|
Results page
1,
2
After each iteration of the code,
a single-line forewarning summary is given detailing attributes of
the run such as the parameter set values, true
positives & true negatives, the total true rate, etc.. For
example,
A standard forewarning summary would be written
as,
1 189
19640 2 3 28 0 10 1
6 5 0.826 0.9167 5
0
Isolating each value,
|
a |
b |
c |
d |
e |
f |
g |
h |
i |
j |
k |
l |
m |
n |
p |
|
1 |
189 |
19640 |
2 |
3 |
28 |
0 |
10 |
1 |
6 |
5 |
0.826 |
0.9167 |
5 |
0 |
Where,
a = montage (0 = monopolar, 1 =
bipolar)
b =
half
width of the artifact
filter (w)
c =
#
pts per cutset
d = # of dimensions
in
the
PS*
e =
#
symbols
(S)
f =
time-delay lag (lamda) g =
uE
(0=
uniform,
1 = equiprobable) h =
# of basecase cutsets
i = inter-PS*-symbol
lag
j = # DM*
above threshold within successive occurence
window
k =
# successive occurences above
threshold
l =
threshold
m =
total true
rate (%) n =
# false negatives p =
# false positives
*PS-
phase-space, DM- dissimilairity measures
Through analysis of the
forewarning summaries, it was possible to shrink the parameter space by
graphing the total true rate versus each parameter. By
doing so, a visible parameter value region is shown and it's
possible to see which values generate the higher total
true rates.
|
