检索结果-内蒙古大学图书馆

International Workshop on Robot Sensing (ROSE)

作者： Zeyad Hosny Abdullah Nassar Ahmed AboElyazeed Mahmoud Mohamed Mohammed Abouheaf Wail Gueaieb School of Electrical Engineering and Computer Science University of Ottawa Ottawa ON K1N6N5 Canada Robotics Engineering Bowling Green State University Bowling Green 43402 OH USA

Controlling 6 Degrees-of-Freedom (DoF) robotic manipulators in an online, model-free manner poses significant challenges due to their complex coupling, non-linearities, and the need to account for unmodeled dynamics. This paper introduces a model-free adaptive approach for real-time control of a 6 DoF “EPSON” robotic manipulator, without requiring any prior knowledge of the manipulator’s dynamics. Initially, we lay out the framework for an optimal control solution. A performance index is introduced, leveraging error dynamics and correction control signals, offering the capability to incorporate high-order error dynamics without the need to explicitly derive error trajectories. The order of error dynamics is determined by the chosen number of error samples. We assume a kernel-based solution structure aligning with the performance index, resulting in a temporal difference equation. This equation can be optimized to formulate a model-free control strategy. Subsequently, a reinforcement learning approach is adopted to approximate the underlying strategy. Infeasible exact solutions are overcome by employing a value iteration mechanism to adapt the actor-critic structures within an adaptive critics framework. To validate the proposed approach, it is compared against a conventional proportional-integral controller. A Unified Robot Description Format file is generated to facilitate the import of the robotic manipulator into the MATLAB Simulink environment, enabling its control. Ultimately, the proposed method yields superior results in terms of the dynamic characteristics of the response, demonstrating its effectiveness over the conventional approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fetal Brain MRI Segmentation via Boundary-Aware Voxel-Level Contrastive Learning 26

Fetal Brain MRI Segmentation via Boundary-Aware Voxel-Level ...

引用

26th ACIS International Winter Conference on Software engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD-Winter 2023

作者： Lu, Wenying Zhang, Xin Xu, Qin Chen, Wenjun Yang, Chaoxiang Xing, Xiaofen Xu, Xiangmin Anhui University AHU-IAI Ai Joint Laboratory Hefei230601 China School of Electronic and Information Engineering South China University of Technology China School of Computer Science and Technology Anhui University Hefei230601 China School of Future Technology South China University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Department of Radiology Guangdong Women and Children Hospital Guangzhou China

ISBN: (纸本)9798350345865

Fetal brain MRI segmentation provides quantitative analysis of the fetal brain development for timely diagnosis. However, low contrast among neighboring tissues limits the precise region segmentation. This paper proposes a boundary-aware voxel-level contrastive learning mechanism for fetal brain tissue segmentation in MRI data. We design a novel sam-pling strategy for the contrastive learning which takes the prior boundary information into consideration. The proposed method can be inserted into Transformer based backbones, which clearly improves their capabilities to learn detailed features. Extensive experiments demonstrate the effective-ness of the proposed method. Best dice score of our method reaches to 89.48 and boundary accuracy is improved by 1.53%. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

LP-ICP: General Localizability-Aware Point Cloud Registration for Robust Localization in Extreme Unstructured Environments

arXiv

引用

arXiv 2025年

作者： Yue, Haosong Xu, Qingyuan Chen, Fei Pan, Jia Chen, Weihai School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Department of Computer Science The University of Hong Kong Hong Kong Hangzhou Innovation Institute Beihang University Hangzhou310053 China

The Iterative Closest Point (ICP) algorithm is a crucial component of LiDAR-based SLAM algorithms. However, its performance can be negatively affected in unstructured environments that lack features and geometric structures, leading to low accuracy and poor robustness in localization and mapping. It is known that degeneracy caused by the lack of geometric constraints can lead to errors in 6-DOF pose estimation along ill-conditioned directions. Therefore, there is a need for a broader and more fine-grained degeneracy detection and handling method. This paper proposes a new point cloud registration framework, LP-ICP, that combines point-to-line and point-to-plane distance metrics in the ICP algorithm, with localizability detection and handling. LP-ICP consists of a localizability detection module and an optimization module. The localizability detection module performs localizability analysis by utilizing the correspondences between edge points (with low local smoothness) to lines and planar points (with high local smoothness) to planes between the scan and the map. The localizability contribution of individual correspondence constraints can be applied to a broader range. The optimization module adds additional soft and hard constraints to the optimization equations based on the localizability category. This allows the pose to be constrained along ill-conditioned directions, with updates either tending towards the constraint value or leaving the initial estimate unchanged. This improves accuracy and reduces fluctuations. The proposed method is extensively evaluated through experiments on both simulation and real-world datasets, demonstrating higher or comparable accuracy than the state-of-the-art methods. The dataset and code of this paper will also be open-sourced at https://***/xuqingyuan2000/LP-ICP. Copyright © 2025, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

