检索结果-内蒙古大学图书馆

4th International Conference on Computer science and Blockchain, CCSB 2024

作者： Zhang, Dan Yang, Yong Qu, Fuheng Liu, Yiyao School of Computer Science and Technology Changchun University of Science and Technology Changchun China School of Software Jilin Electronic Information Vocational and Technical College Jilin China

ISBN: (纸本)9798350356502

Aiming at the problems of blurred boundaries and discontinuous roads in high-resolution remote sensing images in traditional road extraction methods, a road extraction model for high-resolution remote sensing images with improved deeplabv3+ is proposed. Attention mechanism and D-Inception module are added to the encoder to obtain the global context information, capture the road detail information as well as the correlation information between the surrounding environment and the road, and finally improve the accuracy of semantic segmentation. The experimental results based on the road extraction dataset show that: The road extraction model proposed in this paper is feasible on high-resolution remote sensing images, and the Miou, Mpa, and MF1 of the roads reach 79.87%, 88.79%, and 87.08%, respectively, with high extraction accuracy. A new improvement idea and method are provided to improve the road extraction. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Safe Q-Learning for Data-Driven Nonlinear Optimal Control With Asymmetric State Constraints

引用

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2408-2422页

作者： Mingming Zhao Ding Wang Shijie Song Junfei Qiao the School of Information Science and Technology the Beijing Key Laboratory of Computational Intelligence and Intelligent Systemthe Beijing Laboratory of Smart Environmental Protectionand the Beijing Institute of Artificial IntelligenceBeijing University of Technology.Beijing 100124China IEEE the School of Mechanical and Electrical Engineering University of Electronic Science and Technology of ChinaChengdu 611731China

This article develops a novel data-driven safe Q-learning method to design the safe optimal controller which can guarantee constrained states of nonlinear systems always stay in the safe region while providing an optimal ***,we design an augmented utility function consisting of an adjustable positive definite control obstacle function and a quadratic form of the next state to ensure the safety and ***,by exploiting a pre-designed admissible policy for initialization,an off-policy stabilizing value iteration Q-learning(SVIQL)algorithm is presented to seek the safe optimal policy by using offline data within the safe region rather than the mathematical ***,the monotonicity,safety,and optimality of the SVIQL algorithm are theoretically *** obtain the initial admissible policy for SVIQL,an offline VIQL algorithm with zero initialization is constructed and a new admissibility criterion is established for immature iterative ***,the critic and action networks with precise approximation ability are established to promote the operation of VIQL and SVIQL ***,three simulation experiments are conducted to demonstrate the virtue and superiority of the developed safe Q-learning method.

关键词： Adaptive critic control adaptive dynamic programming(ADP) control barrier functions(CBF) stabilizing value iteration Q-learning(SVIQL) state constraints

来源：评论

学校读者我要写书评

暂无评论

Overcoming bubble formation in polydimethylsiloxane-made PCR chips: mechanism and elimination with a high-pressure liquid seal

引用

Microsystems & Nanoengineering 2024年第5期10卷 209-219页

作者： Shiyuan Gao Tiegang Xu Lei Wu Xiaoyue Zhu Xuefeng Wang Xiaohong Jian Xinxin Li State Key Laboratory of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghai 200050China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of SciencesBejing 100049China School of Information Science and Technology ShanghaiTech UniversityShanghai 201210China Fujian Provincial Key Laboratory of Haixia Applied Plant Systems Biology Metabolomics CenterHaixia Institute of Science and TechnologySchool of Future TechnologyFujian Agriculture and Forestry UniversityFuzhou 350002China School of Biological Engineering Sichuan University of Science and EngineeringYibin 644000China

The thermal expansion of gas and the air permeability of polydimethylsiloxane(PDMS)were previously thought to be the main causes of bubbles and water loss during polymerase chain reaction(PCR),resulting in a very complex chip design and ***,by calculating and characterizing bubble formation,we discovered that water vapor is the main cause of *** PCR,heat increases the volume of the bubble by a factor of only~0.2 in the absence of water vapor but by a factor of~6.4 in the presence of water *** addition,the phenomenon of"respiration"due to the repeated evaporation and condensation of water vapor accelerates the expansion of bubbles and the loss of water.A water seal above 109 kPa can effectively prevent bubbles in a bare PDMS chip with a simple structure,which is significant for the wide application of PDMS chips.

