Journal of Cloud Computing

Advances, Systems and Applications

Table 2 Normal and Anomaly classification experimental results

From: An efficient quality of services based wireless sensor network for anomaly detection using soft computing approaches

Algorithms	Train ACC%	Train Loss	Test ACC%	Test Loss
Proposed+LR	91.32	0.16	91.88	0.21
Proposed+KNN	93.76	0.13	93.21	0.15
Proposed+SVM	95.30	0.11	95.81	0.10
Confusion Metric
Algorithms	TP	FP	FN	TN
Proposed+LR	19942	1022	563	22112
Proposed+KNN	19989	1154	512	22367
Proposed+SVM	20098	1354	443	22661
Classification Report
Algorithms	Class Labels	Precision	Recall	F1 Score
Proposed+LR	Normal Class	91.00	91.50	92.00
	Anomaly Class	91.65	91.73	92.11
Proposed+KNN	Normal Class	92.54	92.89	93.12
	Anomaly Class	92.99	93.11	93.34
Proposed+SVM	Normal Class	94.00	98.00	96.00
	Anomaly Class	98.00	94.00	96.00

Back to article page