检索结果-内蒙古大学图书馆

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Yunshuai Gao Yingsong Li Luyu Zhao Zhixiang Huang Eugene Sinkevich Vladimir Mordachev Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China EMC R and D laboratory Belarusian State University of Informatics and Radioelectronics Minsk Belarus

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

A novel miniaturized and low-profile FSS is presented for electromagnetic shielding, which consists of a layer of metal patch and a layer of dielectric substrate, resulting in a small unit and low profile with a thickness of only $0.0054\lambda$ , where $\lambda$ corresponds to the resonant frequency of the first operating band. Additionally, the folded structure not only reduces the unit size but also creates two stop bands, corresponding to around 7.7GHz and 16.7GHz. There is a low-insertion passband between the stopbands, which has a bandwdith of 2G Hz wide. The created FSS allows for signal transmission within the passband while it suppresses unrelated signals incident from both sides.

关键词： Wireless communication Conferences Dielectric substrates Resonant frequency Metals Interference Electromagnetic compatibility

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

LCS-based Visual Recognition for AGV Guide Paths under Complex Illumination Conditions 15

LCS-based Visual Recognition for AGV Guide Paths under Compl...

引用

15th International Conference on Measurement Technology and Mechanical Automation, ICMTMA 2023

作者： Wang, Z.M. Li, M. Gao, C. Jin, X.M. School of Computer Science and Technology Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

Complex lighting is one of the most challenging problems in automatic guided vehicle (AGV) vision recognition system. In order to overcome the influence of uneven illumination on the accuracy and robustness of path recognition, this paper proposes the LCS based visual recognition for AGV guide paths under complex illumination conditions method, which converts the collected image into an invariant image through logarithmic chromaticity space (LCS) to eliminate the influence of illumination, and the minimum average entropy angle is used as the projection angle to generate the invariant image to improve the speed of image conversion to the invariant image. Experimental results show that the proposed method can effectively improve the robustness of AGV vision recognition system under complex lighting conditions. © Published under licence by IOP Publishing Ltd.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

A Microwave Sensor for Detection of Water Adulteration and Spoilage in Milk Based on Split-Ring Resonator

A Microwave Sensor for Detection of Water Adulteration and S...

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Shuying Ding Yingsong Li Zhixiang Huang Eugene Sinkevich Vladimir Mordachev Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China EMC R and D Laboratory Belarusian State University of Informatics and Radioelectronics Minsk Belarus

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

The paper introduces a microwave sensor based on split-ring resonators (SRR) for detecting the moisture content and spoilage of milk. This sensor is characterized by its simple structure and high sensitivity, utilizing SRR to enhance the local electric field intensity of the electromagnetic field. By measuring the transmission characteristics of microwave signals, it can accurately detect the moisture content and spoilage of milk samples. The sensor operates at a frequency of 6 GHz and has dimensions of 30×25×1.6 mm³. The study establishes the relationship between resonance frequency and water content in milk through simulated data, which provides an effective method for monitoring milk quality and holds potential applications in the food industry, contributing significantly to ensuring food safety.

关键词： Microwave measurement Microwave integrated circuits Dairy products Sensitivity Resonant frequency Moisture Microwave sensors

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware Superpoint Graph Transformer for Weakly Supervised 3D Semantic Segmentation

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1899-1912页

作者： Fan, Yan Wang, Yu Zhu, Pengfei Hui, Le Xie, Jin Hu, Qinghua Tianjin University College of Intelligence and Computing Tianjin300350 China Ministry of Education of the People's Republic of China Engineering Research Center of City Intelligence and Digital Governance China Haihe Laboratory of Itai Tianjin China Northwestern Polytechnical University School of Electronics and Information Shaanxi Key Laboratory of Information Acquisition and Processing China Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

Weakly supervised 3D semantic segmentation has successfully mitigated the labor-intensive and time-consuming task of annotating 3D point clouds. However, reliably utilizing the minimal point-wise annotations for unlabeled data in complex and large-scale scenes is still challenging, such as only 20 points labeled in 2 million points. To tackle this challenge, we propose a new Uncertainty-aware Superpoint Graph Transformer (UaSGT) framework that utilizes minimal annotations for unlabeled data learning through reliable long-range supervision propagation from labeled superpoints to unlabeled superpoints. First, we propose a superpoint graph transformer to achieve long-range supervision propagation along the attention-based fuzzy subsets defined on superpoints. The attention-based fuzzy subset measures the membership of unlabeled superpoints to clusters centered on labeled superpoints. Second, we employ an uncertainty-aware membership rectification technique on the fuzzy subset to ensure reliable propagation among superpoints within the same category. This technique integrates an uncertainty prediction module to mask the influence of unreliable membership and a spatial prior refinement module to reduce uncertainty in intra-class membership degrees. Finally, experimental results on two large-scale benchmarks S3DIS and ScanNet-V2 demonstrate the superiority of our approach compared to the state-of-the-art with at least 90% annotation reduction, and our method also achieves comparable performance to fully supervised methods with less than 0.1% labeled points. Our code is available at https://***/fanyan0411/UaSGT. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimization Strategies for Hydrogen Mixing Scheduling in Natural Gas Networks in Integrated Energy Systems

Optimization Strategies for Hydrogen Mixing Scheduling in Na...

