formats
S. Aslan, “TEMPORAL CLUSTERING OF MULTIVARIATE TIME SERIES,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.