检索结果-内蒙古大学图书馆

IEEE Transactions on intelligent Vehicles 2024年 1-15页

作者： Zhou, Lingyun Ning, Xinzhi You, Ming-Yi Zhang, Rongqing Shi, Qingjiang Department of Hubei Key Laboratory of Intelligent Wireless Communications Hubei Engineering Research Center of Intelligent Internet of Things Technology College of Electronics and Information Engineering South-Central Minzu University Wuhan China School of Software Engineering Tongji University Shanghai China National Key Laboratory of Electromagnetic Space Security No.36 Research Institute of CETC Jiaxing China

Unmanned aerial vehicle (UAV) swarm-based localization technology has become increasingly popular due to its exceptional maneuverability, versatile coverage capabilities, and reliable line-of-sight (LoS) connectivity. However, the accuracy improvement by exploiting UAVs' placement poses a new challenge on multi-UAV localization system. This paper investigates the placement optimization problem for a multi-UAV localization network, where each UAV is equipped with a uniform circular array (UCA) to locate the target by adopting the angle-ofarrival (AOA) measurement. To measure the accuracy of the UCA-based localization system, we characterize the measurement error to be dependent on target-to-UAV distance and present a comprehensive derivation of the Cramer-Rao lower bound ´ (CRLB). Next, we formulate the problem as a non-convex semi-infinite optimization, aiming to minimize the worst-case squared position error bound (SPEB) by designing the robust placement strategy under some stringent geometric position constraints. We address this problem by alternatively solving two sub-problems, corresponding to a slave problem for calculating the worstcase SPEB of the uncertainty region under a fixed deployment of UAVs, as well as a master problem for optimizing UAVs' placement. By virtue of the particular problem structure, we develop the gradient projection-based method for the slave problem. Meanwhile, considering the lack of a closed expression for the maximum SPEB concerning UAVs' deployment in the master problem, we devise an iterative algorithm to acquire an efficient solution with the aid of Gibbs Sampling approach. Extensive simulation results demonstrate the efficacy of the proposed algorithms. IEEE

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Learning to represent 2D human face with mathematical model

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 54-68页

作者： Liping Zhang Weijun Li Linjun Sun Lina Yu Xin Ning Xiaoli Dong AnnLab Institute of SemiconductorsChinese Academy of SciencesBeijingChina Center of Materials Science and Optoelectronics Engineering School of Integrated CircuitsUniversity of Chinese Academy of SciencesBeijingChina Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology BeijingChina

How to represent a human face pattern?While it is presented in a continuous way in human visual system,computers often store and process it in a discrete manner with 2D arrays of *** authors attempt to learn a continuous surface representation for face image with explicit ***,an explicit model(EmFace)for human face representation is pro-posed in the form of a finite sum of mathematical terms,where each term is an analytic function ***,to estimate the unknown parameters of EmFace,a novel neural network,EmNet,is designed with an encoder-decoder structure and trained from massive face images,where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of *** authors demonstrate that our EmFace represents face image more accurate than the comparison method,with an average mean square error of 0.000888,0.000936,0.000953 on LFW,IARPA Janus Benchmark-B,and IJB-C *** results show that,EmFace has a higher representation performance on faces with various expressions,postures,and other ***,EmFace achieves reasonable performance on several face image processing tasks,including face image restoration,denoising,and transformation.

关键词： artificial neural networks face analysis image processing mathematics computing

来源：评论

学校读者我要写书评

暂无评论

Boosting Meaningful Dependency Mining with Clustering and Covariance Analysis 40

Boosting Meaningful Dependency Mining with Clustering and Co...

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Wang, Xi Jin, Ruochun Huang, Wanrong Tang, Yuhua Institute for Quantum Information State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China College of Computer Science and Technology Department of Intelligent Data Science National University of Defense Technology Changsha China

ISBN: (纸本)9798350317152

Functional dependencies (FDs) form a valuable ingredient for various data management tasks. However, existing methods can hardly discover practical and interpretable FDs, especially in large noisy real-life datasets. This paper studies the problem of discovering meaningful functional dependencies (FDms) that utilize support and error parameters to capture interesting dependencies in such datasets and proposes an efficient discovery algorithm called FDM?. In order to scale with large datasets, FDM ? employs an efficient sampling method with accuracy guarantees to capture the differences between tuple pairs and to quantify the connection between support/error of dependencies on samples and those on the entire dataset. Moreover, it adopts a clustering-based correlated attributes extraction to divide the exponentially large search space into multiple small sub-spaces and proposes an easy-first traversal strategy with covariance-based guidance that quickly detects candidate dependencies and validates them. Additionally, we prove a covariance lower bound as an additional pruning criterion to reduce the search space. Extensive experiments on real-life and synthetic datasets demonstrate that FDM ? is 14 times faster than existing discovery algorithms on average, up to 31 times, and scales to larger datasets with the least memory cost. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

