检索结果-内蒙古大学图书馆

17th International Conference on Intelligent Robotics and Applications, ICIRA 2024

作者： Li, Meng Yun, Juntong Jiang, Du Tao, Bo Li, Gongfa Liu, Rong Liu, Ying Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Wuhan430081 China Research Center for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Wuhan430081 China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Wuhan430081 China Precision Manufacturing Research Institute Wuhan University of Science and Technology Wuhan430081 China School of Medicine Wuhan University of Science and Technology No. 1 Huangjia Lake University Town Wuhan430065 China School of Mechanical Engineering Hubei Engineering University Xiaogan432000 China

ISBN: (纸本)9789819607761

Image segmentation plays a crucial role in target recognition as it provides an essential prerequisite for identifying targets. However, UNet cannot acquire comprehensive information about the image, which limits its ability to effectively segment small and discrete objects. A new network structure, called MorNet, is proposed. It applies dilation and erosion operations in morphological opening and closing for connected and discrete region segmentation. MorNet effectively integrates global segmentation images, emphasizing small and discrete area segmentation and enhancing the segmentation of large continuous areas. This method enhances the understanding of the location of organs and diseased sites, enabling accurate segmentation. A side-out (SO) monitoring mechanism is introduced into the decoder to provide monitoring information for the original image and the predicted results. Compared with current UNet-like networks, our proposed method achieved the highest Dice scores (96.4635%, 94.0514%, 94.3444%) and PPV scores (94.2226%, 90.2361%, 91.5582%) for liver tumor, brain tumor, and liver segmentation tasks, respectively. The experimental results show that MorNet successfully combines the segmentation of connected and discrete regions. MorNet locates organs and lesions more accurately than current state-of-the-art medical image segmentation models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Transmission Schedule for Remote State Estimation in CPSs with Energy Harvesting and Sharing Two-Hop Networks

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green communications and Networking 2025年

作者： Xing, Wei Zhang, Junfeng Zong, Guangdeng Wang, Yuhan Zhao, Xudong Hainan University School of Information and Communication Engineering China Tiangong University School of Control Science and Engineering China Ministry of Education Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Dalian University of Technology China

This paper investigates the problem of optimizing the transmission schedule between a sensor and a relay in cyber-physical systems to achieve accurate remote state estimation. The considered system model represents the plant as a linear time-invariant system, wherein the sensor measurements are transmitted to the remote estimator using an intelligent relay. Both the sensor and relay nodes are capable of harvesting energy from the external environment, and they are required to make transmission decisions at each time step to ensure the stability of system's operation. In addition, energy sharing between each other can yield significant advantages by capitalizing on the available battery power and maximizing energy harvesting from the external environment. We describe the problem of finding the optimal transmission schedule as a dynamic programming model, and establish structural properties on the optimal schedule of the sensor and relay nodes, more precisely, (i) for given battery levels and harvested energy, the optimal transmission strategy is to transmit the measurements when the error covariances at the relay and the remote estimator meet certain conditions, (ii) for given harvested energy and error covariances at the relay and the remote estimator, the optimal transmission strategy is a threshold-based strategy on the battery levels. © 2025 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Coordinated and Optimized Scheduling of Integrated Energy System Based on Improved Beluga Algorithm 9th

Coordinated and Optimized Scheduling of Integrated Energy Sy...

引用

9th Purple Mountain Form on Smart Grid Protection and control, PMF 2024

作者： Zhang, Zhuanqin Wang, Hui Xiao, Jieping Zhou, Weichao Zhao, Zijun Guan, Baojin School of Electrical Engineering and Information Technology Changchun Institute of Technology Changchun130012 China National Local Joint Engineering Research Center for Smart Distribution Grid Measurement and Control with Safety Operation Technology Changchun130012 China State Grid Jilin Electric Power Co. Ltd. Yanbian Power Supply Company Yanbian133000 China Jilin Institute of Chemical Technology Jilin132022 China

ISBN: (纸本)9789819616701

In order to solve the problems of low energy utilization, high carbon emission and poor economic benefit of integrated energy system, this paper proposes an improved beluga algorithm to realize coordinated and optimal dispatching of integrated energy system. Firstly, the operation framework of the integrated energy system is built, and the two-stage electricity-to-gas model and carbon trading mechanism model were constructed. Secondly, the improved Moby Dick algorithm is used to optimize the comprehensive energy system. Finally, the matlab2021a+gurobi solution environment is used to verify the solution. The results show that the proposed algorithm can effectively improve the energy utilization rate of the system, while ensuring the low carbon and economy of the integrated energy system. © State Grid Electric Power 2025.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-agent Federated Reinforcement Learning for Task Offloading 7th

Robust Multi-agent Federated Reinforcement Learning for Task...

