Improved Instance Selection Methods for Support Vector Machine Speed Optimization

Table 6

Comparison between techniques.

Total email	Technique	APA (%)	GB	FP (%)	FN (%)	(%)	Pr (%)	FM (%)	(s)
4000	EISA	100	100	0.00	0.00	100	100	100	191.62
4000	Clustering	99.98	100	0.03	0.00	100	99.80	99.80	1438.39
4000	KNN	99.78	100	0.26	0.00	100	98.27	99.12	47.73
4000	FFA	99.55	100	0.26	1.80	98.20	98.29	98.13	45.94
4000	FFA_Clus	99.98	100	0.03	0.00	100	99.80	99.90	29.66
4000	SVM	99.98	100	0.02	0.00	100	99.86	99.93	2544.72

Key: GB: global best, APA: average prediction accuracy, FP: false positive, FN: false negative, : recall, Pr: precision, FM: -measure, and : time.