A Data Mining Classification Approach for Behavioral Malware Detection

Table 2

The statistical analysis of data set 2 for specified classification methods.

Algorithms	⁢Results
	Correctly Classified Instances; Number, %	Incorrectly Classified Instances; Number, %	Mean absolute error	Relative absolute error	Kappa statistic	Root mean squared error	Root relative squared error	Total number of instances
NaiveBayes	2678, 85.5318%	453, 14.4682%	0.012	15.3329%	0.8459	0.1026	51.8792%	3131
BayesNet	2874, 91.7918%	257, 8.2082%	0.0073	9.3575%	0.9127	0.0747	37.7504%	3131
IB1	3028, 96.7103%	103, 3.2897%	0.0027	3.5032%	0.965	0.0524	26.472%	3131
J48	3008, 96.0715%	123, 3.9285%	0.0043	5.5353%	0.9581	0.0527	26.652%	3131
Regression	3069, 98.321%	62, 1.679%	0.0021	2.2102%	0.9578	0.0543	27.4333%	3131
SVM	1698, 54.2319%	1433, 45.7681%	0.0046	5.7993%	0.5011	0.1942	98.1954	3131