Research on unsupervised anomaly data detection method based on improved automatic encoder and Gaussian mixture model

Journal of Cloud Computing

Advances, Systems and Applications

Table 4 Comparison of the results of each anomaly detection algorithm under the NSL-KDD dataset

Dataset	Models	Accuracy	Precision	Recall	F-score
NSL-KDD	Multi-level SVM	0.9575	0.9311	0.9517	0.9413
	K-means	0.8944	0.8008	0.7515	0.7754
	Autoencoder	0.9170	0.8745	0.8468	0.8605
	DAGMM	0.8985	0.9214	0.7560	0.8305
	MemAE	0.9636	0.9627	0.9655	0.9641
	CAE-GMM	0.9682	0.9532	0.9578	0.9555
	Model of this paper	0.9987	0.9964	1.0000	0.9982