检索结果-内蒙古大学图书馆

4th IEEE International Conference on Electronics and communication Engineering, ICECE 2021

作者： Li, Xiaole Zhang, Cuiping Sun, Jian Zhang, Wensheng Wang, Cheng-Xiang Shandong Provincial Key Lab of Wireless Communication Technologies School of Information Science and Engineering Shandong University Qingdao China Shandong Provincial Key Lab of Wireless Communication Technologies Shandong University Qingdao China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Nanjing University of Aeronautics and Astronautics Nanjing China National Mobile Communications Research Laboratory School of Information Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories Nanjing China

ISBN: (纸本)9781728194226

Indoor hot spots is a major deployment scenario of the fifth generation (5G) network. In the indoor scenario, the radio wave propagation characteristics of underground garages are still not fully understood. In addition, Sub-6 GHz band is the main frequency band used in domestic 5G networks recently. This paper mainly uses ray tracing to study the wireless channel characteristics in the scenario of underground garage under Sub-6 GHz frequency band. Firstly, a three-dimensional (3D) simulation scenario is built, and the channel simulation is carried out at 3.5 GHz frequency band. According to the simulation data, the results shows that the path loss index is smaller than that in the 3GPP indoor scenario. Then, the channel data of Sub-6 GHz continuous frequency band is simulated at 500 MHz interval, the influence of material properties on channel characteristics is studied. We find that the path loss increases while the distance between the transmitter (Tx) and receiver (Rx) increases, and the change is obvious at a long distance with increasing frequency. ©2021 IEEE

关键词： Ray tracing

来源：评论

学校读者我要写书评

暂无评论

Pyramid Pooling-based Local Profiles for Graph Classification

Pyramid Pooling-based Local Profiles for Graph Classificatio...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Chengpei Wu Yang Lou Junli Li College of Computer Science Sichuan Normal University Chengdu China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate School of Information Science and Technology Osaka University Osaka Japan

Many natural and engineering systems can be modeled and represented in the forms of graph data, and then studied using graph theory and network analysis tools. Graph representation learning aims at generating lower-dimensional representations from higher-dimensional graph data, which is a crucial step that facilitates the follow-up tasks, such as node and graph classifications. In this paper, we present a simple but effective graph representation learning method, namely the pyramid pooling-based local profile (PPLP), which enables local nodal profiles to be transformed into a graph representation, with multi-scale features extracted. PPLP can be either embedded into a graph neural network as the readout layer, or perform independently as a graph embedding algorithm. The resultant representations of PPLP are for graph-level tasks. PPLP is experimentally tested by performing graph classification tasks on ten representative datasets, either as the readout layer of different graph neural networks, or as an independent graph embedding algorithm. Experimental results demonstrate that: 1) when embedded into graph neural networks, PPLP outperforms the widely-used global pooling-based readout methods; 2) as an independent graph embedding algorithm, PPLP performs fairly good, especially on the social network datasets. The investigation confirms PPLP as a simple but promising method for graph-level tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Image Feature Extraction 21

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Im...

引用

Proceedings of the 2021 5th International Conference on Video and Image Processing

作者： Sheng Ji Qijun Gu Ye Yuan Peng Zhao Tao Fang Hong Huo Xin Niu Department of Automation_School of Electronic Information and Electrical Engineering_Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University China College of Computer Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology China

ISBN: (纸本)9781450385893

SNNs have achieved great attention in recent years as they contain neurons more like those in the brain and use spikes to encode and transmit information efficiently among neurons with lower energy consumption. A Retina-LGN-V1 structure-like spiking neuron network (RLVSL-SNN) is proposed in this paper. It is inspired by the structure of mammalian primary visual pathway, and simulates different biological structures of Retina, LGN and V1. Noise reduction circuit and light adaptation circuit are also simulated for enhancing the robustness of its extracted features. RLVSL-SNN is a bio-plausible neuron network as it has firing rates of neurons in each layer that are similar to those of biological experiments. Besides, a full-connected SNN (FC SNN) is implemented following RLVSL-SNN for classification to evaluate the extracted features. The additive spiking timing dependent plasticity (STDP) learning rules and the ANN-to-SNN conversion method are utilized to train RLVSL-SNN and FC SNN, respectively. The experiments on MNIST dataset have verified that RLVSL-SNN is comparable to AlexNet for classification by features from spikes.

