abline(h = 0, lty = "dotted")
abline(v = 0, lty = "dotted")
# Step 3: representation of fuzzy clusters
for (i in 1:k) {
gg <- dc.scores[spefuz.g == i, ]
hpts <- chull(gg)
hpts <- c(hpts, hpts[1])
lines(gg[hpts, ], col = i + 1)
}
stars(
spe.fuz$membership,
location = dc.scores,
key.loc = c(0.6, 0.4),
key.labels = 1:k,
draw.segments = TRUE,
add = TRUE,
# scale = FALSE,
len = 0.075,
col.segments = 2:(k + 1)
)
25
24
23
20
26
30
28
27
29
22
21
19
10
15
5
18
9
16
17
6
1
14
4
11
13
7
12
3
2
Silhouette width s i
0.0
0.2
0.4
0.6
0.8
1.0
Silhouette plot - Fuzzy clustering
Average silhouette width : 0.34
n = 29
4 clusters C j
j : n j | ave i Cj s i
1 : 10 | 0.39
2 : 8 | 0.02
3 : 8 | 0.60
4 : 3 | 0.34
Fig. 4.35 Silhouette plot of the c-means fuzzy clustering of the fish data preserving the chord
distance
4.15 A Very Different Approach: Fuzzy Clustering
143