A DRL-Framework for Full-Duplex WPCN Enabled Mobile Edge Computing

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Bao, Senlei Zhang, Shubin Chi, Kaikai Yu, Keping Mumtaz, Shahid Zhejiang University of Technology School of Computer Science and Technology China Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan Silesian University of Technology Department of Applied Informatics Poland Nottingham Trent University Department of Engineering United Kingdom

As the Internet of Things (IoT) continues to expand in both daily life and industrial production, the data generated by IoT devices is increasing rapidly. To address the challenges of limited battery life and computational capacity in these devices, two promising solutions have emerged: wireless power transfer (WPT) and mobile edge computing (MEC). By receiving radio frequency (RF) energy from a hybrid access point (HAP), wireless devices (WDs) can either offload data to the HAP or process it locally. In this paper, we explore the full-duplex WPT-MEC scenario and maximize the sum computation rate (SCR) by optimizing the offloading decision and resource allocation of WDs in different access modes and energy harvest models. This problem is formulated as a mixed-integer nonlinear programming (MINLP) problem. To address this, we decompose the problem into two sub-problems: one focuses on optimizing offloading decisions, and the other focuses on energy power and bandwidth allocation under given the offloading decisions. We propose a deep reinforcement learning approach based on policy gradients to make offloading decisions, and we design an optimization algorithm for efficient bandwidth and energy resource allocation. Simulation results show that our proposed algorithm achieves approximately 96% of the maximum possible computation rate while maintaining low computational complexity © 1967-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting

arXiv

引用

arXiv 2024年

作者： Wang, Hongjun Chen, Jiyuan Zhang, Lingyu Jiang, Renhe Song, Xuan SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and Engineering China Shenzhen China School of Artificial Intelligence Jilin University China Center for Spatial Information Science University of Tokyo Tokyo Japan

Spatiotemporal Graph Neural Networks (ST-GNNs) and Transformers have shown significant promise in traffic forecasting by effectively modeling temporal and spatial correlations. However, rapid urbanization in recent years has led to dynamic shifts in traffic patterns and travel demand, posing major challenges for accurate long-term traffic prediction. The generalization capability of ST-GNNs in extended temporal scenarios and cross-city applications remains largely unexplored. In this study, we evaluate state-of-the-art models on an extended traffic benchmark and observe substantial performance degradation in existing ST-GNNs over time, which we attribute to their limited inductive capabilities. Our analysis reveals that this degradation stems from an inability to adapt to evolving spatial relationships within urban environments. To address this limitation, we reconsider the design of adaptive embeddings and propose a Principal Component Analysis (PCA) embedding approach that enables models to adapt to new scenarios without retraining. We incorporate PCA embeddings into existing ST-GNN and Transformer architectures, achieving marked improvements in performance. Notably, PCA embeddings allow for flexibility in graph structures between training and testing, enabling models trained on one city to perform zero-shot predictions on other cities. This adaptability demonstrates the potential of PCA embeddings in enhancing the robustness and generalization of spatiotemporal models. The code is released in code. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Container Anomaly Detection System Based on Rule Mining and Matching

Container Anomaly Detection System Based on Rule Mining and ...

引用

2022 International Conference on Blockchain Technology and Information Security, ICBCTIS 2022

作者： Yu, Daisong Xie, Yulai Long, Huachao Jin, Minpeng Li, Xuan School of Cyber Science and Engineering Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan China Wuhan National Lab for Optoelectronics F311 Wuhan China School of Computer Science Huazhong University of Science and Technology Wuhan China Nsfocus Inc. A9-3/F Optical Valley Software Park Wuhan China

ISBN: (数字)9781665496919

ISBN: (纸本)9781665496919

Compared with virtual machine technology, container technology is more and more popular by virtue of its excellent convenience and reliable security isolation. Containers will encounter various anomalies during operation. For maintenance personnel, a large number of abnormal logs makes the work of anomaly analysis very difficult, so anomaly detection technology is needed. In this paper, a container anomaly detection system based on rule mining and matching is proposed, which collects and simplifies the container's logs generated in the abnormal time period, then delivers them to association rule mining algorithm for rule mining and display rules to the maintainer who makes a decision after a simple analysis. The experimental results show that the rule mining algorithm can process log entries in less time consumption compared with traditional association rule mining algorithm, and container anomaly detection system can effectively help system administrator to locate anomalies. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Low Range-Doppler Sidelobe ISAC Waveform Design: A Low-Complexity Approach

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Li, Peishi Li, Ming Liu, Rang Liu, Qian Swindlehurst, A. Lee Dalian University of Technology School of Information and Communication Engineering Dalian116024 China University of California Center for Pervasive Communications and Computing IrvineCA92697 United States Dalian University of Technology School of Computer Science and Technology Dalian116024 China

