Protein Sequence Classification with Improved Extreme Learning Machine Algorithms

Table 2

Training time comparisons of different classifiers: fixed protein sequence training dataset (pir1) and testing dataset (pir2), where L, S, and G stand for the linear kernel, the sigmoid kernel, and the Gaussian kernel, respectively.

Methods	L		S		G
	Training time (s)	Speedup	Training time (s)	Speedup	Training time (s)	Speedup
VOP-ELM	5.5685	105.4	86.80	13.37	95.22	13.93
V-ELM	0.4590	1279.3	0.9020	1286.14	0.8680	1528.34
OP-ELM	1.8588	315.90	30.11	38.53	30.45	43.57
SVM	236.16	2.486	236.67	4.90	243.10	5.46
BP	587.20	1	1160.1	1	1326.6	1
ELM	0.0612	9594.8	0.0799	14519	0.0792	16750