Towards parameter-free data mining

By Eamonn J. Keogh, Stefano Lonardi, Chotirat (Ann) Ratanamahatana. Knowledge Discovery and Data Mining, 2004

662 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Economics and Econometrics, Signal Processing

View Paper: https://www.semanticscholar.org/paper/d0329d8cdd95a7091c983b36b4e65b98d22182b2

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

k-Nearest Neighbour Classifiers - A Tutorial (2020, neutral): “[30, 24].”
Clustering and Community Detection in Directed Networks: A Survey (2013, neutral): “[143]) for several reasons.”
Experiencing SAX: a novel symbolic representation of time series (2007, methodology): “2005), compression-based distance measures (Keogh et al. 2004), etc.”
Author ' s personal copy A Fast Quartet tree heuristic for hierarchical clustering (2010, methodology): “A variant has been experimentally tested on all time sequence data used in all the major data-mining conferences in the last decade [27].”
Outlier Analysis (2013, methodology): “A method for determining outliers based in information theoretic measures was proposed in [259].”
The Google Similarity Distance (2004, methodology): “Previously, we and others developed a compression-based method to establish a universal similarity metric among objects given as ﬁnite binary strings [2], [25], [26], [7], [8], [39], [40], which was widely reported [20], [21], [13].”
Time-series clustering - A decade review (2015, background): “Symbolic Approximation (SAX) O(n) Data adaptive Usage: [111]”
Trajectory clustering: a partition-and-group framework (2007, methodology): “This idea is tightly connected with the MDL principle [13].”
Characteristic-Based Clustering for Time Series Data (2006, methodology): “• Compression-based Dissimilarity Measures (CDM) is proposed by Keogh and others to compare long time series structure using co-compressibility as a dissimilarity measure (Keogh et al., 2004).”
Anomaly Detection for Discrete Sequences: A Survey (2012, methodology): “Another variation of the basic anomaly detection technique, known as Window Comparison Anomaly Detection (WCAD), was proposed by Keogh et al. [70].”
Clustering by compression (2003, methodology): “Recently, [20] has experimented with our method on all time sequence data used in all the major data-mining conferences in the last decade.”
Streaming Pattern Discovery in Multiple Time-Series (2005, methodology): “[27] propose parameter-free methods for classic data mining tasks (i.”
HOT SAX: efficiently finding the most unusual time series subsequence (2005, methodology): “In contrast, many other anomaly detection algorithms require 3 to 7 unintuitive parameters [6].”
Modeling multiple time series for anomaly detection (2005, methodology): “Some proven and broadly applicable techniques such as WCAD [4] and neural networks suffer from opacity.”
Gorilla: A Fast, Scalable, In-Memory Time Series Database (2015, methodology): “We also identiﬁed lossy time series approximation techniques used in data mining to make the problem set more easily ﬁt within memory [15, 11], but Gorilla is focused on keeping the full resolution representation of data.”
Anomaly detection: A survey (2009, methodology): “Kolomogorov complexity [Li and Vitanyi 1993] has been used by several techniques [Arning et al. 1996; Keogh et al. 2004].”