data_ECM_MC

Citation Author(s):
Qidong
Dai
Submitted by:
Qidong Dai
Last updated:
Sat, 03/29/2025 - 10:08
DOI:
10.21227/1pxd-dt73
License:
14 Views
Categories:
Keywords:
0
0 ratings - Please login to submit your rating.

Abstract 

Ensemble clustering, which integrates multiple base clusterings to enhance robustness and accuracy, is commonly evaluated on over 10 benchmark datasets. These include 6 synthetic datasets (e.g., 3MC,atom,Chainlink,Flame,Jain,wingnut) designed to test algorithms on nonlinear separability and density variations. The 14 real-world datasets span diverse domains: classical UCI datasets (Iris,Heart,IS,ISOLET,LM,MF,ODR,SPF,waveform), scikit-learning datasets (lung,USPS,TOX), MSRA..These datasets collectively address challenges in cluster shape complexity, dimensionality, noise resilience, and scalability, enabling researchers to assess ensemble methods like CSPA, HGPA, and meta-clustering approaches using metrics such as ACC,NMI ,ARI and F1-score. Such evaluations drive advancements in applications like bioinformatics, customer segmentation, and anomaly detection.

 

Instructions: 

Input the dataset into the clustering method to obtain the clustering results, and then input them into the ensemble clustering method

Comments

dataset link?

Submitted by Rajdip Khan on Tue, 04/01/2025 - 03:07

More from this Author