检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Xiu Ji Chenglong Qi Beimin Xei Meng Li Hui Wang Yang Bai National Local Joint Engineering Research Center for Smart Distribution Grid Measurement and Control With Safety Operation Technology Changchun Institute of Technology Changchun State Grid Jilin Electric Power Co. Ltd. Ultra High Voltage Company Changchun

As the core equipment of the energy internet, the energy router (ER) plays an important role in basic equipment energy regulation, renewable energy access, energy information collection, etc. This paper introduces a three-layer architecture of energy router, which includes aggregation service layer, optimization control layer and control execution layer. This paper mainly studies the internal energy management strategy of the energy router, proposes an improved particle swarm optimization algorithm and verifies the solution performance of this algorithm, and applies it to the internal energy management of the energy router to improve the economic efficiency and reduce the loss of the microgrid, and realize the optimal operation of the upper, middle and lower layers. The experimental results verify the effectiveness of the coordination control and energy management strategy of the algorithm, and show that the energy router has satisfactory performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two Enhanced-rate Power Allocation Strategies for Active IRS-assisted Wireless Network

arXiv

引用

arXiv 2023年

作者： Cheng, Qiankun Dong, Rongen Cai, Wenlong Liu, Ruiqi Shu, Feng Wang, Jiangzhou The School of Information and Communication Engineering Hainan University Haikou570228 China The School of Information and Communication Engineering Collaborative Innovation Center of Information Technology Hainan University Haikou570228 China The School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute Beijing China The Wireless and Computing Research Institute ZTE Corporation Beijing100029 China The School of Engineering University of Kent CanterburyCT2 7NT United Kingdom

Due to its ability of overcoming the impact of double-fading effect, active intelligent reflecting surface (IRS) has attracted a lot of attention. Unlike passive IRS, active IRS should be supplied by power, thus adjusting power between base station (BS) and IRS having a direct impact on the system rate performance. In this paper, the active IRS-aided network under a total power constraint is modeled with an ability of adjusting power between BS and IRS. Given the transmit beamforming at BS and reflecting beamforming at IRS, the SNR expression is derived to be a function of power allocation (PA) factor, and the optimization of maximizing the SNR is given. Subsequently, two high-performance PA strategies, enhanced multiple random initialization Newton's (EMRIN) and Taylor polynomial approximation (TPA), are proposed. The former is to improve the rate performance of classic Netwon's method to avoid involving a local optimal point by using multiple random initializations. To reduce its high computational complexity, the latter provides a closed-form solution by making use of the first-order Taylor polynomial approximation to the original SNR function. Actually, using TPA, the original optimization problem is transformed into a problem of finding a root for a third-order polynomial. Simulation results are as follows: the first-order TPA of SNR fit its exact expression well, the proposed two PA methods performs much better than fixed PA in accordance with rate, and appoaches exhaustive search as the number of IRS reflecting elements goes to large-scale. Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Combined calibration method for large field of view multi-camera system

Combined calibration method for large field of view multi-ca...

引用

Chinese Automation Congress (CAC)

作者： Wei Sun Ju Huo You Li Muyao Xue JianBao Zhou School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China Shanghai Space Propulsion Technology Research Institute Shanghai China Harbin Nuoxin University of Technology Measurement and Control Technology Co. Ltd. Harbin China

In the calibration process of multi-camera system with large field of view, aiming at the problem of self occlusion in the plane calibration method and the problem of low calibration accuracy of one-dimensional calibration methods, a calibration method of multi-camera system based on the combination of plane target and one-dimensional target is proposed. Firstly, a mathematical model of multi-camera calibration is established with pin-hole model and rigid body transformation theory; the internal parameters and distortion coefficients of each camera are calibrated by two-dimensional plane target; on this basis, analyze the uncertainty of imaging error of circular feature points, cost function of random sample consensus algorithm(RANSAC) is improved. Using the camera imaging model, the essential matrix between cameras is estimated, and the initial value of camera external parameters is decomposed and determined; lastly, multiple nonlinear optimization algorithms are used to refine and obtain the camera matrix, The simulation and actual experimental results show that the multi camera system combination calibration method proposed in this paper can realize the parameter calibration of four camera measurement system, and the measurement space is 2000mm×2000mm×2000mm, the 3D reconstruction error is less than 0.15mm. Compared with the traditional calibration method, it has more accurate calibration accuracy.

