Cluster validity index for irregular clustering results

Liang, Shaoyi; Han, Deqiang; Yang, Yi

doi:10.1016/j.asoc.2020.106583

Cited by 28 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, for comparison with existing methods, we performed principal component analysis (PCA) and feature extraction (amplitude and number of peaks) followed by k -means and hierarchical clustering using MATLAB. 19,31 The comparison of various clustering methods was performed using seven different validation techniques as presented in Liang et al 39…”

Section: Methodsmentioning

confidence: 99%

Quantitative Confocal Microscopy for Grouping of Dose–Response Data: Deciphering Calcium Sequestration and Subsequent Cell Death in the Presence of Excess Norepinephrine

et al. 2021

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Quantitative Confocal Microscopy for Grouping of Dose–Response Data: Deciphering Calcium Sequestration and Subsequent Cell Death in the Presence of Excess Norepinephrine

et al. 2021

View full text Add to dashboard Cite

“…It measures how compact the cluster is formed based on the ratio of the minimum distance between objects that are not in the same cluster using the maximum intra-cluster distance [21]. The compact clusters have a Di value close to one.…”

Section:  Dunn Indexmentioning

confidence: 99%

Hierarchical clustering for crime rate mapping in Indonesia

2022

View full text Add to dashboard Cite

The Sustainable Development Goals (SDGs) are a blueprint for improving the human life quality. Goal 16 (G16) is related to security, and it is in line with the Universal Declaration of Human Rights and the Preamble to the 1945 Constitution. To support the implementation of the G16 achievement, the Indonesian National Police (Polri) has made serious efforts to provide a sense of safety for the community and to minimize crime rates. One of the efforts that could be made is to map areas based on the level of crimes so that the Polri can determine the appropriate strategy/priority of action for mitigation. Therefore, this study aimed to cluster provinces in Indonesia based on the four G16 indicators of the SDGs related to security, namely the number of homicide cases, the victim proportion, the proportion of people who feel safe walking alone in the area where they live, and the proportion of victims of violence that reported to the police in the past year using five hierarchical clustering methods, namely: Single-Linkage, Average-Linkage, Complete-Linkage, Ward, and Division Analysis. Then, methods were validated and compared using six cluster validations to obtain the most compact method. The results showed that Ward's method outperformed the others and produced three clusters. Clusters 1, 2, and 3 contained 18, 5, and 11 provinces respectively.

show abstract

“…Some validity indexes [11,12,13,14] worked with hierarchical clustering algorithm, and got good results. According to arbitrary shaped mass data set, literature [15,16,17] presented separation method to improve performance of validity index which partitioned the original data space into a grid-based structure that allowed the introduction of a new measurement for assessing the true data distribution between any two clusters instead of the distance between the two cluster prototypes. This method measures spherical data set and irregular data set.…”

Section: Introductionmentioning

confidence: 99%

A New Cluster Validity Index for Fuzzy Clustering Using Separation and Compactness

Chen¹,

Zhong²,

Chen

et al. 2023

Preprint

View full text Add to dashboard Cite

Aiming at weak point of classical validity index based on Euclidean distance, we proposed a new validity index which based on Non-Euclidean Distance. First of all, we constructed compact index by using improved membership degree and then made use of anti-close degree to constructed separation index. Finally, a new validity index based on these was proposed. This method overcame the drawbacks of classical validity index based on Euclidean distance, which did not correctly reflect the relation of intra-class and inter-class. Experiments on different datasets show that new method has good performance in noise data environment. The capacity of new method is superior to others with regard to cope with overlap dataset. New method has more obvious superiority especially on high dimensional dataset.

show abstract

Cluster validity index for irregular clustering results

Cited by 28 publications

References 35 publications

Quantitative Confocal Microscopy for Grouping of Dose–Response Data: Deciphering Calcium Sequestration and Subsequent Cell Death in the Presence of Excess Norepinephrine

Quantitative Confocal Microscopy for Grouping of Dose–Response Data: Deciphering Calcium Sequestration and Subsequent Cell Death in the Presence of Excess Norepinephrine

Hierarchical clustering for crime rate mapping in Indonesia

A New Cluster Validity Index for Fuzzy Clustering Using Separation and Compactness

Contact Info

Product

Resources

About