检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Ziyang Ye, Yiwen Pan, Yongsheng Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China Ningbo Institute of Northwestern Polytechnical University Ningbo China

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address this issue by fine-tuning pre-trained models with test data during inference. These methods, however, often suffer from less-satisfactory optimization due to suboptimal optimization direction (dictated by the gradient) and fixed step-size (predicated on the learning rate). In this paper, we propose the Gradient alignment-based Test-time adaptation (GraTa) method to improve both the gradient direction and learning rate in the optimization procedure. Unlike conventional TTA methods, which primarily optimize the pseudo gradient derived from a self-supervised objective, our method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Such gradient alignment enables the model to excavate the similarities between different gradients and correct the gradient direction to approximate the empirical gradient related to the current segmentation task. Additionally, we design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients, thereby empowering the adaptive fine-tuning of pre-trained models on diverse test data. Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Impacts of government attention on achieving Sustainable development Goals:Evidence from China

引用

Geography and Sustainability 2025年第2期6卷 181-193页

作者： Chenggang Li Ziling Chen Qutu Jiang Mu Yue Liang Wu Youhui Bao Bei Huang Alexander Boxuan Wang Yuanyuan Tan Zhenci Xu School of Big Data Application and Economics Guizhou University of Finance and EconomicsGuiyang 550025China School of Economics and Management Huazhong Agricultural UniversityWuhan 430070China Department of Geography The University of Hong KongHong Kong 999077China School of Physical and Mathematical Sciences Nanyang Technological University637371Singapore School of Economics and Management Guizhou Normal UniversityGuiyang 550025China Key Laboratory of Coast&Island Development the Ministry of Education Nanjing UniversityNanjing 210023China High School Shanghai American School Pudong CampusShanghai 201201China School of Foreign Languages Guizhou University of Finance and EconomicsGuiyang 550025China

The Sustainable development Goals(SDGs)are crucial in tackling the sustainability challenges and emerging issues faced by humanity,with government attention being a significant factor in promoting their successful ***,there is limited quantitative research systematically examining the impacts of government attention on SDGs *** study employs text analysis and a panel regression model to analyze the impacts of government attention intensity,text similarity,and tone on the achievement of SDGs,utilizing data extracted from China’s Government Work Reports spanning the decade from 2010 to *** findings reveal that the Chinese government attention to the SDGs has generally increased over *** heightened focus has notably bolstered the achievement of the SDGs,with the most significant impact observed *** attention intensity was identified as the most impactful ***,government attention intensity,text similarity,and tone have positively influenced the coupling coordination relationship between 17 SDGs,as measured by the coupling coordination degree,leading to a more harmonious and balanced achievement of socioeconomic and environmental goals in *** investment served as a moderating factor,enhancing the positive impacts of attention intensity,text similarity and tone on the promotion of SDGs *** effects of government attention on SDGs progress were notably positive in the eastern region,exhibiting greater significance in areas with stronger governance capacity compared to those with weaker governance *** study provides insightful information for enhancing the modernization and efficiency of China’s national governance system,promoting SDGs at local and global scales,and fostering sustainable transformation.

关键词： Government attention Sustainable development Coupling coordination Text analysis Financial investment SDG

来源：评论

学校读者我要写书评

暂无评论

An Overhead Crane Anti-Swing Control Method Integrating Clustering Salp Swarm Algorithm and Fuzzy PID

An Overhead Crane Anti-Swing Control Method Integrating Clus...

引用

Chinese Automation Congress (CAC)

作者： Zhe Sun Lei Yue Zhixin Sun Post Industry Technology Research and Development Center of State Posts Bureau Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing University of Posts and Telecommunications Nanjing China Nanjing University of Posts and Telecommunications Nanjing China

To address the anti-swing problem in the overhead crane system, fuzzy PID is a common approach. However, the requirement for expert involvement in parameter configuration of fuzzy PID poses challenges for its widespread application. In order to address this issue, we introduce clustering operators into the enhancement of the Salp Swarm Algorithm. By integrating Clustering Salp Swarm Algorithm and fuzzy PID and conduct comparative experiments with other classical swarm intelligence algorithms, the proposed approach enables effective fuzzy control even in the absence of expert experience. Simulation validation of this method has been conducted in the overhead crane system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective and Real-time Time-Slot Power Detection Method 3

