Parameter selection algorithm of DBSCAN based on K-means two classification algorithm
Clustering algorithm is one of the most important algorithms in unsupervised learning. For density-based spatial clustering of applications with noise (DBSCAN) density clustering algorithm, the selection of neighborhood radius and minimum number is the key to get the best clustering results. Aiming...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-10-01
|
| Series: | The Journal of Engineering |
| Subjects: | |
| Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2018.9082 |
| _version_ | 1818613778144559104 |
|---|---|
| author | Shouhong Chen Xinyu Liu Jun Ma Shuang Zhao Xingna Hou |
| author_facet | Shouhong Chen Xinyu Liu Jun Ma Shuang Zhao Xingna Hou |
| author_sort | Shouhong Chen |
| collection | DOAJ |
| description | Clustering algorithm is one of the most important algorithms in unsupervised learning. For density-based spatial clustering of applications with noise (DBSCAN) density clustering algorithm, the selection of neighborhood radius and minimum number is the key to get the best clustering results. Aiming at the problems of traditional DBSCAN algorithm, such as the neighborhood radius and the minimum number of points, this article puts forward two classifications based on K-means algorithm, and gets two clustering centers. Where calculated between two data points and the cluster center-to -center distance, clustering, distance, statistics in a distance of data points within the scope of the search, the number of data points corresponding to the maximum distance value, and thus the parameters for the DBSCAN algorithm to estimate and selection of initial radius of neighborhood with the minimum number of clustering start critical value. When the parameters are iterated and optimized continuously, the data are divided into clusters, and the most suitable neighborhood radius and the minimum point number are obtained. The experimental data analysis show that the improved algorithm reduces the human factors in the traditional algorithm and improves the efficiency, so as to get the accurate clustering results. |
| first_indexed | 2024-12-16T16:07:31Z |
| format | Article |
| id | doaj.art-5c4ed66e9fbd4bce9d2d7b54a9d2ebf2 |
| institution | Directory Open Access Journal |
| issn | 2051-3305 |
| language | English |
| last_indexed | 2024-12-16T16:07:31Z |
| publishDate | 2019-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Engineering |
| spelling | doaj.art-5c4ed66e9fbd4bce9d2d7b54a9d2ebf22022-12-21T22:25:19ZengWileyThe Journal of Engineering2051-33052019-10-0110.1049/joe.2018.9082JOE.2018.9082Parameter selection algorithm of DBSCAN based on K-means two classification algorithmShouhong Chen0Xinyu Liu1Jun Ma2Shuang Zhao3Xingna Hou4Guilin University of Electronic TechnologyGuilin University of Electronic TechnologyGuilin University of Electronic TechnologyGuilin University of Electronic TechnologyGuilin University of Electronic TechnologyClustering algorithm is one of the most important algorithms in unsupervised learning. For density-based spatial clustering of applications with noise (DBSCAN) density clustering algorithm, the selection of neighborhood radius and minimum number is the key to get the best clustering results. Aiming at the problems of traditional DBSCAN algorithm, such as the neighborhood radius and the minimum number of points, this article puts forward two classifications based on K-means algorithm, and gets two clustering centers. Where calculated between two data points and the cluster center-to -center distance, clustering, distance, statistics in a distance of data points within the scope of the search, the number of data points corresponding to the maximum distance value, and thus the parameters for the DBSCAN algorithm to estimate and selection of initial radius of neighborhood with the minimum number of clustering start critical value. When the parameters are iterated and optimized continuously, the data are divided into clusters, and the most suitable neighborhood radius and the minimum point number are obtained. The experimental data analysis show that the improved algorithm reduces the human factors in the traditional algorithm and improves the efficiency, so as to get the accurate clustering results.https://digital-library.theiet.org/content/journals/10.1049/joe.2018.9082data analysisunsupervised learningpattern clusteringpattern classificationhuman factorsstart critical value clusteringdbscan algorithmneighbourhood radiusexperimental data analysis showminimum point numbermaximum distance valuecluster centre-to-centre distancedata pointsclustering centresnoise density clustering algorithmunsupervised learningclassification algorithmparameter selection algorithm |
| spellingShingle | Shouhong Chen Xinyu Liu Jun Ma Shuang Zhao Xingna Hou Parameter selection algorithm of DBSCAN based on K-means two classification algorithm The Journal of Engineering data analysis unsupervised learning pattern clustering pattern classification human factors start critical value clustering dbscan algorithm neighbourhood radius experimental data analysis show minimum point number maximum distance value cluster centre-to-centre distance data points clustering centres noise density clustering algorithm unsupervised learning classification algorithm parameter selection algorithm |
| title | Parameter selection algorithm of DBSCAN based on K-means two classification algorithm |
| title_full | Parameter selection algorithm of DBSCAN based on K-means two classification algorithm |
| title_fullStr | Parameter selection algorithm of DBSCAN based on K-means two classification algorithm |
| title_full_unstemmed | Parameter selection algorithm of DBSCAN based on K-means two classification algorithm |
| title_short | Parameter selection algorithm of DBSCAN based on K-means two classification algorithm |
| title_sort | parameter selection algorithm of dbscan based on k means two classification algorithm |
| topic | data analysis unsupervised learning pattern clustering pattern classification human factors start critical value clustering dbscan algorithm neighbourhood radius experimental data analysis show minimum point number maximum distance value cluster centre-to-centre distance data points clustering centres noise density clustering algorithm unsupervised learning classification algorithm parameter selection algorithm |
| url | https://digital-library.theiet.org/content/journals/10.1049/joe.2018.9082 |
| work_keys_str_mv | AT shouhongchen parameterselectionalgorithmofdbscanbasedonkmeanstwoclassificationalgorithm AT xinyuliu parameterselectionalgorithmofdbscanbasedonkmeanstwoclassificationalgorithm AT junma parameterselectionalgorithmofdbscanbasedonkmeanstwoclassificationalgorithm AT shuangzhao parameterselectionalgorithmofdbscanbasedonkmeanstwoclassificationalgorithm AT xingnahou parameterselectionalgorithmofdbscanbasedonkmeanstwoclassificationalgorithm |