检索结果-内蒙古大学图书馆

Deep Unfolding Learning Aided ISAC Transceiver Design

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Jifa Zhu, Yongxu Zhao, Nan Jin, Shi Wang, Xianbin Ng, Derrick Wing Kwan Al-Dhahir, Naofal Dalian University of Technology School of Information and Communication Engineering Liaoning Dalian China Southeast University National Communications Research Laboratory Nanjing China Western University Department of Electrical and Computer Engineering LondonONN6A 5B9 Canada University of New South Wales School of Electrical Engineering and Telecommunications Sydney2052 Australia The University of Texas at Dallas Department of Electrical and Computer Engineering RichardsonTX75080 United States

Integrated sensing and communication (ISAC) can enhance spectral efficiency and facilitate the diverse emerging applications via sharing the same spectrum and hardware between communication and sensing. However, effective operation of ISAC may suffer from high complexity. In this paper, we develop a low-complexity deep unfolding learning-aided transceiver design scheme for ISAC in a cluttered environment. In particular, we optimize the transmit waveform and receive filtering to minimize the weighted sum of multi-user interference power and the reciprocal of sensing signal-to-interference-plus-noise ratio (SINR), while adhering to the constraints of a constant modulus signal and waveform similarity. An alternating direction method of multipliers (ADMM)-based iterative algorithm is first developed to address this non-convex optimization problem with both equality and inequality constraints. To further reduce the computational complexity, we develop two deep unfolding neural networks (NNs), termed ADMM-DL-NET and ADMM-PGD-NET, to handle this problem, which can unfold the underlying ADMM-based iterative algorithm to a lightweight neural network with learnable parameters and eliminate the need for the bisection method by adopting the Uzawa’s method and projected gradient descent, respectively. Simulation results demonstrate that our proposed deep unfolding NNs can achieve comparable performance to the ADMM-based iterative algorithm with significantly reduced complexity, and outperform the unsupervised learning benchmarks in performance and number of learnable parameters. © 2002-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Complex Hermitian Positive Definite Manifold Embedding Transformer Network for Time-Varying Direction of Arrival Tracking

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Teng, Liping Wang, Qing Wang, Yanhui Guo, Qinghua Li, Wanqing Tianjin University School of Electrical and Information Engineering Tianjin300072 China Nantong University School of Information Science and Technology Nantong226019 China Science and Technology on Space Physics Laboratory Beijing100076 China University of Wollongong School of Electrical Computer and Telecommunications Engineering WollongongNSW2522 Australia University of Wollongong Advanced Multimedia Research Lab WollongongNSW2522 Australia

In this work, we address the challenge of stable and robust time-varying direction-of-arrival (DOA) tracking, where both the DOA trajectory and the number of sources change over time across different scenarios. We formulate the problem as a multi-label classification task and propose a novel solution leveraging Riemannian manifold geometry and advanced neural networks for sequential data processing. Specifically, we introduce the Complex Hermitian Positive Definite embedding Transformer (C-HPD-T) network, which learns statistical representations of covariance matrices. The C-HPD-T consists of an HPD module and a Transformer module. The HPD module learns an appropriate statistical representation and the complex Transformer module models the data temporally. In particular, in the C-HPD-T network, we build a complex singular value decomposition (SVD) module to ensure that complex structure is preserved during the calculation of each layer. Meanwhile, we design a Transformer-based sequential network to capture the temporal relationship of signals and for the time-varying DOAs. Through training the network with varying numbers of moving targets featuring diverse motion trajectories, the network demonstrates excellent performance and robustness against array imperfections. Extensive simulation results demonstrate its superior performance gains compared to existing methods. © 2015 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A Cybertwin-Based Trading Mechanism for Personalized Transmission Services in Cloud Native Networks

引用

IEEE Wireless Communications Letters 2025年

作者： Zeng, Zhiyong Liang, Dandan Qin, Meng Sun, Ruijin Liang, Hui Zhang, Wei Peking University Shenzhen Graduate School School of Electronic and Computer Engineering Shenzhen518055 China Pengcheng Laboratory Shenzhen518055 China Pengcheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518055 China Xidian University Guangzhou institute of technology Guangzhou510555 China Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China University of New South Wales School of Electrical Engineering and Telecommunications SydneyNSW2052 Australia