关键词： bubble expansion elimination

来源：评论

学校读者我要写书评

暂无评论

Research on Low Sampling Rate Digital Pre-distortion technology Based on Improved Chebyshev Polynomial

引用

Instrumentation 2023年第2期10卷 57-66页

作者： LU Xu ZHOU Xianchun ZHANG Ying YE Yuxuan School of Electronic and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044 School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing 210044

This paper presents a low sampling rate digital pre-distortion technique based on an improved Chebyshev polynomial for the non-linear distortion problem of amplifiers in 5G broadband communication *** improved Chebyshev polynomial is used to construct the behavioural model of the broadband amplifier,and an undersampling technique is used to sample the output signal of the amplifier,reduce the sampling rate,and extract the pre-distortion parameters from the sampled signal through an indirect learning structure to finally correct the non-linearity of the amplifier *** technique is able to improve the linearity and efficiency of the power amplifier and provides better *** results show that by constructing the behavioural model of the amplifier using memory polynomials(MP),generalised polynomials(GMP)and modified Chebyshev polynomials respectively,the adjacent channel power ratio of the obtained system can be improved by more than 13.87d B,17.6dB and 19.98dB respectively compared to the output signal of the amplifier without digital *** Chebyshev polynomial improves the neighbourhood channel power ratio by 6.11dB and 2.38dB compared to the memory polynomial and generalised polynomial respectively,while the normalised mean square error is effectively improved and *** shows that the improved Chebyshev pre-distortion can guarantee the performance of the system and improve the non-linearity better.

关键词： Digital Pre-distortion Improved Chebyshev Polynomials Undersampling Techniques Indirect Learning Structures

来源：评论

学校读者我要写书评

暂无评论

Dynamic Privacy Protection with Large Language Model in Social Networks 24th

Dynamic Privacy Protection with Large Language Model in So...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xie, Yizhe Zhu, Congcong Zhang, Xinyue Hu, Xiangyu Liu, Xuan School of Data Science City University of Macau Macau China Hainan International College Minzu University of China Hainan China School of Information Engineering Minzu University of China Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan China

ISBN: (纸本)9789819615445

In contemporary social networks, dynamic privacy protection remains a pivotal yet challenging endeavor due to the intricate and evolving nature of information exchange. Traditional privacy models, predominantly static, falter in effectively safeguarding privacy amidst the complex interplay of continuously changing network interactions and structures. Addressing these deficiencies, this study introduces a novel dynamic privacy protection system anchored by large language model (LLM). Leveraging the natural language processing prowess of LLM, this system excels in real-time, context-sensitive analysis and protection of textual data within vast and variable social networks. By integrating closed-loop control theory, the system adeptly balances robust privacy safeguards with the requisite fluidity of information exchange. Experimental validations on large network datasets illustrate the system’s adeptness in balancing privacy leaks and information distortion through intelligent adaptations to privacy thresholds and strategic noise injection. The outcomes highlight the system’s utility in enhancing data security and operational efficiency, promising significant implications for future applications in broader domains such as mobile computing and IoT. This study not only propels forward the capabilities of dynamic privacy protection mechanisms but also sets a foundational architecture for subsequent innovations in privacy-sensitive, data-intensive environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Water Gauge Image Denoising Model Based on Improved Adaptive Total Variation

引用

Instrumentation 2023年第1期10卷 59-68页

作者： SHI Zhenting ZHOU Xianchun ZHANG Ying LI Ting LU Siqi School of Electronic and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044 School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing 210044

As an important part of water level warning in water conservancy projects,often due to the influence of environmental factors such as light and stains,the acquired water gauge images have sticky,broken and bright spot conditions,which affect the identification of water *** solve this problem,a water gauge image denoising model based on improved adaptive total variation is ***,the regular term exponent in the adaptive total variational equation is changed to an inverse cosine function;secondly,the differential curvature is used to distinguish the image noise points and increase the smoothing strength at the noise points;finally,according to the characteristics of the gradient mode and adaptive gradient threshold after Gaussian filtering,the New model can adaptively denoise in the smooth area and protect the edge area,so as to have the characteristics of both edge-preserving *** experimental results show that the new model has a great improvement in image vision,higher iteration efficiency and an average increase of 1.6 dB in peak signal-to-noise ratio,and an average increase of 9%in structural similarity,which is more beneficial to practical applications.

关键词： Water Gauge Image Adaptive Total Variation Differential Curvature Gradient Mode Adaptive Gradient Threshold

来源：评论

学校读者我要写书评

暂无评论

Low-Light lensless image enhancement via diffusion model 14

Low-Light lensless image enhancement via diffusion model

引用

Holography, Diffractive Optics, and Applications XIV 2024

作者： Liu, Ziyang Zeng, Tianjiao He, Qifan Zhan, Xu Zhang, Wensi Zhang, Xiaoling School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781510682085

This paper introduces a deep learning-based low-light lensless image reconstruction enhancement algorithm that can effectively reconstruct low-light lensless images and achieve significant enhancement effects under low-light conditions. The algorithm comprises two stages: (1) A preliminary imaging stage, where the forward imaging model is utilized as a prior knowledge to obtain the initial reconstruction results;(2) A perceptual enhancement network built upon the conditional diffusion model for detailed enhancement, resulting in realistic images with normal lighting and reduced noise. Experimental results on simulated datasets demonstrate that this algorithm exhibits superior reconstruction performance with Learned Perceptual Image Patch Similarity (LPIPS) and Structural Similarity Index Measure (SSIM) up to 0.0887 and 0.7454, respectively, and successfully realizes the reconstruction and enhancement of lensless low-light images. © 2024 SPIE. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Approximate CN scheme and its open region problems for metamaterial rotational symmetric simulation