关键词： Solid modeling Uncertainty Three-dimensional displays measurement uncertainty Nonlinear distortion Cameras Cost function

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Framework for Predicting Industrial Wastewater Influent Quality Based on Graph Optimization

SSRN

引用

SSRN 2024年

作者： Cao, Jiafei Xue, Anke Yang, Yong Lu, Rongfeng Hu, Xiaojing Zhang, Le Cao, Wei Cao, Guanglong Geng, Xiulin Wang, Lin Institute of Information and Control Hangzhou Dianzi University Zhejiang Hangzhou310018 China Anhui Huizhou Economic Development Zone Management Committee Anhui Huangshan245061 China College of Communication Engineering Hangzhou Dianzi University Zhejiang Hangzhou310018 China School of Electrical Engineering Yancheng Institute of Technology Yancheng224051 China

Due to the impact of excessive influent water quality and water quantity fluctuations, current industrial effluent treatment plants (IETPs) cannot maintain stable decontamination capabilities, posing serious threats to the ecological environment. Thus, It is imperative to predict the influent quality of IETPs to facilitate predictive maintenance. However, due to industrial wastewater's highly nonlinear nature and variability, single-model often limits the accuracy of predictions. Therefore, this study innovatively constructs a comprehensive and highly adaptable hybrid deep learning prediction framework, GCN-CNNGA. By integrating GCN, CNN, GRU, and Attention Mechanism, it effectively captures the high-dimension features of influent data and the complex nonlinear spatiotemporal patterns among variables. Specifically, CNN is used to extract key local features from the IETP time series accurately. Building on this, GCN is utilized to further capture the topological information among key influent parameters, revealing their interconnections and deeply mining the complex dependencies among pollutants. Then, GRU effectively captures long-term dependencies not considered in the above processes, while the attention mechanism optimizes weight distribution, overall enhancing the precision of predictions. In real data testing at a wastewater treatment plant in an industrial park in East China, the GCN-CNNGA model outperforms mainstream prediction methods in terms of prediction accuracy and robustness. The findings of this study offer a high-accuracy prediction model that is expected to significantly improve the predictive maintenance level of IETPs, providing strong technical support for maintaining optimal operational conditions and having significant implications for protecting the ecological environment and promoting sustainable development. © 2024, The Authors. All rights reserved.

关键词： Effluent treatment

来源：评论

学校读者我要写书评

暂无评论

Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation

arXiv

引用

arXiv 2023年

作者： Islam, Mobarakol Seenivasan, Lalithkumar Sharan, S.P. Viekash, V.K. Gupta, Bhavesh Glocker, Ben Ren, Hongliang Dept. of Computing Imperial College London United Kingdom Dept. of Biomedical Engineering National University of Singapore Singapore Dept. of Electronics and Communication Engineering National Institute of Technology Tiruchirappalli India Dept. of Instrumentation and Control Engineering National Institute of Technology Tiruchirappalli India Dept. of Mechanical Engineering Indian Institute of Technology Delhi India Dept. of Electrical Engineering Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods heavily rely on the ability to score the difficulty of data samples, an optimal scoring function is still under exploration. Methodology: Distillation is a knowledge transfer approach where a teacher network guides a student network by feeding a sequence of random samples. We argue that guiding student networks with an efficient curriculum strategy can improve model generalization and robustness. For this purpose, we design an uncertainty-based paced curriculum learning in self-distillation for medical image segmentation. We fuse the prediction uncertainty and annotation boundary uncertainty to develop a novel paced-curriculum distillation (PCD). We utilize the teacher model to obtain prediction uncertainty and spatially varying label smoothing with Gaussian kernel to generate segmentation boundary uncertainty from the annotation. We also investigate the robustness of our method by applying various types and severity of image perturbation and corruption. Results: The proposed technique is validated on two medical datasets of breast ultrasound image segmentation and robotassisted surgical scene segmentation and achieved significantly better performance in terms of segmentation and robustness. Conclusion: P-CD improves the performance and obtains better generalization and robustness over the dataset shift. While curriculum learning requires extensive tuning of hyper-parameters for pacing function, the level of performance improvement suppresses this limitation. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Safety and Security of the Car-Sharing System