The Cybertwin-based cloud native network (CCNN) with a cloud-edge-end architecture is to provide personalized user services, which includes both wireless access networks and cloud networks. However, the limited availability of resources and intense user competition present significant challenges. While prior studies have contributed to this issue, they overlook the feasibility of using resources as the trading object in a user-centric approach, particularly in wireless networks. To address this gap, this letter proposes a Cybertwin-based Personalized Transmission Service Trading Mechanism (CPTSTM), employing a one-to-many concurrent bilateral negotiation model for dynamic multi-provider trading. An optimization problem is formulated to minimize user costs by modeling the negotiation as a sequential decision-making process, accounting for individual rationality and system uncertainties. Given restricted and hybrid action spaces, we introduce a Constrained Parameterized Deep Q-learning Network (CPDQN)-based negotiation strategy integrating offer evaluation, acceptance, and bidding strategies. Simulation results confirm the feasibility of the proposed mechanism and demonstrate that the CPDQN-based algorithm outperforms existing methods in terms of trade success rate (nearly 100%) and the number of negotiation rounds (reduced by 75%) while maintaining comparable user utility across various scenarios. © 2012 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Advancing Orchard Fruit Detection: An Innovative Agricultural Foundation Model Approach

Advancing Orchard Fruit Detection: An Innovative Agricultura...

引用

2024 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2024

作者： Li, Jiajia Lammers, Kyle Yin, Xunyuan Yin, Xiang He, Long Lu, Renfu Li, Zhaojian Department of Electrical and Computer Engineering Michigan State University MI United States School of Chemical and Biomedical Engineering Nanyang Technological University Singapore Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Department of Agricultural and Biological Engineering Pennsylvania State University United States United States Department of Agriculture Agricultural Research Service East LansingMI United States Department of Mechanical Engineering Michigan State University East LansingMI United States

ISBN: (纸本)9798331302214

Fruit harvesting poses a significant labor and financial burden on the fruit industry, which underscore the urgent need for advancements in robotic harvesting solutions. Despite considerable progress in leveraging deep learning and machine learning techniques for fruit detection, a common shortfall is the inability to swiftly extend the developed models across different orchards and/or various fruit species. Additionally, the limited availability of pertinent data further compounds these challenges. In this work, we introduce MetaFruit, the largest publicly available multi-class fruit dataset, comprising 4,248 images and 248,015 manually labeled instances across diverse U.S. orchards. Furthermore, this study proposes an innovative open-set fruit detection system leveraging advanced Vision Foundation Models (VFMs) for fruit detection that can adeptly identify a wide array of fruit types under varying orchard conditions. This system not only demonstrates remarkable adaptability in learning from minimal data through few-shot learning but also shows the ability to interpret human instructions for subtle detection tasks. The performance of the developed foundation model is comprehensively evaluated across several metrics, outperforming existing state-of-the-art algorithms in our MetaFruit, thereby setting a new benchmark in the field of agricultural technology and robotic harvesting. The MetaFruit dataset (https://***/datasets/jiajiali/metafruit) and detection framework (https://***/JiajiaLi04/FMFruit) are open-sourced to foster future research in vision-based fruit harvesting, marking a significant stride toward addressing the urgent needs of the agricultural sector. © 2024 ASABE Annual International Meeting. All rights reserved.

关键词： Orchards

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Emotional Stress Classification using Smart Learning Dataset 15

CNN-Based Emotional Stress Classification using Smart Learni...

