检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Luo, Xianrui Sun, Huiqiang Peng, Juewen Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of AIA Huazhong University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore

Dynamic Neural Radiance Field (NeRF) from monocular videos has recently been explored for space-time novel view synthesis and achieved excellent results. However, defocus blur caused by depth variation often occurs in video capture, compromising the quality of dynamic reconstruction because the lack of sharp details interferes with modeling temporal consistency between input views. To tackle this issue, we propose D2RF, the first dynamic NeRF method designed to restore sharp novel views from defocused monocular videos. We introduce layered Depth-of-Field (DoF) volume rendering to model the defocus blur and reconstruct a sharp NeRF supervised by defocused views. The blur model is inspired by the connection between DoF rendering and volume rendering. The opacity in volume rendering aligns with the layer visibility in DoF rendering. To execute the blurring, we modify the layered blur kernel to the ray-based kernel and employ an optimized sparse kernel to gather the input rays efficiently and render the optimized rays with our layered DoF volume rendering. We synthesize a dataset with defocused dynamic scenes for our task, and extensive experiments on our dataset show that our method outperforms existing approaches in synthesizing all-in-focus novel views from defocus blur while maintaining spatial-temporal consistency in the scene. Copyright © 2024, The Authors. All rights reserved.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Citywide package deliveries via crowdshipping:minimizing the efforts from crowdsourcers

引用

Frontiers of Computer Science 2022年第5期16卷 57-69页

作者： Sijing CHENG Chao CHEN Shenle PAN Hongyu HUANG Wei ZHANG Yuming FENG College of Computer Science Chongqing UniversityChongqing 400044China Centre de Gestion Scientifigue-I3-UMR CNRS 9217 Mines ParisTechPSL Research UniversityParis 75272France Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges UniversityChongqing 404100China

Most current crowdsourced logistics aim to minimize systems cost and maximize delivery capacity,but the efforts of crowdsourcers such as drivers are almost *** the delivery process,drivers usually need to take long-distance detours in hitchhiking rides based package *** this paper,we propose an approach that integrates offline trajectory data mining and online route-and-schedule optimization in the hitchhiking ride scenario to find optimal delivery routes for packages and ***,we propose a two-phase framework for the delivery route planning and *** the first phase,the historical trajectory data are mined offline to build the package transport *** the second phase,we model the delivery route planning and package-taxi matching as an integer linear programming problem and solve it with the Gurobi *** that,taxis are scheduled to deliver packages with optimal delivery paths via a newly designed scheduling *** evaluate our approach with the realworld datasets;the results show that our proposed approach can complete citywide package deliveries with a high success rate and low extra efforts of taxi drivers.

关键词： crowdshipping hitchhiking rides dynamic delivery optimization package delivery taxi scheduling

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: A new sequence optimization algorithm based on particle swarm for machine learning (Journal of Ambient Intelligence and Humanized Computing, (2022), 13, 5, (2601-2619), 10.1007/s12652-021-03004-3)

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 295-295页

作者： Xie, Chaofan Zhang, Fuquan Electronic Information and Engineering Institute Fuqing Branch of Fujian Normal University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

https://***/10.1007/s12652-021-03004-3. The Publisher has retracted this article in agreement with the Editor-in-Chief. The article was submitted to be part of a guest-edited issue. An investigation by the publisher found a number of articles, including this one, with a number of concerns, including but not limited to compromised editorial handling and peer review process, inappropriate or irrelevant references or not being in scope of the journal or guest-edited issue. Based on the investigation’s findings the publisher, in consultation with the Editor-in-Chief therefore no longer has confidence in the results and conclusions of this article. The authors have not responded to correspondence regarding this retraction. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Microgrid energy management strategy considering microgrid economy and rSOC stability: A model-based study

Microgrid energy management strategy considering microgrid e...