引用

7th International Conference on Wireless communications, Networking and Applications, WCNA 2023

作者： Yan, Dibao Wang, Yongfeng Hou, Wenjing Song, Huanhuan Wen, Hong Ma, Wendi Sun, Fan School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent IoT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

With the proliferation of various mobile smart devices, edge computing and computational offloading technologies have emerged as pivotal support mechanisms, enhancing the service quality of these devices. To facilitate the learning of task offloading strategies across diverse and complex scenarios, this study introduces a federated learning strategy algorithm based on multi-agent deep reinforcement learning. This algorithm aims to aggregate the training strategies of multiple edge computing devices, thereby enabling the synthesis of superior task offloading strategies tailored to a wide array of environments while also providing safeguards against malicious nodes. This paper specifically examines the reward inversion attack, illustrating the algorithm’s capability to identify and counteract such malicious threats effectively. Experimental results validate that the proposed algorithm not only robustly defends against these attacks but also adeptly learns the task offloading strategies pertinent to each node. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Causal Attention Transformer for Video Text Retrieval

引用

IET Image Processing 2025年第1期19卷

作者： Lan, Hua Lv, Chaohui School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China

In the metaverse, video text retrieval is an urgent and challenging need for users in social entertainment. The current attention-based video text retrieval models have not fully explored the interaction between video and text, and only brute force feature embedding. Moreover, Due to the unsupervised nature of attention weight training, existing models have weak generalization performance for dataset bias. Essentially, the model learns that false relevant information in the data is caused by confounding factors. Therefore, this article proposes a video text retrieval method based on causal attention transformer. Assuming that the confounding factors affecting the performance of video text retrieval all come from the dataset, a structural causal model that conforms to the video text retrieval task is constructed, and the impact of confounding effects during data training is reduced by adjusting the front door. In addition, we use causal attention transformer to construct a causal inference network to extract causal features between video text pairs, and replace the similarity statistical probability with causal probability in the video text retrieval framework. Experiments are conducted on the MSR-VTT, MSVD, and LSMDC datasets, which proves the effectiveness of the retrieval model proposed in this paper. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and technology.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Adaptive communication Spectrum Sensing Algorithm Based on Energy Detection 7th

Adaptive Communication Spectrum Sensing Algorithm Based on E...

引用

7th International Conference on Wireless communications, Networking and Applications, WCNA 2023

作者： Shi, Weihong Tang, Tao Zhao, Runhui Wen, Hong Feng, Xuewei School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent loT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

Based on the traditional energy detection algorithm, an adaptive communication spectrum sensing algorithm based on energy detection is proposed for signals whose noise power is difficult to be estimated accurately. The algorithm takes into account the problem of large error in calculating the energy detection judgment threshold by noise power when the estimated value of noise power is inaccurate, and is able to perform adaptive communication spectrum sensing for signals with less a priori information and noise power that cannot be estimated accurately. Simulation results show that the adaptive communication spectrum sensing algorithm based on energy detection can effectively improve the performance of spectrum sensing for signals, and the algorithm can effectively detect and sense signals under the condition of reasonable setting of judgment coefficients. © The Author(s) 2025.

关键词： Adaptive Cognitive radio Energy detection Spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

An Offline Learning-Based Anti-interference communication Scheme for UAV Networks 7th

An Offline Learning-Based Anti-interference Communication Sc...

引用

7th International Conference on Wireless communications, Networking and Applications, WCNA 2023

作者： Tang, Tao Zhao, Runhui Wen, Hong Feng, Xuewei Shi, Weihong Peng, Yulin School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China Sichuan Intelligent IoT Communication Technology Engineering Research Center UESTC Chengdu China

ISBN: (纸本)9789819624089

Unmanned Aerial Vehicles (UAV) face challenges from advanced interference technologies, making them susceptible to malicious node attacks, data interception, and tampering. Traditional anti-interference decisions have limitations, as they cannot adaptively adjust to changes in interference signals. Moreover, anti-interference communication models based on Deep Reinforcement Learning (DRL) require prolonged interactions with the environment, demanding high requirements for anti-interference environments. This paper investigates an offline anti-interference decision based on Decision-Transformers, which can quickly and stably acquire practical anti-interference decision models. Simulation experiments have verified the effectiveness of this algorithm in making anti-interference decisions under AWGN and fading channel conditions. Furthermore, this offline approach can achieve the expected reward targets with fewer training iterations. © The Author(s) 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Chaotic index modulation and subcarrier intra-block-inter-block shuffling for secure CO-OFDM-PON based on a hybrid 4D chaos

引用

Optics Express 2025年第10期33卷 21217-21235页

作者： Wang, Yun Pan, Xiaolong Zhang, Qi Xin, Xiangjun Gao, Ran Yao, Haipeng Tian, Feng Wang, Fu Li, Zhipei Liu, Xiangyu Tian, Qinghua Wang, Yongjun Yang, Leijing Zhou, Sitong Li, Zuolin Li, Ying School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China Beijing Key Laboratory of Space-round Interconnection and Convergence BUPT Beijing 100876 China School of Information and Electronics Beijing Institute of Technology (BIT) Beijing 100081 China School of Information and Communication Engineering BUPT Beijing 100876 China Beijing Institute of Control and Electronic Technology Beijing 100038 China Beijing Institute of Remote Sensing Equipment Beijing 100039 China

