检索结果-内蒙古大学图书馆

ieee/IFIP Network Operations and Management symposium

作者： Babbar, Himanshi Bouachir, Ouns Rani, Shalli Aloqaily, Moayad Chitkara Univ Inst Engn & Technol Rajpura India Zayed Univ Coll Technol Innovat CTI Dubai U Arab Emirates Mohamed Bin Zayed Univ Artificial Intelligence MB Machine Learning Dept Abu Dhabi U Arab Emirates

ISBN: (纸本)9781665406017

Intelligent Transportation Systems (ITS), mainly Autonomous Vehicles (AV's), are susceptible to security and safety problems that risk the users' lives. Sophisticated threats can damage the security of AV's communications and computational capabilities, slowing down their integration into our daily lives. Cyber-attacks are getting more complex, posing greater hurdles in identifying intrusions effectively. Failing to prevent the intrusions could tarnish the security services' reliability, including data confidentiality, authenticity, and reliability. IDS is an overall prediction paradigm for detecting malicious network traffic in the ITS. This article studies the role of machine or deep learning in Software Defined-Intrusion Detection System (SD-IDS) in ITS;discusses the mathematical analysis of existing deep learning models and evaluates their performances on the basis of the various metrics (i.e., accuracy, precision, recall, f-measure) to observe which model gives the best results for the existing state of art. The results show that improved Recurrent Neural Networks (RNN) is best suited for the detection of SD-IDS attacks in the data plane and control plane.

关键词： Software Defined-Intelligent Transportation Systems Internet of Vehicles Internet of Things Deep Learning Intrusion Detection System Evaluation Metrics

来源：评论

学校读者我要写书评

暂无评论

Exploring Image Generation for UAV Change Detection

引用

ieee/CAA Journal of Automatica Sinica 2022年第6期9卷 1061-1072页

作者： Xuan Li Haibin Duan Yonglin Tian Fei-Yue Wang Peng Cheng Laboratory Shenzhen 518000China IEEE State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical EngineeringBeihang UniversityBeijing 100083 Department of Automation University of Science and Technology of ChinaHefei 230027 State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Research Center for Computational Experiments and Parallel Systems Technology National University of Defense TechnologyChangsha 410073China

Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and ***,even the most advanced models require large amounts of data for model training and ***,sufficient labeled images with different imaging conditions are *** by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated *** simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection ***,we propose an image translation framework that translates simulated images to synthetic *** framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training *** experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.

关键词： Change detection computer graphics image translation simulated images synthetic images unmanned aerial vehicles(UAVs)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Receding Horizon control For Nonlinear Systems Exemplified by Two Coupled van der Pol Oscillators 16

Adaptive Receding Horizon Control For Nonlinear Systems Exem...

引用

16th ieee International symposium on Applied computational intelligence and Informatics, SACI 2022

作者： Atinga, Awudu Wirtu, Amensisa Tar, Jozsef K. School of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary Institute of Mechatronics and Vehicle Engineering Óbuda University Donat Banki Faculty of Mechanical and Safety Engineering Budapest Hungary Antal Bejczy Center for Intelligent Robotics University Research and Innovation Center Óbuda University Budapest Hungary Institute of Applied Mathematics Óbuda University John von Neumann Faculty of Informatics Budapest Hungary

ISBN: (数字)9781665481250

ISBN: (纸本)9781665481250

A heuristic 'Adaptive Receding Horizon controller' (ARHC) approach was recently suggested in which tracking the 'nominal trajectory' was formulated as minimizing a cost term by the use of a 'heavy dynamic model', and the so obtained 'optimized path' was adaptively tracked by the use of a 'less heavy' engine for which only an approximate model was available. For tracking this optimized trajectory a Fixed Point Iteration-based solution was suggested on the basis of Banach's Fixed Point Theorem. For reducing the computational burden of optimization the heavy dynamic model was not taken into account as a constraint (as usually it used to be), but it was directly used in building up the horizon with forward differences. As a consequence the number of the free variables of optimization was drastically decreased, and the computational burden of gradient reduction was spared, too. In this paper this method is further investigated by the use of two nonlinearly coupled van der Pol oscillators as a paradigm of nonlinear dynamical system. Furthermore, the usual quadratic cost functions were substituted by much simpler ones. In the paper simulation results exemplify the operation of the method that seems to be promising for breaking out of the realm of the traditional quadratic cost functions, and linear time-invariant dynamic models. © 2022 ieee.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Beyond Traditional Driving Scenes: A Robotic-Centric Paradigm for 2D+3D Human Tracking Using Siamese Transformer Network 7

Beyond Traditional Driving Scenes: A Robotic-Centric Paradig...