An Effective and Real-time Time-Slot Power Detection Method

引用

3rd International Conference on Electronic Informationtechnology and Smart Agriculture, ICEITSA 2023

作者： Zhang, Xian Luo, Xinhui Qu, Taiguo Yin, Dong Huaihua University Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua University Hunan Huaihua418000 China Department of Art Design Huaihua Tourism School Hunan Huaihua418000 China

ISBN: (纸本)9798400716775

To efficiently detect the time-slot power of the Time Division Multiple Access (TDMA) communication systems such as repeaters and base stations in real-time. This article designs a signal-sampling hardware circuit based on the Advanced RISC Machine (ARM) platform and proposes a comprehensive method to calculate the time-slot power values. The signal sampling circuit uses the ADC108S052 chip with an 8-channel linked to the ARM via the Serial Peripheral Interface (SPI), and the time-slot power detection approach consists of a signal timing sampling module, sampling data reading module, and sampling data processing module to compute the detected time-slot power comprehensively. We design experiments to evaluate the efficacy of the approach to detect the time-slot power with the system power-on and normality running condition, the detection of the system CPU resource consumption for the time-slot power, the detection of the error value for the time-slot power, etc. The experimental results demonstrate that the approach can be efficient, and real-time detection of the time-slot power of the TDMA system, the system of repeaters and base stations and other systems of signal coverage, optimization and so on is of great significance. © 2023 ACM.

关键词： Signal sampling

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT AZIMUTH SAMPLING DESIGN NETWORK FOR SPARSE SAR IMAGING

AN EFFICIENT AZIMUTH SAMPLING DESIGN NETWORK FOR SPARSE SAR ...

引用

IET International Radar Conference 2023, IRC 2023

作者： Wu, Yuwei Zhang, Zhe Qiu, Xiaolan Zhao, Yao Yu, Weidong Song, Ruizhen Department of Space Microwave Remote Sensing System Beijing100090 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou215123 China Suzhou Aerospace Information Research Institute Suzhou215123 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Guangdong University of Technology Guangdong Guangzhou China

ISBN: (纸本)9781839539954

Conventional synthetic aperture radar (SAR) imaging methods based on the Nyquist sampling theorem encounters the dilemma of balancing imaging quality and resource consumption. In order to solve the problem, we propose a novel network to optimize the azimuth sampling pattern for sparse SAR imaging. We harness the impressive information extraction capabilities inherent in deep neural networks to efficiently segregate valuable information from clutter. This empowers us to extract more pertinent data while minimizing pulse utilization. Additionally, we have integrated the nonuniform fast Fourier transform (NUFFT) MF operator into the network-based SAR imaging framework, ensuring both efficiency and viability of the proposed approach. Experiments on real SAR scene data have been conducted, and both visual comparisons and numerical analysis demonstrate the efficiency and superiority of our method in the field of sparse SAR imaging. © The Institution of Engineering & technology 2023.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Momentum Recursive Darts

SSRN

引用

SSRN 2023年

作者： Ma, Benteng Xia, Yong Zhang, Yanning National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Research and Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

DARTS has emerged as a popular method for neural architecture search (NAS) owing to its efficiency and simplicity. It employs gradient-based bi-level optimization to iteratively optimize the upper-level architecture parameters and lower-level super-network weights. One of the key challenges in DARTS is the accurate estimation of gradients for both upper-level and lower-level object functions, which existing methods struggle with, leading to significant errors in gradient approximation. To address this issue, we propose a new approach called MR-DARTS that incorporates a momentum term and a recursive scheme to improve gradient estimation. Specifically, MR-DARTS leverages historical information by using a running average of past observed gradients to enhance the quality of current gradient estimation in both upper-level and lower-level functions. Our theoretical analysis shows that the variance of our estimated gradient decreases with each iteration. By utilizing momentum and a recursive scheme, MR-DARTS effectively controls the error in stochastic gradient updates that results from inaccurate gradient estimation. Furthermore, we utilize the Neumann series approximation and Hessian Vector Product scheme to reduce computational requirements and memory usage. We evaluate our proposed method on several search spaces, including NAS Bench-201 and four variants of the DARTS search space, and demonstrate its effectiveness through comprehensive experiments. © 2023, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Five-user quantum virtual local area network with an AlGaAs entangled photon source

