Parallel Implementation of Density Peaks Clustering Algorithm Based on Spark

Li, Rui; Li, Xiaoge; Du, Liping; Zhi, Shuting; Wei, Mian

doi:10.1016/j.procs.2017.03.138

Cited by 14 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al proposed a parallel clustering algorithm Parallel DP [71] based on Spark Graphx and Density Peaks [72]. e main difference between this algorithm and the parallel DBSCAN algorithm is the selection of centroid of clusters.…”

Section: Parallel Density Clustering Algorithmmentioning

confidence: 99%

A Survey of Parallel Clustering Algorithms Based on Spark

Xiao

2020

Scientific Programming

View full text Add to dashboard Cite

Clustering is one of the most important unsupervised machine learning tasks, which is widely used in information retrieval, social network analysis, image processing, and other fields. With the explosive growth of data, the classical clustering algorithms cannot meet the requirements of clustering for big data. Spark is one of the most popular parallel processing platforms for big data, and many researchers have proposed many parallel clustering algorithms based on Spark. In this paper, the existing parallel clustering algorithms based on Spark are classified and summarized, the parallel design framework of each kind of algorithms is discussed, and after comparing different kinds of algorithms, the direction of the future research is discussed.

show abstract

Section: Parallel Density Clustering Algorithmmentioning

confidence: 99%

A Survey of Parallel Clustering Algorithms Based on Spark

Xiao

2020

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…In order to benefit from the high performance of multiprocessor computer systems, many efforts have been made to develop and implement parallel pattern analysis algorithms [1][2][3][4][5][6][7][8][9][10][11]. Improvement for the k-means algorithm (IMR-KCA) proposed in [1].…”

Section: Related Researchmentioning

confidence: 99%

“…In [3], the authors proposed Spark's GraphX based algorithm for density peaks clustering. Comparing to MapReduce implementation the system in [3] improves the performance significantly.…”

Section: Related Researchmentioning

confidence: 99%

Density based Clustering Algorithm for Distributed Datasets using Mutual k-Nearest Neighbors

Salim¹

2019

ijacsa

View full text Add to dashboard Cite

Privacy and security have always been a concern that prevents the sharing of data and impedes the success of many projects. Distributed knowledge computing, if done correctly, plays a key role in solving such a problem. The main goal is to obtain valid results while ensuring the non-disclosure of data. Density-based clustering is a powerful algorithm in analyzing uncertain data that naturally occur and affect the performance of many applications like location-based services. Nowadays, a huge number of datasets have been introduced for researchers which involve high-dimensional data points with varying densities. Such datasets contain data points with highdensity regions surrounded by data points with sparse density. The existing clustering approaches handle these situations inefficiently, especially in the context of distributed data. In this paper, we design a new decomposable density-based clustering algorithm for distributed datasets (DDBC). DDBC utilizes the concept of mutual k-nearest neighbor relationship to cluster distributed datasets with different density. The proposed DDBC algorithm is capable of preserving the privacy and security of data on each site by requiring a minimal number of transmissions to other sites.

show abstract

“…One method for grouping data is clustering. In clustering, existing data are grouped based on the level of similarity data sharing common characteristics with other data are grouped into one cluster, while data that do not have similarities be grouped with other clusters [4]. Clustering methods have been widely used in various fields, including pattern recognition, data analysis, and image processing [5].…”

Section: A Clusteringmentioning

confidence: 99%

The Comparative Study on Clustering Method Using Hospital Facility Data in Jakarta District and Surrounding Areas

Romadon¹,

Fitrianah²

2019

IJMLC

View full text Add to dashboard Cite

The present study reports the findings of a comparative analysis conducted on health facility research (HFR) data, based on a clustering method with K-Means and K-Medoids algorithm. The K-Means algorithm consist of four steps: specifyng the centroid values, grouping data on the centroid, calculating centroid values, repeating grouping data on the centroid, and calculating the values until the cluster is stable (convergence), The K-Medoids algorithm consists of six steps: medoids initialization, data allocation to the nearest medoid, determinination of new medoids, calculation of data distance with medoid, calculation of deviation, and repeating the determination of new medoids, until the deviation to the convergence cluster is counted. The data utilized in this study are HFR data located in the Jakarta district and surrounding areas, from 2013 to 2018. Our results showed that the execution time from K-Medoids algorithm outperformed the K-Means algorithm. The K-Medoids algorithm speeded up the execution time, and at the same time improved the density value between clusters (silhouette). By utilizing the clustering method, health facilities in hospitals in Jabodetabek can be categorized based on their resources.

show abstract

Parallel Implementation of Density Peaks Clustering Algorithm Based on Spark

Cited by 14 publications

References 2 publications

A Survey of Parallel Clustering Algorithms Based on Spark

A Survey of Parallel Clustering Algorithms Based on Spark

Density based Clustering Algorithm for Distributed Datasets using Mutual k-Nearest Neighbors

The Comparative Study on Clustering Method Using Hospital Facility Data in Jakarta District and Surrounding Areas

Contact Info

Product

Resources

About