检索结果-内蒙古大学图书馆

Towards non-uniform shadow removal using shadow adaptive normalization

Digital Signal Processing 2025年 166卷

作者： Xinjie Li Yang Zhao Yuan Chen Dong Wang Li Cao Xiaoping Liu School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui 230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei Anhui 230009 China School of Internet Anhui University Hefei Anhui 230039 China

Image shadow removal has received increasing attention in recent years. Existing deep learning-based shadow removal methods usually rely on the assumption of globally uniform illumination or employ simplified multiplicative illumination models to estimate parameters related to shadow-free image reconstruction. However, the shading process often contains non-uniform, diverse, and complex shadow patterns, substantially reducing the robustness of current shadow removal techniques and limiting their performance. To address this issue, this paper revisits the traditional shadow degradation model and introduces a pixel-wise adaptive non-uniform illumination model. Building upon this model, a shadow adaptive normalization (SAN) module is designed to estimate the parameter maps of the illumination model and rectify the shadow features within the latent space. The proposed SAN dynamically performs attentive normalization on shadow region features, which can align the statistical distributions of shadow and non-shadow regions. To enhance the efficiency of the SAN module, this paper introduces an intra-module complexity reduction strategy to reduce computational complexity while improving the stability of the training process. In addition, to mitigate the color deviation between paired training data, this paper introduces a Poisson-function-based loss to achieve color robustness. Extensive experiments on image shadow triplet dataset (ISTD), adjusted image shadow triplet dataset (ISTD+), and shadow removal dataset (SRD) validate the superiority of the proposed method over other state-of-the-art (SOTA) approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Charging Power Forecast of EVCS: Reinforcement Learning Assisted Deep Learning Approach

arXiv

引用

arXiv 2022年

作者： Li, Yuanzheng He, Shangyang Li, Yang Ge, Leijiao Lou, Suhua Zeng, Zhigang School of Artificial Intelligence and Automation Key Laboratory on Image Information Processing and Intelligent Control of Ministry of Education Huazhong University of Science and Technology Wuhan430074 China China-Belt and Road Joint Laboratory on Measurement and Control Technology Wuhan430074 China China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering Northeast Electric Power University Jilin 132012 China The Key Laboratory of Smart Grid of Ministry of Education Tianjin University Tianjin 300072 China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan430074 China

The electric vehicle (EV) and electric vehicle charging station (EVCS) have been widely deployed with the development of large-scale transportation electrifications. However, since charging behaviors of EVs show large uncertainties, the forecasting of EVCS charging power is non-trivial. This paper tackles this issue by proposing a reinforcement learning assisted deep learning framework for the probabilistic EVCS charging power forecasting to capture its uncertainties. Since the EVCS charging power data are not standard time-series data like electricity load, they are first converted to the time-series format. On this basis, one of the most popular deep learning models, the long short-term memory (LSTM) is used and trained to obtain the point forecast of EVCS charging power. To further capture the forecast uncertainty, a Markov decision process (MDP) is employed to model the change of LSTM cell states, which is solved by our proposed adaptive exploration proximal policy optimization (AePPO) algorithm based on reinforcement learning. Finally, experiments are carried out on the real EVCSs charging data from Caltech, and Jet Propulsion Laboratory, USA, respectively. The results and comparative analysis verify the effectiveness and outperformance of our proposed framework. Copyright © 2022, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Groundwater resources survey of tongchuan city using the audio magnetotelluric method

引用

Applied Geophysics 2020年第5期17卷 660-671,900页

作者： Xu Zhi-min Tang Jing-tian Li Guang Xin Hui-Cui Xu Zhang-jian Tan Xin-ping LI Jin Heibei Instrument&Meter Engineering Technology Research Center Chengde Petroleum CollegeChengde 067000China School of Geosciences and Info-Physics Central South UniversityChangsha 410083China Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Monitoring Ministry of Education(Central South University)Changsha 410083China Northwest Research Institution of Engineering Investigations and Design Xi’an 710003China School of Geophysics and Measurement-control Technology Nanchang 330013China College of Information Science and Engineering Hunan Normal UniversityChangsha 410081China

The development of Tongchuan City,Shaanxi Province,located in the northwestern region of China,is restricted by water *** direct current resistivity and induced polarization sounding methods are typically applied in finding urban *** methods,however,are not effective due to their complicated topography and geological *** application practice shows that the audio magnetotelluric(AMT)method has a large depth of exploration,high work effi ciency,and high lateral *** investigate the distribution of groundwater resources,we deployed three audio-frequency magnetotelluric profiles in the city *** impedance tensor information of AMT data is obtained using *** data dimension analysis reveals that the two-dimensional structural features of the observation area are *** main structure of the observation area is about 45°northeast,as indicated by structural trend analysis.A shallow two-dimensional electrical profile of 1 km in Tongchuan City is obtained by two-dimensional nonlinear conjugate gradient ***,combined with regional geological information,the geological structure characteristics reflected by the electrical profile were obtained along with the detailed characteristics of water-rich structures in the *** infl uence of the structure on the groundwater distribution was analyzed,and the water-rich areas were identifi *** work contributes to the prospective development of Tongchuan City.