DASC-SPT: Towards Self-Supervised Panoramic Semantic Segmentation

DASC-SPT: Towards Self-Supervised Panoramic Semantic Segment...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Tan, Tianlong Chen, Bin Cao, Hongliang Yan, Chenggang Ma, Yike Dai, Feng Institute of Computing Technology Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Beijing China Shandong University China University of Chinese Academy of Sciences Beijing China Hangzhou Dianzi University China

ISBN: (纸本)9798331510831

Self-Supervised Semantic Segmentation, aiming to leverage masses of unlabeled data for boosting semantic segmentation, has been rapidly emerging as an active task in recent years. However, existing self-supervised semantic segmentation approaches mainly focus on planar images, leaving multiple distorted objects encountered in panoramic images unexplored due to the formidable challenge of handling heterogeneous degrees of distortions across different locations. In this paper, we propose a novel Self-Supervised Panoramic Semantic Segmentation model, termed DASC-SPT, built upon the mainstream contrastive learning framework. Towards distortions in panoramic images, we present two structures to better learn from distorted features by applying planar images. For the input images of self-supervision, we design a Spherical Projection Transformation (SPT) strategy that involves randomly projecting planar images onto various locations of the sphere to introduce the distortions. For pixel-wise distorted features, we construct a Deformation-aware Sampling Consistency (DASC) framework to further utilize the shared content and discrepancies caused by different distortions of paired views, where the deformation-aware consistency can be quantified on pixel-wise features. Both of the two components facilitate the model to adapt to distortions and boost panoramic semantic segmentation. Extensive comprehensive experiments on three panoramic datasets demonstrate the effectiveness and superiority of DASC-SPT approach. © 2025 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

K-MEANS CLUSTERING BASED SPARSE CROSS-ENTROPY MINIMIZATION ALGORITHM FOR DOA ESTIMATION

K-MEANS CLUSTERING BASED SPARSE CROSS-ENTROPY MINIMIZATION A...

引用

IET International Radar Conference 2023, IRC 2023

作者： Guo, Qiang Jiang, Hanyu Xiang, Jianhong Zhong, Yu College of Information and Communication Harbin Engineering University Harbin China Key Laboratory of Advanced Ship Communication and Information Technology Harbin Engineering University Harbin China Agile and Intelligent Computing Key Laboratory Chengdu China

ISBN: (纸本)9781839539954

Aiming at the problem that traditional greedy class compressed sensing algorithms are influenced by noise in the estimation of direction of arrival (DOA), this paper proposes the K-Means Clustering based Sparse Cross-Entropy Minimization (KMCSCEM) algorithm. First the algorithm selects atoms by minimizing the sparse cross-entropy to improve the accuracy of atom selection at the low signal-to-noise ratio (SNR). Subsequently, K-mean clustering is added in each iteration to reduce the range of atom selection, which further improves the estimation accuracy. Finally, the speed of convergence is improved by introducing an orthogonal least squares (OLS) criterion. Simulation experiments show that the proposed algorithm has an exact estimation ratio close to 90% when the SNR is less than -5 dB. © The Institution of Engineering & technology 2023.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Simulation analysis of erosion characteristics of slurry pipelines based on CFD-DDPM pipeline parameters 43

Simulation analysis of erosion characteristics of slurry pip...

引用

43rd Chinese Control Conference, CCC 2024

作者： Yuan, Haoran Wu, Jiande Xiong, Xin Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan Kunming650500 China Kunming University of Science and Technology Faculty of Information Engineering and Automation Yunnan Kunming650500 China Kunming University of Science and Technology Yunnan Key Laboratory of Intelligent Control and Application Yunnan Kunming650500 China

ISBN: (纸本)9789887581581

In order to explore the impact of pipe diameter, bend-diameter ratio and bend angle on the erosion of slurry pipe, a numerical simulation method approach grounded in Computational Fluid Dynamics - Dense Discrete Phase Model (CFD-DDPM) is proposed. Firstly, the geometric models of bends with different pipe diameters, bend-diameter ratios, and bend angles are constructed;secondly, the slurry pipe erosion model based on Dense Discrete Phase Model (DDPM) is constructed;then, model validation is conducted on the slurry pipe erosion model to affirm the accuracy of the model;finally, the computational fluid dynamics method is employed to simulate the erosion and wear behavior of the pipeline, to investigate the impact of pipe diameter, bend-diameter ratio and bend angle on the erosion and wear of the slurry pipeline. At the same time, gray correlation analysis was also used to analyze the significant relationship between the three pipeline factors and erosion and wear. The results show that the main erosion area is not determined, with the change of the pipeline parameters, the most serious erosion area will move;the effect of different pipeline parameter variations on the erosion rate is different, in which the pipe diameter of the largest impact, the second largest bend-diameter ratio, the smallest impact of the bend angle. Therefore, in the design of slurry pipeline, should first consider the influence of pipe diameter factors. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Slurry pipelines

