检索结果-南通市图书馆

Illumination Adaptive Identification Algorithm of a Reconfigurable Modular Robot

在线全文

学校读者我要写书评

暂无评论

Instrumentation 2024年第1期11卷 79-87页

作者： fangyi xing Cheng Xu Yanming Wu Hongwei Gao School of Automation and Electrical Engineering Shenyang Ligong UniversityShenyang 110158 State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 School of Instrument Science and Engineering Southeast UniversityNanjing 210096 School of Automation Shenyang Aerospace UniversityShenyang 110135

Reconfigurable modular robots feature high mobility due to their unconstrained connection *** by the snake multi-joint crawling principle,a chain-type reconfigurable modular robot(CRMR)is designed,which could reassemble into various configurations through the compound joint ***,an illumination adaptive modular robot identification(IAMRI)algorithm is proposed for *** first,an adaptive threshold is applied to detect oriented FAST features in the robot ***,the effective detection of features in non-uniform illumination areas is achieved through an optimized quadtree decomposition *** matching features,an improved random sample consensus algorithm is employed to eliminate the mismatched ***,the reconfigurable robot module is identified effectively through the perspective *** with ORB,MA,Y-ORB,and S-ORB algorithms,the IAMRI algorithm has an improvement of over 11.6%in feature uniformity,and 13.7%in the comprehensive indicator,*** IAMRI algorithm limits the relative error within 2.5 pixels,efficiently completing the CRMR identification under complex environmental changes.

关键词： reconfigurable modular robot visual identification feature detection feature matching

在线全文

学校读者我要写书评

暂无评论

冲击挤密式月球表面钻探潜入器设计

电子测量与仪器学报 2022年第11期36卷 9-16页

作者：徐成行芳仪赵宝生辽宁科技大学机械工程与自动化学院鞍山114051 中国科学院沈阳自动化研究所机器人学国家重点实验室沈阳110016 沈阳理工大学自动化与电气工程学院沈阳110158

为了提高冲击式潜入器的下潜效率,利用质量-弹簧系统建立了潜入器单周期下潜过程的动力学方程,通过遍历寻优的方式获得了潜入器高效下潜的最优质量刚度匹配关系,基于ADAMS对潜入器工作过程中的运动状态进行了仿真研究,在此基础上设计了... 详细信息

为了提高冲击式潜入器的下潜效率,利用质量-弹簧系统建立了潜入器单周期下潜过程的动力学方程,通过遍历寻优的方式获得了潜入器高效下潜的最优质量刚度匹配关系,基于ADAMS对潜入器工作过程中的运动状态进行了仿真研究,在此基础上设计了一种高性能冲击挤密式月球表面钻探潜入器,并制作了原理样机,开展了潜入器下潜特性实验。实验结果表明,相较于旧样机,所设计的潜入器下潜效率提高了63.7%,且稳定性良好,各部件运动工作协调,实际下潜深度与理论和仿真结果基本一致,具有较好的理论意义和重要的应用价值。

关键词：潜入器动力学建模 ADAMS仿真质量刚度匹配潜入实验

在线全文

学校读者我要写书评

暂无评论

高效高精度光照自适应的ORB特征匹配算法

电子测量与仪器学报 2023年第7期37卷 140-147页

作者：行芳仪徐成高宏伟沈阳理工大学自动化与电气工程学院沈阳110158 中国科学院沈阳自动化研究所机器人学国家重点实验室沈阳110016 东南大学仪器科学与工程学院南京210096

针对非均匀光照下ORB图像特征检测算法存在特征点过于聚集、匹配准确率不高等问题,提出了一种高效高精度光照自适应的ORB图像特征匹配算法。利用自适应阈值提取待测图像的oFAST特征点,通过优化的四叉树分解法均匀分配,进一步提高了低照... 详细信息

针对非均匀光照下ORB图像特征检测算法存在特征点过于聚集、匹配准确率不高等问题,提出了一种高效高精度光照自适应的ORB图像特征匹配算法。利用自适应阈值提取待测图像的oFAST特征点,通过优化的四叉树分解法均匀分配,进一步提高了低照度或高曝光区域特征点的数量,随后,根据汉明距离进行特征匹配,使用改进的RANSAC算法剔除误匹配,提高ORB算法中特征点的匹配准确率。实验结果表明,针对具有明显光照变化的数据集,相较于ORB、MA、Y-ORB及S-ORB算法,本文算法的平均特征分布均匀度提高13.1%,特征提取时间节省26.3%,综合评价指标提升18.5%,可高效完成复杂场景变化下的特征匹配,对目标识别和三维重建等领域具有较强的应用价值。

