Online Clustering with Variable Sized Clusters

Csirik, János; Epstein, Leah; Imreh, Csanád; Levin, Asaf

doi:10.1007/s00453-011-9586-2

Cited by 19 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, clustering algorithms require a number of assumptions and parameters to be known in advance [1][2][3][4][5][6][7][8][9], for instances, number of clusters in k-means clustering algorithm [1], the kernel size in mean shift clustering algorithm [2], which usually are impractical for users to decide in reality. In addition, most of the well-known clustering algorithms [1][2][3][4][5] as well as many recently proposed clustering algorithms [8,10] are restricted to offline data processing and not applicable to the live data streams with potential changes of data patterns [11,12].…”

Section: Introductionmentioning

confidence: 99%

Autonomous data-driven clustering for live data stream

Angelov

2016

2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

In this paper, a novel autonomous data-driven clustering approach, called AD_clustering, is presented for live data streams processing. This newly proposed algorithm is a fully unsupervised approach and entirely based on the data samples and their ensemble properties, in the sense that there is no need for user-predefined or problem-specific assumptions and parameters, which is a problem most of the current clustering approaches suffer from. Moreover, the proposed approach automatically evolves its structure according to the experimentally observable streaming data and is able to recursively update its self-defined parameters using only the current data sample, meanwhile, discards all the previous data samples. Experimental results based on benchmark datasets exhibit the higher performance of the proposed fully autonomous approach compared with the comparative approaches with userand problem-specific parameters to be predefined. This new clustering algorithm is a promising tool for further applications in the field of real-time streaming data analytics.

show abstract

Section: Introductionmentioning

confidence: 99%

Autonomous data-driven clustering for live data stream

Angelov

2016

2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

View full text Add to dashboard Cite

show abstract

“…Points that arrive consecutively have to be assigned to clusters at the time of arrival. Previous results on the online data clustering problem for data sequences can be found, for example, in [5,11], with unit sized clusters and in [7,8,9] with variable sized clusters.…”

Section: Introductionmentioning

confidence: 99%

A new model for the linear 1-dimensional online clustering problem

London

Németh

et al. 2014

Acta Universitatis Sapientiae, Informatica

View full text Add to dashboard Cite

In this study, a mathematical model is presented for an online data clustering problem. Data clustering plays an important role in many applications like handling the data acknowledgment problem and data stream management in real-time locating systems. The inputs in these problems are data sequences, each containing several data elements. Each data element has an arrival time and a weight that reflects its importance. The arrival times are not known in advance, and some data elements never arrive. Hence the system should decide which moment is optimal for forwarding the collected data for processing. This requires finding a good trade-off between the amount of collected information and the waiting time, which may be regarded as a minimization problem. Here, we investigate several online algorithms and present their competitive analysis and average case studies. Experimental results, based on simulations using artificially generated data, are also presented and they confirm the efficiency of our methods.

show abstract

“…In [6] the one-dimensional variant of our problem is examined (with linear cost), where there is no restriction on the length of a cluster, and the cost of a cluster is the sum of a fixed setup cost and its diameter. Both the strict and the flexible model have been investigated and an intermediate model, where the diameter is fixed in advance but the exact location can be modified is also studied.…”

Section: Introductionmentioning

confidence: 99%

“…Both the strict and the flexible model have been investigated and an intermediate model, where the diameter is fixed in advance but the exact location can be modified is also studied. In [6], tight bounds are given on the competitive ratio of any online algorithm belonging to any of these variants. Tight bounds are given of 1+ √ 2 ≈ 2.414 on the competitive ratio for the online problem in the strict model, and tight bounds of 2 in the semi-online version.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online Clustering on the Line with Square Cost Variable Sized Clusters

Divéki¹

2013

Acta Cybern

View full text Add to dashboard Cite

In the online clustering problems, the classification of points into sets (called clusters) is done in an online fashion. Points arrive one by one at arbitrary locations, to be assigned to clusters at the time of arrival without any information about the further points. A point can be assigned to an existing cluster, or a new cluster can be opened for it. Existing clusters cannot be merged or split. We study one-dimensional variants. The cost of a cluster is the sum of a fixed setup cost scaled to 1 and the square of the diameter of the cluster. The goal is to minimize the sum of costs of the clusters used by the algorithm. In this paper we investigate the problem on the line. We examine two versions, both maintaining the properties that a point which was assigned to a given cluster must remain assigned to this cluster, and clusters cannot be merged. In the strict variant, the size and the exact location of the cluster must be fixed when it is initialized. In the flexible variant, the algorithm can shift the cluster or expand it, as long as it contains all points assigned to it. We consider the online and the semi-online (the input is sorted according to their coordinates from smallest to largest i.e., from left to right) versions of the above two variants. We present the first online algorithms for the solution of the problem. We describe algorithms for the strict and the flexible variant both for the online and semi-online versions. We also give lower bounds on the possible competitive ratio in all of the cases.

show abstract

Online Clustering with Variable Sized Clusters

Cited by 19 publications

References 14 publications

Autonomous data-driven clustering for live data stream

Autonomous data-driven clustering for live data stream

A new model for the linear 1-dimensional online clustering problem

Online Clustering on the Line with Square Cost Variable Sized Clusters

Contact Info

Product

Resources

About