0
306views
Discuss the basic subspace clustering approaches.

Discuss the basic subspace clustering approaches.

1 Answer
0
2views


Basic subspace clustering approaches are :-

  • Grid-based subspace clustering :

    • In this approach, data space is divided into axis-parallel cells. Then the cells containing objects above a predefined threshold value given as a parameter are merged to form subspace clusters. Number of intervals is another input parameter which defines range of values in each grid.

    • Apriori property is used to prune non-promising cells and to improve efficiency.

    • If a unit is found to be dense in k – 1 dimension, then it is considered for finding dense unit in k dimensions.

    • If grid boundaries are strictly followed to separate objects, accuracy of clustering result is decreased as it may miss neighbouring objects which get separated by string grid boundary. Clustering quality is highly dependent on input parameters.


  • Window-based subspace clustering :-

    • Window-based subspace clustering overcomes drawbacks of cell-based subspace clustering that it may omit significant results.

    • Here a window slides across attribute values and obtains overlapping intervals to be used to form subspace clusters.

    • The size of the sliding window is one of the parameters. These algorithms generate axis-parallel subspace clusters.


  • Density- based subspace clustering :

    • A density-based subspace clustering overcome drawbacks of grid?based subspace clustering algorithms by not using grids.

    • A cluster is defined as a collection of objects forming a chain which fall within a given distance and exceed predefined threshold of object count. Then adjacent dense regions are merged to form bigger clusters.

    • As no grids are used, these algorithms can find arbitrarily shaped subspace clusters.

    • Clusters are built by joining together the objects from adjacent dense regions.

    • These approaches are prone to values of distance parameters.

    • The effect curse of dimensionality is overcome in density-based algorithms by utilizing a density measure which is adaptive to subspace size.

Please log in to add an answer.