引用

7th International symposium on Autonomous Systems, ISAS 2024

作者： Xin, Shuo Liu, Liang Kang, Xiao Zhang, Zhen Wang, Mengmeng Liu, Yong Zhejiang University Institute of Cyber-Systems and Control Hangzhou China China North Vehicle Research Institute Beijing China

ISBN: (纸本)9798350363173

3D human tracking plays a crucial role in the automation intelligence system. Current approaches focus on achieving higher performance on traditional driving datasets like KITTI, which overlook the jitteriness of the platform and the complexity of the environments. Once the scenarios are migrated to jolting robot platforms, they all degenerate severely with only a 20-60% success rate, which greatly restricts the high-level application of autonomous systems. In this work, beyond traditional flat scenes, we introduce Multi-modal Human Tracking Paradigm (MHTrack), a unified multimodal transformer-based model that can effectively track the target person frame-by-frame in point and video sequences. Specifically, we design a speed-inertia module-assisted stabilization mechanism along with an alternate training strategy to better migrate the tracking algorithm to the robot platform. To capture more target-aware information, we combine the geometric and appearance features of point clouds and video frames together based on a hierarchical Siamese Transformer Network. Additionally, considering the prior characteristics of the human category, we design a lateral cross-attention pyramid head for deeper feature aggregation and final 3D BBox generation. Extensive experiments confirm that MHTrack significantly outperforms the previous state-of-the-arts on both open-source datasets and large-scale robotic datasets. Further analysis verifies each component's effectiveness and shows the robotic-centric paradigm's promising potential when deployed into dynamic robotic systems. © 2024 ieee.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

A Novel Miner Action Recognition Model Based on Contrastive Learning

A Novel Miner Action Recognition Model Based on Contrastive ...

引用

2022 International symposium on Computing and Artificial intelligence, ISCAI 2022

作者： Yang, Yi College of Electrical and Control Engineering Xi'An University of Science and Technology Xi'an China

ISBN: (纸本)9798350323252

To address the problems of high training resource consumption and lack of generality in current miner action recognition methods, in this paper, we design a new miner action recognition model based on the multimodal learning framework of contrast learning, which more effectively utilizes the semantic information in the labels and improves the scalability of the model. Then, we use a fixed pre-trained model as the backbone in the video encoder, which greatly reduces the parameters that need to be trained and the resources consumed in the training. At the same time, we design an auxiliary branch to extract temporal information from the video, which effectively improves the accuracy of miner action detection without significantly increasing the computational consumption. Finally, we validate the accuracy performance of the model on the miner action dataset, and its recognition accuracy outperforms other methods in the comparison. © 2022 ieee.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Performance-Guaranteed Multi-Train Cooperative control using Event-Triggered and Sign-Rectified Regressor

Performance-Guaranteed Multi-Train Cooperative Control using...

引用

International Conference on control and automation (ICCA)

作者： Yue Zheng Shigen Gao Zixuan Zhang Xiying Song Hairong Dong School of Automation and Intelligence Beijing Jiaotong University Beijing China Department of Automation Tsinghua University Beijing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This paper presents a performance-guaranteed method of cooperative tracking for multiple high-speed trains while considering computational resource limitations and security constraints. First, the prescribed performance control is employed to transform constrained train states into an unconstrained format. Radial basis function neural networks are used to efficiently approximate the unknown resistance, and an innovative sign-rectified regressor neural network update strategy is employed to significantly improve computational efficiency and ensure high estimation accuracy even with limited neuron number and weak excitation. Secondly, an event-triggered mechanism is designed to determine the timings of updates for the train controller and neural network, adapted for on-board computational resource limits. Subsequently, the triggering conditions for each train are then designed to facilitate a safe cooperative control method, which combines an event-triggered processor with a performance control protocol that ensures limited state tracking error within a predefined performance function. Finally, in order to validate the effectiveness of the proposed scheme, we applied the control strategy in simulation experiments using collected data from the high-speed railway line.

关键词： Resistance Neurons Estimation Radial basis function networks Transforms Safety computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Robust Adaptive Formation control of Fixed Wing UAVs Using Disturbance Estimators

Robust Adaptive Formation Control of Fixed Wing UAVs Using D...

引用

International symposium on computational intelligence and Informatics

作者： Stephen Kimathi Bela Lantos Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary

ISBN: (数字)9798350353433

ISBN: (纸本)9798350353440

This paper presents the formation control of multiple homogeneous fixed-wing unmanned aerial vehicles subjected to parameter perturbations and external disturbances. A leader-follower with virtual leader formation architecture is used, and the communication between the vehicles is modelled using a directed graph. A distributed model reference adaptive control strategy is used for the formation acquisition and maintenance. The robustification of the control is achieved using a disturbance estimator developed to estimate and cancel out the effect of the disturbances on the dynamic model. In this formulation, the designed control law does not require any information about the magnitude of the disturbance, or derivative of the states. The simulation results validate the effectiveness of the proposed control strategy.