关键词： Additive Spiking Timing Dependent Plasticity Learning Primary Visual Pathway Image Classification Spiking Neural Network

来源：评论

学校读者我要写书评

暂无评论

Emission Evaluation for Diesel Vehicles Under Typical Operating Conditions

Emission Evaluation for Diesel Vehicles Under Typical Operat...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiaren Li Zhenyi Xu Yang Cao Xiushan Xia Yu Kang AHU-IAI AI Joint Laboratory Anhui University Hefei China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Department of Automation University of Science and Technology of China Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei China

China‘s ambient air quality has improved significantly as a result of the formulation and implementation of the Action Plan for the Prevention and control of Air Pollution and the Three-Year Action Plan for Winning the Blue Sky Defense War, but the air pollution problem in key regions remains severe, diesel truck pollution has not been effectively addressed, and mobile sources are an important source of nitrogen oxide emissions. The existing diesel vehicle emission model is primarily divided based on average vehicle speed and VSP binning methods, and it lacks an instantaneous vehicle speed model. This paper collected data from 10 diesel vehicles in order to accurately evaluate driving conditions and promote energy saving and emission reduction of heavy-duty diesel vehicles. Then we extracted 51,925 kinematic fragment data after cleaning abnormal data and built a kinematic feature evaluation system of diesel vehicles closely related to NOx emission. The sample data of kinematic segments were clustered into two groups of low-speed conditions and medium-speed conditions using the standardized mutual information to extract the characteristics with strong correlation with NOx and the vehicle driving conditions assessment model of cluster analysis. From the clustering results, the high NOx emission is completely classified into the low-speed working condition, which matches the conclusion that the high NOx emission region appears in the low-speed acceleration region reached by previous researchers through experimental studies, indicating that the kinematic feature evaluation model of diesel vehicles established in this paper is reasonable and effective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Cruise control of Virtual Coupled High-Speed Trains

Adaptive Cruise Control of Virtual Coupled High-Speed Trains

引用

2021 China Automation Congress, CAC 2021

作者： Wang, Di Cao, Yuan Su, Shuai State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Beijing China School of Electric and Information Engineering Beijing Jiaotong University Beijing China Frontiers Science Center for Smart High-speed Railway System State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

ISBN: (纸本)9781665426473

The adaptive cruise formation control problem for multiple high-speed trains (MHSTs) with input, speed and minimum tracking distance constraints under virtual coupling (VC) is proposed in this paper. First, the dynamic equation of MHSTs is created based on the law of kinematics. The communication topology is modeled by graph theory. Next, the speed limit, minimum tracking distance with adjacent trains are dealt with by using the ideas of the potential function. The resistance and unknown disturbances are dealt with by using adaptive control. Then, a cruise control protocol for MHSTs to track the expected trajectory is designed. The Lyapunov theory is used to prove the system stability. Finally, numerical experiments are conducted, which illustrates that the control protocol is effective. © 2021 IEEE

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

LuTan-1: An Innovative L-band Spaceborne Bistatic Interferometric SAR Mission 15

LuTan-1: An Innovative L-band Spaceborne Bistatic Interferom...

引用

15th European Conference on Synthetic Aperture Radar, EUSAR 2024

作者： Wang, Robert Liu, Kaiyu Cai, Yonghua Liang, Da Yu, Wei Liu, Dacheng Chen, Yafeng Yang, Qingyue Li, JunFeng Liu, Lizhi National Key Laboratory of Microwave Imaging Technology Aerospace Information Research Institute Chinese Academy of Sciences No. 19 North Fourth Ring West Road Haidian District Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences No. 1 Yanqihu East Road Huairou District Beijing China Department of Space Microwave Remote Sensing System Aerospace Information Research Institute Chinese Academy of Sciences No. 19 North Fourth Ring West Road Haidian District Beijing China College of Marine Technology Ocean University of China No. 238 Songling Road Laoshan District Qingdao China 14th Research Institute of China Electronics Technology Group Corporation No. 8 Guorui Road Yuhuatai District Nanjing China

ISBN: (纸本)9783800762873

LuTan-1 is an innovative L-Band spaceborne bistatic interferometric SAR mission, aimed at monitoring surface deformations and acquiring highly accurate DEMs. In phase I, two satellites fly in a close helix formation for DEM generation using InSAR. In phase II, two satellites share the common reference orbit with a 180-degree orbital phase difference for differential interferometric applications. Up to now, the first phase of LuTan-1 has successfully completed. In this paper, the processing flowchart along with several results during phase I are demonstrated. In the following lifetime, LuTan-1 will continually provide observation data of high quality for Earth observation. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Event-triggered model predictive control for cyber-physical system under false data injection attacks

Event-triggered model predictive control for cyber-physical ...

