检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pan, Qingtao Qiao, Wenhao Lou, Jingjiao Ji, Bing Li, Shuo School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education China Department of Computer and Data Science Department of Biomedical Engineering Case Western Reserve University United States

Semi-supervised medical image segmentation (SSMIS) uses consistency learning to regularize model training, which alleviates the burden of pixel-wise manual annotations. However, it often suffers from error supervision from low-quality pseudo labels. Vision-Language Model (VLM) has great potential to enhance pseudo labels by introducing text prompt guided multimodal supervision information. It nevertheless faces the cross-modal problem: the obtained messages tend to correspond to multiple targets. To address aforementioned problems, we propose a Dual Semantic Similarity-Supervised VLM (DuSSS) for SSMIS. Specifically, 1) a Dual Contrastive Learning (DCL) is designed to improve cross-modal semantic consistency by capturing intrinsic representations within each modality and semantic correlations across modalities. 2) To encourage the learning of multiple semantic correspondences, a Semantic Similarity-Supervision strategy (SSS) is proposed and injected into each contrastive learning process in DCL, supervising semantic similarity via the distribution-based uncertainty levels. Furthermore, a novel VLM-based SSMIS network is designed to compensate for the quality deficiencies of pseudo-labels. It utilizes the pretrained VLM to generate text prompt guided supervision information, refining the pseudo label for better consistency regularization. Experimental results demonstrate that our DuSSS achieves outstanding performance with Dice of 82.52%, 74.61% and 78.03% on three public datasets (QaTa-COV19, BM-Seg and MoNuSeg). Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Application of Genetic Algorithm for Calibration of an X-band Vector-sum Phase Shifter with Integrated Auxiliary DAC

Application of Genetic Algorithm for Calibration of an X-ban...

引用

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Evgeniy A. Fedorov Feodor I. Sheyerman Alexey V. Pomazanov Andrey A. Kokolov Dmitriy E. Minenko Leonid I. Babak Laboratory of Intelligent Computer System (LICS) Tomsk State University of Control Systems and Radioelectronics Tomsk Russia

ISBN: (数字)9781665498043

ISBN: (纸本)9781665498050

This paper presents a genetic algorithm for the discrete optimization problem, namely, the selection of optimal states of the auxiliary DACs of the X-band vector-sum phase shifter. The auxiliary DAC allows to fine-tune the VGA module and change accordingly the phase and amplitude of a signal in a small range. Genetic algorithms are able to select the optimal configuration of the auxiliary DAC of the vector-sum phase shifter in a few minutes (800-1000 iterations) in order to reduce RMS phase and amplitude errors at a defined frequency. In addition, this configuration of the vector-sum phase-shifter and optimization algorithm allows to achieve significant improvements in the characteristics in a narrow frequency band, and in this manner, it is possible to compensate for process variations. Vector-sum phase shifter manufactured using 0.25 m SiGe BiCMOS technology. The chip size is 1.51x1.05 mm 2 Minimum RMS phase and amplitude error values for 10 GHz center frequency were from 0.61 degrees and 0.26 dB respectively.

关键词： Heuristic algorithms Phase shifters Optimization methods BiCMOS integrated circuits Calibration Electron devices Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Resolution Planar Region Extraction for Uneven Terrains

Multi-Resolution Planar Region Extraction for Uneven Terrain...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Yinghan Sun Linfang Zheng Hua Chen Wei Zhang Shenzhen Key Laboratory of Control Theory and Intelligent Systems School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China School of Computer Science University of Birmingham UK

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper studies the problem of extracting planar regions in uneven terrains from unordered point cloud measurements. Such a problem is critical in various robotic applications such as robotic perceptive locomotion. While existing approaches have shown promising results in effectively extracting planar regions from the environment, they often suffer from issues such as low computational efficiency or loss of resolution. To address these issues, we propose a multi-resolution planar region extraction strategy in this paper that balances the accuracy in boundaries and computational efficiency. Our method begins with a pointwise classification preprocessing module, which categorizes all sampled points according to their local geometric properties to facilitate multi-resolution segmentation. Subsequently, we arrange the categorized points using an octree, followed by an in-depth analysis of nodes to finish multi-resolution plane segmentation. The efficiency and robustness of the proposed approach are verified via synthetic and real-world experiments, demonstrating our method’s ability to generalize effectively across various uneven terrains while maintaining real-time performance, achieving frame rates exceeding 35 FPS.

