2016
DOI: 10.17485/ijst/2016/v9i3/75971
|View full text |Cite
|
Sign up to set email alerts
|

A Survey on Clustering Techniques for Big Data Mining

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
47
0

Year Published

2018
2018
2021
2021

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 100 publications
(47 citation statements)
references
References 24 publications
0
47
0
Order By: Relevance
“…There are various clustering algorithms which differ from each other in terms of the approach they follow in order to do the grouping of the objects according to their characteristics. These are stated as follows [23] -In Partitioned Based Clustering all the data points are taken as a single cluster in the beginning. These data points are then separated into clusters by iteratively positioning these objects between the clusters.…”
Section: Using Clustering Techniques For Customer Segmentationmentioning
confidence: 99%
See 1 more Smart Citation
“…There are various clustering algorithms which differ from each other in terms of the approach they follow in order to do the grouping of the objects according to their characteristics. These are stated as follows [23] -In Partitioned Based Clustering all the data points are taken as a single cluster in the beginning. These data points are then separated into clusters by iteratively positioning these objects between the clusters.…”
Section: Using Clustering Techniques For Customer Segmentationmentioning
confidence: 99%
“…Hence it is easy to choose and decide on the number of clusters that we wish to take by looking at the dendrogram. However, for a large number of observations its computational speed is very low as compared to the nonhierarchical methods of clustering [23]. Hence, the size and order of the data have an impact on the final results obtained.…”
mentioning
confidence: 99%
“…Partition based algorithms can found clusters of Non convex shapes. [8] Some algorithm which can use this concept are planned as follows :…”
Section: Methodsmentioning
confidence: 99%
“…By comparing most similarity other object is assigning to the cluster. For each data vector the algorithm calculates the distance between data vector and each cluster centroid.This algorithm works as follows [8] : Algorithm: Generate K-Means Input: Training Data Output: Decision Value • Load dataset, Take the experiment of gathering a sample of observed values • select number of k clusters • Randomly generates k-cluster and evaluate cluster center and generate k random points as cluster centres using k-means function.…”
Section: K-meansmentioning
confidence: 99%
“…DBSCAN is one of effective density-based cluster algorithm, its simple and create cluster in arbitrary shape also cluster information as noise and outliers, DBSCAN is fast and its efficient with large Data Base, it has two inputs first radius second the minimum points found in radius, DBSCAN general idea based on finding minimum number of point in radius space to form clusters else if the number of minimum points not found in radius it will mark as noise [15] [3], DBSCAN algorithm is stated below [16] . Algorithm 2: DBSCAN outlier [16]  Set of points to be considered to form a graph.…”
Section: Dbscan Algorithmmentioning
confidence: 99%