Search

For a better detection in Network information security monitoring system, the author proposes a method based on adaptive depth detection. A deep belief network (DBN) was designed and implemented, and the intrusion detection system model was combined with a support vector machine (SVM). The data set adopts the NSL-KDD network communication data set, and this data set is authoritative in the security field. Redundant cleaning, data type conversion, normalization, and other processing operations are performed on the data set. Using the data conversion method based on the probability mass function probability mass function coding, a standard data set with low redundancy and low dimensionality can be obtained. Research indicates that when the batch size reaches 64, the accuracy of the test set reaches its maximum value. As the batch size increases, the accuracy first increases and then decreases. When the batch size continues to increase, the model will inevitably fall into the local optimal state, resulting in the degradation of the detection performance of the system. In terms of the false alarm rate, the DBN-SVM model is also the highest; however, it is only 10.73%. Under the premise of increasing the detection rate, the false alarm rate is improved; for the overall detection performance of the model, it is within an acceptable range. In terms of accuracy, the DBN-SVM model also scored the highest. The accuracy rate is the ratio of normal and correct classification for intrusion detection. It can explain the detection ability of the model. In summary, the overall detection ability of the DBN-SVM model is the best. The good classification ability to use SVM is proved, and the classification of low-dimensional features is expected to increase the detection rate of the system.

Due to the complexity and versatility of network security alarm data, a cloud-based network security data extraction method is proposed to address the inability to effectively understand the network security situation. The information properties of the situation are generated by creating a set of spatial characteristics classification of network security knowledge, which is then used to analyze and optimize the processing of hybrid network security situation information using cloud computing technology and co-filtering technology. Knowledge and information about the security situation of a hybrid network has been analyzed using cloud computing strategy. The simulation results show that a cyber security crash occurs in window 20, after which the protection index drops to window 500. The increase in the security index of 500 windows is consistent with the effectiveness of the concept of this document method, indicating that this document method can sense changes in the network security situation. Starting from the first attacked window, the defense index began to decrease. In order to simulate the added network defense, the network security events in the 295th time window were reduced in the original data, and the defense index increased significantly in the corresponding time period, which is consistent with the method perception results, which further verifies the effectiveness and reliability of this method on the network security event perception. This method provides high-precision knowledge of network security situations and improves the security and stability of cloud-based networks.

This research concerns examining the non-Newtonian blood flow behavior through an artery of elliptic cross-section, affected by several stenoses. The Rabinowitsch fluid model is used to investigate the non-Newtonian behavior of the blood for uniform and nonuniform shapes of stenosis. The mathematical equations have been converted into a dimensionless form, and their nonlinearity is reduced by applying the assumptions of mild stenosis. The resulting differential equations are solved by using analytical techniques. A new polynomial of degree eight is introduced to complete the solutions of mathematical equations. The entropy generation is studied mathematically to analyze the irreversibility effects. The detailed graphical examination delineates the physical aspects of mathematical results. The flow velocity is higher for uniform shape than for nonuniform stenosis. The rising percentage of stenosis significantly enhances the flow velocity of the stenotic region. The entropy is enormous near the stenotic wall and has small values near the centerline, which assures the smooth flow in this region. Further, the streamlines are plotted to find the position of stenosis and assess the flow nature for the growing height of stenosis and rising flow rate. [ABSTRACT FROM AUTHOR]

This novel study unfolds the heat and mass transfer investigation of Williamson nanofluid (WNF) through a porous medium past a stretching plate, along with considering heat generation/absorption. Nanoparticles hold significant significance in thermal engineering, industrial operations, and biomedical advancements, contributing to enhanced heat transfer, cooling mechanisms, thermal extrusion processes, and applications in cancer treatment, particularly in addressing brain tumors. The coupled ordinary differential equations (ODEs) are gained from governing partial differential equations (PDEs) by applying sufficient transformations. Then the ODEs of a nonlinear nature, along with boundary conditions, are solved through bvp4c, a built-in MATLAB program. A good agreement has been found in comparing the present study with already published papers. Numerical values for skin friction, mass transfer, and heat transfer are shown through a table against involved physical parameters, especially for both injection (S < 0) and suction (S > 0) cases, by varying the values of unsteadiness parameter A and Weissenberg number W e . The effects of the physical parameters on velocity, temperature, and mass profile are graphically depicted and illustrated minutely. It is noted that both the magnetic and Williamson parameters cause the thickness of the boundary layer to be reduced. It can be deduced from these findings that the rate of heat transfer over the surface of the plate decreases as the unsteadiness parameter increases. Furthermore, it is observed that an increase in the parameters of thermophoresis and Brownian motion leads to a higher temperature of the nanofluid. [ABSTRACT FROM AUTHOR]

This research seeks to explore the behavior of Ree–Eyring nanofluid over an extended surface influenced by an inclined magnetic field within a permeable medium. The local thermal non‐equilibrium between the particle, liquid, and solid phases is represented by a three‐temperature model. The problem is addressed numerically using bvp4c code in MATLAB software. The findings are displayed in the format of tables and graphs. The study shows that higher values of the interface heat transfer parameter led to a decrease and increase in the fluid phase and solid phase Nusselt number, respectively. The velocity and concentration distributions decrease with increasing porosity coefficient. Nevertheless, the fluid phase temperature distribution shows an opposing trend. Furthermore, increasing the non‐Newtonian fluid parameter leads to a raise in the surface drag coefficient. [ABSTRACT FROM AUTHOR]

Foreign object debris (FOD) includes any unwanted and unintentional material lying on the charging lane or parking lots, posing a risk to the wireless charging system, the vehicle, or the people inside. FOD in an Electric Vehicle (EV) wireless charging system can cause problems, including decreased charging efficiency, safety risks, charging system damage, communication issues, and health risks. To address this problem, this paper proposes the deep learning object detection network approach of using YOLOv4 (You Only Look Once), which is a single-shot detector. Additionally, for real-time implementation, YOLOv4-Tiny is suggested, which is a compressed version of YOLOv4 designed for devices with low computational power. YOLOv4-Tiny enables faster inferences and facilitates the deployment of FOD detectors on edge devices. The algorithm is trained using the FOD dataset, consisting of images of common debris on runways or taxiways. Furthermore, utilizing the concept of transfer learning, the last few layers of the pre-trained YOLOv4 model are modified using the COCO (Common Objects in Context) dataset to transfer features to the new network and retrain the model on the FOD dataset. The results obtained using this YOLOv4 model yielded a precision rate of 99.05%, while the results from YOLOv4-Tiny achieved a precision rate of 97.74%, with an average inference time of 150 ms under the ambient light and weather conditions. [ABSTRACT FROM AUTHOR]