引用

Journal of Systems engineering and electronics 2022年第6期33卷 1081-1087页

作者： WU Peiyu YU Han HU Yenan XIE Yongjun JIANG Haolin School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Institute of Aerospace Systems Engineering Beijing 100076China School of Electronic&Information Engineering Nanjing University of Information Science and TechnologyNanjing 210096China

In order to simulate metamaterial rotational symmetric open region problems,unconditionally stable perfectly match layer(PML)implementation is proposed in the body of revolution(BOR)finite-difference time-domain(FDTD)*** precisely,the proposed algorithm is implemented by the Crank-Nicolson(CN)Douglas-Gunn(DG)procedure for BOR metamaterial *** constitutive relationship of metamaterial can be expressed by the Drude model and calculated by the piecewise linear recursive convolution(PLRC)*** effectiveness including absorption,efficiency,and accuracy is demonstrated through the numerical *** can be concluded that the proposed implementation is to take the advantages of the CNDG-PML procedure,PLRC approach,and BORFDTD algorithm in terms of considerable accuracy,enhanced absorption and remarkable ***,it can be demonstrated that the proposed scheme can maintain its unconditional stability when the time step exceeds the CourantFriedrichs-Levy(CFL)condition.

关键词： body of revolution(BOR) Crank-Nicolson(CN) finite-difference time-domain(FDTD) perfectly match layer(PML) metamaterial

来源：评论

学校读者我要写书评

暂无评论

Wavelength-decoupled reflection-type metasurface with Hybrid Phase Modulation

Wavelength-decoupled reflection-type metasurface with Hybrid...

引用

2024 International Applied Computational Electromagnetics Society Symposium, ACES-China 2024

作者： Zhang, Yuqiong Wang, Hui Liu, Tong Wen, Guangjun Xu, He-Xiu Huang, Yongjun School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Air Force Engineering University Department of Electronic Science and Technology Xi'an China

ISBN: (纸本)9798350355581

Manipulating the phase of incident electromagnetic (EM) waves is vital for directional modulation-enabled devices. Yet it still challenging to realize dual- or multi-wavelength independent phase modulations, where conventional multi-wavelength phase-controlled MSs consist of several resonant structures that make the process of design and fabrication complicated. Here, we employed a corner-truncated patch with hybrid phase modulation to simultaneously and mutually manipulate the reflective phase of dual wavelengths for circularly polarized (CP) incident EM waves, where it introduces Geometrical-Scaling-Induced (GSI) phase and Pancharatnam-Berry (PB) phase. To validate our concept, a multifunction polarization converter integrated on a 27 × 27 metasurface is devised, numerically characterized, and simulated, exhibiting distinct beam radiations within dual wavelength. Our study holds a novel possibility to realize multi-wavelength message encryption devices in smart communication and imaging systems. © 2024 IEEE.

关键词： Phase modulation

来源：评论

学校读者我要写书评

暂无评论

FusFormer: global and detail feature fusion transformer for semantic segmentation of small objects

引用

Multimedia Tools and Applications 2024年第41期83卷 88717-88744页

作者： Li, Zheng Chen, Houjin Li, Jupeng Peng, Song Zhang, Zhenhao Wang, Baozheng Wang, Changyong School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China Beijing Institute of Basic Medical Sciences Beijing100850 China

Improving the segmentation accuracy of small objects is essential for tasks such as autono-mous driving and remote sensing. However, the current main semantic segmentation methods are inadequate for small objects. To improve the segmentation accuracy of small objects, long-range global information and fine local details are needed, and neither pure Convolutional Neural Networks (CNNs) nor Vision Transformers (ViTs) can effectively provide these two different types of information simultaneously. In this paper, we introduce a novel model FusFormer for finding a solution, which contains a global branch and a detailed branch to fully capture the long-range features and spatial detail features from the input image. The global branch is based on MiT-B2 to efficiently acquire global context, while the detailed branch acquires rich local detail information by Spatial Prior Module (SPM) and Multi-scale Module (MSM). Feature Interaction Module (FIM) is proposed to perform information fusion across features at a dual scale. In addition, Multi-scale Edge Extraction Module (MSEEM) is utilized to supplement the missing edge information during model training, helping the model to better enhance the intra-class consistency of small objects. Extensive experiments on Cityscapes, ADE20K and PASCAL VOC 2012 show that our model achieves competitive overall segmentation accuracy, especially on small objects. FusFormer achieves 82.6%, 47.3% and 82.4% mIoU on the Cityscapes, ADE20K and PASCAL VOC 2012 validation sets, compared with other state-of-the-art methods, the proposed model significantly improves the IoU on small objects by 2%-4%. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Semantic Segmentation

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：