检索结果-内蒙古大学图书馆

Progress in Electromagnetic Research Symposium (PIERS)

作者： Jiangling Dou Chenyang Zhao Jian Song Qingwang Wang Tao Shen School of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China Graduate School Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

As antenna structure grow in complexity, the problem of time-consuming in electromagnetic (EM) simulation have become more common. This problem undoubtedly brings a series of the challenges in raising the effectiveness of antenna optimization. In order to overcome the existing difficulties, an antenna optimization method based on RF-GWO method is proposed. This approach consists of three major components. Firstly, an artificial neural network (ANN) is used to build the dataset. Compared with the traditional sampling method, the data filtered by the artificial neural network (ANN) are closer to the optimization objective. Consequently, it can better responsive to the relationship between the antenna parameters and the optimization objective. Then, the Random Forest method (RF) is utilized to analyze the impact of the ten selected parameters based on the electromagnetic (EM) simulation results on the antenna performance. Random Forest Algorithm (RF) has strong interpretability, allowing for the assessment of the contribution of different parameters to the optimization objective, which can effectively reduce the number of design variables. Finally, the antenna optimization is performed utilizing the Grey Wolf Optimization (GWO) algorithm. Combined with the sensitivity analysis results, the Gray Wolf Algorithm (GWO) can effectively search for improved results in a faster manner. In order to evaluate the algorithm’s performance, the proposed method is employed to optimize a multiband miniaturized microstrip antenna. The result demonstrates that substantial improvement in impedance bandwidth is achieved by the proposed method, with an approximate 29% increase compared to conventional manual optimization methods. This outcome has proved potential and effectiveness of the proposed method in practical implications of antenna optimization.

关键词： Dimensionality reduction Sensitivity analysis Simulation Optimization methods Artificial neural networks Microstrip antennas Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Legal Judgment Prediction with Multiple Perspectives on Civil Cases 1st

Legal Judgment Prediction with Multiple Perspectives on Civi...

引用

1st CAAI International Conference on Artificial Intelligence, CICAI 2021

作者： Zhao, Lili Yue, Linan An, Yanqing Liu, Ye Zhang, Kai He, Weidong Chen, Yanmin Yuan, Senchao Liu, Qi Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science and School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9783030930455

Legal Judgment Prediction, which aims at predicting the judgment result based on case materials, is an essential task in Legal Intelligence. Most existing studies have analyzed and modeled criminal cases as a whole, while a small part of the research focuses on civil cases which are also significant in the legal system. In these studies, most model on a certain type of civil causes and make the judgment prediction based on the ascertained fact from the perspective of the court. However, in real-world scenarios, there are different civil cases on various causes, and every case is judged from multiple perspectives (i.e., plaintiff, defendant, and the court). It is difficult to make judgment predictions on various civil causes. To address the above challenges, in this paper, we propose a novel Civil Case Judgment (CCJudge) prediction method by simulating the logic of judges. Following this logic, we construct an external knowledge base that contains the explanations and applications of every cause, it helps make the judgment on various causes. Furthermore, a special encoder layer and interaction layer are designed for learning linguistic semantics from multiple perspectives. We conduct extensive experiments on a real-world dataset. The experimental results demonstrate the effectiveness of our method. © 2021, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

User-Specified Conditional Preferences Driven Personalized Skyline Web Services Selection

User-Specified Conditional Preferences Driven Personalized S...

引用

IEEE International Conference on Software Engineering and Service Sciences (ICSESS)

作者： Senfu Ke Xiaodong Fu Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan Province China Yunnan Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan Province China

ISBN: (数字)9798350389166

ISBN: (纸本)9798350389173

The proliferation of web services with similar functionalities challenges selecting the most relevant service based on Quality of Service (QoS). Skyline queries help by reducing the candidate pool, but the resulting service skyline can still be extensive, making selection difficult. A personalized Skyline service selection method provides a smaller, more manageable set. Current approaches often overlook inter-dependencies between user preferences, complicating complex preference management. This paper introduces CP-Skyline, an efficient method leveraging Conditional Preference Networks (CP-Nets) to incorporate user-specific preferences and personalize the service selection process. We present a personalized conditional preference model based on CP-Nets to prune candidate services and compress the query space, defining a new dominance relation for CP-Skyline computation, and validate our approach through extensive experiments on synthetic and real-world datasets.

