检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Mingzhou Sun, Xinwei Qiao, Yu Wang, Yizhou School of Computer Science Peking University China Peking University China Sch. of Data Science Fudan University China Dep. of Automation Shanghai Jiao Tong University China Inst. for Artificial Intelligence Peking University China Nat'l Eng. Research Center of Visual Technology Peking University China Nat'l Key Lab of General Artificial Intelligence Peking University China

Distinguishing causal connections from correlations is important in many scenarios. However, the presence of unobserved variables, such as the latent confounder, can introduce bias in conditional independence testing commonly employed in constraint-based causal discovery for identifying causal relations. To address this issue, existing methods introduced proxy variables to adjust for the bias caused by unobserveness. However, these methods were either limited to categorical variables or relied on strong parametric assumptions for identification. In this paper, we propose a novel hypothesis-testing procedure that can effectively examine the existence of the causal relationship over continuous variables, without any parametric constraint. Our procedure is based on discretization, which under completeness conditions, is able to asymptotically establish a linear equation whose coefficient vector is identifiable under the causal null hypothesis. Based on this, we introduce our test statistic and demonstrate its asymptotic level and power. We validate the effectiveness of our procedure using both synthetic and real-world data. Code is publicly available at https://***/lmz123321/proxy_causal_discovery. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

MPFFNet:Semantic Segmentation of Remote Sensing Image Buildings Based on Multipath Feature Fusion 8

MPFFNet:Semantic Segmentation of Remote Sensing Image Buildi...

引用

8th International Conference on Communication, Image and Signal Processing, CCISP 2023

作者： Dong, Jie Mao, Jingkun Liu, Kun Cheng, Liangyong School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Interplanetary Space Technology Development Co. LTD Tianjin China

ISBN: (纸本)9798350305838

The buildings with variable scales and complex background information in remote sensing images often result in missed and misclassified segmentation of buildings. To address this issue, this paper designs an multipath feature fusion network (MPFFNet). MPFFNet has an overall encoding and decoding structure, embedded with an residual depth Inception block(RDI) module to extract multi-scale features. At the same time, MPFFNet uses the multipath residual channel attention (MPRCA) module to expand the Receptive field of the feature map to obtain rich multi-scale context information. The validity of the proposed algorithm is proved on the WHU Buildings data set, with F1 reaching 94.70%, IOU reaching 89.93%, and Recall reaching 94.98%. © 2023 IEEE.

关键词： Buildings

来源：评论

学校读者我要写书评

暂无评论

RANSACs for 3D Rigid Registration:A Comparative Evaluation

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1861-1878页

作者： Jiaqi Yang Zhiqiang Huang Siwen Quan Zhiguo Cao Yanning Zhang the National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710072China the School of Electronic and Control Engineering Chang’an UniversityXi’an 710064China the School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China IEEE

Estimating an accurate six-degree-of-freedom(6-Do F)pose from correspondences with outliers remains a critical issue to 3D rigid *** sample consensus(RANSAC)and its variants are popular solutions to this *** there have been a number of RANSAC-fashion estimators,two issues remain ***,it is unclear which estimator is more appropriate to a particular ***,the impacts of different sampling strategies,hypothesis generation methods,hypothesis evaluation metrics,and stop criteria on the overall estimators remain *** work fills these gaps by first considering six existing RANSAC-fashion methods and then proposing eight variants for a comprehensive *** objective is to thoroughly compare estimators in the RANSAC family,and evaluate the effects of each key stage on the eventual 6-Do F pose estimation *** have been carried out on four standard datasets with different application scenarios,data modalities,and *** provide us with input correspondence sets with a variety of inlier ratios,spatial distributions,and *** on the experimental results,we summarize remarkable outcomes and valuable findings,so as to give practical instructions to real-world applications,and highlight current bottlenecks and potential solutions in this research realm.

关键词： 3D rigid registration performance evaluation point cloud pose estimation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Dynamics Modeling and Trajectory Planning for a Cable-Trailer System with a Quadruped Robot

arXiv

引用

arXiv 2024年

作者： Zhang, Wentao Xu, Shaohang Zuo, Gewei Zhu, Lijun School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Data Science City University of Hong Kong Hong Kong

Inspired by the utilization of dogs in sled-pulling for transportation, we introduce a cable-trailer system with a quadruped robot. The motion planning of the proposed robot system presents challenges arising from the nonholonomic constraints of the trailer, system underactuation, and hybrid interaction through the cable. To tackle these challenges, we develop a hybrid dynamics model that accounts for the cable’s taut/slack status. Since it is computationally intense to directly optimize the trajectory, we first propose a search algorithm to compute a sub-optimal trajectory as the initial solution. Then, a novel collision avoidance constraint based on the geometric shapes of objects is proposed to formulate the trajectory optimization problem for the hybrid system. The proposed trajectory planning method is implemented on a Unitree A1 quadruped robot with a customized cable-trailer and validated through experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Cables

来源：评论

学校读者我要写书评

暂无评论

Research on Robot-Assisted Bathing Based on Impedance Iterative Learning Sliding Mode Control Algorithm 12

Research on Robot-Assisted Bathing Based on Impedance Iterat...

