Characteristic-Based Clustering for Time Series Data

By Xiaozhe Wang, K. Smith‐Miles, Rob J Hyndman. 2006

692 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Economics and Econometrics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Economics and Econometrics

In Signal Processing

Citations in the corpus

Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “dierent scales, etc. Also, many such measures mostly focus on the shape of the respective time series (Aghabozorgi et al., 2015), and they may yield unintuitive results and limited interpretability (Wang et al., 2006). Therefore, we focus on feature-based clustering techniques, which, instead of cap”
Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach (2017, background): “In terms of feature extraction, there is a lot of work present in the literature investigating the use of features of a time series as a data-mining tool for extracting useful patterns (Nanopoulos et al., 2001; Wang et al., 2006; Fulcher and Jones, 2014; Mörchen, 2003).”
Rotation-invariant similarity in time series using bag-of-patterns representation (2012, background): “Several structure-or model-based similarities have been proposed that extract global features such as autocorrelation, skewness, and model parameters from data (Keogh 2004; Nanopoulos et al. 2001; Wang et al. 2006).”
Highly Comparative Feature-Based Time-Series Classification (2014, background): “Furthermore, for many applications, the mechanisms underlying the data are not well understood, making it diﬃcult to develop a well-motivated set of features for classiﬁcation.”
The Zwicky Transient Facility: Science Objectives (2019, methodology): “Recently, new methods have been proposed that overcome these challenges (e.g. Wang et al. 2006) and these could be useful for the analysis of ZTF light curve population studies.”
Time-series clustering - A decade review (2015, methodology): “However, hierarchical clustering is essentially not capable to deal effectively with large time-series [21] due to its quadratic computational complexity and accordingly, it leads to be restricted to small datasets because of its poor scalability.”
Cross-disciplinary perspectives on meta-learning for algorithm selection (2009, methodology): “The usefulness of the meta-data for clustering problems was also illustrated [Wang et al. 2006] and suggests an interesting approach for unsupervised learning of meta-data for knowledge discovery not often considered by the meta-learning community.”
Large-Scale Unusual Time Series Detection (2015, methodology): “The synthetic dataset was generated by varying various time series parameters such as the trend, seasonality and noise.”
catch22: CAnonical Time-series CHaracteristics (2019, background): “From among this wide range of possible features, selecting a set of features that successfully captures the dynamics relevant to the problemat handhas typically been donemanually without quantitative comparison across a variety of potential candidates (Timmer et al. 1993; Nanopoulos et al. 2001; Mör”
Visualising forecasting algorithm performance using time series instance spaces (2017, methodology): “…characterising a time series as a feature vector is not new, and has been used for classifying time series (Nanopoulos, Alcock, and Manolopoulos, 2001), clustering time series (Wang, Smith, and Hyndman, 2006), and for identifying outlying or anomalous time series (Hyndman, Wang, and Laptev, 2015).”
k-Shape: Efficient and Accurate Clustering of Time Series (2015, methodology): “algorithms, statistical-based approaches use measures that summarize characteristics [82], coefficients of models [38], or portions of time series (i.”