检索结果-南通市图书馆

FlowGANAnomaly: Flow-Based Anomaly Network Intrusion Detection with Adversarial Learning

Chinese Journal of Electronics 2024年第1期33卷 58-71页

作者： Zeyi LI pan WANG Zixuan WANG School of Computer Science Nanjing University of Posts and Telecommunications School of Modern Posts Nanjing University of Posts and Telecommunications School of Internet of Things Nanjing University of Posts and Telecommunications

In recent years, low recall rates and high dependencies on data labelling have become the biggest obstacle to developing deep anomaly detection(DAD) techniques. Inspired by the success of generative adversarial networks(GANs) in detecting anomalies in computer vision and imaging, we propose an anomaly detection model called Flow GANAnomaly for detecting anomalous traffic in network intrusion detection systems(NIDS). Unlike traditional GAN-based approaches, which are composed of a flow encoder, a convolutional encoder-decoder-encoder, a flow decoder and a convolutional encoder, the architecture of this model consists of a generator(G) and a discriminator(D).Flow GANAnomaly maps the different types of traffic feature data from separate datasets to a uniform feature space,thus can capture the normality of network traffic data more accurately in an adversarial manner to mitigate the problem of the high dependence on data labeling. Moreover, instead of simply detecting the anomalies by the output of D, we proposed a new anomaly scoring method that integrates the deviation between the output of two Gs’ convolutional encoders with the output of D as weighted scores to improve the low recall rate of anomaly detection. We conducted several experiments comparing existing machine learning algorithms and existing deep learning methods(Auto Encoder and VAE) on four public datasets(NSL-KDD, CIC-IDS2017, CIC-DDo S2019, and UNSW-NB15). The evaluation results show that Flow GANAnomaly can significantly improve the performance of anomaly-based NIDS.

关键词： Deep learning Machine learning algorithms Computational modeling Network intrusion detection Imaging Telecommunication traffic Generative adversarial networks

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Depth-Guided Vision Transformer With Normalizing Flows for Monocular 3D Object Detection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 673-689页

作者： Cong pan Junran Peng Zhaoxiang Zhang the Center for Research on Intelligent Perception and Computing(CRIPAC) National Laboratory of Pattern Recognition(NLPR)Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 the School of Future Technology University of Chinese Academy of Sciences(UCAS)Beijing 100049China the Huawei Inc. Beijing 100085China IEEE the Institute of Automation Chinese Academy of Sciences(CASIA)Beijing 100190 the University of Chinese Academy of Sciences(UCAS) Beijing 100049 the Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science&Innovation Chinese Academy of Sciences(HKISI CAS)Hong Kong 999077China

Monocular 3D object detection is challenging due to the lack of accurate depth *** methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB ***-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion ***,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with *** from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth *** we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each ***,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input *** method is the first Swin-Transformer-based backbone architecture for monocular 3D object *** experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.

关键词： Monocular 3D object detection normalizing flows Swin Transformer

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An Encoding-Decoding Framework Based on CNN for circ RNA-RBP Binding Sites Prediction

引用

Chinese Journal of Electronics 2024年第1期33卷 256-263页

作者： Yajing GUO Xiujuan LEI Yi pan School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Department of Computer Science Georgia State University

Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.

关键词： Proteins RNA Neural networks Encoding Robustness Decoding Convolutional neural networks

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

State-sensitive convolutional sparse coding for potential biomarker identification in brain signals

引用

Science China(Information Sciences) 2024年第5期67卷 270-286页

作者： Puli WANG Yu QI Gang pan College of Computer Science and Technology Zhejiang University State Key Laboratory of Brain-Machine Intelligence Zhejiang University MOE Frontier Science Center for Brain Science and Brain-machine Integration Zhejiang University Affiliated Mental Health Center & Hangzhou Seventh People's Hospital Zhejiang University School of Medicine

The identification of prototypical waveforms, such as sleep spindles and epileptic spikes, is crucial for the diagnosis of neurological disorders. These prototypical waveforms are usually recurrently presented in certain brain states, serving as potential biomarkers for clinical evaluations. Convolutional sparse coding(CSC) approaches have demonstrated strength in identifying recurrent patterns in time-series. However,existing CSC approaches do not explicitly explore state-specific patterns, making it difficult to identify state-related biomarkers. To address this problem, we propose state-sensitive CSC to learn state-specific prototypical waveforms. Specifically, we model signals of a certain state with specific waveforms that only appear frequently in this state and background waveforms that are independent of states. Based on this,state-sensitive CSC separates state-specific waveforms from background ones explicitly by incorporating incoherence constraints into optimizations. Experiments with epilepsy brain signals demonstrate that our approach can effectively identify prototypical waveforms in pre-ictal states, providing potential biomarkers for seizure prediction. Our approach provides a promising tool for automatic biomarker candidate identification.

