检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Lijuan Xu Haixiao Mei Fenghua Tong Dawei Zhao Fuqiang Yu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Recent end-to-end image compressive sensing networks primarily use Convolutional Neural Networks (CNNs) and Transformers, each with distinct limitations: CNNs struggle with global feature capture, while Transformers lack local feature extraction. We propose a novel network, DCCT-Net, which combines Dynamic CNN (DCNN) and Transformer. This integration leverages DCNN’s local feature strengths and the Transformer’s global representation capabilities, resulting in superior image reconstruction quality. To further enhance the network’s performance, we propose a Feature Dynamic Augment Module (FDAM), which dynamically extracts features based on the saliency of segmented image regions, thereby amplifying the CNN’s local feature expression. Additionally, we design a Weighted Fusion Module (WFM), which optimizes the combination of local and global features extracted by the DCNN and Transformer, respectively. Extensive experiments demonstrate that our proposed DCCT-Net significantly outperforms most existing state-of-the-art methods in the field.

关键词： Image segmentation Image coding Signal processing Transformers Feature extraction Sensors Convolutional neural networks Speech processing Compressed sensing Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Probabilistic model for state assessment of offshore pipeline with anti-corrosion coating based on Wiener process and Bayesian network

引用

Ocean Engineering 2025年 337卷

作者： Xiwen Xie Haiying Li Changzheng Yin Changhong Peng School of Nuclear Science and Technology University of Science and Technology of China Hefei China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China

The demand for fresh water resources and sustainable energy is continuously growing, leading to the rapid development of nuclear energy systems. Maintaining a stable supply of electricity requires the essential service water system (SEC) to effectively cool the power generation equipment. As a key structure connecting the SEC and seawater, the integrity of pipeline affects the safety and economy of the power production. Reasonably assessing the corrosion state of pipelines in the complex marine environment is crucial for maintenance decision-making. By integrating stochastic process theory and probabilistic methods, this paper proposes an effective framework for evaluating the corrosion depth of pipelines with anti-corrosion coatings. The proposed framework leverages Wiener processes to describe the degradation behavior of anti-corrosion coatings and establishes availability models of repairable epoxy coatings with two feasible maintenance policies: periodic maintenance and state-based maintenance. Furthermore, to better align the model with real-world engineering conditions, the influence of maintenance quality on coating availability is considered. A Bayesian network is utilized to infer the probabilistic relationships between environmental variables and corrosion model parameters, with the posterior distribution means being used for corrosion depth predictions. The proposed method is practically implemented through a detailed case study of the SEC pipelines at a Chinese offshore nuclear power facility. The results illustrate the necessity of regular inspection and maintenance of pipelines to ensure their long-term service life and provide recommendations for the optimization of maintenance decisions. This framework accounts for various environmental factors and inherent uncertainties, providing a robust and comprehensive approach for estimating the long-term corrosion state of coated pipelines in marine environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The design and Implementation of Global Navigation Satellite system Remote Docking Test Platform 11th

The Design and Implementation of Global Navigation Satellite...

引用

11th EAI International Conference on Wireless and Satellite systems, WiSATS 2020

作者： Wei, Wang Qiang, Chai Weiguang, Gao Jun, Lu Shihai, Shao Yu, Bai Jingyi, Niu Wenjing, Feng Shaoqian, Li Beijing Institute of Tracking and Communication Technology Beijing100094 China GNSS System Engineering Center China Academy of Aerospace Electronics Technology Beijing100094 China Shanghai Engineering Center for Microsatellites Shanghai201203 China National Key Laboratory of Science and Technology On Communications University of Electronic Science and Technology of China Chengdu611731 China Beijing Institute of Spacecraft System Engineering Beijing100094 China

ISBN: (纸本)9783030690717

The global navigation satellite system (GNSS) includes satellites of multiple types, ground facilities with multiple functions, and various user terminals. The docking test of multiple systems in ground is an important part for managing the design, construction, and deployment of the satellite navigation system. To achieve efficient parallel docking of multiple systems, this paper designs a platform for remote docking test. Specifically, the architecture, operating process, and functional performance of the docking test platform are designed according to the task and characteristics of the docking test for satellite navigation. Besides, some key techniques are also analyzed including the management of command and dispatch for multi-node system as well as the interconnection of remote fiber. This paper implements the effective interconnection between the simulation verification system and real engineering system, and realizes command control and timing scheduling with high-precision. The designed platform has the capability of full coverage test for signal and information projects, and the capability of remote docking test for multi-systems that work in parallel. By applying our platform, the docking efficiency can be improved, the docking cost can be reduced, and the implementation of high-density networking for satellite can be promoted. © 2021, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Geometric Constellation Shaping for Wireless Optical Intensity Channels: An Information-Theoretic Approach

arXiv

引用

arXiv 2024年

作者： Zhou, Suhua Li, Tianqi Fang, Zhaoxi Zhou, Jing Zhang, Wenyi School of Automation Beijing Information Science and Technology University Beijing100192 China National Computer System Engineering Research Institute of China Beijing100083 China Department of Computer Science and Engineering Shaoxing University Shaoxing312000 China Henan Key Laboratory of Visible Light Communications Zhengzhou450002 China Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China