引用

12th International Conference on CYBER Technology in automation, Control, and Intelligent Systems, CYBER 2022

作者： Xu, Yuexuan Guo, Xin Xuan, Bokai Ma, Tianyi Liu, Minghe Ding, Qingsong Tan, Yinglun Li, Jian Sun, Hao Hebei University of Technology School of Artificial Intelligence and Data Science Tianjin300400 China Beijing University of Posts and Telecommunications School of Automation Beijing100876 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Aiming at providing effective technical means for intelligent bathing and low-intensity care for the semi-disabled elderly, an impedance iterative learning sliding mode control (IILSMC) scheme for robot-assisted bathing with unknown model parameters is investigated in this paper. Firstly, the desired trajectory is adjusted by impedance control in order to ensure the active compliance control of the robot-assisted bathing. Secondly, iterative learning control (ILC) is implemented to dynamically estimate the unknown model parameters, and reconstructed trajectory method is employed to ensure the convergence accuracy of iterative learning with any initial conditions. Thirdly, as for handling nonparametric uncertainties, external disturbances and the human-machine interaction (HMI) torque, adaptive sliding mode control (SMC) is proposed where the chattering problem in output torque is suppressed by adaptive method. Based on the composite energy function (CEF) method, the convergence of the double closed-loop system in the time domain and iterative domain is proved. Finally, through co-simulation of MATLAB and ADAMS, tracking errors of all joint angles can be maintained within 0.002rad with constant HMI force. The simulation results demonstrate that the IILSMC strategy is verified to be effective and superior. © 2022 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Mathematical modeling of the synergetic effect between radiotherapy and immunotherapy

引用

Mathematical Biosciences and Engineering 2025年第5期22卷 1206-1225页

作者： Xing, Yixun Moore, Casey Saha, Debabrata Nguyen, Dan Bleile, MaryLena Jia, Xun Timmerman, Robert Peng, Hao Jiang, Steve Medical Artificial Intelligence and Automation Laboratory University of Texas Southwestern Medical Center DallasTX75390 United States Department of Advanced Data Analytics University of North Texas DentonTX76205 United States Department of Radiation Oncology University of Texas Southwestern Medical Center DallasTX75390 United States Department of Statistical Science Southern Methodist University DallasTX75275 United States

The synergy between radiotherapy and immunotherapy plays a pivotal role in enhancing tumor control and treatment outcomes. To explore the underlying mechanisms of synergy, we investigated a novel treatment approach known as personalized ultra-fractionated stereotactic adaptive radiation (PULSAR) therapy, which emphasizes the impact of radiation timing. Unlike conventional daily treatments, PULSAR delivers high-dose radiation in spaced intervals over weeks or months, enabling tumors to adapt and potentially enhancing synergy with immunotherapy. Drawing on insights from small-animal radiation studies, we developed a discrete-time model based on multiple difference equations to elucidate the temporal dynamics of tumor control driven by both radiation and the adaptive immune response. By accounting for the migration and infiltration of T cells within the tumor microenvironment, we established a quantitative link between radiation therapy and immunotherapy. Model parameters were estimated using a simulated annealing algorithm applied to training data, and our model achieved high accuracy for the test data with a root mean square error of 287 mm3. Notably, our framework replicated the PULSAR effect observed in animal studies, revealing that longer intervals between radiation treatments in the context of immunotherapy yielded enhanced tumor control. Specifically, mice receiving immunotherapy alongside radiation pulses delivered at extended intervals, ten days, showed markedly improved tumor responses, whereas those treated with shorter intervals did not achieve comparable benefits. Moreover, our model offers an in-silico tool for designing future personalized ultra-fractionated stereotactic adaptive radiation trials. Overall, these findings underscore the critical importance of treatment timing in harnessing the synergy between radiotherapy and immunotherapy and highlight the potential of our model to optimize and individualize treatment protocols. ©2025 the Author(s)

关键词： T-cells

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

Sustainable Self-evolution Adversarial Training 24

Sustainable Self-evolution Adversarial Training

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University China Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi'an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi'an China

ISBN: (纸本)9798400706868

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Agile and Safe Trajectory Planning for Quadruped Navigation with Motion Anisotropy Awareness

arXiv

引用

arXiv 2024年

作者： Zhang, Wentao Xu, Shaohang Cai, Peiyuan Zhu, Lijun School of Artificial Intelligence and Automation Huazhong University of Science and Technology China School of Data Science City University of Hong Kong HKSAR Hong Kong

Quadruped robots demonstrate robust and agile movements in various terrains;however, their navigation autonomy is still insufficient. One of the challenges is that the motion capabilities of the quadruped robot are anisotropic along different directions, which significantly affects the safety of quadruped robot navigation. This paper proposes a navigation framework that takes into account the motion anisotropy of quadruped robots including kinodynamic trajectory generation, nonlinear trajectory optimization, and nonlinear model predictive control. In simulation and real robot tests, we demonstrate that our motion-anisotropy-aware navigation framework could: (1) generate more efficient trajectories and realize more agile quadruped navigation;(2) significantly improve the navigation safety in challenging scenarios. The implementation is realized as an open-source package at https://***/ZWT006/agile navigation. Copyright © 2024, The Authors. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimal Coordination Control For Nonlinear Multi-agent Systems Under Dos Attack

Distributed Optimal Coordination Control For Nonlinear Multi...

引用

第42届中国控制会议

作者： Zhirui Wang Xiaoyuan Zheng Sha Fan School of Artificial Intelligence and Data Science Hebei University of Technology School of Automation East China University of Science and Technology

This paper is concerned with the distributed optimal coordination control of nonlinear multi-agent systems(NMASs)under the denial of service(DoS) attacks. The purpose of this paper is to design a distributed control rate for an unknown nonlinear multi-agent system with power interval and time-varying packet loss probability under Dos attack that accurately simulates the impact of DoS attack on NMASs. Then adaptive dynamic programming(ADP) algorithm is used to solve the coupled Hamilton-Jacobi-Bellman(HJB) equation. In order to realize the proposed method, the critic neural network(NN)and actor neural network are used to approximate value functions and control policy. Finally the NN actor-critic policy for optimal control of NMASs under DoS attack with power interval is found. It is proved that the weight estimation error and local neighborhood coordination error are uniformly ultimately bounded(UUB). Finally, the simulation results show the effectiveness of the coordinated control.

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：