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Andreas, Andreou Mavromoustakis, Constandinos X. Song, Houbing Batalla, Jordi Mongay Department of Computer Science University of Nicosia University of Nicosia Research Foundation Nicosia Cyprus Security and Optimization for Networked Globe Laboratory Department of Electrical Engineering and Computer Science Embry-Riddle Aeronautical University Daytona Beach FL32114-3900 United States Warsaw University of Technology National Institute of Telecommunications Warsaw Poland

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Smart learning analytics aims to support researchers investigating mental health by improving the interpretation of the datasets acquired from physiological biomarkers. The key enabler for emotional stress classification are Machine Learning (ML) methods in conjunction with Online Transfer Learning (OTL). The knowledge of high-level characteristics at the top layers is obtained through an optimized Convolutional Neural Network (CNN)-based on emotional stress datasets. Nevertheless, the lack of performance in a real-time environment and the temporal patterns of data acquisition complications and their interpretation motivated us to contribute by tackling these concerns. Therefore, we propose an innovative procedure based on the aforementioned orientation through our research work. Considering mining data streams with concept drifts, we enable the ensemble classifiers. For evaluation, we compare the proposed classification, the LIBrary for Large LINEAR classification (LIBLINEAR) and the Deep Belief Network with Transfer Learning (DBNTL) model. Furthermore, we utilized a multimodal dataset of physical and biological characteristics obtained by fifteen individuals during a lab study. Finally, our framework based on the extracted results has presented more accuracy in classifying an individual's sense of stress. Hence, the proposed method achieves higher efficiency than the state-of-the-art models. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Swing-Up and Stable control Strategy for Pendubot Based on Nonlinear Model Predictive Method

A Swing-Up and Stable Control Strategy for Pendubot Based on...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Lejun Liu, Yiqin Zhang, Ruihuan Huang, Zixin Cai, Zhen School of Automation School of Industrial Internet Chongqing University of Posts and Telecommunications Chongqing400065 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Hubei Key Laboratory of Digital Textile Equipment Wuhan Textile University Wuhan430200 China School of Electrical and Information Engineering Wuhan Institute of Technology Wuhan430205 China School of Information Engineering Wuhan City Polytechnic Wuhan430064 China

ISBN: (纸本)9798350303759

The control objective of Pendubot is to stabilise the system in a vertically upward position by swinging up from a vertically downward position. Facing various physical constraints in practical applications, this paper proposes a swing-up stabil-isation control strategy based on a nonlinear model prediction method to accomplish the above control objective. On the basis of the system dynamics model, the forward Euler method is used to construct a nonlinear prediction model of the system. According to the control objectives and physical constraints of the system, the performance index function is designed, and then the control inputs of each sampling cycle are obtained through rolling optimisation and feedback correction, so that the system state gradually converges to the target trajectory, thus achieving the motion control objective. Based on the simulation results, it can be seen that the strategy proposed in this paper is efficient and robust under external disturbances. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Integrated sensing and full-duplex communication: Joint transceiver beamforming and power allocation

arXiv

引用

arXiv 2023年

作者： He, Zhenyao Xu, Wei Shen, Hong Ng, Derrick Wing Kwan Eldar, Yonina C. You, Xiaohu National Mobile Communications Research Laboratory Southeast University Bangladesh School of Electrical Engineering and Telecommunications University of New South Wales Australia Faculty of Mathematics and Computer Science Weizmann Institute of Science

Beamforming design has been widely investigated for integrated sensing and communication (ISAC) systems with full-duplex (FD) sensing and half-duplex (HD) communication. To achieve higher spectral efficiency, in this paper, we extend existing ISAC beamforming design by considering the FD capability for both radar and communication. Specifically, we consider an ISAC system, where the base station (BS) performs target detection and communicates with multiple downlink users and uplink users reusing the same time and frequency resources. We jointly optimize the downlink dual-functional transmit signal and the uplink receive beamformers at the BS and the transmit power at the uplink users. The problem is formulated to minimize the total transmit power of the system while guaranteeing the communication and sensing requirements. The downlink and uplink transmissions are tightly coupled, making the joint optimization challenging. To handle this issue, we first determine the receive beamformers in closed forms with respect to the BS transmit beamforming and the user transmit power and then suggest an iterative solution to the remaining problem. We demonstrate via numerical results that the optimized FD communication-based ISAC leads to power efficiency improvement compared to conventional ISAC with HD communication. Copyright © 2023, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

research of Improved TD3 Robotic Arm Path Planning using Evolutionary Algorithm

Research of Improved TD3 Robotic Arm Path Planning using Evo...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Feng Zhang Jianqiang Xiong Shuai Yuan Ke Wen School of Electrical and Control Engineering Shenyang Jianzhu University Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Branch of National Special Computer Engineering Technology Research Center Shenyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