关键词： convolutional sparse coding prototypical waveforms state-specific dictionary biomarker identification neural signal processing

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano friction behaviour between magnetic materials and copper considering the inter-diffusion effect

引用

Friction 2024年第7期12卷 1532-1547页

作者： Zilin LI Lisha DOU Shiyu YANG Huajiang OUYANG Qichen ZHU Xiaoyang CHEN Xin JIA Shuaiwei DOU Xiaolong cui Yudong ZHANG Jingjiang QIU Guochen QI Bangbang NIE pan LIU Ronghan WEI School of Mechanics and Safety Engineering Zhengzhou UniversityZhengzhou 450001China Engineering Technology Research Center of Henan Province for MEMS Manufacturing and Application Zhengzhou UniversityZhengzhou 450001China Institute of Intelligent Sensing Zhengzhou UniversityZhengzhou 450001China School of Engineering University of LiverpoolLiverpool L693GHUK School of Cyber Science and Engineering&Hanwei Institute of Internet of Things Zhengzhou UniversityZhengzhou 450001China

Copper,permalloy,cobalt,and silicon are the materials that have been widely utilised in magnetic *** the size of interest is down to the nanoscale,the inter-diffusion between certain materials becomes *** paper studies the nanoscale friction characteristics between frictional pairs with and without inter-diffusion properties through the atomic force *** distinct evolution features of nanoscale friction force when inter-diffusion is involved are discovered experimentally,which is also confirmed through theoretical ***,through the thin film deposition method,four pairs of contact materials(Cu–Ni_(81)Fe_(19),Si–Ni_(81)Fe_(19),Cu–Co,Cu–Si)are designed for friction tests,in which diffusion occurs at the interface of Cu–Ni_(81)Fe_(19)***,the effects of sliding velocity and loading force on the nano friction of each pair are *** is found that regardless of the diffusion phenomenon:(1)the adhesion force values exhibit a notable correlation to the values of the friction force;(2)the friction force in all four material pairs consistently increases with the growth of the normal loading force,although the growth rate may *** terms of the sliding velocity effect,the friction forces of immiscible materials(Si–Ni_(81)Fe_(19),Cu–Co,and Cu–Si)are found to increase with the increasing sliding ***,the friction force of Cu–Ni_(81)Fe_(19),decreases with the increasing sliding ***,a compositive friction model considering both the velocity and the normal force effect was proposed,which shows good agreement with the experimental results and explains the nano friction behaviour of both miscible and immiscible metals.

关键词： atomic force microscope friction force normal load sliding velocity

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A numerical simulation strategy for a compressor’s underlying axisymmetric characteristic and its application in body force model

引用

Chinese Journal of Aeronautics 2024年第8期37卷 79-90页

作者： Shijie LIU Tianyu pan Qiushi LI School of Energy and Power Engineering Beihang UniversityBeijing 100191China Research Institute of Aero-Engine Beihang UniversityBeijing 100191China Key Laboratory of Fluid and Power Machinery Ministry of EducationXihua UniversityChengdu 610039China

Accurate prediction of the aerodynamic response of a compressor under inlet distortion is crucial for next-generation civil aircraft,such as Boundary Layer Ingestion(BLI)silent ***,research on the Body Force(BF)model plays a significant role in achieving this ***,distorted inlet airflow can lead to varying operating conditions across different spatial locations of the compressor,which may cause some regions to operate outside the stability ***,the accuracy of BF model simulations might be *** address this issue,this paper proposes a numerical simulation strategy for acquiring the steady axisymmetric three-dimensional flow field of a compressor operating at low mass flow rates,which is known as the Underlying Axisymmetric Pressure Rise Characteristic(UAPRC).The proposed simulation accounts for two different rotor speeds of a transonic compressor and identifies initial positions in the flow field where deterioration occurs based on prior experimental ***,simulation results are incorporated into the BF model to replicate hub instability observed in *** results demonstrate that this strategy provides valid predictions of the UAPRC of the compressor,thereby addressing the limitations associated with the BF model.

关键词： Compressor partial instability Performance at low mass flow rates Underlying axisymmetric pressure rise characteristic Novel simulation strategy Body force model

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

2-local unstable homotopy groups of indecomposable A3～2-complexes

引用

Science China Mathematics 2024年第3期67卷 607-626页

作者： Zhongjian Zhu Jianzhong pan College of Mathematics and Physics Wenzhou University Hua Loo-Keng Key Laboratory of Mathematics Institute of MathematicsAcademy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematical Sciences University of Chinese Academy of Sciences

In this paper,we calculate the 2-local unstable homotopy groups of indecomposable A3～*** main technique used is analysing the homotopy property of J（A,X）,defined by Gray（1973） for a CW-pair（X,A）,which is homoto... 详细信息

关键词： homotopy groups A 2 n -complexes fibration sequence relative James construction 55P15

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Determination method of mesh size for numerical simulation of blast load in near-ground detonation

