A Hybrid Method Based on Extreme Learning Machine and Self Organizing Map for Pattern Classification

Figure 5

Box plots depicting the performance of training algorithms. Accuracy value variation of the (a) Ionosphere dataset, (b) Iris dataset, (c) Wine dataset, (d) Balance dataset, (e) Zoo dataset, (f) Image segmentation dataset, (g) Ecoli dataset, (h) Multiple features dataset, and (i) Jaffe dataset.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)

(i)