From: A novel algorithm for fast and scalable subspace clustering of high-dimensional data
Notation | Meaning |
---|---|
D B | The database of points |
|T| | The cardinality of a set T |
n | The total number of points, n=|D B| |
D | The set of attributes, D={d 1,d 2,…,d k } |
k | The total number of dimensions, k=|D| |
d i | The i th dimension, d i ∈D |
P i | The i th point, P i ∈D B |
S | A subspace, S⊂D |
\({P_{i}^{S}}\) | The i th point projected on a subspace S |
N S | The neighbourhood of a point in a subspace S |
d i s t() | The distance function to find neighbourhood |
C | A cluster |
CS | A core set of density connected points within ε distance |
\(\mathcal {U}\) | A dense unit, \(|\mathcal {U}|=\tau +1\) |
1-D | One dimensional |
\(\mathcal {H}\) | Signature of a dense unit |
L | Large Integer |
K | A set of random large integers, |K|=n |
hTable | A hash table |