The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks.
Magnetoelectric multiferroics in which ferroelectricity and magnetism coexist have attracted extensive attention because they provide great opportunities for the mutual control of electric polarization by magnetic fields and magnetization by electric fields. From a practical point view, the main challenge in this field is to find proper multiferroic materials with a high operating temperature and great magnetoelectric sensitivity. Here we report on the magnetically tunable ferroelectricity and the giant magnetoelectric sensitivity up to 250 K in a Y-type hexaferrite, BaSrCoZnFe 11 AlO 22 . Not only the magnitude but also the sign of electric polarization can be effectively controlled by applying low magnetic fields (a few hundreds of Oe) that modifies the spiral magnetic structures. The magnetically induced ferroelectricity is stabilized even in zero magnetic field. Decayless reproducible flipping of electric polarization by oscillating low magnetic fields is shown. The maximum linear magnetoelectric coefficient reaches a high value of ~ 3.0×10 3 ps/m at 200 K.In the past several years, spiral magnetic order induced multiferroics and magnetoelectric (ME) effects have been observed in a number of transition metal oxides such as TbMnO 3 , RMn 2 O 5 , CoCr 2 O 4 , and others [1][2][3] . In these spiral magnets, the magnetic order and ferroelectricity are inherently coupled and thus pronounced ME effects could be expected. 4,5 The microscopic mechanism has been well described with the spin current model 6 or the inverse Dzyaloshinskii-Moriya (DM) interaction model 7 . However, the ME effects in these spiral magnets are not useful for practical applications because they occur at low temperatures and require a large magnetic field of several tesla. Recently, the hexaferrites with helical spin order have been suggested as promising candidates for high temperature multiferroics. It was reported that some Y-type hexaferrites, such as (Ba,Sr) 2 Zn 2 Fe 12 O 22 and Ba 2 Mg 2 Fe 12 O 22 , can show magnetically induced ferroelectricity and pronounced ME effects due to modifications of spiral magnetic structures by applying magnetic fields [8][9][10][11] . Although the magnetic ordering temperatures of these Y-type hexaferrites are above room temperature, their ME effects are observable only below ~ 130 K. Subsequently, ME effects were also observed in Z-type 12,13 , M-type 14 , and U-type 15 hexaferrites.Especially, the low field ME effect in a Z-type hexaferrite, Sr 3 Co 2 Fe 24 O 41 , happens at room temperature, representing a big step towards practical applications 12. Nevertheless, there are still some critical problems to be overcome. For instance, although magnetic control of electric polarization at room temperature has been achieved, the reversal of electric polarization by magnetic fields has been realized only at low temperatures 10,11,14 . We prepared the Y-type hexaferrites by solid state reaction in oxygen. The as-sintered samples are not insulating enough at high temperatures, and thus a post-annealing...
Graph sampling with noise is a fundamental problem in graph signal processing (GSP). Previous works assume an unbiased least square (LS) signal reconstruction scheme and select samples greedily via expensive extreme eigenvector computation. A popular biased scheme using graph Laplacian regularization (GLR) solves a system of linear equations for its reconstruction. Assuming this GLR-based scheme, we propose a reconstruction-cognizant sampling strategy to maximize the numerical stability of the linear system-i.e., minimize the condition number of the coefficient matrix. Specifically, we maximize the eigenvalue lower bounds of the matrix, represented by left-ends of Gershgorin discs of the coefficient matrix. To accomplish this efficiently, we propose an iterative algorithm to traverse the graph nodes via Breadth First Search (BFS) and align the leftends of all corresponding Gershgorin discs at lower-bound threshold T using two basic operations: disc shifting and scaling. We then perform binary search to maximize T given a sample budget K. Experiments on real graph data show that the proposed algorithm can effectively promote large eigenvalue lower bounds, and the reconstruction MSE is the same or smaller than existing sampling methods for different budget K at much lower complexity.
Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph signal compression and denoising. Previous graph learning algorithms either i) make assumptions on graph connectivity (e.g., graph sparsity), or ii) make edge weight assumptions such as positive edges only. In this paper, given an empirical covariance matrixC computed from data as input, we consider an eigen-structural assumption on the graph Laplacian matrix L: the first K eigenvectors of L are pre-selected,
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.