关键词： Point cloud compression Deep learning Accuracy Octrees Noise Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

A Node Confidence Determination Based Moving Target Defense Strategy for SDN

A Node Confidence Determination Based Moving Target Defense ...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Shimin Sun Guowei Xu Li Han Tianjin Key Laboratory of Autonomous Intelligent Technology and System School of Software Tiangong Tianjin China School of Computer Science and Engineering Tianjin University of Technology National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin China

With the rapid development of Internet technology, network assets have become an indispensable part of modern society. Especially in the face of high-value network assets, the attacker is faced with paying a greater cost to study the network structure. Due to the unknown attacker and attack means, the attacker has an advantage in the attack and defense situation. The moving target defense technique can flexibly change the static characteristics of the network attack surface and increase the difficulty for the attacker to detect the network, thus achieving the purpose of enhancing network security. Based on this technique, this paper proposes a defense strategy based on node confidence. It puts forward stricter constraints on the differential selection of address/port hopping paths, dynamically selects the hopping objects according to the node’s confidence, and implements the defense strategy of differential complexity. This further increases the network’s uncertainty and the difficulty for the attacker to detect the network structure. The experimental results show that in the path differentiation comparison, the maximum improvement is about 18% compared to the Dynamic Random Route Hopping strategy. In the CPU load experiment, the CPU load rate is reduced by about 4.625% on average compared to the Double Address Hopping strategy. Moreover, for larger hopping period, the proposed strategy also performs well in terms of CPU load rate. The proposed strategy also exhibits good performance in terms of CPU load ratio for large hopping cycles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Frequency stability enhancement of a two-area interconnected power system under error-based active disturbance rejection control

引用

Measurement: Journal of the International Measurement Confederation 2025年 254卷

作者： Pang, Dawei Qin, Tianmu Du, Ming Niu, Yuguang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing102206 China Beijing Huairou Laboratory Beijing101400 China

In the context of grid-connected renewable energy sources and deep peak shaving of thermal power units, the grid structure and characteristics are variable. In this regard, the application of error-based active disturbance rejection control (EADRC) in a two-area interconnected power system is considered with the aim of enhancing the frequency stability of the system. The stability of the proposed strategy is demonstrated and the effects of load variations and renewable energy output fluctuations on frequency are analyzed by modeling the two-area power system. Meanwhile, a comparison of control strategies of different orders is carried out. Simulation results show that the use of EADRC technique under NSGA-II rectification significantly improves the frequency response, both in terms of error and output smoothness. The effectiveness of the proposed strategy is verified in the IEEE 39-Bus system. The proper controller order selection and disturbance rejection core idea are beneficial to enhance the overall frequency stability of the power system. © 2025

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Method for Evaluating the Performance of Aircraft Collaborative Decision-Making Based on Dynamic Bayesian Network

Method for Evaluating the Performance of Aircraft Collaborat...

引用

Electronics and Devices, Computational Science (ICEDCS), International Conference on

作者： Wenbo Zhang Boxiao Yu Jiahui Tong Jing Li National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing Electro-Mechanical Engineering Institute Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798331527624

ISBN: (纸本)9798331527631

This research addresses the challenge of assessing equipment decision-making effectiveness in environments characterized by uncertainty and multiple influencing factors. We propose a novel approach involving the creation and optimization of a dynamic Bayesian network-based model tailored for equipment decision-making processes. The model facilitates a systematic evaluation of decision-making effectiveness by incorporating various factors, including equipment performance, environmental conditions, and enemy defensive capabilities. A comprehensive assessment system has been developed to simulate the penetration capabilities of different equipment through enemy defenses. Moreover, this study identifies potential errors in the effectiveness evaluation model by analyzing its performance in typical scenarios, pinpointing areas for enhancement.

关键词： Accuracy Uncertainty systematics Scientific computing Atmospheric modeling Computational modeling Decision making Data models Bayes methods Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Timescale Trading Strategy for Renewable Power to Ammonia Virtual Power Plant in the Electricity, Hydrogen, and Ammonia Markets

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2023年第4期1卷 322-335页

作者： Wu, Sirui Lin, Jin Li, Jiarong Liu, Feng Song, Yonghua Xu, Yanhui Cheng, Xiang Yu, Zhipeng Tsinghua University State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Department of Electrical Engineering Beijing100087 China Tsinghua University Sichuan Energy Internet Research Institute Chengdu610213 China University of Macau Department of Electrical and Computer Engineering Macau999078 China Tsinghua University Department of Electrical Engineering Beijing100087 China State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing102206 China

Renewablepower to ammonia (RePtA) is a prominent zero-carbon pathway for decarbonization. Due to the imbalance between renewables and production energy demand, the RePtA system relies on electricity exchange with the power grid. Participating in the electricity market as a virtual power plant (VPP) may help to reduce energy costs. However, the power profile of local photovoltaics and wind turbines is similar to those in the market, resulting in rising energy costs under the conventional strategy. Hence, we develop a multi-timescale trading strategy for the RePtA VPP in the electricity, hydrogen, and ammonia markets. By utilizing the hydrogen and ammonia buffer systems, the RePtA VPP can optimally coordinate production planning. Moreover, we find it possible to describe the trading of electricity, ammonia, and hydrogen in a unified timeframe. The two-stage robust optimization model of the electricity market is extended to multiple markets and solved by the column and constraint generation (CC&G) algorithm. The case is derived from an actual project in the Inner Mongolia Autonomous Region. Sensitivity analysis demonstrates the economic advantages of the RePtA VPP joining multiple markets over the conventional strategy and reveals the necessity of the hydrogen and ammonia buffer and reactor flexibility. © 2023 IEEE.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

A Recommendation system Based on Adaptive Genetic Algorithm for Enclosed Spaces 6

A Recommendation System Based on Adaptive Genetic Algorithm ...