关键词： urban geology audio magnetotelluric sounding method electrical structure groundwater resources

来源：评论

学校读者我要写书评

暂无评论

Experiment on the Influence of Drill String Damping and Pressurization Device on Bottom Hole Wob(Weight on Bit) Fluctuation

SSRN

引用

SSRN 2022年

作者： Yongwang, Liu Zhang, Hongning Niu, Yixiang Lin, Guojun Liu, Wentao Li, Yiwu School of Petroleum Engineering in China University of Petroleum Qingdao266580 China Ministry of Education Qingdao266580 China Shandong Ultro-deep Drilling Process Control Tech R&D Center Qingdao266580 China SINOPEC Research Institute of Petroleum Engineering Beijing100101 China Zhengzhou Shiqi Measurement and Control Technology CO. LTD Zhengzhou45001 China Beijing Liuhe Greatness Technology Co. Ltd. Beijing100160 China

Large amplitude and high frequency WOB fluctuation will lead to problems such as low rock breaking efficiency, short service life and slow drilling speed. This problem is particularly prominent in hard and difficult to drill formation and multi interlayer formation. The development of drilling string damping and pressurization device provides an idea for the utilization of vibration energy. Theoretically, the installation of drill string damping and pressurization device can ensure the smooth operation of the bit. However, up to now, the influence of the characteristic parameters and application methods of drill string damping and pressurization device on the WOB fluctuation at the bit is not clear. Based on the drill string dynamics experimental device, the influence of drill string damping and pressurization device on WOB fluctuation at the bit is tested and analyzed. The results show that whether the drill string vibration damping and pressurization device can stabilize the bit WOB is related to its elastic stiffness, installation position, bit speed and WOB;When the WOB remains unchanged, the elastic stiffness of the elastic element of the drill string damping and pressurization device increases, and the fluctuation range of the WOB at the bit increases;Increasing the rotating speed and increasing the WOB is conducive to controlling the WOB fluctuation of the bit. Under the condition of high rotating speed, shortening the distance between the drill string damping and pressurization device and the bit is conducive to restraining the WOB fluctuation. The research results provide a reference for the design, development and application of damping elements of drilling string damping and pressurization device. © 2022, The Authors. All rights reserved.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Federated Multi-Agent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multi-Microgrid Energy Management

arXiv

引用

arXiv 2022年

作者： Li, Yuanzheng He, Shangyang Li, Yang Shi, Yang Zeng, Zhigang School of Artificial Intelligence and Automation Key Laboratory on Image Information Processing and Intelligent Control of Ministry of Education Huazhong University of Science and Technology Wuhan430074 China China-Belt and Road Joint Laboratory on Measurement and Control Technology Wuhan430074 China China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering Northeast Electric Power University Jilin132012 China The Department of Mechanical Engineering University of Victoria VictoriaBC V8P 5C2 Canada

The utilization of large-scale distributed renewable energy promotes the development of the multi-microgrid (MMG), which raises the need of developing an effective energy management method to minimize economic costs and keep self energy-sufficiency. The multi-agent deep reinforcement learning (MADRL) has been widely used for the energy management problem because of its real-time scheduling ability. However, its training requires massive energy operation data of microgrids (MGs), while gathering these data from different MGs would threaten their privacy and data security. Therefore, this paper tackles this practical yet challenging issue by proposing a federated multi-agent deep reinforcement learning (F-MADRL) algorithm via the physics-informed reward. In this algorithm, the federated learning (FL) mechanism is introduced to train the F-MADRL algorithm thus ensures the privacy and the security of data. In addition, a decentralized MMG model is built, and the energy of each participated MG is managed by an agent, which aims to minimize economic costs and keep self energy-sufficiency according to the physics-informed reward. At first, MGs individually execute the self-training based on local energy operation data to train their local agent models. Then, these local models are periodically uploaded to a server and their parameters are aggregated to build a global agent, which will be broadcasted to MGs and replace their local agents. In this way, the experience of each MG agent can be shared and the energy operation data is not explicitly transmitted, thus protecting the privacy and ensuring data security. Finally, experiments are conducted on Oak Ridge national laboratory distributed energy control communication lab microgrid (ORNL-MG) test system, and the comparisons are carried out to verify the effectiveness of introducing the FL mechanism and the outperformance of our proposed F-MADRL. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A High-Fidelity Virtual Liver Model Incorporating Biological Characteristics