引用

Defence Technology（防务技术） 2024年第8期38卷 111-125页

作者： Doudou Si Zuanfeng pan Haipeng Zhang College of Civil Engineering Tongji UniversityShanghai 200092China State Key Lab of Disaster Reduction in Civil Engineering Tongji UniversityShanghai 200092China

In order to improve the overall resilience of the urban infrastructures, it is required to conduct blast resistant design for important building structures in the city. For complex terrain in the city, it is recommended to determine the blast load on the structures via numerical simulation. Since the mesh size of the numerical model highly depends on the explosion scenario, there is no generally applicable approach for the mesh size selection. An efficient method to determine the mesh size of the numerical model of near-ground detonation based on explosion scenarios is proposed in this study. The effect of mesh size on the propagation of blast wave under different explosive weights was studied, and the correlations between the mesh size effect and the charge weight or the scaled distance was described. Based on the principle of the finite element method and Hopkinson-Cranz scaling law, a mesh size measurement unit related to the explosive weight was proposed as the criterion for determining the mesh size in the numerical simulation. Finally, the applicability of the method proposed in this paper was verified by comparing the results from numerical simulation and the explosion tests and was verified in AUTODYN.

关键词： Blast load Mesh size effect Numerical simulation Scaled mesh size Verification

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Network analysis of the relationships between depressive symptoms and social participation activities among Chinese older adults and its implications for nursing

引用

International Journal of Nursing Sciences 2024年第4期11卷 465-472,I0002页

作者： Yebo Yu Hewei Min Wei pan ping Chen Xuxi Zhang Xinying Sun Department of Social Medicine and Health Education School of Public HealthPeking UniversityBeijingChina Center for Geriatric Health Research Peking UniversityBeijingChina

Objective:Network analysis was used to explore the complex inter-relationships between social participation activities and depressive symptoms among the Chinese older population,and the differences in network structures among different genders,age groups,and urban-rural residency would be ***:Based on the 2018 wave of the Chinese Longitudinal Healthy Longevity Survey(CLHLS),12,043 people aged 65 to 105 were *** 10-item Center for Epidemiologic Studies Depression(CESD)Scale was used to assess depressive symptoms and 10 types of social participation activities were collected,including housework,tai-chi,square dancing,visiting and interacting with friends,garden work,reading newspapers or books,raising domestic animals,playing cards or mahjong,watching TV or listening to radio,and organized social activities.R 4.2.1 software was used to estimate the network model and calculate strength and bridge ***:21.60%(2,601/12,043)of the participants had depressive *** total social participation score was negatively associated with depressive symptoms after adjusting for sociodemographic *** network of social participation and depressive symptoms showed that“D9(Inability to get going)”and“S9(Watching TV and/or listening to the radio)”had the highest strength within depressive symptoms and social participation communities,respectively,and“S1(Housework)”,“S9(Watching TV and/or listening to the radio)”,and“D5(Hopelessness)”were the most prominent bridging nodes between the two *** edges linking the two communities were negative.“S5(Graden work)-D5(Hopelessness)”and“S6(Reading newspapers/books)-D4(Everything was an effort)”were the top 2 strongest negative *** females had signiﬁcantly denser network structures than older *** to older people aged 65e80,the age group 81e105 showed higher network global ***:This study provides novel insights into the complex relationships between social

关键词： Depressive symptoms Network analysis Older adults Sex characteristics Social participation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Event-triggered predefined-time control for full-state constrained nonlinear systems: A novel command filtering error compensation method

引用

Science China(Technological Sciences) 2024年第9期67卷 2867-2880页

作者： pan YingNan CHEN YiLin LIANG HongJing College of Control Science and Engineering Bohai UniversityJinzhou 121013China School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing 100089China

In this paper, a command filter-based adaptive fuzzy predefined-time event-triggered tracking control problem is investigated for uncertain nonlinear systems with time-varying full-state constraints. By designing a sliding mode differentiator, the inherent computational complexity problem within the predefined-time backstepping framework is solved. Different from the existing command filter-based finite-time and fixed-time control strategies that the convergence time of the filtering error is adjusted through the system initial value or numerous parameters, a novel command filtering error compensation method is presented,which tunes one control parameter to make the filtering error converge in the predefined time, thereby reducing the complexity of design and analysis of processing the filtering error. Then, an improved event-triggered mechanism(ETM) that builds upon the switching threshold strategy, in which an inverse cotangent function is designed to replace the residual term of the ETM,is proposed to gradually release the controller's dependence on the residual term with increasing time. Furthermore, a tan-type nonlinear mapping technique is applied to tackle the time-varying full-state constraints problem. By the predefined-time stability theory, all signals in the uncertain nonlinear systems exhibit predefined-time stability. Finally, the feasibility of the proposed algorithm is substantiated through two simulation results.

关键词： predefined-time control command filtering error compensation method event-triggered mechanism time-varying full-state constraints uncertain nonlinear systems

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：