关键词： ORB算法特征检测特征匹配四叉树分解法 RANSAC算法

Insight Into the Separation-of-Variable Methods for the Closed-Form Solutions of Free Vibration of Rectangular Thin Plates

在线全文

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 329-355页

作者： Yufeng xing Ye Yuan Gen Li Institute of Solid Mechanics Beihang University(BUAA)Beijing100191China

The separation-of-variable(SOV)methods,such as the improved SOV method,the variational SOV method,and the extended SOV method,have been proposed by the present authors and coworkers to obtain the closed-form analytical solutions for free vibration and eigenbuckling of rectangular plates and circular cylindrical *** taking the free vibration of rectangular thin plates as an example,this work presents the theoretical framework of the SOV methods in an instructive way,and the bisection–based solution procedures for a group of nonlinear eigenvalue ***,the explicit equations of nodal lines of the SOV methods are presented,and the relations of nodal line patterns and frequency orders are *** is concluded that the highly accurate SOV methods have the same accuracy for all frequencies,the mode shapes about repeated frequencies can also be precisely captured,and the SOV methods do not have the problem of missing roots as well.

关键词： Separation-of-variable method Rayleigh quotient nodal line eigenvalue equation bisection method

Loss Aware Feature Attention Mechanism for Class and Feature Imbalance Issue

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 751-775页

作者： Yuewei Wu Ruiling Fu Tongtong xing Fulian Yin College of Information and Communication Engineering Communication University of ChinaBeijing100024China State Key Laboratory of Media Convergence and Communication Communication University of ChinaBeijing100024China

In the Internet era,recommendation systems play a crucial role in helping users find relevant information from large *** imbalance is known to severely affect data quality,and therefore reduce the performance of recommendation *** to the imbalance,machine learning algorithms tend to classify inputs into the positive(majority)class every time to achieve high prediction *** can be categorized such as by features and classes,but most studies consider only class *** this paper,we propose a recommendation system that can integrate multiple networks to adapt to a large number of imbalanced features and can deal with highly skewed and imbalanced datasets through a loss *** propose a loss aware feature attention mechanism(LAFAM)to solve the issue of feature *** network incorporates an attention mechanism and uses multiple sub-networks to classify and learn *** better results,the network can learn the weights of sub-networks and assign higher weights to important *** propose suppression loss to address class imbalance,which favors negative loss by penalizing positive loss,and pays more attention to sample points near the decision *** on two large-scale datasets verify that the performance of the proposed system is greatly improved compared to baseline methods.

关键词： Imbalanced data deep learning e-commerce recommendation loss function big data analysis

Domain generalization with semi-supervised learning for people-centric activity recognition

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2025年第1期68卷 171-188页

作者： Jing LIU Wei ZHU Di LI xing HU Liang SONG Academy for Engineering & Technology Fudan University Shanghai East-bund Research Institute on Networking Systems of AI School of Optoelectronic Information and Computer Engineering University of Shanghai for Science & Technology

People-centric activity recognition is one of the most critical technologies in a wide range of real-world applications,including intelligent transportation systems, healthcare services, and brain-computer interfaces. Large-scale data collection and annotation make the application of machine learning algorithms prohibitively expensive when adapting to new tasks. One way of circumventing this limitation is to train the model in a semi-supervised learning manner that utilizes a percentage of unlabeled data to reduce the labeling burden in prediction tasks. Despite their appeal, these models often assume that labeled and unlabeled data come from similar distributions, which leads to the domain shift problem caused by the presence of distribution gaps. To address these limitations, we propose herein a novel method for people-centric activity recognition,called domain generalization with semi-supervised learning(DGSSL), that effectively enhances the representation learning and domain alignment capabilities of a model. We first design a new autoregressive discriminator for adversarial training between unlabeled and labeled source domains, extracting domain-specific features to reduce the distribution gaps. Second, we introduce two reconstruction tasks to capture the task-specific features to avoid losing information related to representation learning while maintaining task-specific consistency. Finally, benefiting from the collaborative optimization of these two tasks, the model can accurately predict both the domain and category labels of the source domains for the classification task. We conduct extensive experiments on three real-world sensing datasets. The experimental results show that DGSSL surpasses the three state-of-the-art methods with better performance and generalization.