引用

第33届中国过程控制会议

作者： Bin Zhang Zhiwen Wang Yanrong Lu Long Li College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Gansu Advanced Control for Industrial Processes Lanzhou University of Technology National Demonstration Center for Experimental Electrical and Control Engineering Education Lanzhou University of Technology GS-Unis Intelligent Transportation System&Control Technology Co. Ltd.

In this paper,an event-triggered model predictive control strategy is proposed for cyber-physical systems under the perception of false data injection *** on attack perception,two different event-triggered mechanisms are designed for the sensor-to-controller channel and the controller-to-actuator *** the sensor-to-controller channel,the event-triggered strategy 1 effectively reduces the network bandwidth pressure caused by the sensor *** the controller-actuator channel,the event-triggered model predictive control strategy effectively compensates for the adverse effects of signal data loss or unavailability of signal data caused by spurious data injection ***,the simulation of the networked first-order inverted pendulum model shows the effectiveness of the proposed methods.

关键词： Cyber-physical systems False data injection attacks Event-triggered mechanism Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Building-level Day Ahead Power Load Forecasting Based on Gated Recurrent Unit Networks

A Hybrid Model for Building-level Day Ahead Power Load Forec...

引用

2021 IEEE Sustainable Power and Energy Conference, iSPEC 2021

作者： Zhang, Hualu Deng, Boya Shi, Jie Northeast Electric Power University Jilin Key Laboratory of Modern Power System Simulation Control and Green Power New Technology Ministry of Education Jilin China Nanjing Nanrui Information Communication Technology Co. Ltd. Nari Group Corporation State Grid Electric Power Research Institute Nanjing China

ISBN: (纸本)9781665414395

Accurate forecasting of day-ahead electrical load is a key to optimize the operation of the integrated energy system (IES) and a fundamental function of the cyber-physical system (CPS) of IES. Due to the characteristics of different features, data collected by CPS often have different sampling frequencies, resulting in mining data trends inadequately when making a load forecast. This paper proposes an GRU-based model to combine historical data with different sampling frequencies in forecasting day-ahead building-level load. First, day-level features are clustered by K-means. Hour-levels features are then partitioned according to clustering results and inputted separately into a gated recurrent unit (GRU) based neural network to capture relationships between external features and load fluctuations. The temporal dependencies of minute-level data are captured by the GRU network directly without any external features. Finally, the least square method is used to combine forecasting results at each hour of two models. The simulation results present that the proposed model performs better than a single model when applying to real-world data. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability

arXiv

引用

arXiv 2023年

作者： Zhang, Yechao Hu, Shengshan Zhang, Leo Yu Shi, Junyu Li, Minghui Liu, Xiaogeng Wan, Wei Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Adversarial examples for deep neural networks (DNNs) have been shown to be transferable: examples that successfully fool one white-box surrogate model can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable adversarial examples, many of these findings fail to be well explained and even lead to confusing or inconsistent advice for practical use. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing "little robustness" phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates for transfer attacks, we attribute it to a trade-off between two dominant factors: model smoothness and gradient similarity. Our research focuses on their joint effects on transferability, rather than demonstrating the separate relationships alone. Through a combination of theoretical and empirical analyses, we hypothesize that the data distribution shift induced by off-manifold samples in adversarial training is the reason that impairs gradient similarity. Building on these insights, we further explore the impacts of prevalent data augmentation and gradient regularization on transferability and analyze how the trade-off manifest in various training methods, thus building a comprehensive blueprint for the regulation mechanisms behind transferability. Finally, we provide a general route for constructing superior surrogates to boost transferability, which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other,

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：