引用

第43届中国控制会议

作者： Haizhou Huang Zhiping Xia Xinkai Shan Jie Wang Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Microgrids possess the ability to use renewable energy efficiently and play an increasingly significant role in environmental protection and sustainable development. Meanwhile, reversible solid oxide fuel cell(rSOC) is currently a new type of energy conversion and storage. Combining with microgrid systems is a great way to benefit from its high capacity, high efficiency, and cleanliness. However, r SOC's complex system of coupled heat, electricity, and gas presents a significant challenge in finding energy management strategies for microgrid applications containing rSOC. In this study, for a microgrid system combining rSOC, battery energy storage system(BESS), solar photovoltaic(PV), and wind turbine generator(WTG), we propose a model-based energy management strategy that simultaneously takes into account the economy of the microgrid system and the stability of the rSOC system. First of all, the microgrid is modeled with great detail, including the wind turbine, solar panels, battery storage system, and rSOC. In addition, the microgrid energy management problem is framed as a mathematical programming problem, with the attention focusing on the costs of BESS aging and operational energy loss of rSOC. In particular,this study also proposes a penalty strategy to reduce the power fluctuation amplitude of the rSOC system and reduce the mode switching frequency of the rSOC system. Using the solver, solving for each device's target power in a microgrid. The actual power operating curve is output by tracking the target power under slope constraints using the Simulink model. We then conduct a case study using data from Wuhan, China. Our research shows that compared with the control strategy based on rule control,the control strategy proposed in this study can reduce the power variation amplitude of the rSOC system by 79%, reduce the mode switching frequency by 85%, reduce the system operating cost by 4.5% and increase the energy self-sufficiency rate by9%.

关键词： Microgrid Reversible solid oxide cell Multiple constraints Energy management system

来源：评论

学校读者我要写书评

暂无评论

A dual-stream recurrence-attention network with global–local awareness for emotion recognition in textual dialog

arXiv

引用

arXiv 2023年

作者： Li, Jiang Wang, Xiaoping Zeng, Zhigang Wuhan430074 China Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems Wuhan430074 China

In real-world dialog systems, the ability to understand the user’s emotions and interact anthropomorphically is of great significance. Emotion Recognition in Conversation (ERC) is one of the key ways to accomplish this goal and has attracted growing attention. How to model the context in a conversation is a central aspect and a major challenge of ERC tasks. Most existing approaches struggle to adequately incorporate both global and local contextual information, and their network structures are overly sophisticated. For this reason, we propose a simple and effective Dual-stream Recurrence-Attention Network (DualRAN), which is based on Recurrent Neural Network (RNN) and Multi-head ATtention network (MAT). DualRAN eschews the complex components of current methods and focuses on combining recurrence-based methods with attention-based ones. DualRAN is a dual-stream structure mainly consisting of local- and global-aware modules, modeling a conversation simultaneously from distinct perspectives. In addition, we develop two single-stream network variants for DualRAN, i.e., SingleRANv1 and SingleRANv2. According to the experimental findings, DualRAN boosts the weighted F1 scores by 1.43% and 0.64% on the IEMOCAP and MELD datasets, respectively, in comparison to the strongest baseline. On two other datasets (i.e., EmoryNLP and DailyDialog), our method also attains competitive results. Copyright © 2023, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Serialized Model and Feature Extraction Algorithm for Solid Oxide Fuel Cell State Prediction

Deep Learning-based Serialized Model and Feature Extraction ...

引用

第43届中国控制会议

作者： Jiajian Wu Kanglin Zhu Han Wu Guohui Xiang Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science & Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Deep learning-based methods have shown their wide application prospects in the field of solid oxide fuel cell(SOFC)***,the irrationality of the prediction object and the lack of prediction accuracy have hindered the progress of the prediction methods for SOFC ***,two algorithms are proposed in this study,a feature selection algorithm based on maximum information coefficient and Bayesian information criterion for identifying key variables that are sensitive to changes in the SOFC system,and a prediction model based on a genetic algorithm optimized for sequence to sequence *** M/BIC algorithm reduces the number of features by 62.5%(from 40 to 15),which contributes to the acceleration of the algorithm training and the subsequent sensor layout *** prediction model incorporates a two-dimensional convolutional neural network and a multi-head attention mechanism to capture more information in the input sequence,an encoder-decoder architecture and a Gated recurrent unit to better predict performance *** with real experimental data show significant changes in feature dimensionality reduction and prediction accuracy.