引用

IEEE International Conference on Power and Power and Renewable Energy (ICPRE)

作者： Zixun Zhang Xiaohan Fang Yuan Fan Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei China

Developing a clean and efficient Integrated Energy System (IES) is critical to optimizing the use of renewable energy sources and harnessing new forms of energy to achieve the country’s 2030 carbon peak and 2060 carbon neutrality targets. Existing natural gas pipelines in China facilitate the transport of hydrogen blended into the natural gas network and offer the possibility of storing hydrogen blended into natural gas pipelines. This paper proposes an optimal integrated energy dispatch strategy based on electricity-gas-hydrogen-heat-cooling demand, taking into account carbon emissions and economic efficiency, where renewable energy is no longer connected to the grid or stored in batteries, but converted to hydrogen mixed into the natural gas grid for transport and storage, with the economic objective of minimizing the total IES operating cost, the wind and light abandonment cost and the carbon emission cost. The CPLEX solver is used to solve the problem, and the feasibility of the proposed model is verified by simulation results, which promotes the consumption of renewable and clean energy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Drug-Protein Interaction Prediction by Fusion of Attention and Graph Neural Network 42

Drug-Protein Interaction Prediction by Fusion of Attention a...

引用

42nd Chinese Control Conference, CCC 2023

作者： Chen, Tianrui Tuo, Shouheng Feng, Zengyu School of Computer Science and Technology Xi'An University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi'an710121 China Xi'An Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China

ISBN: (纸本)9789887581543

The identification of drug-protein interactions (DTIs) is a critical step in drug development and repositioning. However, detecting these interactions using scientific methods presents a formidable challenge. Existing models often struggle to extract relevant information from drug-protein sequences, and they fail to consider pre-existing interactions between pairs. Here, we introduce a deep learning model, DPAG, based on attention mechanisms and graph neural networks, which overcomes these limitations. DPAG leverages information from both the drug and protein sequences, as well as the association between drug-protein pairs, to predict DTIs. We conducted multiple experiments to evaluate the performance of the model in benchmark datasets, and the results showed that DPAG achieved excellent performance in terms of AUC, AUPR, precision, and recall. Our findings suggest that DPAG holds significant potential as a promising tool for predicting DTIs in drug development and repositioning. Code is available at https://***/veresse/DPAG. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Stackelberg Game Model for Optimal Dispatching of Electricity Consumption for Community Microgrid Considering Demand Response Mechanism

Stackelberg Game Model for Optimal Dispatching of Electricit...

引用

IEEE International Conference on Power and Power and Renewable Energy (ICPRE)

作者： Di Tan Xiaohan Fang Yuan Fan Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei China

Community microgrid is a kind of new power system that acts as an intermediary between community consumers and the grid, playing an important role in realising distributed autonomy and improving the power supply level. To achieve optimal power dispatch in community microgrid, this paper establishes a Stackelberg game model with the community microgrid operator (CMO) as the leader and the consumers aggregator as the follower, and combines the internal pricing method with the demand response mechanism. The paper uses a combination of genetic algorithm and solver to solve the Stackelberg game model to maximise the interests of all parties. Simulation results show that the model can secure the interests of each game subject, balance power supply and demand, and promote peak shaving and valley filling of electrical loads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Target Localization based on Double RIS

Enhanced Target Localization based on Double RIS

引用

International Symposium on Wireless Communication Systems (ISWCS)

作者： Lei He Liping Li Yingsong Li Paulo S. R. Diniz Run Ying The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei The Universidade Federal do Rio de Janeiro Rio de Janeiro

ISBN: (数字)9798350362510

ISBN: (纸本)9798350362527

Reconfigurable intelligent Surface (RIS) has become an enabling technology for economically and efficiently realizing intelligent and reconfigurable wireless communication environments. Previous positioning research based on RIS has mainly focused on single RIS without considering the improvement in positioning accuracy brought by double RIS, thus failing to reveal the full potential of a double RIS-assisted wireless communication system. This paper investigates a target positioning system assisted by double RIS, where double RIS is used to enhance communication between users and the receiver. Firstly, the reception signal model based on the collaborative effect of double RIS is constructed, and then we formulate the target positioning problem based on this model, aiming to obtain the optimal target signal while minimizing system noise. Moreover, to verify the effectiveness of the localization system with double RIS assistance, we also configured a scenario of a single RIS localization system for comparative analysis. Simulation results indicate that the proposed target positioning method based on double RIS exhibits certain superiority in improving system positioning performance compared to single RIS.

关键词： Location awareness Wireless communication Accuracy Simulation Noise Estimation Collaboration

来源：评论

学校读者我要写书评

暂无评论

Mixture of experts for audio-visual learning 24

Mixture of experts for audio-visual learning

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Ying Cheng Yang Li Junjie He Rui Feng School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing and Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University and Shanghai Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

With the rapid development of multimedia technology, audio-visual learning has emerged as a promising research topic within the field of multimodal analysis. In this paper, we explore parameter-efficient transfer learning for audio-visual learning and propose the Audio-Visual Mixture of Experts (AVMoE) to inject adapters into pre-trained models flexibly. Specifically, we introduce unimodal and cross-modal adapters as multiple experts to specialize in intra-modal and intermodal information, respectively, and employ a lightweight router to dynamically allocate the weights of each expert according to the specific demands of each task. Extensive experiments demonstrate that our proposed approach AVMoE achieves superior performance across multiple audio-visual tasks, including AVE, AVVP, AVS, and AVQA. Furthermore, visual-only experimental results also indicate that our approach can tackle challenging scenes where modality information is missing. The source code is available at https://***/yingchengy/AVMOE.

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：