引用

IFAC-PapersOnLine 2022年第4期55卷 121-126页

作者： J. Arm P. Dvorsky P. Fiedler C. Falcou J. Orlicky Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic Central European Institute of Technology Brno University of Technology Brno Czech Republic THALES – DIS Gemenos Cedex France Institute of Microelectronic Applications Prague Czech Republic

In the SECREDAS project, the car-sharing system embodies one of the laboratory demonstrators (pilots). The system consists of an embedded device for car access, a backend server, and a mobile app. In addition, the system can be easily adapted to an access control system in general, such as car fleet management. Our team designed, implemented, and validated the system in a laboratory environment, therefore TRL (technology Readiness Level) 4 was achieved. The implementation was also supported by design patterns developed in the project. Moreover, we addressed the security, safety, and privacy issues. This article reports the progress of work and the results achieved. Key aspects such as Identity management, Representative State Transfer (REST) API (Application Programming Interface), threat assessment and key transfer methods are also described in more detail. In this work, the symmetric rent token (car key) is heavily used; however, other techniques are presented.

关键词： Security car sharing authentication identity management safety privacy

来源：评论

学校读者我要写书评

暂无评论

Reliability modeling and verification of communication algorithm flow for intelligent control system 4

Reliability modeling and verification of communication algor...

引用

4th International Conference on Advanced Electronic Materials, Computers and Software engineering, AEMCSE 2021

作者： Ran, Wu Jiajia, Wang Beijing Air Traffic Control Engineering Technology Co. Ltd Beijing China Applied Mathematics Research Center of CASIC Beijing Jinghang Research Institute of Computing and Communication Beijing China

ISBN: (纸本)9781665415965

The intelligent system controls the subsystems of each aircraft in real time to ensure the normal development of the tasks of the aircraft system. In the process of system communication, the control system is required to strictly control the correctness of the control algorithm flow and the accuracy of the control sequence in order to ensure the safety of the aircraft system. This paper uses UPPAAL, a formal model detection tool based on time automata theory, to formally model and validate the algorithm flow of an intelligent system and a subsystem. First, the algorithm flow of the intelligent system is analyzed, and then it is formally modeled using the time automaton method. Second, the properties that need to be verified are extracted from the algorithm flow and described with the formal language BNF. Finally, the function and performance correctness are automatically verified using the UPPAAL model detection tool. The experimental results verify that the intelligent system meets the security, accessibility and activity requirements. © 2021 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Feature Enrichment and Fidelity Preservation Learning Framework for Skeleton-based Action Recognition

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Li, Chuankun Li, Shuai Gao, Yanbo Gao, Xingyu Chen, Ping Li, Jian Li, Wanqing North University of China State Key Laboratory of Dynamic Testing Technology School of Information and Communication Engineering Taiyuan030051 China Shandong University School of Control Science and Engineering School of Software Jinan250100 China Chinese Academy of Sciences Institute of Microelectronics Beijing100029 China University of Wollongong Advanced Multimedia Research Lab WollongongNSW2522 Australia

Unsupervised skeleton-based action recognition has achieved remarkable progress recently. Existing unsupervised learning methods suffer from severe overfitting problem, and thus small networks are used, significantly reducing the representation capability. To address this problem, the overfitting mechanism behind the unsupervised learning for skeleton-based action recognition is first investigated. It is observed that skeleton is already a relatively high-level and low-dimension feature, but not in the same manifold as the features for action recognition. Simply applying the existing unsupervised learning method tends to produce features that discriminate the different samples rather than action classes, resulting in the overfitting problem. To address this problem, this paper proposes an Unsupervised spatial-temporal Feature Enrichment and Fidelity Preservation (U-FEFP) learning framework to generate rich distributed features that contain all the information of a skeleton sample. A spatial-temporal feature transformation subnetwork is developed using channel-wise topology refinement graph convolutional block and graph convolutional gated recurrent unit block as the basic feature extraction network. The unsupervised Bootstrap Your Own Latent-based learning is utilized to generate rich distributed features, and the unsupervised pretext task-based learning is employed to preserve the information contained in the skeleton. The two unsupervised learning ways are collaborated as U-FEFP to produce robust and discriminative representations. Experimental results on four widely used benchmarks, namely NTU-RGB+D-60, PKU-MMD, NTU-RGB+D-120 and UAV-Human dataset, demonstrate that the proposed U-FEFP obtains the best result compared with the state-of-the-art unsupervised learning methods. © 1991-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Research on Autonomous Maneuvering Strategies of UAV Swarm for Saturation Attack