引用

6th International Symposium on Autonomous systems, ISAS 2023

作者： Guo, Meng Chen, Songhang Wang, Yaozong Fujian Normal University College of Computer and Cyber Security Fuzhou China Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Department of Quanzhou Institute of Equipment Manufacturing Quanzhou China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Department of Quanzhou Institute of Equipment Manufacturing Quanzhou China

ISBN: (纸本)9798350316155

Most of the management systems used in common enclosed spaces only have basic functions such as booking and payment, and do not have epidemic prevention and traceability functions. In the COVID-19 pandemic, enclosed scenes, without an epidemic prevention system, clearly increase the risk of cross-contamination of the population, making it a black box that will amplify the severity of the outbreak. In this paper, we develop an intelligent recommendation system designed to coordinate the operation of enclosed spaces and decentralize the new customers to a low-infection risk box. An adaptive genetic algorithm is proposed to achieve optimal allocation of personnel and boxes, which can avoid contact between customers during low peak hours and minimize cross-contact during peak hours. On the one hand, it guarantees the user experience, and on the other hand, it guarantees these enclosed spaces have a high decentralization of crowd density when an epidemic occurs. This greatly reduces the risk of exposure to infection and is of great significance in preventing the spread of the epidemic. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Gain-Scheduled Improved Active Disturbance Rejection control for Flexible Peak-Shaving Thermal Power Units

SSRN

引用

SSRN 2024年

作者： Yang, Chaojie Chao Liu, Changliang Liu, Weiliang Liu, Shuai School of Control and Computer Engineering North China Electric Power University Beijing100096 China Baoding key Laboratory of State Detection and Optimization Regulation for Integrated Energy System Baoding070013 China

Enhance the flexibility and adaptability of peak shaving and frequency regulation for thermal power units is a necessary prerequisite for the stable operation of new energy generation and power grids. In this paper, a gain-scheduled improved active disturbance rejection control (GS-IADRC) is proposed. Firstly, the thermal process of thermal power units is uniformly equivalent to a multi-order time-delay system to accurately characterize different characteristic thermal processes. Secondly, a feedforward compensator is added based on the first-order active disturbance rejection control (ADRC) to enhance the state estimation accuracy of the extended state observer (ESO). Furthermore, based on two equivalent structures of IADRC, quantitative parameter tuning rules of IADRC are derived, and closed-loop stability is proved. Moreover, the rough relationship between the load and the controlled process is introduced into IADRC, and the parameters to be adjusted are inversely calculated using the maximum sensitivity function as a constraint condition to achieve unified robustness under multi-conditions. Finally, the single-loop and coupled system adaptability of GS-IADRC in multi-condition SST and load coordination systems are verified respectively. Compared with existing methods, GS-IADRC demonstrates superior applicability and robustness under various conditions, and simplifies the engineering applicability of GS-IADRC without decoupling in coupled system applications. © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Alignment of diffraction features in the Optical Thomson Scattering Laser at the National ignition Facility 6

Alignment of diffraction features in the Optical Thomson Sca...

引用

High Power Lasers for Fusion Research VI 2021

作者： Awwal, Abdul A. S. Integrated Computer Control System National Ignition Facility Computational Engineering Division Lawrence Livermore National Laboratory LivermoreCA94551 United States

ISBN: (数字)9781510641686

ISBN: (纸本)9781510641679

The world's largest and most energetic laser facility, the National Ignition Facility (NIF) is dedicated to understanding inertial confinement fusion by irradiating a mm scale fusion target using 192 precisely aligned laser beams. The optical Thompson scattering (OTS) laser is being commissioned to understand the target implosion physics, especially for under-dense plasma conditions. The OTS will enable the diagnosis of the plasma performance leading to better control of the symmetry and efficiency of target implosion. Both 3w and 5w probe beams can be selectively chosen for diagnosing various plasma densities. Just as the NIF laser, the OTS system is aligned using several closed loop controls. CCD images of the laser beams are analyzed using automatic alignment image processing algorithm to provide beam position and motorized mirrors are mobilized to steer those beams to the desired path and location. One such control loop of the OTS uses a pair of far field diffraction pattern generated by a spherical object connected to a shaft. During the control loop alignment movements, the diffraction rings may be partially missing due to obstruction by the aperture. This paper describes the systematic process of algorithm development for detection of the diffraction rings and the necessary modifications as the requirements change. It describes the template design and algorithm for position detection from such images under challenging illumination and obstructive conditions. Among other novelties of this work is the use of a single computational neuron, inspired by a bipolar binary associative memory, employed to evaluate the quality and uncertainty of the location measurement, and avoid false detection. © 2021 SPIE. All rights reserved.

关键词： Laser beams

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：