关键词： Adaptation models Uncertain systems Simulation Perturbation methods Directed graphs Computer architecture Formation control Topology Adaptive control Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

First Principle Modeling of a Morphable Unmanned Aerial-Aquatic Vehicle: Mirs-Alioth

First Principle Modeling of a Morphable Unmanned Aerial-Aqua...

引用

International Conference on control and automation (ICCA)

作者： Dongyue Huang Minghao Dou Xuchen Liu Ruixin Yan Songqun Gao Zixuan Liu Biao Wang Lihua Dou Ben M. Chen Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin Hong Kong Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing Jiangsu China School of Automation Beijing Institute of Technology Beijing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

This paper establishes a hybrid system model for a morphable unmanned aerial-aquatic vehicle (UAAV), named Mirs-Alioth, incorporating hydrodynamic parameters through the first principle. Unlike other current UAAVs, variable thrust tilt angles make Mirs-Alioth's model mutable. Thus, this paper directly employs geometric features of the vehicle, integrating a morphing model into a comprehensive dynamics of the vehicle and switching models between different media triggered by depth. The comprehensive model parameters including the rigid body part and the hydrodynamic part is then identified through experiments and computational fluid dynamic (CFD) methods.

关键词： Adaptation models automation Accuracy computational modeling computational fluid dynamics Switches Media

来源：评论

学校读者我要写书评

暂无评论

Design and Application of DHP controller Based on Online Leaky Echo State Network

Design and Application of DHP Controller Based on Online Lea...

引用

2022 ieee International symposium on Product Compliance Engineering - Asia, ISPCE-ASIA 2022

作者： Wang, Hongyu Yang, Cuili Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Laboratory for Intelligent Environmental Protection Beijing Institute of Artificial Intelligence Beijing University of Technology Beijing100124 China

ISBN: (数字)9798350332483

ISBN: (纸本)9798350332483

In wastewater treatment process (WWTP), which has nonlinear and dynamic characteristics, it is difficult to realize the tracking control of dissolved oxygen (DO). To solve this problem, the online double heuristic programming (DHP) controller based on leaky echo state network (LESN) is proposed, the controller is named as DHP-LESN for short. Firstly, three Leaky ESNs are used in DHP to produce the control strategy, the system state and the derivatives of evaluation function, respectively. Then, the online gradient algorithm is used to update the output weights of three LESNs. Finally, the performance of the proposed DHP-LESN controller is tested and evaluated on Benchmark Simulation Model 1 (BSM1). The simulation results show that the proposed DHP-LESN controller can achieve better control performance than PID controller. © 2022 ieee.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Enabling IoT Continuous Connectivity in Smart Spaces 22

Enabling IoT Continuous Connectivity in Smart Spaces

引用

22nd International symposium on Parallel and Distributed Computing, ISPDC 2023

作者： Andreou, Andreas Mavromoustakis, Constandinos X. Batalla, Jordi Mongay Dobre, Ciprian Markakis, Evangelos Mastorakis, George University of Nicosia University of Nicosia Research Foundation Departement of Computer Science Nicosia Cyprus Warsaw University of Technology Warsaw Poland University Politehnica of Bucharest National Institute for Research and Development in Informatics Automatic Control and Computers Bucharest Romania Hellenic Mediterranean University Department of Electrical and Computer Engineering Heraklion Greece Hellenic Mediterranean University Department of Management Science and Technology Agios Nikolaos Greece

ISBN: (纸本)9798350341270

Smart spaces are a rapidly emerging concept in technology. They result from the convergence of various novel technologies, such as the Internet of Things, Machine Learning and Artificial intelligence, which allow for greater levels of automation and control within physical environments. The devices which are connected to the IoT network are equipped with sensors to acquire and exchange data. As a result, the IoT has transformed how we live, work, and play. However, the deployment in smart spaces is not always the best due to the issues arising from network node positioning. Therefore, we are investigating solutions to this problem with a novel approach which utilises Voronoi diagrams in conjunction with the algorithmic genetic technique. First, the initial positions of the IoT nodes will be determined by simulating a homogeneous Poisson point process in the smart space environment. Then, after dividing the area into the Voronoi cells, the genetic algorithm will optimise the position towards achieving full network coverage within the smart space. Experimental results prove the 100% network coverage within the specified area. © 2023 ieee.

关键词： Genetic algorithms

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：