In the face of the effective popularity of the Internet of Things(IoT),but the frequent occurrence of cybersecurity incidents,various cybersecurity protection means have been proposed and applied.Among them,Intrusion ...In the face of the effective popularity of the Internet of Things(IoT),but the frequent occurrence of cybersecurity incidents,various cybersecurity protection means have been proposed and applied.Among them,Intrusion Detection System(IDS)has been proven to be stable and efficient.However,traditional intrusion detection methods have shortcomings such as lowdetection accuracy and inability to effectively identifymalicious attacks.To address the above problems,this paper fully considers the superiority of deep learning models in processing highdimensional data,and reasonable data type conversion methods can extract deep features and detect classification using advanced computer vision techniques to improve classification accuracy.TheMarkov TransformField(MTF)method is used to convert 1Dnetwork traffic data into 2D images,and then the converted 2D images are filtered by UnsharpMasking to enhance the image details by sharpening;to further improve the accuracy of data classification and detection,unlike using the existing high-performance baseline image classification models,a soft-voting integrated model,which integrates three deep learning models,MobileNet,VGGNet and ResNet,to finally obtain an effective IoT intrusion detection architecture:the MUS model.Four types of experiments are conducted on the publicly available intrusion detection dataset CICIDS2018 and the IoT network traffic dataset N_BaIoT,and the results demonstrate that the accuracy of attack traffic detection is greatly improved,which is not only applicable to the IoT intrusion detection environment,but also to different types of attacks and different network environments,which confirms the effectiveness of the work done.展开更多
In deep underground mining,achieving stable support for roadways along with long service life is critical and the complex geological environment at such depths frequently presents a major challenge.Owing to the coupli...In deep underground mining,achieving stable support for roadways along with long service life is critical and the complex geological environment at such depths frequently presents a major challenge.Owing to the coupling action of multiple factors such as deep high stress,adjacent faults,cross-layer design,weak lithology,broken surrounding rock,variable cross-sections,wide sections up to 9.9 m,and clusters of nearby chambers,there was severe deformation and breakdown in the No.10 intersection of the roadway of large-scale variable cross-section at the−760 m level in a coal mine.As there are insufcient examples in engineering methods pertaining to the geological environment described above,the numerical calculation model was oversimplifed and support theory underdeveloped;therefore,it is imperative to develop an efective support system for the stability and sustenance of deep roadways.In this study,a quantitative analysis of the geological environment of the roadway through feld observations,borehole-scoping,and ground stress testing is carried out to establish the FLAC 3D variable cross-section crossing roadway model.This model is combined with the strain softening constitutive(surrounding rock)and Mohr–Coulomb constitutive(other deep rock formations)models to construct a compression arch mechanical model for deep soft rock,based on the quadratic parabolic Mohr criterion.An integrated control technology of bolting and grouting that is mainly composed of a high-strength hollow grouting cable bolt equipped with modifed cement grouting materials and a high-elongation cable bolt is developed by analyzing the strengthening properties of the surrounding rock before and after bolting,based on the Heok-Brown criterion.As a result of on-site practice,the following conclusions are drawn:(1)The plastic zone of the roof of the cross roadway is approximately 6 m deep in this environment,the tectonic stress is nearly 30 MPa,and the surrounding rock is severely fractured.(2)The deformation of the roadway progressively increa展开更多
基金support and help from the People’s Armed Police Force of China Engineering University,College of Information Engineering Subject Group,which funded this work under the All-Army Military Theory Research Project,Armed Police Force Military Theory Research Project(WJJY22JL0498).
文摘In the face of the effective popularity of the Internet of Things(IoT),but the frequent occurrence of cybersecurity incidents,various cybersecurity protection means have been proposed and applied.Among them,Intrusion Detection System(IDS)has been proven to be stable and efficient.However,traditional intrusion detection methods have shortcomings such as lowdetection accuracy and inability to effectively identifymalicious attacks.To address the above problems,this paper fully considers the superiority of deep learning models in processing highdimensional data,and reasonable data type conversion methods can extract deep features and detect classification using advanced computer vision techniques to improve classification accuracy.TheMarkov TransformField(MTF)method is used to convert 1Dnetwork traffic data into 2D images,and then the converted 2D images are filtered by UnsharpMasking to enhance the image details by sharpening;to further improve the accuracy of data classification and detection,unlike using the existing high-performance baseline image classification models,a soft-voting integrated model,which integrates three deep learning models,MobileNet,VGGNet and ResNet,to finally obtain an effective IoT intrusion detection architecture:the MUS model.Four types of experiments are conducted on the publicly available intrusion detection dataset CICIDS2018 and the IoT network traffic dataset N_BaIoT,and the results demonstrate that the accuracy of attack traffic detection is greatly improved,which is not only applicable to the IoT intrusion detection environment,but also to different types of attacks and different network environments,which confirms the effectiveness of the work done.
基金supported by the National Natural Science Foundation of China(Grant Nos.52074296,52004286)the China Postdoctoral Science Foundation(Grant Nos.2020T130701,2019M650895).
文摘In deep underground mining,achieving stable support for roadways along with long service life is critical and the complex geological environment at such depths frequently presents a major challenge.Owing to the coupling action of multiple factors such as deep high stress,adjacent faults,cross-layer design,weak lithology,broken surrounding rock,variable cross-sections,wide sections up to 9.9 m,and clusters of nearby chambers,there was severe deformation and breakdown in the No.10 intersection of the roadway of large-scale variable cross-section at the−760 m level in a coal mine.As there are insufcient examples in engineering methods pertaining to the geological environment described above,the numerical calculation model was oversimplifed and support theory underdeveloped;therefore,it is imperative to develop an efective support system for the stability and sustenance of deep roadways.In this study,a quantitative analysis of the geological environment of the roadway through feld observations,borehole-scoping,and ground stress testing is carried out to establish the FLAC 3D variable cross-section crossing roadway model.This model is combined with the strain softening constitutive(surrounding rock)and Mohr–Coulomb constitutive(other deep rock formations)models to construct a compression arch mechanical model for deep soft rock,based on the quadratic parabolic Mohr criterion.An integrated control technology of bolting and grouting that is mainly composed of a high-strength hollow grouting cable bolt equipped with modifed cement grouting materials and a high-elongation cable bolt is developed by analyzing the strengthening properties of the surrounding rock before and after bolting,based on the Heok-Brown criterion.As a result of on-site practice,the following conclusions are drawn:(1)The plastic zone of the roof of the cross roadway is approximately 6 m deep in this environment,the tectonic stress is nearly 30 MPa,and the surrounding rock is severely fractured.(2)The deformation of the roadway progressively increa
基金supported by the National Natural Science Foundation China(52073121)the Science and Technology Program of Guangzhou(202102010117)+1 种基金the Fundamental Research Funds for the Central Universities(21622406)the Project Team of Foshan National Hi-tech Industrial Development Zone Industrialization Entrepreneurial Teams Program(2220197000129).
