www-ai.cs.tu-dortmund.de/LEHRE/FACHPROJEKT/SS12/paper/clustering/aggarwal2003.pdf
pap.dvi
55 —54 53 —52 51 1 54 —52 50 —48 46 2 52 —48 44 —40 36 3 —48 40 —32 24 —16 4 48 —32 16 5 32
Table 1: An example of snapshots stored for α = 2 and l = 2
(2+1) · log2(100∗365∗24∗60∗60) ≈ 95. This is quite [...] exactly the same reason.
Property 2 Let C1 and C2 be two sets of points such that C1 ⊇ C2. Then, the cluster feature vector
CFT (C1 − C2) is given by CFT (C1) − CFT (C2)
The subtractive property helps [...] points Xi1 . . . Xin
with time stamps
Ti1 . . . Tin is defined as the (2 · d + 3) tuple
(CF2x, CF1x, CF2t, CF1t, n), wherein CF2x and
CF1x each correspond to a vector of d entries. The definition of each …