A simple geometric shaping method is proposed for optical wireless communication systems based on intensity modulation and direct detection (IM/DD) from an information-theoretic perspective. Constellations consisting of equiprobable levels with exponential-like distribution are obtained, which possesses asymptotic optimality in the sense that the high-SNR capacity of average-intensity constrained optical intensity channel can be approached by such constellations with increasing size. All 2b levels (b ∈ N) of the obtained constellation can be represented by a basic level and b + 2 bits, thereby reducing the required resolution of the digital-to-analog converter (DAC) without affecting the asymptotic optimality. Achievable information rate evaluations verify the asymptotic optimality. As an example, error performance results of a simple 16-level LDPC coded modulation scheme show that a shaping gain of 0.65 dB can be obtained by applying the proposed constellation design. This method can also be applied to more specific IM/DD channel models, since it only requires a near-optimal continuous input distribution. © 2024, CC BY-NC-ND.

关键词： Digital to analog conversion

来源：评论

学校读者我要写书评

暂无评论

Numerical comparison of transpiration cooling designs using real gas effects and approximate gas model

Numerical comparison of transpiration cooling designs using ...

引用

2021 International Conference on Fluid and Chemical Engineering, ICFCE 2021

作者： Wang, Meng Wang, Jianhua He, Fei Qian, Kang Wu, Yadong Zhu, Guangsheng CAS Key Laboratory of Mechanical Behaviour and Design of Materials Department of Thermal Science and Energy Engineering University of Science and Technology of China Anhui Hefei230027 China Beijing Institute of Astronautical System Engineering Beijing100076 China

In the severe high-temperature environment caused by aerodynamic heating, the vibrational excitation, dissociation and ionization of gas may successively occur, which are known as real gas effects. Under the real gas effects, the thermodynamic properties of gas vary drastically and significantly influence the performances of the active thermal protection system of hypersonic vehicles, especially in the case with coolant outflow, for example transpiration cooling. This paper numerically investigates the transpiration cooling performance with the consideration of the interaction between coolant outflow and hypersonic flow under the real gas effects. The mathematical models and coupled numerical strategy are firstly validated by experimental data, then the influences of real gas effects on the transpiration cooling of a wedged leading edge (WLE) are studied under a flight Mach number range from 8 to 12 and a flight height of 40 km. The analysis and discussions of the numerical results reveal some important phenomena and demonstrate the need to consider real gas effects.

关键词： Hypersonic vehicles

来源：评论

学校读者我要写书评

暂无评论

Experimental study of thermal and hydraulic characteristics of pressurizertype heating container during blowdown process

Experimental study of thermal and hydraulic characteristics ...

引用

2020 International Conference on Nuclear Engineering, ICONE 2020, collocated with the ASME 2020 Power Conference

作者： Ke, Bingzheng Gao, Puzhen Wang, Bo Chen, Bowen Li, Ru Tian, Ruifeng Cheng, Kun Lu, Chuan Fundamental Science on Nuclear Safety and Simulation Technology Laboratory Harbin Engineering University Harbin China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China

ISBN: (纸本)9780791883785

Blowdown process is an important process in LOCA. Studying the internal thermal hydraulic characteristics of the pressurizer during LOCA blowdown process can help to accurately analyze the process of the whole LOCA, which is of great significance to reduce the hazard of accidents and improve the safety of nuclear power plants. An experiment system of blowdown process under low pressure conditions is built, and it uses a pressure gauge and a differential pressure level gauge to measure the pressure and liquid level in the pressurizer-type heating container, and uses a thermocouple to measure the temperature in the pressurizer-type heating container at different heights and distances from the centerline. The changes of pressure, liquid level and temperature characteristics during the blowdown process were obtained. The research results show that the higher the heating power, the greater the slope of pressure change in the heating container, and the pressure changes from negative to positive growth;The greater the heating power is, the faster the liquid level decreases, and the liquid level decreases sharply after the blowdown inflection point. The greater the heating power is, the greater the rate of temperature change, from negative growth to positive growth. The temperature change rate after the blowdown inflection point is reduced. As the height increases, the temperature inside the container first increases and then decreases;the further away from the container's centerline, the higher the measured temperature. © 2020 American Society of Mechanical Engineers (ASME). All rights reserved.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

design of Programmable Droplet Manipulation Platform Based on Magnetic Control 12

Design of Programmable Droplet Manipulation Platform Based o...