In this paper, a four-dimensional (4-D) encryption scheme with chaotic index modulation (IM) and subcarrier intra-block-inter-block shuffling is proposed to enhance the physical layer security of coherent orthogonal frequency division multiplexing passive optical network (CO-OFDM-PON). The scheme utilizes a hybrid 4-D chaotic scheme consisting of 1-D Cubic chaotic mapping and 3-D T-S Fuzzy chaotic system to generate four dynamic scrambling factors to achieve 4-D ultra-high security encryption of index bits, data bits, intra-subcarrier block, and inter-subcarrier block. Firstly, the chaotic many-to-many mapping rule between index bits and subcarrier activation patterns (SAPs) is constructed based on the IM principle to realize the index bit encryption;secondly, the data bit encryption is realized by heterodyning with chaotic bits. Further, the chaotic shuffling algorithm is proposed to disrupt and rearrange the symbols within and between subcarrier blocks to realize OFDM-IM symbol secondary encryption. To validate the feasibility of the proposed encryption scheme, simulations in a CO-OFDM-PON system evaluate the performance of a 63.76 Gb/s encrypted 16 quadrature amplitude modulation (QAM) OFDM-IM signal over transmission distances of 25 km and 80 km through standard single-mode fiber (SSMF). The results demonstrate that legitimate users can successfully recover the encrypted signals, while eavesdroppers consistently experience a bit error rate (BER) close to 0.5, making it nearly impossible to extract useful information. The initial value sensitive tolerance precision of the key (x0, y0, z0, w0, a1, b1, c1, a2, b2, c2, a3, b3, c3, µ) is (10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁶, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁵, 10⁻¹⁴, 10⁻¹⁶, 10⁻¹⁶, 10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁵, 10⁻¹⁵), and the key space is as high as 10²¹⁰. The proposed scheme achieves th

关键词： Frequency division multiplexing Laser communications Neural networks Optical access networks Signal transmission Single mode fibers

来源：评论

学校读者我要写书评

暂无评论

Optical attenuation coefficient based optical coherence tomography angiography

引用

Optics communications 2025年 586卷

作者： Xiang, Ben Ding, Ning Jiang, Huiwen Liu, Jian Yu, Yao Luan, Jingmin Zhao, Yuqian Wang, Yi Yang, Yanqiu Wang, Fengwen Ma, Zhenhe School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinhuangdao066004 China College of Information Science and Engineering Northeastern University Shenyang110819 China School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China

In this study, we reported an optical coherence tomography angiography (OCTA) method based on optical attenuation coefficients (OAC), called OAC-based decorrelation (OACD), for mapping high-quality microvascular images. OACD utilizes the OAC instead of amplitude or phase to calculate flow signals, so OACD can intrinsically suppress noise arising from phase errors and intensity variations in OCT signals caused by the blood flow in superficial vasculature. The performance of the newly proposed algorithm is tested against previously reported OCTA algorithms (i.e., split-spectrum amplitude and phase-gradient angiography (SSAPGA) and principal component analysis (PCA)). Compared to SSAGPA and PCA, OACD can provide enhanced motion contrast in phantoms and in vivo experiments, facilitating better differentiation between vessels and static tissue. Benefiting from these advantages, the vascular images processed by the OACD method exhibit increased vascular visibility and connectivity, enhancing overall image quality. Our method holds promise for disease diagnosis and monitoring. © 2025 Elsevier B.V.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

A Deep Reinforcement Learning-Based Multi-Objective Charging Scheduling Method for Electric Vehicle Charging Station

引用

IEEE Internet of Things Journal 2025年

作者： Zhao, Qiang Wu, Wenwei Cheng, Ningyu Guo, Ge Han, Yinghua Northeastern University at Qinhuangdao School of Control Engineering Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology Qinghuangdao066004 China Northeastern University at Qinhuangdao School of Control Engineering Qinhuangdao066004 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110004 China Northeastern University at Qinhuangdao School of Computer and Communication Engineering Hebei Qinhuangdao066004 China

This paper investigates the charging scheduling problem within an Electric Vehicle Charging Station (EVCS), aiming to coordinate multiple charging piles to optimize the charging process. The objectives are to increase the profit for the Charging Station Operator (CSO) and enhance user satisfaction while mitigating significant fluctuations in grid load. However, since these objectives originate from different stakeholders, they are inherently conflicting;a strategy trained using fixed objective weights cannot satisfy all of them simultaneously. Additionally, uncertainties such as vehicle arrival and departure times, power requirements, and grid tariffs complicate the modeling of this process. To address these challenges, this paper reformulates the scheduling process as a Markov Decision Process (MDP) and proposes a novel model-free reinforcement learning method. By integrating randomly varying objective preferences into the inputs of agents, a set of policies corresponding to different objective preferences can be learned through a single training session. As a result, agents can execute various policies to satisfy the stakeholders’ needs based on these preferences. Moreover, a sampling adjustment strategy is introduced to improve the uniformity of the final non-dominated solution set and enhance the ability of the agent to explore the objective space. Experiments show that the proposed method can effectively solve the multi-objective problem of cooperative charging within an EVCS. Compared to the baseline method, the proposed method can achieve superior results while simultaneously reducing the computational cost to a significant extent. © 2014 IEEE.

关键词： Deep reinforcement 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：