mRMR-ABC: A Hybrid Gene Selection Algorithm for Cancer Classification Using Microarray Gene Expression Profiling

Table 5

Comparison between mRMR-ABC and ABC algorithms classification performance when applied with the SVM classifier for colon dataset.

Number of genes	Classification accuracy
	mRMR-ABC			ABC
	Best	Mean	Worst	Best	Mean	Worst
3	88.71%	87.50%	85.48%	87.10%	85.91%	83.87%
4	90.23%	88.27%	87.10%	87.10%	86.71%	85.48%
5	91.94%	89.50%	87.10%	90.32%	87.98%	85.48%
6	91.94%	90.12%	87.10%	90.32%	88.44%	85.48%
7	993.55%	91.64%	88.81%	91.94%	90.20%	88.81%
8	93.55%	91.80%	88.81%	91.94%	90.61%	88.81%
9	93.55%	92.11%	90.16%	91.94%	90.95%	88.81%
10	93.55%	92.74%	90.16%	93.55%	91.31%	88.81%
15	96.77%	93.60%	91.93%	93.55%	91.38%	90.32%
20	96.77%	94.17%	91.93%	95.61%	92.44%	90.32%