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Overview of Swarm Coordinated Control

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 1918-1938页

作者： Yu, Dengxiu Li, Jiacheng Wang, Zhen Li, Xuelong Northwestern Polytechnical University Unmanned System Research Institute Xi'an710072 China Xi'an710072 China Northwestern Polytechnical University Key Laboratory of Intelligent Interaction and Applications Ministry of Industry and Information Technology Xi'an710072 China

In recent years, with the rapid development of swarm control technology, the swarm system has shown broad application prospects in military, civil, and other fields, which has gradually become a research hotspot in the area of automatic control. To further promote the development of swarm technology, this article reviews the detail research on the swarm control, especially the results after 2018. In order to cover all the important and hot topics in the field of swarm control research, we conducted a literature search based on the Google Scholar and Web of Science databases and collected hundreds of articles on the swarm control for review. The topics include swarm, formation, consistency, topology switching, delay control, convergence time control, obstacle avoidance, path planning, etc. Besides, the evaluation methods and applications such as vicinagearth security are introduced. Then, based on the latest existing research methods and results, the future research directions are proposed, including survival-intelligence-based, learning-based, and heterogeneous-control-based. In conclusion, the main purpose of this article is to sort out the latest achievements in the development of swarm control technology, providing important research references for scholars. © 2023 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A Meta-learning-based Domain-invariant Method for Cuff-less Blood Pressure Estimation 10

A Meta-learning-based Domain-invariant Method for Cuff-less ...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Guo, Jinpeng Fan, Feiyi Liu, Renju Jin, Yuan Zhang, Wei Chen, Yiqiang Gu, Yang Zhengzhou University Henan Institute of Advanced Technology Zhengzhou China Chinese Academy of Sciences Institute of Computing Technology Beijing China The Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China Intelligent Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798331520861

Cuff-less blood pressure estimation methods usually require personalized fine-tuning to achieve better estimation accuracy due to significant inter-individual data variability. The emerging domain generalization methods can extract blood pressure-related knowledge from diverse individuals and estimate readings for unseen subjects;however, these existing methods are less effective in aligning distributions for regression tasks on highly individual physiological time-series data. In this paper, we present a meta-learning-based approach for domainin-variant blood pressure estimation (MetaDIBP), which optimizes a temporal invariant representation learning module with a twostage meta-learning strategy. Specifically, we minimize differences between a prospective target domain and the rest of the source domains in the meta-training stage;update the model utilizing all source domains to ensure consistent and robust performance across various unseen target domains in the successive metatesting stage;and incorporate deep feature extraction, Correlation Alignment loss, and Maximum Mean Discrepancy loss into a temporal invariant representation learning module to serve as the network architecture for feature distribution discrepancy reduction. Our experimental results demonstrate that the proposed method outperforms traditional domain generalization and deep-learning-based blood pressure models, achieving a mean absolute error of 12.989 ~ m m H g for systolic blood pressure and 7.391 mmHg for diastolic blood pressure. With personalized finetuning, the mean absolute error further improves to 7.464 mmHg for systolic blood pressure and 4.509 ~ m m H g for diastolic blood pressure, showing advantages over existing methods. © 2024 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Novel camera self-calibration method with clustering prior and nonlinear optimization from an image sequence

引用

Multimedia Tools and Applications 2024年第42期83卷 90553-90572页

作者： Jiang, Xiaohui Zhu, Haijiang An, Ning Xie, Binjian Wei, Hao Tang, Fulin Wu, Yihong College of Information Science and Technology Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of Multimodal Artificial Intelligence Institute of Automation Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Intelligent Coal Mining and Strata Control Beijing100013 China Research Institute of Mine Big Data China Coal Research Institute Beijing100013 China

In many 3D reconstruction, Simultaneous Localization and Mapping (SLAM), AR, and VR systems, the camera focal length constantly changes slightly due to loose hardware, causing their performances to deteriorate. To address this problem, we propose a novel camera self-calibration method that incorporates clustering prior and nonlinear optimization. By leveraging the Kruppa equation, we roughly estimate multiple analytical solutions for the camera focal length from an image sequence. Then, robust clustering based on the Gaussian mixture model is introduced to obtain an initial camera focal length value. Finally, a nonlinear cost function is proposed to refine the initial camera focal length value. Extensive experimental results on simulation and real data demonstrate that the proposed method outperforms the state-of-the-art methods, exhibiting good robustness and high accuracy. Moreover, the proposed method can be used in real-time videos for SLAM systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cost functions

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：