关键词： Web services Computational modeling Quality of service Software engineering

来源：评论

学校读者我要写书评

暂无评论

A Multi-objective Antenna Optimization Method Based on Preferred Parameter Spaces

A Multi-objective Antenna Optimization Method Based on Prefe...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Jiangling Dou Siyu Lin Jian Song Qingwang Wang Tao Shen School of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China Graduate School Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

Machine learning has been successfully used in the field of multi-objective antenna design, enabling the enhancement of antenna performance and optimizing efficiency. However, the prediction within an exceptionally vast parameter space imposes significant demands on machine learning algorithms. Moreover, minor adjustments in dimensions can bring about significant alterations in antenna performance, which renders simultaneous optimization for all objectives exceedingly challenging. To solve the multi-objective antenna optimization problem, a multi-objective antenna optimization method based on a preferred parameter space is proposed. Specifically, this method utilizes the KNN algorithm to preliminarily optimize the antenna and acquire a high-quality dataset. Subsequently, the sensitivity of ten selected parameters based on the electromagnetic (EM) simulation results is calculated by the XGBoost algorithm. The value of the parameter sensitivity is acquired by averaging ten calculations. The top four ranked parameters are designated as variables while the rest are fixed as constants. This approach reduces the number of parameters for subsequent optimization, thus greatly improving the subsequent prediction accuracy while ensuring the antenna performance. Finally, the variables derived from XGBoost are input into the fruit-fly optimization algorithm (FOA) to find the near-optimal solution. Hence, the task of parameter optimization under the multi-objectives of the impedance bandwidth and circular polarization characteristics can be effectively accomplished. To further validate its performance, the proposed algorithm is applied to optimize the S-band miniaturized broadband circularly polarized antenna. Compared to the results obtained by electromagnetic simulation only, the optimized results exhibit a 17.95% improvement of impedance bandwidth and a 42.86% enhancement of axial ratio bandwidth. Numerical outcomes validate that the proposed method achieves multi-objective o

关键词： Sensitivity Optimization methods Bandwidth Prediction algorithms Approximation algorithms Broadband communication Broadband antennas

来源：评论

学校读者我要写书评

暂无评论

A Dual-Branch Model with Inter- and Intra-branch Contrastive Loss for Long-tailed Recognition

arXiv

引用

arXiv 2023年

作者： Chen, Qiong Huang, Tianlin Zhu, Geren Lin, Enlu School of Computer Science and Engineering South China University of Technology China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application China

Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the decision boundaries are ambiguous. Therefore, in this paper, we propose a simple yet effective model, named Dual-Branch Long-Tailed Recognition (DB-LTR), which includes an imbalanced learning branch and a Contrastive Learning Branch (CoLB). The imbalanced learning branch, which consists of a shared backbone and a linear classifier, leverages common imbalanced learning approaches to tackle the data imbalance issue. In CoLB, we learn a prototype for each tail class, and calculate an inter-branch contrastive loss, an intra-branch contrastive loss and a metric loss. CoLB can improve the capability of the model in adapting to tail classes and assist the imbalanced learning branch to learn a well-represented feature space and discriminative decision boundary. Extensive experiments on three long-tailed benchmark datasets, i.e., CIFAR100-LT, ImageNet-LT and Places-LT, show that our DB-LTR is competitive and superior to the comparative methods. © 2023, CC BY-NC-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Spatial-Temporal Near-Field Passive Localization Based on an Exact Spatial Propagation Model

Three-Dimensional Spatial-Temporal Near-Field Passive Locali...

