检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ziqiao Zhang Shengkang Chen Scott Mayberry Fumin Zhang School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA USA George W. Woodruff School of Mechanical Engineering Georgia Institute of Technology Atlanta GA United States Cheng Kar-Shun Robotics Institute Hong Kong University of Science and Technology Hong Kong China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Opinions of individuals in large groups evolve through interactions with neighbors and the environment, which can be modeled with opinion dynamics. In this paper, we propose a distributed opinion-based strategy for large-scale multi-robot task allocation utilizing the convergence behaviors of opinion dynamics. The strategy relies on the specialized opinion dynamics on the unit sphere for robot task selection. We investigate the convergence behaviors of opinion dynamics in the context of regions of attraction. Simulation results with a swarm of 200 homogeneous robots validate the effectiveness of our proposed strategy.

关键词： Simulation Dynamic scheduling Resource management Intelligent robots Convergence

来源：评论

学校读者我要写书评

暂无评论

Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-Template Matching

arXiv

引用

arXiv 2024年

作者： Guo, Jiaxin Wang, Jiangliu Li, Zhaoshuo Jia, Tongyu Dou, Qi Liu, Yun-Hui CUHK T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Johns Hopkins University United States Faculty of Urology Third Medical Center Chinese PLA General Hospital Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Center for Logistics Robotics Hong Kong

Soft tissue tracking is crucial for computer-assisted interventions. Existing approaches mainly rely on extracting discriminative features from the template and videos to recover corresponding matches. However, it is difficult to adopt these techniques in surgical scenes, where tissues are changing in shape and appearance throughout the surgery. To address this problem, we exploit optical flow to naturally capture the pixel-wise tissue deformations and adaptively correct the tracked template. Specifically, we first implement an inter-frame matching mechanism to extract a coarse region of interest based on optical flow from consecutive frames. To accommodate appearance change and alleviate drift, we then propose an adaptive-template matching method, which updates the tracked template based on the reliability of the estimates. Our approach, Ada-Tracker, enjoys both short-term dynamics modeling by capturing local deformations and long-term dynamics modeling by introducing global temporal compensation. We evaluate our approach on the public SurgT benchmark, which is generated from Hamlyn, SCARED, and Kidney boundary datasets. The experimental results show that Ada-Tracker achieves superior accuracy and performs more robustly against prior works. Code is available at https://***/wrld/Ada-Tracker. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

FedFC: An Efficient Personalized Federated Learning Method on Non-iid Data

FedFC: An Efficient Personalized Federated Learning Method o...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yuxin Yang Yifei Wang Chanying Huang Qianmu Li Shan Xiao School of Cyber Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science & Engineering Nanjing University of Science & Technology Nanjing China School of Cyber Science & Engineering Nanjing Univ. of Science & Technology Nanjing China Fiberhome R & D Center Fiberhome Communication Tech. Co. Wuhan China

Federated Learning has been widely used due to its ability to train models while ensuring data privacy and security. However, the presence of non-i.i.d. (independent and identically distributed) data among different participating entities leads to significant performance disparities in Federated Learning. In addition, as the essence of Federated Learning involves model training on local devices without centralized data storage, it poses certain challenges in personalized tasks. Traditional centralized machine learning methods can perform deep learning and personalized model training on centralized data, while distributed data in Federated Learning may not provide enough information to support personalized requirements. In this paper, we propose a personalized Federated Learning method called FedFC, which adopts parameter decoupling to address the data domain shift issue in Federated Learning. We experimentally validate our proposed solutions on the OrganCMNIST and COVID-19 datasets. The experimental results show that compared to existing methods, FedFC achieves average accuracy improvements of 4.93% and 6.31% on the two datasets, respectively. Additionally, by employing partial gradient uploading, we successfully reduce the communication overhead by 22.67% and 26.91% for each dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Low-Latency Collaborative Inference for Multi-Branch Models in D2D-Assisted MEC

Learning-Based Low-Latency Collaborative Inference for Multi...

引用

IEEE Conference on Wireless Communications and Networking

作者： Kai Guo Yilin Xiao Xiaozhen Lu Liang Xiao Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Peng Cheng Laboratory Shenzhen China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Department of Information and Communication Engineering Xiamen University Xiamen China

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Deploying high-complexity deep neural network (DNN) on mobile devices presents significant challenges, stemming from the conflict between their computationally intensive demands and the constrained computational resources. Device-to-device ( $D$ 2 $D$ ) assisted mobile edge computing (MEC) exploits sharing resources among devices to perform DNN inference collaboratively for higher efficiency. However, most existing collaborative inference schemes ignore the structure of DNN models, thus suffering from high latency under dynamic network conditions and computational loads. In this paper, we propose a learning-based low-latency collaborative inference scheme for multi-branch models, which schedules the computations of each DNN layer to optimize the alignment between the DNN structure's characteristics and the D2D network environments. Specifically, the computational task of each branch is assigned to nearby mobile devices or the edge server for efficient collaboration. In addition, we design proximal policy optimization with task-specific architecture to choose the computational scheduling policy, which contains a two-stream NN to extract features from the D2D network and the tasks at each layer, as well as a multi-head output to obtain the collaborative devices for all tasks in the layer. Simulation results show that the proposed scheme reduces the inference latency compared with benchmarks.

