GFDC: A Granule Fusion Density-Based Clustering with Evidential
Reasoning
- URL: http://arxiv.org/abs/2305.12114v1
- Date: Sat, 20 May 2023 06:27:31 GMT
- Title: GFDC: A Granule Fusion Density-Based Clustering with Evidential
Reasoning
- Authors: Mingjie Cai, Zhishan Wu, Qingguo Li, Feng Xu, Jie Zhou
- Abstract summary: density-based clustering algorithms are widely applied because they can detect clusters with arbitrary shapes.
This paper proposes a granule fusion density-based clustering with evidential reasoning (GFDC)
Both local and global densities of samples are measured by a sparse degree metric first.
Then information granules are generated in high-density and low-density regions, assisting in processing clusters with significant density differences.
- Score: 22.526274021556755
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Currently, density-based clustering algorithms are widely applied because
they can detect clusters with arbitrary shapes. However, they perform poorly in
measuring global density, determining reasonable cluster centers or structures,
assigning samples accurately and handling data with large density differences
among clusters. To overcome their drawbacks, this paper proposes a granule
fusion density-based clustering with evidential reasoning (GFDC). Both local
and global densities of samples are measured by a sparse degree metric first.
Then information granules are generated in high-density and low-density
regions, assisting in processing clusters with significant density differences.
Further, three novel granule fusion strategies are utilized to combine granules
into stable cluster structures, helping to detect clusters with arbitrary
shapes. Finally, by an assignment method developed from Dempster-Shafer theory,
unstable samples are assigned. After using GFDC, a reasonable clustering result
and some identified outliers can be obtained. The experimental results on
extensive datasets demonstrate the effectiveness of GFDC.
Related papers
- GCC: Generative Calibration Clustering [55.44944397168619]
We propose a novel Generative Clustering (GCC) method to incorporate feature learning and augmentation into clustering procedure.
First, we develop a discrimirative feature alignment mechanism to discover intrinsic relationship across real and generated samples.
Second, we design a self-supervised metric learning to generate more reliable cluster assignment.
arXiv Detail & Related papers (2024-04-14T01:51:11Z) - DECWA : Density-Based Clustering using Wasserstein Distance [1.4132765964347058]
We propose a new clustering algorithm based on spatial density and probabilistic approach.
We show that our approach outperforms other state-of-the-art density-based clustering methods on a wide variety of datasets.
arXiv Detail & Related papers (2023-10-25T11:10:08Z) - Research on Efficient Fuzzy Clustering Method Based on Local Fuzzy
Granular balls [67.33923111887933]
In this paper, the data is fuzzy iterated using granular-balls, and the membership degree of data only considers the two granular-balls where it is located.
The formed fuzzy granular-balls set can use more processing methods in the face of different data scenarios.
arXiv Detail & Related papers (2023-03-07T01:52:55Z) - GBMST: An Efficient Minimum Spanning Tree Clustering Based on
Granular-Ball Computing [78.92205914422925]
We propose a clustering algorithm that combines multi-granularity Granular-Ball and minimum spanning tree (MST)
We construct coarsegrained granular-balls, and then use granular-balls and MST to implement the clustering method based on "large-scale priority"
Experimental results on several data sets demonstrate the power of the algorithm.
arXiv Detail & Related papers (2023-03-02T09:04:35Z) - Enhancing cluster analysis via topological manifold learning [0.3823356975862006]
We show that inferring the topological structure of a dataset before clustering can considerably enhance cluster detection.
We combine manifold learning method UMAP for inferring the topological structure with density-based clustering method DBSCAN.
arXiv Detail & Related papers (2022-07-01T15:53:39Z) - VDPC: Variational Density Peak Clustering Algorithm [16.20037014662979]
We propose a variational density peak clustering (VDPC) algorithm to identify clusters with variational density.
VDPC outperforms two classical algorithms (i.e., DPC and DBSCAN) and four state-of-the-art extended DPC algorithms.
arXiv Detail & Related papers (2021-12-29T12:50:09Z) - Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly
Types [60.45942774425782]
We introduce anomaly clustering, whose goal is to group data into coherent clusters of anomaly types.
This is different from anomaly detection, whose goal is to divide anomalies from normal data.
We present a simple yet effective clustering framework using a patch-based pretrained deep embeddings and off-the-shelf clustering methods.
arXiv Detail & Related papers (2021-12-21T23:11:33Z) - Density-Based Clustering with Kernel Diffusion [59.4179549482505]
A naive density corresponding to the indicator function of a unit $d$-dimensional Euclidean ball is commonly used in density-based clustering algorithms.
We propose a new kernel diffusion density function, which is adaptive to data of varying local distributional characteristics and smoothness.
arXiv Detail & Related papers (2021-10-11T09:00:33Z) - Very Compact Clusters with Structural Regularization via Similarity and
Connectivity [3.779514860341336]
We propose an end-to-end deep clustering algorithm, i.e., Very Compact Clusters (VCC) for the general datasets.
Our proposed approach achieves better clustering performance over most of the state-of-the-art clustering methods.
arXiv Detail & Related papers (2021-06-09T23:22:03Z) - Skeleton Clustering: Dimension-Free Density-based Clustering [0.2538209532048866]
We introduce a density-based clustering method called skeleton clustering.
To bypass the curse of dimensionality, we propose surrogate density measures that are less dependent on the dimension but have intuitive geometric interpretations.
arXiv Detail & Related papers (2021-04-21T21:25:02Z) - Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
Existing scalable hierarchical clustering methods sacrifice quality for speed.
We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
arXiv Detail & Related papers (2020-10-22T15:58:35Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.