引用

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

作者： Jiaxiong Fang Juan Liu Hua Chen Wei Liu Ye Tian Gang Wang Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology Ningbo China School of Electronic Engineering and Computer Science Queen Mary University of London London UK

Based on the exact source-sensor spatial geometry, a three-dimensional (3-D) spatial-temporal localization algorithm for multiple near-field (NF) sources is proposed without adopting the Fresnel approximation, which simplifies the spatial phase difference by Taylors polynomial. In addition, considering the propagation attenuation which varies from different sensors, the spatial and temporal information can be exploited to construct a third-order parallel factor (PARAFAC) data model and the array manifold matrices can be extracted by trilinear decomposition; then, estimation of the unambiguous range and angle parameters of the NF sources is achieved from the spatial amplitude-phase factors by the least squares method. The obtained 3-D parameters associated with each source require no additional pairing process, as also demonstrated by simulation results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing 41

How Universal Polynomial Bases Enhance Spectral Graph Neural...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Huang, Keke Wang, Yu Guang Li, Ming Liò, Pietro School of Computing National University of Singapore Singapore Institute of Natural Sciences School of Mathematical Sciences Zhangjiang Institute for Advanced Study Shanghai Jiao Tong University Shanghai China Shanghai AI Laboratory Shanghai China School of Mathematics and Statistics University of New South Wales Sydney Australia Zhejiang Institute of Optoelectronics Jinhua China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua China Department of Computer Science and Technology Cambridge University Cambridge United Kingdom

Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an attempt to avert prohibitive computations, numerous polynomial filters have been proposed. However, polynomials in the majority of these filters are predefined and remain fixed across different graphs, failing to accommodate the varying degrees of heterophily. Addressing this gap, we demystify the intrinsic correlation between the spectral property of desired polynomial bases and the heterophily degrees via thorough theoretical analyses. Subsequently, we develop a novel adaptive heterophily basis wherein the basis vectors mutually form angles reflecting the heterophily degree of the graph. We integrate this heterophily basis with the homophily basis to construct a universal polynomial basis UniBasis, which devises a polynomial filter-based graph neural network - UniFilter. It optimizes the convolution and propagation in GNN, thus effectively limiting over-smoothing and alleviating over-squashing. Our extensive experiments, conducted on datasets with a diverse range of heterophily, support the superiority of UniBasis in the universality but also its proficiency in graph explanation. Copyright 2024 by the author(s)

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation for Histopathology Image

SS-WSSS: Small-Scale Weakly Supervised Semantic Segmentation...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jiatai Lin Guoqiang Han Jingxuan Zhou Zhenwei Shi Zaiyi Liu Chu Han South China University of Technology Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Semantic segmentation for histopathology images is one of the fundamental tasks in computational pathology. Due to the high cost of pixel-level annotation acquisition, the weakly supervised semantic segmentation (WSSS) attempts to achieve information-intensive segmentation task for histopathology images to reduce the labeling effort of pathologists by leveraging image-level labels. However, traditional WSSS requires a large-scale training set with image-level labels, which still imposes considerable labeling costs on pathologists. To this end, this work proposes a Small-Scale Weakly Supervised Semantic Segmentation (SS-WSSS) approach to achieve the comparable performance only with small-scale weakly-labeled data to further reduce pathologist’s labeling effort. Since histopathology images can easily generate massive unlabeled data, our SS-WSSS aims to learn with the unlabeled data to bridge the information gap. First, we propose a Single-to-Multi Prototype Similarity (S2M-PS) method to generate reliable pseudo-labels for unlabeled data by measuring the similarity between single-label prototypes and multi-label feature maps. Then, we introduce a Cross-Task CoTraining (CT 2 ) method for pseudo-supervision of models with pseudo-labels self-refinement to avoid overfitting to noisy labels. We conduct the experiment on two public datasets to demonstrate the effectiveness of our SS-WSSS. In the experiment, our method achieves comparable performance with SOTA methods only using 30% labeled data.

