Mindmap
DBSCAN Clustering Algorithm

Inhalt der Mindmap
DBSCAN Clustering Algorithm
Definition
- Essencial technique
- Used in domains and industries
- Acrostic
- D
- Density
- Density
- B
- Based
- S
- Spatial
- Spatial
- C
- Clustering
- A
- Applications
- N
- Noise
- D
Why we need it?
- To create arbitrary shapes
- Varying densities
- Varying densities
- Detects noise
- To create arbitrary shapes
Reachability and Connectivity
- Reachability
- A data point can be accessed from another data point directly or indirectly
- A data point can be accessed from another data point directly or indirectly
- Connectivity
- If two data points belong to the same cluster or not.
- If two data points belong to the same cluster or not.
- Two points can be
- Directly Density-Reachable
- Density-Reachable
- Density-Connected
- Directly Density-Reachable
- Reachability
Parameter Selection
- MinPoints
- Dimensions + 1
- Epsilon
- Can be decided from the K-distance graph.
- MinPoints
Proposed by
- Martin Ester (1996)
- Martin Ester (1996)
Characteristics
- It's robust to outliers.
- Parameters
- Epsilon
- Radius
- Radius
- MinPoints
- Central point
- Central point
- Epsilon
Carlos Daniel Cedeño Ruiz
Bilder und Dateien der Mindmap
Informationen
- Beschreibung
- Mindmap am DBSCAN Clustering Algorithm, erstellt von ROSA KAROL GARCIA PALOS . am 19/09/2021.
- Erstellt von
- ROSA KAROL GARCIA PALOS .
- Aufrufe
- 0
- Bewertung