Research on Autonomous Maneuvering Strategies of UAV Swarm f...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Zhang, Tingting Zuo, Yi Zhang, Dongning Ding, Fei Huang, Jun Lin, Yun College of Command and Control Engineering Army Engineering University of the Pla Nanjing China Key Laboratory of Information System Requirements Nanjing China Fifty-fourth Research Institute of China Electronics Technology Group Corporation Shijiazhuang China Internet of Things Academy Nanjing University of Posts and Telecommunications Nanjing China Jsti Group Nanjing China Harbin Engineering University Department of Information and Communication Engineering Harbin China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

In order to solve the problem of unmanned aerial Vehicle (UAV) cluster saturation attack, the autonomous maneuver strategy of UAV is studied. Based on the distributed partial observable Markov decision process, the autonomous maneuver decision model of UAV is constructed, and the Recurrent Multi-Agent Deep Deterministic Policy Gradient (RMADDPG) is used to learn the maneuver strategy of UAV cluster saturation attack. Combined with the typical characteristics of saturation attack scenario, two reward functions of global reward and local reward for UAV maneuver are designed. The trained UAVs can effectively perform suicide saturation attack task. According to the mission target design evaluation index of saturation attack, the Monte Carlo analysis method is used to compare the proposed method with particle swarm optimization (PSO) algorithm in three aspects: inter aircraft collision avoidance, NFZ avoidance and simultaneous attack. The experimental results show that the trained UAVs can effectively perform the suicide saturation attack task under the condition of a small amount of communication, which provides a method for the application of multi-agent deep reinforcement learning to UAV cluster operations. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Adversarial Examples Detection of Electromagnetic Signal Based on GAN

Adversarial Examples Detection of Electromagnetic Signal Bas...

引用

International Conference on Big Data Computing and communications (BIGCOM)

作者： Jiawei Zhu Jiangpeng Li Dongwei Xu Chuntao Gu Qi Xuan Shunling Wang Security Control Laboratory Science and Technology on Communication Information Jiaxing China Institute of Cyberspace Security Zhejiang University of Technology College of Information Engineering Zhejiang University of Technology Hangzhou China

In the field of signal modulation classification, deep neural networks (DNNs) perform very well and have good generalization ability. However, the DNN model is extremely vulnerable. The model gives a false output with high confidence from an input example, which formed only by deliberately adding tiny disturbances. Such elaborate examples that make the model misclassify are called adversarial examples. In this paper, for the detection of adversarial examples in electromagnetic signals, we propose a method based on generative adversarial networks (GANs), a novel strategy to defend deep neural networks against such attacks. First of all, by experiment we came to the conclusion that the confidence of the DNN model for normal examples is stable, and the confidence for adversarial examples is unstable. We trained a classifier that performs well in extracting electromagnetic signal features. Then, We feed the normal examples to the generative adversarial network, the generator generates examples with similar data distribution to the clean examples. We send such pairs of examples to the classifier to calculate a threshold T, and the same operations will be performed on the test examples. Finally, the absolute error E of each pair of test examples will be calculated and compared with the threshold T to achieve electromagnetic signal adversarial examples detection. We define the method in the paper as Detect-GAN. The experimental results show that Detect-GAN can effectively defend against common and powerful attack algorithm. Comparing with other detection methods, Detect-GAN achieves more competitive performance.

关键词： Deep learning Neural networks Modulation Big Data Generative adversarial networks Feature extraction Generators

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：