Grid-Based Clustering Using Boundary Detection

Du, Mingjing; Wu, Fuyu

doi:10.3390/e24111606

Cited by 10 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, some new grid-based clustering methods have been proposed to solve the above problems [ 19 , 20 , 21 , 22 , 23 , 24 ]. These methods captured attention with the advantage over other approaches because they process data with grid cells.…”

Section: Related Workmentioning

confidence: 99%

“…To the best of our knowledge, existing grid clustering algorithms work by dealing with nodes and cells. The former mainly includes FDGB [ 21 ] and GCBD [ 22 ], while the latter mainly includes GBCN [ 23 ], GCDPP [ 24 ], NGCGAL [ 25 ], and CMSPGD [ 26 ]. However, different grid-based clustering methods have their own considerations in grid space, node or cell processing, and cluster generation strategies, resulting in differences in clustering performance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Clustering Method Based on Adjacent Grids Searching

Li,

Zhong,

Liao

et al. 2023

Entropy

View full text Add to dashboard Cite

Clustering is used to analyze the intrinsic structure of a dataset based on the similarity of datapoints. Its widespread use, from image segmentation to object recognition and information retrieval, requires great robustness in the clustering process. In this paper, a novel clustering method based on adjacent grid searching (CAGS) is proposed. The CAGS consists of two steps: a strategy based on adaptive grid-space construction and a clustering strategy based on adjacent grid searching. In the first step, a multidimensional grid space is constructed to provide a quantization structure of the input dataset. The noise and cluster halo are automatically distinguished according to grid density. Moreover, the adaptive grid generating process solves the common problem of grid clustering, in which the number of cells increases sharply with the dimension. In the second step, a two-stage traversal process is conducted to accomplish the cluster recognition. The cluster cores with arbitrary shapes can be found by concealing the halo points. As a result, the number of clusters will be easily identified by CAGS. Therefore, CAGS has the potential to be widely used for clustering datasets with different characteristics. We test the clustering performance of CAGS through six different types of datasets: dataset with noise, large-scale dataset, high-dimensional dataset, dataset with arbitrary shapes, dataset with large differences in density between classes, and dataset with high overlap between classes. Experimental results show that CAGS, which performed best on 10 out of 11 tests, outperforms the state-of-the-art clustering methods in all the above datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Novel Clustering Method Based on Adjacent Grids Searching

Li,

Zhong,

Liao

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…These maps also circumvent the limitations of maps based on aggregate data, which miss local interactions among geo-referenced variables ( 18 ). In contrast, grid-based maps can display a high level of granularity ( 19 ). Furthermore, bio-geographical methods do not assume space homogeneity –an assumption associated with classic spatial statistics, which considers that neighbors are epidemiologically similar ( 20 , 21 ).…”

Section: Introductionmentioning

confidence: 99%

Geo-temporal patterns to design cost-effective interventions for zoonotic diseases -the case of brucellosis in the country of Georgia

Rivas,

Smith,

Basiladze

et al. 2023

Front. Vet. Sci.

View full text Add to dashboard Cite

IntroductionControl of zoonosis can benefit from geo-referenced procedures. Focusing on brucellosis, here the ability of two methods to distinguish disease dissemination patterns and promote cost-effective interventions was compared.MethodGeographical data on bovine, ovine and human brucellosis reported in the country of Georgia between 2014 and 2019 were investigated with (i) the Hot Spot (HS) analysis and (ii) a bio-geographical (BG) alternative.ResultsMore than one fourth of all sites reported cases affecting two or more species. While ruminant cases displayed different patterns over time, most human cases described similar geo-temporal features, which were associated with the route used by migrant shepherds. Other human cases showed heterogeneous patterns. The BG approach identified small areas with a case density twice as high as the HS method. The BG method also identified, in 2018, a 2.6–2.99 higher case density in zoonotic (human and non-human) sites than in non-zoonotic sites (which only reported cases affecting a single species) –a finding that, if corroborated, could support cost-effective policy-making.DiscussionThree dissemination hypotheses were supported by the data: (i) human cases induced by sheep-related contacts; (ii) human cases probably mediated by contaminated milk or meat; and (iii) cattle and sheep that infected one another. This proof-of-concept provided a preliminary validation for a method that may support cost-effective interventions oriented to control zoonoses. To expand these findings, additional studies on zoonosis-related decision-making are recommended.

show abstract

“…Classic CHAMELEON [39] and CURE [40] are agglomerative and divisive hierarchical clustering algorithms respectively. Grid-based clustering algorithms enjoy extremely high attention due to their low complexity in computation and high efficiency in processing spatial datasets [41,42]. STING [43], one of the most classic grid-based clustering algorithms, generates statistical information of several individual grid units by dividing the original spatial data instead of scanning all individual points to reduce the time complexity further.…”

Section: Introductionmentioning

confidence: 99%

Density peaks clustering algorithm with connected local density and punished relative distance

Xiong,

Zang,

Zhao

et al. 2023

J Supercomput

View full text Add to dashboard Cite

Density peaks clustering (DPC) algorithm has been widely applied in many fields due to its innovation and efficiency. However, the original DPC algorithm and many of its variants choose Euclidean distance as local density and relative distance estimations, which affects the clustering performance on some specific shaped datasets, such as manifold datasets. To address the above-mentioned issue, we propose a density peak clustering algorithm with connected local density and punished relative distance (DPC-CLD-PRD). Specifically, the proposed approach computes the distance matrix between data pairs using the flexible connectivity distance metric. Then, it calculates the connected local density of each data point via combining the flexible connectivity distance measure and k-nearest neighbor method. Finally, the punished relative distance of each data point is obtained by introducing a connectivity estimation strategy into the distance optimization process. Experiments on synthetic, real-world, and image datasets have demonstrated the effectiveness of the algorithm in this paper.

show abstract

Grid-Based Clustering Using Boundary Detection

Cited by 10 publications

References 30 publications

A Novel Clustering Method Based on Adjacent Grids Searching

A Novel Clustering Method Based on Adjacent Grids Searching

Geo-temporal patterns to design cost-effective interventions for zoonotic diseases -the case of brucellosis in the country of Georgia

Density peaks clustering algorithm with connected local density and punished relative distance

Contact Info

Product

Resources

About