引用

12th International Conference on CYBER technology in Automation, Control, and Intelligent systems, CYBER 2022

作者： Zhang, Xianmiao Liu, Jie Liu, Jiying Wang, Yuzhe Zhang, Mian Xiang, Hongbiao School of Mechanical Engineering Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin300384 China National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin University of Technology Tianjin300384 China Hong Kong Baptist University United International College Division of Culture and Creativity Beijing Normal University Guangdong Zhuhai519087 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Droplet actuation simplifies the handling of various reagents or samples and can be applied to a wide range of fields, including chemistry, biology, biomedical, and others. This paper presents a programmable droplet control system based on a magnetoelastic membrane and electromagnetic pillar array. Different magnetic blocks with different magnetization directions were designed on the silicone rubber membrane, and the magnetoelastic membrane deformed under the magnetic field generated by the array of electromagnetic pillars. By combining the gravitational forces of the droplet and the deformation of the magnetic membranes, the motion of the droplet can be controlled. Furthermore, the surface of membranes was ablated with a laser machine to impart superhydrophobic properties. The simulation results show that with the different magnetic fields, the droplet can move lengthwise, widthwise, and diagonally in the horizontal plane, and multiple droplets can be merged and mixed. In contrast to the traditional droplet control method, the droplet programmable movement control system utilizing superhydrophobic magnetoelastic membranes and an electromagnetic pillar array has better stationarity, flexibility and does not affect the basic properties of the droplets. © 2022 IEEE.

关键词： Silicones

来源：评论

学校读者我要写书评

暂无评论

Efficient Multivariate Time Series Anomaly Detection Through Transfer Learning for Large-Scale Web Services

Efficient Multivariate Time Series Anomaly Detection Through...

引用

IEEE International Conference on Web Services (ICWS)

作者： Yongqian Sun Minghan Liang Zeyu Che Dongwen Li Tinghua Zheng Shenglin Zhang Pengtian Zhu Yuzhi Zhang Dan Pei Nankai University Tianjin China Tianjin Key Laboratory of Operating System (TKL-OS) Tianjin China Haihe Laboratory of Information Technology Application Innovation (HL-IT) Tianjin China Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology (BNRist) Beijing China

Timely anomaly detection of multivariate time series (MTS) is of vital importance for managing large-scale Web services. However, many deep learning-based MTS anomaly detection models require long-term MTS training data to achieve good performance, which conflicts with frequent pattern changes in Web services entities. Moreover, the training overhead of vast MTS in large-scale Web services is unacceptable. To address these issues, we design OmniTransfer, a model-agnostic framework that combines improved hierarchical agglomerative clustering with an adaptive transfer learning strategy, making many state-of-the-art (SOTA) MTS anomaly detection models efficient and effective. Extensive experiments using real-world data from a large Web content service provider show that OmniTransfer significantly reduces the model initialization time by 59.72% and the training cost by 85.01%, while maintaining high accuracy in detecting anomalies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Downstream-agnostic Adversarial Examples

arXiv

引用

arXiv 2023年

作者： Zhou, Ziqi Hu, Shengshan Zhao, Ruizhi Wang, Qian Zhang, Leo Yu Hou, Junhui Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Cyber Science and Engineering Wuhan University China School of Information and Communication Technology Griffith University Australia Department of Computer Science City University of Hong Kong Hong Kong National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial use. In this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder. Our codes are available at: https://github. com/CGCL-codes/AdvEncoder. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Resource Allocation for On-Device Distributed Federated Learning systems

Multi-Resource Allocation for On-Device Distributed Federate...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yulan Gao Ziqiang Ye Han Yu Zehui Xiong Yue Xiao Dusit Niyato The National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of China The School of Computer Science and Engineering Nanyang Technological University Singapore Pillar of Information Systems Technology and Design Singapore University of Technology and Design (SUTD) Singapore

ISBN: (纸本)9781665435413

This work poses a distributed multi-resource allocation scheme for minimizing the weighted sum of latency and energy consumption in the on-device distributed federated learning (FL) system. Each mobile device in the system engages the model training process within the specified area and allocates its computation and communication resources for deriving and uploading parameters, respectively, to minimize the objective of system subject to the computation/communication budget and a target latency requirement. In particular, mobile devices are connect via wireless TCP/IP architectures. Exploiting the optimization problem structure, the problem can be decomposed to two convex sub-problems. Drawing on the Lagrangian dual and harmony search techniques, we characterize the global optimal solution by the closed-form solutions to all sub-problems, which give qualitative insights to multi-resource tradeoff. Numerical simulations are used to validate the analysis and assess the performance of the proposed algorithm.

关键词： Wireless communication Training Machine learning algorithms Federated learning Computational modeling Simulation Search methods

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：