|
gptkbp:instanceOf
|
gptkb:algorithm
density-based algorithm
|
|
gptkbp:advantage
|
parameter sensitivity
robust to outliers
can find clusters of arbitrary shape
difficulty with varying density
|
|
gptkbp:category
|
unsupervised learning
|
|
gptkbp:citation
|
over 30,000 (as of 2024)
|
|
gptkbp:compatibleWith
|
number of clusters as input
|
|
gptkbp:complexity
|
O(n log n) with spatial index
O(n^2) without spatial index
|
|
gptkbp:detects
|
gptkb:music
arbitrarily shaped clusters
|
|
gptkbp:fullName
|
gptkb:Density-Based_Spatial_Clustering_of_Applications_with_Noise
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
DBSCAN algorithm
|
|
gptkbp:input
|
feature vectors
|
|
gptkbp:introduced
|
gptkb:Hans-Peter_Kriegel
gptkb:Jörg_Sander
gptkb:Martin_Ester
gptkb:Xiaowei_Xu
|
|
gptkbp:introducedIn
|
1996
|
|
gptkbp:language
|
English
|
|
gptkbp:openSource
|
gptkb:ELKI
gptkb:scikit-learn
gptkb:R_(dbscan_package)
|
|
gptkbp:output
|
cluster labels
noise label
|
|
gptkbp:parameter
|
epsilon (ε)
minPts
|
|
gptkbp:publishedIn
|
gptkb:Proceedings_of_the_2nd_International_Conference_on_Knowledge_Discovery_and_Data_Mining_(KDD-96)
|
|
gptkbp:step
|
cluster expansion
core point identification
density reachability
noise identification
|
|
gptkbp:supportsAlgorithm
|
gptkb:HDBSCAN
gptkb:K-means
gptkb:OPTICS
|
|
gptkbp:usedIn
|
gptkb:machine_learning
data mining
spatial data analysis
|
|
gptkbp:bfsParent
|
gptkb:Martin_Ester
gptkb:Xiaowei_Xu
|
|
gptkbp:bfsLayer
|
7
|