SSRN

引用

SSRN 2022年

作者： Zhang, Xiaorui Zhang, Wenzheng Sun, Wei Song, Aiguo Xu, Tong Wuxi Research Institute Nanjing University of Information Science & Technology Wuxi214100 China Engineering Research Center of Digital Forensics Ministry of Education Jiangsu Engineering Center of Network Monitoring School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China School of Automation Nanjing University of Information Science & Technology Nanjing210044 China State Key Laboratory of Bioelectronics Jiangsu Key Lab of Remote Measurement and Control School of Instrument Science and Engineering Southeast University Nanjing210096 China University of Southern California Los AngelesCA United States

Flexible tissue modeling plays an important role in the field of telemedicine. It is related to whether the soft tissue deformation process can be accurately, real-time and vividly simulated during surgery. Most existing models lack the unique biological characteristics. To enhance visual perception ability, a high-fidelity virtual liver model incorporating biological characteristics, such as the viscoelastic, anisotropic and nonlinear biological characteristics, is proposed based on the finite element model with the fourth-order Runge-Kutta method. When simulating the resection of diseased livers, the model undergoes a plastic deformation process where the model loses elasticity due to excessive deformation, but does not reach the cutting fracture threshold. To improve the fidelity of the liver model, this study is the first to introduce the viscoplasticity of biological tissues to the liver model. The 3DMax2020 and OpenGL4.6 were used to build a liver surgery simulation platform, and the PHANTOM OMNI manual controller was used to sense the feedback force during the operation. The proposed model was verified from three aspects of accuracy, fidelity and real-time performance. The experimental results show that the proposed virtual liver model can achieve real visual reproduction, with natural deformation effect, accurate simulation and high fidelity. © 2022, The Authors. All rights reserved.

关键词： Simulation platform

来源：评论

学校读者我要写书评

暂无评论

Deployment of NRF in the Docker and Kubernetes - Based NFV Platform

Deployment of NRF in the Docker and Kubernetes - Based NFV P...

引用

Workshops of the 34th International Conference on Advanced Information Networking and Applications, WAINA 2020

作者： Huang, Di Xu, Zhan Tian, Zhigang Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science & Technology University Beijing China School of Information and Communication Engineering Beijing Information Science & Technology University Beijing China Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783030440374

Network Function Virtualization (NFV) which is one of the core technologies plays an important role in reality. NFV permits using Virtual Network Functions (VNF) as software components on top of a virtualization system (i.e., Virtual Machines or Containers) hosted in a cloud, which makes network services and functions deployed in high flexibility and elasticity. Therefore, based on this design concept, in 5G core networks, NRF (Network Repository Function), which was implemented in a server, supports network function of registering and monitoring conditions. It achieves automatic management, selection, and scalability of network function services. In this paper, NRF is deployed in Docker and Kubernetes-based NFV platform in the form of JSON + HTTP/2.0 that supports service discovery function. The performance is tested on a hardware platform, including Network Function (NF) Register, NF Update and NF Deregister. From the testing data, we can find that the NRF in the Docker and Kubernetes-based NFV platform is better than only Docker implemented platform. © 2020, Springer Nature Switzerland AG.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Retraction of lumbar disc herniation achieved by noninvasive techniques: A case report

引用

World Journal of Clinical Cases 2021年第27期9卷 8082-8089页

作者： Ping Wang Cai Chen Qing-Hao Zhang Guo-Dong Sun Cong-An Wang Wei Li State Key Laboratory of Precision Measurement Technology and Instruments Tianjin UniversityState Key Laboratory of Precision Measurement Technology and InstrumentsTianjin UniversityTianjin 300072China Shandong Academy of Chinese Medicine Jinan 250014Shandong ProvinceChina Medical Rehabilitation Research Center Shandong Institute of Advanced TechnologyChinese Academy of SciencesJinan 250000Shandong ProvinceChina Bone Biomechanics Engineering Laboratory of Shandong Province Neck-Shoulder and Lumbocrural Pain Hospital of Shandong First Medical UniversityJinan 250062Shandong ProvinceChina Academy of Medical Engineering and Translational Medicine Tianjin UniversityTianjin 300072China Department of Rehabilitation The Third Affiliated Hospital of Shandong First Medical University(Affiliated Hospital of Shandong Academy of Medical Sciences)Jinan 250031Shandong ProvinceChina Shandong First Medical University and Shandong Academy of Medical Sciences Neck-Shoulder and Lumbocrural Pain HospitalShandong Medicinal Biotechnology CenterJinan 250062Shandong ProvinceChina School of Control Science and Engineering Biomedical Engineering InstituteShandong UniversityJinan 250061Shandong ProvinceChina