引用

Science China(Physics,Mechanics & Astronomy) 2025年第3期68卷 61-73页

作者： Cheng Qian Hongkai Tian Xu Jing Yichen Liu Zhe Chen Huiran Luo Yuan Du Xiaodong Zheng Tangsheng Chen Yuechan Kong Hua-Lei Yin Dong Jiang Bin Niu Liangliang Lu Key Laboratory of State Manipulation and Advanced Materials in Provincial Universities School of Physical Science and TechnologyNanjing Normal UniversityNanjing210023China School of Internet Anhui UniversityHefei230039China National Key Laboratory of Solid-State Microwave Devices and Circuits Nanjing Chip Valley Industrial Technology InstituteNanjing Electronic Devices InstituteNanjing210016China Research Center for Quantum Optics and Quantum Communication School of ScienceQingdao University of TechnologyQingdao266520China Department of Physics and Beijing Key Laboratory of Opto-electronic Functional Materials and Micro-nano Devices Key Laboratory of Quantum State Construction and Manipulation(Ministry of Education)Renmin University of ChinaBeijing100872China Beijing Academy of Quantum Information Sciences Beijing100193China National Engineering Research Center of Agro-Ecological Big Data Analysis and Application Anhui UniversityHefei230601China National Laboratory of Solid-State Microstructures and School of Physics Nanjing UniversityNanjing210093China Hefei National Laboratory Hefei230088China

The promotion of quantum network applications demands the scalable connection of quantum *** is preferable to set up multiple logical networks coexisting on a single physical network infrastructure to accommodate a larger number of *** we present a quantum virtual network architecture that offers this level of scalability,without being constrained to a fixed physical-layer network relying solely on passive multiplexing *** architecture can be understood as arising from the superposition of a fully connected entanglement distribution network and port-based virtual local area network,which group multiusers by access *** terms of hardware,we leverage a semiconductor chip with a high figure-of-merit modal overlap to directly generate high-quality polarization entanglement,and a streamlined polarization analysis module,which requires only one single-photon detector for each end *** experimentally perform the BBM92 QKD protocol on the five-user quantum virtual network and demonstrate voice and image encryption on a campus area *** results may provide insights into the realization of large-scale quantum networks with integrated and cost-efficient photonic architecture.

关键词： quantum network quantum entanglement distribution integrated photonics image and voice encryption

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Blockchain System for Logistic Tracing 21

Research and Design of Blockchain System for Logistic Tracin...

引用

4th International Conference on Information Science and Systems, ICISS 2021

作者： Cai, Ziyin Yang, Meng Cui, Hongyan Li, Xiaoqiu Xu, Meng State Key Lab of Networking and Switching Tech Beijing University of Post and Telecommunication China Big Data Application Department China Mobile Information Technology Co. Ltd China Research and Development Centre China National Offshore Oil Corp Safety Technology Service Co. Ltd China

ISBN: (纸本)9781450389136

The blockchain is a decentralized network, which can prevent information to be tampered and improves the security and transparency of data. Traditional centralized database to store logistics data is vulnerable to attacks and limits sharing of information. Information isolation and unreliable data make it hard to trace the process of logistics delivery. In this paper, we propose a blockchain based system to improve the performance of logistics tracing service. We design the overall structure of the blockchain system and build a prototype using Hyperledger Fabric. Smart contract is implemented to store the logistic records into the blockchain ledgers and create tracing lists for logistic orders. Performance evaluation shows that the system achieves the logistics tracing ability with good performance. This paper assumes that the IoT devices used in the logistics process are reliable and will not be attacked. In the further work, a smart contract-based access control model can be developed to overcome the vulnerability caused by IoT devices. © 2021 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

IoT Intrusion Detection Using SDN Cloud-Edge Collaboration and Ensemble Deep Learning

IoT Intrusion Detection Using SDN Cloud-Edge Collaboration a...

