E-Transitive: an enhanced version of the Transitive heuristic for clustering categorical data

Slaoui, Saïd Chah; Dafir, Zineb; Lamari, Yasmine

doi:10.1016/j.procs.2018.01.094

Cited by 5 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PFK-means algorithm [21] is a parameter-free clustering algorithm aiming to construct progressively homogeneous clusters until the appropriate number of clusters is automatically detected. This heuristic is a combination of the E-transitive heuristic [22] adjusted for quantitative data, and the traditional K-means [10] [11]. Indeed, the sequential version of the PFK-means algorithm performs a partitioning clustering based on two main stages.…”

Section: A the Sequential Pfk-meansmentioning

confidence: 99%

An Efficient Parallel Algorithm for Clustering Big Data based on the Spark Framework

Dafir¹,

Slaoui²

2022

IJACSA

Self Cite

View full text Add to dashboard Cite

The principal objective of this paper is to provide a parallel implementation focused on the main steps of the parameter-free clustering algorithm based on K-means (PFKmeans) using the Spark framework and a machine learningbased model to process Big Data. Thus, the process consists of parallelizing the main tasks of the first stage of the PFK-means clustering algorithm using successive RDD functions. Then, the parallel K-means provided by Spark MLlib is invoked by setting the cluster centers and the number of clusters determined in the previous step as input parameters of the parallel Kmeans. Furthermore, a comparison between the parallel designed algorithm and the parallel K-means was conducted using UCI data sets in terms of the sum of squared errors and the processing time. The experimental results, performed locally using the Spark framework, demonstrate the efficiency of the proposed solution.

show abstract

Section: A the Sequential Pfk-meansmentioning

confidence: 99%

An Efficient Parallel Algorithm for Clustering Big Data based on the Spark Framework

Dafir¹,

Slaoui²

2022

IJACSA

Self Cite

View full text Add to dashboard Cite

show abstract

“…Set up two mixed data sets V i and V k in two different subspaces M i and M k and use D(i, k) to represent the Euclidean distance of two different subspaces and d(i, k) to represent the Euclidean distance of two mixed data sets [48], [49]. The high-dimensional clustering formula of two mixed data sets of two different subspaces:…”

Section: ) Clustering Analysis Of Multidimensional Subspace Data Setmentioning

confidence: 99%

High-Dimensional Clustering for Incomplete Mixed Dataset Using Artificial Intelligence

2020

IEEE Access

View full text Add to dashboard Cite

In order to address the problem that high energy consumption, high memory usage and low clustering effect in traditional data set high-dimensional clustering algorithms, we propose the highdimensional clustering algorithm of incomplete mixed data set based on artificial intelligence. First, we construct the phase space reconstruction to ensure the invariance of features of incomplete mixed data set by analyzing the incomplete mixed data set and introduce the correlation dimension to obtain the feature correlation value. Second, we introduce the standard deviation and realize the extraction of features of incomplete mixed data set through calculating the sparsity of sample features. Third, we conduct repeated clustering for the mixed data set in the subspace according to the degree of correlation between incomplete mixed data sets in the multidimensional subspace. Last, we realize the design of high-dimensional clustering method for incomplete mixed data set in accordance with the stronger relevance in the mixed data sets. Experimental results show that the proposed algorithm has good correlation dimension processing effects, lower memory usage, time-consuming, lower and concentrated ensemble energy consumption (within 300J), good clustering effects, as high as 92%, which has some advantages and practical application value.

show abstract

A Literature Review on Correlation Clustering: Cross-disciplinary Taxonomy with Bibliometric Analysis

Wahid

Hassini

2022

Oper. Res. Forum

View full text Add to dashboard Cite

E-Transitive: an enhanced version of the Transitive heuristic for clustering categorical data

Cited by 5 publications

References 12 publications

An Efficient Parallel Algorithm for Clustering Big Data based on the Spark Framework

An Efficient Parallel Algorithm for Clustering Big Data based on the Spark Framework

High-Dimensional Clustering for Incomplete Mixed Dataset Using Artificial Intelligence

A Literature Review on Correlation Clustering: Cross-disciplinary Taxonomy with Bibliometric Analysis

Contact Info

Product

Resources

About