关键词： Schedules Processor scheduling Computational modeling Simulation Collaboration Artificial neural networks Mobile handsets Device-to-device communication Servers Low latency communication

来源：评论

学校读者我要写书评

暂无评论

Towards Adaptive Adjusting and Efficient Scheduling Coflows Based on Deep Reinforcement Learning

Towards Adaptive Adjusting and Efficient Scheduling Coflows ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zichao Wang Kedong Yan Guanxin Chang Chanying Huang Shan Xiao Yuxin Yang School of Cyber Science and Engineering Nanjing University of Science and Technology Jiangyin China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Fiberhome R & D Center Fiberhome Communication Technology Co. LTD Wuhan China School of Cyber Science & Engineering Nanjing Univ. of Science & Technology Jiangyin China

The rapid development of current data centers and Industrial Internet of Things has brought about the explosive growth of information, which leads to the need for better performance of cluster communication systems. Coflow scheduling has the potential to enhance communication performance among applications in data parallel clusters. However, current coflow scheduling techniques that lack preliminary knowledge often depend on a fixed set of threshold parameters within a multilevel feedback queue (MLFQ), disregarding network variability. Though manually tweaking threshold settings may support network flexibility, it negatively impacts real-time performance and increases workload. Furthermore, manual threshold adjustments often fail to react promptly and adaptively to network environmental changes. To address the issues highlighted above, this paper presents D-MLFQ, a novel approach that leverages deep reinforcement learning to dynamically and autonomously regulate the threshold of MLFQ. As a result, D-MLFQ offers enhanced scheduling and communication optimization capabilities. Furthermore, the study performs trace-driven simulations to assess the efficacy of D-MLFQ. Empirical data indicate that D-MLFQ outperforms Aalo, which utilizes fixed threshold, by up to 1.39× in terms of coflow’s completion time. Compared to other common scheduling algorithms such as per-flow fairness, D-MLFQ achieves up to 2.13× faster completion time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Secure Machine Learning-Based Malware Detection and Analysis Scheme

Design of a Secure Machine Learning-Based Malware Detection ...

引用

2023 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2023

作者： Kumar, Pankaj Obaidat, Mohammad S. Pandey, Piyush Wazid, Mohammad Das, Ashok Kumar Singh, Devesh Pratap Graphic Era Deemed to Be University Department of Computer Science and Engineering Dehradun India King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computing Srm University Jordan University of Science and Technology Beijing Beijing100083 China School of Computing Srm University TN Kattankulathur603203 India Algorithmic Research International Institute of Information Technology Center for Security Theory Hyderabad India

ISBN: (纸本)9798350302561

Today's world is rapidly growing towards the advanced concept of technology. Technology nowadays is at its peak of development and has great advantages in all fields of work, whether it is in industrial automation, farming, weather forecasting, or disease detection and control. Despite its great advantages, it does have its negative side because a major population is using technology and general-purpose computing devices (i.e., desktops, laptops, smartphones, tablets, etc.). Therefore, most of their personal data is available online. The data is constantly in danger of getting stolen by malicious actors (i.e., hackers), who can find a way to get their hands on this data and then use it for their personal gain (i.e., money-making). The best-known technique to get this information is by using malware exploitation on the machine of the target. Malware is an executable or a binary that is malicious in nature. It may have various devastating effects, and in order to detect and make the system defensive, we need to propose a scheme to detect the malware in the system, analyze the particular file, and then mitigate it. In this paper, we propose a secure machine learning-based malware detection and analysis scheme (in short, SML-MDA). The conducted security analysis and formal security verification of the proposed SMLMDA prove its security against various types of potential attacks. The proposed SML-MDA is then compared with the other similar competing schemes, and its performance has been found to be better in terms of various performance metrics like accuracy and F1-score. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving

SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autono...

引用

International Conference on computer Vision (ICCV)

作者： Yi Wei Linqing Zhao Wenzhao Zheng Zheng Zhu Jie Zhou Jiwen Lu Beijing National Research Center for Information Science and Technology China Department of Automation Tsinghua University China School of Electrical and Information Engineering Tianjin University China PhiGent Robotics