引用

Cyber Science and technology Congress (CyberSciTech), IEEE

作者： Yuhua Xu Yan Li Zhixin Sun Post Big Data Technology and Application Engineering Research Center of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing China Post Industry Technology Research and Development Center of the State Posts Bureau (Internet of Things Technology) Nanjing University of Posts and Telecommunications Nanjing China Broadband Wireless Communication Technology Engineering Research Center of the Ministry of Education Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

5G technology promotes the development of Internet of Things (IoT), but IoT faces various attacks, which lead to cybersecurity threats and property damage. Software Defined Networking (SDN) is one of the key technologies of 5G, and it is a new network paradigm that facilitates monitoring network flows, enabling programmable networks. Leveraging SDN to implement intrusion detection can improve the security of local IoT. In order to ensure the reliable communication of IoT and realize the precise network protection, this paper proposes an IoT intrusion detection scheme based on SDN cloud-edge collaboration and Ensemble Deep Learning (EDL). First, the edge controller realizes the accurate classification of normal traffic and suspicious traffic through the joint model of Naive Bayesian and Back Propagation neural networks (NB - BP), and then transmits the suspicious traffic to the cloud for detection. The attack type of suspicious traffic is identified by the EDL model deployed in the cloud detector, and the result is returned to the edge controller. The controller can adopt corresponding protective measures to protect network security according to the type of attack. It is verified by experiments that NB-BP can betray normal and abnormal traffic more accurately than NB and BP models, while EDL model has higher attack category recognition accuracy than a single deep learning model.

关键词： Deep learning Cloud computing Accuracy 5G mobile communication Image edge detection Computational modeling Collaboration Detectors Internet of Things Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Optimal Dispatching of Distributed Energy Supply system Based on Model Predictive Control 7

Optimal Dispatching of Distributed Energy Supply system Base...

引用

7th Asia Conference on Power and Electrical Engineering, ACPEE 2022

作者： Li, Yanmei Li, Xiaoxue Shi, Chaoyu Li, Yan Li, Man Li, Lifeng Li, Yunpeng Xin, Ya Kunlun Digital Technology Co. Ltd. Business Department Beijing China Beijing Aerospace Data Co. Ltd. Big Data Center Beijing China China Electric Power Research Institute Artificial Intelligence Department Beijing China National Research Center for Rehabilitation and Technical Aids Testing Department Beijing China National Research Center for Rehabilitation and Technical Aids Ai Application Research Department Beijing China Beijing Aerospace Data Co. Ltd. General Headquarters Beijing China

ISBN: (纸本)9781665418195

Regionally distributed energy supply system is not only an important energy Internet physical carrier, but also the prototype and foundation of energy Internet. It focuses on physical technologies such as collaborative optimization between different energy sources. Distributed energy supply system has important research significance for exploring the internal operation mechanism of promoting advanced energy technology and different energy sources. In view of the special position of regionally distributed energy supply system in the transformation of energy system, it is particularly important to realize the scientific and reasonable coordinated operation and optimal dispatching of multiple energy in regionally distributed energy supply system, meet the demand for cooling and heating and power, and maximize the comprehensive economic benefits such as emission reduction and energy conservation. The coordinated operation and optimal scheduling of energy supply equipment in regionally distributed energy supply system is the core technology to ensure the safe, stable and economic operation of distributed energy supply system. Comprehensively considering the complex coupling characteristics of thermoelectricity and the random characteristics of renewable energy and load, coordinating the multi-directional energy flow in distributed energy supply system, studying the optimal operation mode of distributed energy supply system and optimal scheduling strategy will be the key research direction of energy Internet in the future. Based on the conventional cogeneration system, renewable energy generation is introduced. Firstly, the coupling interaction characteristics of photovoltaic power generation systems, wind power and other random power sources in the regionally distributed energy supply system and cogeneration system are considered, and the steady-state model is constructed. Then, combining the characteristics of operation of external energy supply conditions and energy su

关键词： Internet of Energy

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：