Identifying cluster number for subspace projected functional data ...

tealackingΤεχνίτη Νοημοσύνη και Ρομποτική

8 Νοε 2013 (πριν από 3 χρόνια και 7 μήνες)

73 εμφανίσεις

國立中山大學應用數學系

Dept. of Applied Math.,
National Sun Yat
-
sen University

T
alk


Speaker

李百靈

教授

(
Pai
-
Ling Li
)

淡江大學統計



Title

Identifying cluster number for subspace projected
functional

data clustering

Time

201
2
/
0
4
/
12

Thurs
day
,
星期


1
4

1
0

~ 1
5

0
0

Place
:理學院
4
樓理
40
09
-
1

(
教室設備:

板、固定單槍、固定電腦
)

(Room 40
09
-
1
, Dept. of Applied Math, NSYSU)

Tea Time

1
5
:
0
0
~1
5
:
3
0
於理
4010


(
系辦公室
)


Abstract


We propose a new approach, the forward functional testing (FFT) procedure, to
cluster

number selection for functional data clustering. We present

a framework
of subspace

projected functional data clustering based on the functional
multiplicative random
-
effects

model, and propose to perform functional
hypothesis tests on equivalence of cluster

structures to identify the number of
clusters. The aim i
s to find the maximum number of

distinctive clusters while
retaining significant differences between cluster structures. The

null hypotheses
comprise equalities between the cluster mean functions and between the

sets of
cluster eigenfunctions of the covari
ance kernels. Bootstrap resampling methods
are

developed to construct reference distributions of the derived test statistics.
We compare

several other cluster number selection criteria, extended from
methods of multivariate

data, with the proposed FFT proc
edure. The
performance of the proposed approaches is

examined by simulation studies, with
applications to clustering gene expression profiles.



中山大學應用數學系







告!







加!

演講查詢

http://www.math.nsysu.edu.tw/seminar/semi.html

應用數學系

http://www.math.nsysu.edu.tw

校園立體圖

http://web.nsysu.edu.tw/files/11
-
1000
-
1503.php?Lang=zh
-
tw

交通查詢

http://www.nsysu.edu.tw/files/9
0
-
1000
-
7.php?Lang=zh
-
tw