关键词： SOFC Feature selection Performance prediction Deep learning

来源：评论

学校读者我要写书评

暂无评论

Statistical Feasibility Robust Optimization for Hydrogen-Data Center Microgrid Operation

SSRN

引用

SSRN 2024年

作者： Duan, Juntao Li, Yuanzheng Li, Yang Liu, Zhiwei Zhao, Yong 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 Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China

The increasing processing demands of information technology (IT) workloads cause the booming of data centers (DCs) in recent years. The servers in the DC emit much heat when processing the IT workloads and thus the DC temperature rises. The power consumption when controlling the DC temperature using the air conditioning (A/C) of the DC is high, which leads to expensive power bills. To reduce the power cost, using renewable energy (RE) to power DC has raised much attention in recent years. However, the intermittency of RE and the uncertainties of outside temperature pose operational challenges. Therefore, in this paper, a data-driven statistical-feasibility-based robust rolling optimization framework for the operation of hydrogen-DC microgrid (H2-DCMG) is proposed to control the DC temperature considering these uncertainties and the intermittency of RE. In the framework, the hydrogen energy storage system (HESS) is introduced to deal with the intermittency of RE, and robust optimization (RO) is adopted to deal with the uncertainty of outside temperature. The statistical feasibility is introduced into the framework to decrease the conservatism of RO, through relaxing the DC temperature constraints without harming normal DC operations. Moreover, we propose the Statistical-Guarantee-based Vertex Link (SGVL) algorithm to construct a polyhedron uncertain set of outside temperatures that can ensure the results of dispatch are economical and satisfy statistical feasibility. The constructed polyhedron uncertain set is linear, which reduces computational complexity in solving. A case study based on the real-world temperature dataset verifies the superiority of the SGVL algorithm on the aspect of the economic cost. It further validates the effectiveness of the proposed robust optimization framework for DC temperature control. © 2024, The Authors. All rights reserved.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Decoupling of nitrogen and oxygen sensors based on particle swarm optimization and fuzzy feedforward compensation

Decoupling of nitrogen and oxygen sensors based on particle ...

引用

第43届中国控制会议

作者： Can Sun Zhen Wang Jie Wang Yu Qiao Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

A nitrogen oxide sensor that can accurately and quickly detect the content of nitrogen oxides in exhaust gas plays a key role in the treatment of automotive exhaust gas. Due to the characteristics of gas diffusion and chamber structure, nitrogen oxide sensors are difficult to achieve high-precision and fast measurement due to strong coupling. In order to solve this problem, this paper proposes a decoupling control strategy for nitrogen oxide sensors. On the one hand, the strategy uses fuzzy feedforward compensation, and on the other hand, it uses PID control based on particle swarm optimization to achieve control. This not only eliminates the coupling between loops, but also improves the control accuracy. The analysis shows that the design of the decoupling control strategy for nitrogen oxide sensors proposed in this paper is feasible, which allows the nitrogen oxide sensors to work in a stable and reliable state.

关键词： Nitrogen-oxygen sensor Coupling Adaptive PID Fuzzy feedforward decoupling

来源：评论

学校读者我要写书评

暂无评论

Statistical Feasibility Robust Optimization for Hydrogen-Data Center Microgrid Operation

SSRN

引用

SSRN 2024年

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Content-Aware Deep Feature Matching 4th

Content-Aware Deep Feature Matching

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Wang, Weice Li, Zuoyong Zheng, Xiangpan Lai, Taotao Keikhosrokiani, Pantea College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China College of Physics and Electronic Information Engineering Minjiang University Fuzhou350121 China School of Computer Sciences Universiti Sains Malaysia Penang Gelugor11800 Malaysia

ISBN: (纸本)9783031200984

Feature matching is a fundamental and critical step for many tasks of computer vision. In recent years, many methods for feature matching have been proposed. However, the image alignment algorithm used in the state-of-the-art matching method is not robust enough, and the number of the features extracted from the images are insufficient, thus the performance obtained by the state-of-the-art matching method is unsatisfactory. To address these issues, firstly, we use a more robust geometric estimation algorithm to align image pairs. Secondly, based on aligned image pairs, we design a content-aware block to more focus on effective features by using a feature extractor and a mask predictor. Experimental results show that our method achieves more superior results, and outperforms several classical and deep learning methods on the HPatches dataset. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

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：