Iterative Incremental Clustering of Time Series

Lin, Jessica; Vlachos, Michail; Keogh, Eamonn; Gunopulos, Dimitrios

doi:10.1007/978-3-540-24741-8_8

Cited by 135 publications

(85 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This disqualified them because we set the proviso that the results should be independent from the initial conditions -our method of axial K-means (Lelu, 1994) is part of this family; the local optima for a given number of clusters mostly reveal the same main clusters which are often trivial but can also make the most interesting ones of average or low size appear/disappear/amalgamate or split. Quite a lot of incremental variants of these methods have been proposed (Binztock and Gallinari, 2002;Chen et al, 2003) and a partial review of these can be found in Lin et al (2004). Many come from the DARPA-TDT research programme such as Gaudin and Nicoloyannis (2005), Gaber et al (2005).…”

Section: Adapting Methods With Mobile Centres To Incrementalitymentioning

confidence: 99%

Paving the way for next generation data-stream clustering: towards a unique and statistically valid cluster structure at any time step

Cuxac

Lelu

Cadot

2011

IJDMMM

View full text Add to dashboard Cite

Abstract:In the domain of data-stream clustering, e.g., dynamic text mining as our application domain, our goal is two-fold and a long term one: 1 at each data input, the resulting cluster structure has to be unique, independent of the order the input vectors are presented 2 this structure has to be meaningful for an expert, e.g., not composed of a huge 'catch-all' cluster in a cloud of tiny specific ones, as is often the case with large sparse data tables.The first preliminary condition is satisfied by our Germen density-mode seeking algorithm, but the relevance of the clusters vis-à-vis expert judgment relies on the definition of a data density, relying itself on the type of graph chosen for embedding the similarities between text inputs. Having already demonstrated the dynamic behaviour of Germen algorithm, we focus here on appending a Monte-Carlo method for extracting statistically valid inter-text links, which looks promising applied both to an excerpt of the Pascal bibliographic database, and to the Reuters-RCV1 news test collection. Though not being a central issue here, the time complexity of our algorithms is eventually discussed. 342P. Cuxac et al.

show abstract

Section: Adapting Methods With Mobile Centres To Incrementalitymentioning

confidence: 99%

Paving the way for next generation data-stream clustering: towards a unique and statistically valid cluster structure at any time step

Cuxac

Lelu

Cadot

2011

IJDMMM

View full text Add to dashboard Cite

show abstract

“…The most commonly used data mining clustering algorithm is k-means [2,22,21]. We performed k-means using the Euclidean distance on the raw data, and on our bag-of-patterns representation.…”

Section: Partitional Clusteringmentioning

confidence: 99%

Finding Structural Similarity in Time Series Data Using Bag-of-Patterns Representation

Lin

2009

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. For more than one decade, time series similarity search has been given a great deal of attention by data mining researchers. As a result, many time series representations and distance measures have been proposed. However, most existing work on time series similarity search focuses on finding shape-based similarity. While some of the existing approaches work well for short time series data, they typically fail to produce satisfactory results when the sequence is long. For long sequences, it is more appropriate to consider the similarity based on the higher-level structures. In this work, we present a histogram-based representation for time series data, similar to the "bag of words" approach that is widely accepted by the text mining and information retrieval communities. We show that our approach outperforms the existing methods in clustering, classification, and anomaly detection on several real datasets.

show abstract

“…DTW has been extended to deal with unknown start and end points of isolated words in speech [4], [5], and connected word recognition [6], [7], [8]. More recent research on DTW has focused on applying it to mining patterns from one-dimensional time series [9], and indexing and clustering one-dimensional time series [10], [11].…”

Section: Dynamic Time Warpingmentioning

confidence: 99%

Online Context Recognition in Multisensor Systems using Dynamic Time Warping

West

Venkatesh

et al. 2005

2005 International Conference on Intelligent Sensors, Sensor Networks and Information Processing

View full text Add to dashboard Cite

In this paper we present our system for online context recognition of multimodal sequences acquired from multiple sensors. The system uses Dynamic lime Warping (D7W) to recognize multimodal sequences of different lengths, embedded in continuous data streams. We evaluate the performance of our system on two real world datasets: 1) accelerometer data acquired from performning two hand gestures and 2) NOKIA's benchmark dataset for context recognition. The results from both datasets demonstrate that the system can perform online context recognition efficiently and achieve high recognition accuracy.

show abstract

Iterative Incremental Clustering of Time Series

Cited by 135 publications

References 17 publications

Paving the way for next generation data-stream clustering: towards a unique and statistically valid cluster structure at any time step

Paving the way for next generation data-stream clustering: towards a unique and statistically valid cluster structure at any time step

Finding Structural Similarity in Time Series Data Using Bag-of-Patterns Representation

Online Context Recognition in Multisensor Systems using Dynamic Time Warping

Contact Info

Product

Resources

About