In order to improve the accuracy of detecting the new P2P(peer-to-peer)botnet,a novel P2P botnet detection method based on the network behavior features and Dezert-Smarandache theory is proposed.It focuses on the netw...In order to improve the accuracy of detecting the new P2P(peer-to-peer)botnet,a novel P2P botnet detection method based on the network behavior features and Dezert-Smarandache theory is proposed.It focuses on the network behavior features,which are the essential abnormal features of the P2P botnet and do not change with the network topology,the network protocol or the network attack type launched by the P2P botnet.First,the network behavior features are accurately described by the local singularity and the information entropy theory.Then,two detection results are acquired by using the Kalman filter to detect the anomalies of the above two features.Finally,the above two detection results are fused with the Dezert-Smarandache theory to obtain the final detection results.The experimental results demonstrate that the proposed method can effectively detect the new P2P botnet and that it considerably outperforms other methods at a lower degree of false negative rate and false positive rate,and the false negative rate and the false positive rate can reach 0.09 and 0.12,respectively.展开更多
Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagno...Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagnosis, we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature, at high rotation speed, or under high pressure. Thus, there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper, we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances, and propose deep belief networks based on information entropy, IE-DBNs, for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second, the deep belief networks （DBNs） is analyzed and a logistic regression layer is added to the output of the DBNs. Then, information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.展开更多
基金The National High Technology Research and Development Program of China(863 Program)(No.2011AA7031024G)the National Natural Science Foundation of China(No.61133011,61373053,61472161)
文摘In order to improve the accuracy of detecting the new P2P(peer-to-peer)botnet,a novel P2P botnet detection method based on the network behavior features and Dezert-Smarandache theory is proposed.It focuses on the network behavior features,which are the essential abnormal features of the P2P botnet and do not change with the network topology,the network protocol or the network attack type launched by the P2P botnet.First,the network behavior features are accurately described by the local singularity and the information entropy theory.Then,two detection results are acquired by using the Kalman filter to detect the anomalies of the above two features.Finally,the above two detection results are fused with the Dezert-Smarandache theory to obtain the final detection results.The experimental results demonstrate that the proposed method can effectively detect the new P2P botnet and that it considerably outperforms other methods at a lower degree of false negative rate and false positive rate,and the false negative rate and the false positive rate can reach 0.09 and 0.12,respectively.
文摘Precise fault diagnosis is an important part of prognostics and health management. It can avoid accidents, extend the service life of the machine, and also reduce maintenance costs. For gas turbine engine fault diagnosis, we cannot install too many sensors in the engine because the operating environment of the engine is harsh and the sensors will not work in high temperature, at high rotation speed, or under high pressure. Thus, there is not enough sensory data from the working engine to diagnose potential failures using existing approaches. In this paper, we consider the problem of engine fault diagnosis using finite sensory data under complicated circumstances, and propose deep belief networks based on information entropy, IE-DBNs, for engine fault diagnosis. We first introduce several information entropies and propose joint complexity entropy based on single signal entropy. Second, the deep belief networks （DBNs） is analyzed and a logistic regression layer is added to the output of the DBNs. Then, information entropy is used in fault diagnosis and as the input for the DBNs. Comparison between the proposed IE-DBNs method and state-of-the-art machine learning approaches shows that the IE-DBNs method achieves higher accuracy.