BACKGROUND Lumbar disc herniation(LDH)has emerged as one of the most common causes of low back *** routine treatment approach involves chemonucleolysis therapy,discectomy by percutaneous endoscopy,and percutaneous laser disc ***,all of these methods carry inherent risk of causing harm to the patient and,as such,there is an unmet but urgent need for an effective and safe noninvasive treatment for *** purpose of this report is to describe a non-invasive method for re-absorption of *** SUMMARY A 34-year-old woman was admitted with a complaint of waist pain that she reported as having become acutely aggravated over the past 3 d and accompanied by discomfort in the right lower *** self-reported medical history included persistent postpartum low back pain from 7 years *** exam showed positivity for neck flexion test(Lindner sign)and supine abdomen test;the straight leg-raising test showed right 60(+)and left 80(-).Findings from standard imaging(magnetic resonance)and collective physical examinations indicated a L5/S1 herniated lumbar *** consisted of three-dimensional(balanced regulating)spinal manipulation and acupuncture,upon which the LDH resolved by *** Following L5/S1 herniated lumbar disc diagnosis,three-dimensional(balanced regulating)spinal manipulation combined with acupuncture therapy is an effective treatment.

关键词： Low back pain Lumbar disc herniation Retraction Three-dimensional spinal manipulation Balance regulating Manipulation Case report

来源：评论

学校读者我要写书评

暂无评论

Robust Beamforming for Localization-Aided Millimeter Wave Communication Systems

arXiv

引用

arXiv 2022年

作者： Sun, Junchang Ma, Shuai Li, Shiyin Yang, Ruixin Min, Minghui Seco-Granados, Gonzalo The School of Information and Control Engineering China University of Mining and Technology Xuzhou221116 China The Department of Telecommunications and Systems Engineering Universitat Autònoma de Barcelona Barcelona08193 Spain The Engineering Research Center of Intelligent Control for Underground Space Ministry of Education China University of Mining and Technology Xuzhou221116 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Shanxi Key Laboratory of Information Communication Network and Security Xian University of Posts and Telecommunications Xian710121 China

In this letter, we investigate a robust beamforming problem for localization-aided millimeter wave (mmWave) communication systems. To handle this problem, we propose a novel restriction and relaxation (R&R) method. The proposed R&R method aims at minimizing the total transmit power while the positioning error follows a Gaussian distribution. Specifically, in the restriction phase of R&R, the probabilistic constraint is transformed into the deterministic form by using the Bernstein-type inequality. In the relaxation phase of R&R, the non-convex optimization problem is reformulated into a convex semidefinite program (SDP) by using semidefinite relaxation (SDR) and first-order Taylor expansion methods. To the best of our knowledge, we first consider the impact of the distribution of the positioning error on the channel state information (CSI), which further influences the data rate. Numerical results present the trade-off of the beamforming between the communication and positioning. © 2022, CC BY.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Emergent chiral toplogical point gaps in a non-Hermitian quasiperiodic Su-Schrieffer-Heeger model

arXiv

引用

arXiv 2025年

作者： Liang, Zhi-Bin Li, Shan-Zhong Li, Runze Li, Zhi Key Laboratory of Atomic and Subatomic Structure and Quantum Control Ministry of Education Guangdong Basic Research Center of Excellence for Structure and Fundamental Interactions of Matter School of Physics South China Normal University Guangzhou510006 China Guangdong Provincial Key Laboratory of Quantum Engineering and Quantum Materials Guangdong-Hong Kong Joint Laboratory of Quantum Matter Frontier Research Institute for Physics South China Normal University Guangzhou510006 China Centre for Quantum Physics Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement MOE School of Physics Beijing Institute of Technology Beijing100081 China Beijing Key Lab of Nanophotonics & Ultrafine Optoelectronic Systems School of Physics Beijing Institute of Technology Beijing100081 China

We study a quasiperiodic Su-Schrieffer-Heeger lattice with staggered on-site gain-loss. The results reveal that on-site staggered gain-loss can effectively induce non-Hermitian topological gap without introducing imaginary phase. Further analysis exhibits that five different processes of topological phase transitions, including topological re-entrant phenomena, with the gain-loss intensity increasing. In addition, through the analysis of inverse participation ratios, normalized participation ratios, winding number and other indicators, we find that topological phase transitions occur synchronically with localized phase transitions. Finally, by investigating the properties of dual space eigenfunction, we reveal that the non-Hermitian topological point gaps predicted in this paper are chiral point gaps, which have a pair of skin modes along opposite directions simultaneously. Copyright © 2025, The Authors. All rights reserved.

关键词：

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：