Nowadays, application of automated intelligent robot arm devices to improve industrial production efficiency has become a popular research field in the world. The previous off-line path planning method of robotic arm has the inadequacies of low efficiency and slow speed. Although the deep reinforcement learning has accomplished many achievements in the path planning of control manipulator, there are still some problems such as long training time and low planning accuracy. To solve the abovementioned issues, we propose an improved Twin Delayed Deep Deterministic policy gradient (TD3) algorithm (Improved Cross-Entropy Method-TD3: ICEM-TD3) for the path planning of the robotic arm. First, this paper combines evolutionary strategies with TD3 to generate action networks. Then the exploration of TD3 algorithm in the action space is replaced by the exploration in the parameter space. In addition, this paper designs a new reward function to weaken the redundancy of planning and accelerate the convergence speed of training. Finally, the Gazebo simulator is adopted to verify the proposed algorithm, and the results illustrate that the proposed algorithm can greatly improve the accuracy of the path planning of the manipulator using deep reinforcement learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Visual-Kinematic Fusion and Monte Carlo Initialization for Fast-Deployable Cable-Driven Robots

Graph-Based Visual-Kinematic Fusion and Monte Carlo Initiali...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： R. Khorrambakht H. Damirchi M.R. Dindarloo A. Saki S.A. Khalilpour Hamid D. Taghirad Stephan Weiss Electrical & Computer Engineering Department Control/Robotics Research Laboratory Tandon School of Engineering New York University Brooklyn NY School of Computer Science University of Adelaide Australia Faculty of Electrical Engineering University of Technology Tehran Iran Department of Smart Systems Technologies University of Klagenfurt Austria

Ease of calibration and high-accuracy task-space state-estimation purely based on onboard sensors is a key requirement for enabling easily deployable cable robots in real-world applications. In this work, we incorporate the onboard camera and kinematic sensors to drive a statistical fusion framework that presents a unified localization and calibration system which requires no initial values for the kinematic parameters. This is achieved by formulating a Monte-Carlo algorithm that initializes a factor-graph representation of the calibration and localization problem. With this, we are able to jointly identify both the kinematic parameters and the visual odometry scale alongside their corresponding uncertainties. We demonstrate the practical applicability of the framework using our state-estimation dataset recorded with the ARAS-CAM suspended cable driven parallel robot, and published as part of this manuscript.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Q-learning Sampling Based on Advantages 5

Deep Q-learning Sampling Based on Advantages

引用

5th International Conference on Intelligent Robotics and control engineering, IRCE 2022

作者： Xie, Ming Ren, Xinrui Yu, Jianbo Shu, Feng Shanghai Engineering Research Center of Ultra-Precision Motion Control and Measurement Academy for Engineering and Technology Fudan University Shanghai China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China School of Microelectronics Fudan University State Key Laboratory of ASIC and System Shanghai200433 China

ISBN: (数字)9781665469951

ISBN: (纸本)9781665469951

Deep Q-learning (DQN) has shown recent success on a wide range of complicated sequential decision-making issues, especially in the classic control area. However, in most DQN training, the sampling policies, particularly the ϵ-greedy policy and its derivation rules, produce noise erroneously due to the unsteadiness and unreliability of Q values utilized for searching for optimum actions. We begin with a fundamental hypothesis: complete advantages-based exploitation may be employed to help in successful exploration, and the gap between advantages on outstanding and poor actions tends to extend during the early phases of training before stabilizing. We then present a novel DQN architecture with a superior sampling policy that is totally and directly based on advantage values. This new DQN is named A-sampling DQN, and it requires minor code changes based on the original DQN codes. In most cases, A-sampling DQN and its derivatives outperformed the traditional DQN method. © 2022 IEEE.

关键词： Deep learning

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：