3D scene understanding plays a vital role in vision-based autonomous driving. While most existing methods focus on 3D object detection, they have difficulty describing real-world objects of arbitrary shapes and infinite classes. Towards a more comprehensive perception of a 3D scene, in this paper, we propose a SurroundOcc method to predict the 3D occupancy with multi-camera images. We first extract multi-scale features for each image and adopt spatial 2D-3D attention to lift them to the 3D volume space. Then we apply 3D convolutions to progressively upsample the volume features and impose supervision on multiple levels. To obtain dense occupancy prediction, we design a pipeline to generate dense occupancy ground truth without expansive occupancy annotations. Specifically, we fuse multi-frame LiDAR scans of dynamic objects and static scenes separately. Then we adopt Poisson Reconstruction to fill the holes and voxelize the mesh to get dense occupancy labels. Extensive experiments on nuScenes and SemanticKITTI datasets demonstrate the superiority of our method. Code and dataset are available at https://***/weiyithu/SurroundOcc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sparse dual-graph regularized quadratic dimensionality reduction algorithm based on subspace learning

引用

Digital Signal Processing: A Review Journal 2025年 164卷

作者： Ma, Ziping Huang, Yulei Ma, Jinlin Li, Huirong School of Mathematics and Information Science North Minzu University Yinchuan750030 China School of Mathematics and Statistics Ningxia University Yinchuan750030 China School of Computer Science and Engineering North Minzu University Yinchuan750030 China School of Mathematics and Computer Application Shangluo University Shangluo726000 China Ningxia Collaborative Innovation Center for Scientific Computing and Intelligent Information Processing North Minzu University Yinchuan750030 China

Nonnegative matrix factorization (NMF) has been attracting more and more attention due to its significant performance in dimensionality reduction. NMF performs dimensionality reduction by mapping high-dimensional data into low-dimensional space, which might lead to the uncontrollability, i.e. quantity and quality, of dimensions in dimensionality reduction. To address this issue, we innovatively propose a novel sparse dual-graph regularized quadratic dimensionality reduction (SDQDR) algorithm by embedding feature selection mechanism to semi-supervised NMF, which are fused as a whole rather than the simple combinations of NMF and feature selection in existing methods. The proposed SDQDR not only inherits the advantages of semi-supervised NMF but also demonstrates some special and important properties, such as controllability of dimensionality reduction, higher clustering performance, and significant dimensionality reduction with low time cost, etc. Then, to reinforce the sparsity structure and retain the manifold structures of both the data and the feature space simultaneously, 1-2,1/2 sparse constraint and dual graph regularization are incorporated into the proposed framework. Finally, the objective function, convergence proof, and iterative update rules are presented. In comparison with 15 state-of-the-art algorithms, relevant results demonstrate the proposed method is competitive, especially in terms of the efficiency of dimensionality reduction. © 2025 Elsevier Inc.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

GIDCL: A Graph-Enhanced Interpretable Data Cleaning Framework with Large Language Models

引用

Proceedings of the ACM on Management of Data 2024年第6期2卷 1-29页

作者： Mengyi Yan Yaoshu Wang Yue Wang Xiaoye Miao Jianxin Li School of Computer Science and Engineering Beihang University Beijing CN Shenzhen Institute of Computing Sciences Shenzhen University Shenzhen Guangdong CN Shenzhen Institute of Computing Sciences Shenzhen Guangdong CN Center for Data Science Zhejiang University Hangzhou Zhejiang CN

Data quality is critical across many applications. The utility of data is undermined by various errors, making rigorous data cleaning a necessity. Traditional data cleaning systems depend heavily on predefined rules and constraints, which necessitate significant domain knowledge and manual effort. Moreover, while configuration-free approaches and deep learning methods have been explored, they struggle with complex error patterns, lacking interpretability, requiring extensive feature engineering or labeled data. This paper introduces GIDCL (Graph-enhanced Interpretable Data Cleaning with Large language models), a pioneering framework that harnesses the capabilities of Large Language Models (LLMs) alongside Graph Neural Network (GNN) to address the challenges of traditional and machine learning-based data cleaning methods. By converting relational tables into graph structures, GIDCL utilizes GNN to effectively capture and leverage structural correlations among data, enhancing the model's ability to understand and rectify complex dependencies and errors. The framework's creator-critic workflow innovatively employs LLMs to automatically generate interpretable data cleaning rules and tailor feature engineering with minimal labeled data. This process includes the iterative refinement of error detection and correction models through few-shot learning, significantly reducing the need for extensive manual configuration. GIDCL not only improves the precision and efficiency of data cleaning but also enhances its interpretability, making it accessible and practical for non-expert users. Our extensive experiments demonstrate that GIDCL significantly outperforms existing methods, improving F1-scores by 10% on average while requiring only 20 labeled tuples.

关键词： data quality graph neural network interpretable large language models

来源：评论

学校读者我要写书评

暂无评论

Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adaptive-template Matching

Ada-Tracker: Soft Tissue Tracking via Inter-Frame and Adapti...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Jiaxin Guo Jiangliu Wang Zhaoshuo Li Tongyu Jia Qi Dou Yun-Hui Liu CUHK T Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Johns Hopkins University United States Faculty of Urology Third Medical Center Chinese PLA General Hospital Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Hong Kong Center for Logistics Robotics Hong Kong

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

关键词： Deformable models Adaptation models Accuracy Tracking Deformation Biological tissues Surgery

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：