关键词： activity recognition deep learning domain generalization semi-supervised learning adversarial training

同方期刊数据库

Exploring the potential of extrachromosomal DNA as a novel oncogenic driver

在线全文

学校读者我要写书评

暂无评论

Science China Life Sciences 2025年第1期68卷 144-157页

作者： Huanbo Zhu Longtao Huangfu Junbing Chen Jiafu Ji Xiaofang xing Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing) Division of Gastrointestinal Cancer Translational Research LaboratoryPeking University Cancer Hospital & Institute Department of Gastrointestinal Cancer Center Peking University Cancer Hospital & Institute Department of Liver Surgery & Transplantation Liver Cancer InstituteZhongshan HospitalFudan University Key Laboratory of Carcinogenesis and Cancer Invasion Ministry of Education State Key Laboratory of Holistic Integrative Management of Gastrointestinal Cancers Beijing Key Laboratory of Carcinogenesis and Translational ResearchDivision of Gastrointestinal Cancer Translational Research LaboratoryPeking University Cancer Hospital & Institute

Extrachromosomal DNA(ecDNA) is a form of circular DNA mostly found in tumor cells. Unlike the typical chromosomal DNA, ecDNA is circular, self-replicating, and carries complete or partial gene fragments. Although ecDNA occurrence remains a rare event in cancer, recent studies have shown that oncogene amplification on ecDNA is widespread throughout many types of cancer, implying that ecDNA plays a central role in accelerating tumor evolution. ecDNA has also been associated with increased tumor mutation burden, chromosomal instability, and even tumor microenvironment remodeling. ecDNA may be crucial in influencing tumor heterogeneity, drug sensitivity,oncogenic senescence, and tumor immunogenicity, leading to a worsening prognosis for tumor patients. In this way, several clinical trials have been conducted to investigate the importance of ecDNA in clinical treatment. In this review, we summarize the biogenesis, characteristics, and current research methods of ecDNA, discuss the vital role of ecDNA-caused tumor heterogeneity in cancers, and highlight the potential role of ecDNA in cancer therapy.

关键词： extrachromosomal DNA cancer therapy tumor heterogeneity drug resistance tumor evolution

Boosting Oxygen Evolution Reaction Performance on NiFe‑Based Catalysts Through d‑Orbital Hybridization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第1期17卷 281-292页

作者： xing Wang Wei Pi Sheng Hu Haifeng Bao Na Yao Wei Luo State Key Laboratory of New Textile Materials and Advanced Processing Technology Key Laboratory of New Textile Materials and Applications of Hubei ProvinceSchool of Materials Science and EngineeringWuhan Textile UniversityWuhan 430200People’s Republic of China College of Chemistry and Molecular Sciences Wuhan UniversityWuhan 430072People’s Republic of China

Anion-exchange membrane water electrolyzers(AEMWEs)for green hydrogen production have received intensive attention due to their feasibility of using earth-abundant NiFe-based *** introducing a third metal into NiFe-based catalysts to construct asymmetrical M-NiFe units,the d-orbital and electronic structures can be adjusted,which is an important strategy to achieve sufficient oxygen evolution reaction(OER)performance in ***,the ternary NiFeM(M:La,Mo)catalysts featured with distinct M-NiFe units and varying d-orbitals are reported in this *** and theoretical calculation results reveal that the doping of La leads to optimized hybridization between d orbital in NiFeM and 2p in oxygen,resulting in enhanced adsorption strength of oxygen intermediates,and reduced rate-determining step energy barrier,which is responsible for the enhanced OER *** critically,the obtained NiFeLa catalyst only requires 1.58 V to reach 1 A cm^(−2) in an anion exchange membrane electrolyzer and demonstrates excellent long-term stability of up to 600 h.

关键词： NiFe-based catalysts d-orbital coupling Oxygen evolution reaction Anion exchange membrane electrolyzer

Optimal investment, retirement, and life insurance with consumption ratcheting and time-inhomogeneous utility

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2025年

作者： Jie xing Jingtang Ma School of Big Data Application and Economics Guizhou University of Finance and Economics School of Mathematics Southwestern University of Finance and Economics

In this paper, we study a portfolio selection problem of an investor with a retirement option, who has possibility to buy life insurance and does not tolerate any decline in consumption. The agent's optimization problem can be viewed as a mixed singular control and optimal stopping problem with time-inhomogeneous utility functions. The closed-form optimal solution is not available in general. We use the dual control method to convert the original problem into two classes of optimal stopping problems in finite and infinite *** show that the optimal consumption strategy and the best retirement time depend on the free-boundary functions which satisfy Fredholm and Volterra integral equations. We derive the closed-form formulas for these two free boundaries for some special cases and develop numerical methods to solve the integral equations of the free boundaries for general cases.

关键词：