关键词： Training Costs Histopathology Semantic segmentation Semantics Pipelines Prototypes Labeling Noise measurement Reliability

来源：评论

学校读者我要写书评

暂无评论

Design of P Band Filter Antenna with High Out-of-Band Suppression

Design of P Band Filter Antenna with High Out-of-Band Suppre...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Jiangling Dou Yinsu Yuan Jian Song Qingwang Wang Tao Shen School of Information Engineering and Automation Kunming University of Science and Technology Kunming China Yunnan Key Laboratory of Computer Technologies Application Kunming University of Science and Technology Kunming China Graduate School Kunming University of Science and Technology Kunming China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

P-band antennas offer tremendous potential in various fields, including remote sensing, communication, and radar applications. However, It is crucial to enhance their effectiveness in these domains that the current challenges in the P-band, particularly wide bandwidth and exceptional out-of-band suppression be achieved. This paper aims to introduce an efficient design scheme for a high-efficiency, high out-of-band suppression P-band filter antenna. The antenna structure comprises a Y-shaped feeding network, upper and lower parallel dielectric plates, a vertical dielectric plate, a central metal plate, and a pair of microstrip patches. The bottom feeding network employs a Y-shaped feeding network. The coupling of the antenna was effectively controlled and the good bandwidth and impedance matching have been achieved. In order to achieve a wider bandwidth and lower return loss for the antenna, slotting technology was employed on the semi-circular radiation patch. The introduction of a vertical metal plate enhances filtering performance of antenna. Additionally, there are radiation zeros at 0.68 GHz and 1.43 GHz, high-frequency selectivity is imparted and signal reflection losses are effectively reduced. key performance indicators include a filter antenna center frequency of 0.75 GHz, a −10 dB impedance bandwidth of 32.9% (0.89 GHz–1.24 GHz). In the upper stopband (0.5 GHz–0.8 GHz), the suppression level exceeds 20 dB, while in the lower stopband (1.1 GHz–1.8 GHz), suppression level exceeds 15 dB. Significant suppression characteristics are observed in the 0.5 GHz–0.8 GHz and 1.1 GHz–1.8 GHz frequency ranges. Design elements such as the semi-circular radiating patch, slotting technology, and rectangular slots on the substrate have been employed in the antenna. The suppression level, frequency selectivity had been enhance of antenna. Simulation results indicate a gain of 7.06 dB, overall efficiency beyond 95%, co-pol superior to cross-pol by more than 35 dB, and antenna

关键词： Slot antennas Filtering Simulation Bandwidth Microstrip antennas Directive antennas Dielectrics

来源：评论

学校读者我要写书评

暂无评论

MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation

arXiv

引用

arXiv 2023年

作者： Yang, Yong Chen, Qiong Feng, Yuan Huang, Tianlin School of Computer Science and Engineering South China University of Technology China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application China

Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set. However, the extracted knowledge is insufficient to cope with the variable intra-class differences since the knowledge is obtained from a few samples in the support set. To address the problem, we propose a multi-information aggregation network (MIANet) that effectively leverages the general knowledge, i.e., semantic word embeddings, and instance information for accurate segmentation. Specifically, in MIANet, a general information module (GIM) is proposed to extract a general class prototype from word embeddings as a supplement to instance information. To this end, we design a triplet loss that treats the general class prototype as an anchor and samples positive-negative pairs from local features in the support set. The calculated triplet loss can transfer semantic similarities among language identities from a word embedding space to a visual representation space. To alleviate the model biasing towards the seen training classes and to obtain multi-scale information, we then introduce a non-parametric hierarchical prior module (HPM) to generate unbiased instance-level information via calculating the pixel-level similarity between the support and query image features. Finally, an information fusion module (IFM) combines the general and instance information to make predictions for the query image. Extensive experiments on PASCAL-5i and COCO-20i show that MIANet yields superior performance and set a new state-of-the-art. Code is available at ***/Aldrich2y/MIANet. © 2023, CC BY-NC-SA.

关键词： Embeddings

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：