Distribution of RRG state vectors

k-means for time series with many bursts

---

Normal case

---

Pathological case

---

Second normal case

Comparison of k-means and agglomerative hierarchical clustering

---

Time series information

simulation time interval = 0.08
saving to file every: 10 iteration
sample size: 3156

---

Time series plot

---

k-means clustering

---

Agglomerative hierarchical clustering

Method: 'single' = Shortest distance.

Method: 'complete' = Furthest distance.

Method: 'average' = Unweighted average distance (UPGMA).

Method: 'centroid' = Centroid distance (UPGMC).

Method: 'ward' = Inner squared distance (minimum variance algorithm).