Integrated sensing and communication (ISAC) is a pivotal enabler for next-generation wireless networks. A key challenge in ISAC systems lies in designing dual-functional waveforms that can achieve satisfactory radar sensing accuracy by effectively suppressing range-Doppler sidelobes. However, existing solutions are often computationally intensive, limiting their practicality in multi-input multi-output (MIMO) orthogonal frequency division multiplexing (OFDM) ISAC deployments. This paper presents a novel low-complexity algorithm leveraging the augmented Lagrangian method (ALM) and Riemannian conjugate gradient (RCG) optimization techniques to address these challenges. The proposed algorithm achieves superior sidelobe suppression compared to state-of-the-art methods while dramatically reducing computational complexity, making it highly suitable for real-world MIMO-OFDM ISAC systems. Simulation results demonstrate that the proposed approach not only outperforms existing benchmarks in sidelobe reduction but also accelerates convergence, ensuring efficient performance across communication and sensing tasks. © 1967-2012 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Detection of Obstructive Sleep Apnea through Combined ECG and ECG-Derived Respiration Signals

健康数据科学（英文）

引用

健康数据科学（英文） 2023年第4期 16-18页

作者： Yaomin Wang Chenzhe Jin Yuxi Zhou Shenda Hong School of Computer Science and Engineering Tianjin University of TechnologyTianjinChina School of Computer Science and Engineering Tianjin University of TechnologyTianjinChina DCST BNRistRIITInstitute of Internet IndustryTsinghua UniversityBeijingChina National Institute of Health Data Science Peking UniversityBeijingChina Institute of Medical Technology Health Science Center of Peking UniversityBeijingChina

Background:Obstructive sleep apnea(OSA)is a prevalent sleep disorder characterized by recurrent episodes of partial or complete upper airway obstruction during *** studies have estimated that approximately one billion people world-wide suffer from *** or undiagnosed individuals face an elevated risk of cardiovascular diseases,such as hyper-tension,heart failure,and *** current gold standard for diagnosing OSA remains overnight polysomnography(PSG),which involves extensive monitoring of subjects wearing mul-tiple sensors throughout the ***,it is hard to collect PSG data in a home *** non-invasive and portable home monitoring methods for OSA diagnosis mainly rely on modeling monitoring data from wearable devices such as electrocardiogram(ECG).However,these methods often overlook the crucial respiratory information,which is the most direct parameter for detecting OSA,leading to inaccurate analysis of patients'OSA ***,these approaches neglect the influence of demographic characteristics and other relevant features on the model. Objectives:This paper aims to address above challenges by proposing a deep learning-based OSA diagnostic method that incorporates the combination of ECG and ECG-derived respi-ration(EDR)*** also aims to develop an interpretable nomogram model that considers patient demographics. Methods:First,we extract respiration signals from *** involves extracting R-R intervals from the ECG and employing cubic spline interpolation to derive the ***,we pro-pose a deep learning model,which takes ECG and EDR as input,and output the probabilities of OSA from ECG and EDR ***,rather than directly concatenating the features extracted from the ECG and EDR signals,we build a logistic regression(LR)to combine the OSA risk predictions derived from the ECG signal,the EDR signal,and the demographic ***,we employ a nomogram to represent the LR model. Exp

关键词： through detection deep apnea combined ecg-derived learning-based obstructive respiration signals

来源：评论

学校读者我要写书评

暂无评论

Collaborative Task Processing and Resource Allocation Based on Multiple MEC Servers 19th

Collaborative Task Processing and Resource Allocation Based...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Shi, Lei Feng, Shilong Ji, Rui Xu, Juan Ding, Xu Zhan, Baotong School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei230009 China Institute of Industry and Equipment Technology Hefei University of Technology Hefei230009 China Taian Hualu Metalforming Machine Tool Co. Ltd. Shandong Taian271000 China

ISBN: (纸本)9783031545207

Mobile Edge Computing (MEC), an emerging computing paradigm, shifts computing and storage capabilities from the cloud to the network edge, aiming to meet the delay requirements of emerging applications and save backhaul network bandwidth. However, compared to cloud servers, MEC servers have limited computing and storage capabilities, which cannot meet the massive offloading demands of users during high-load periods. In this context, this paper proposes a multi-ENs collaborative task processing model. The model aims to formulate optimal offloading decisions and allocate computing resources for tasks to minimize system delay and cost. To solve this problem, we propose an online algorithm based on Lyapunov optimization called OKMTA, which can work online without the need for predicting future information. Specifically, the problem is formulated as a mixed-integer nonlinear programming (MINLP) problem and decomposed into two subproblems for solution. By using the Lagrange multiplier method to solve the computing resource allocation problem of tasks, and by using matching theory to solve the offloading decision problem of tasks. The simulation results show that our algorithm can achieve near-optimal delay performance while satisfying the long-term system average cost constraint. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with Only Positive Labels by Exploring Label Correlations

arXiv

引用

arXiv 2024年

作者： An, Xuming Wang, Dui Shen, Li Luo, Yong Hu, Han Du, Bo Wen, Yonggang Tao, Dacheng School of Information and Electronics Beijing Institute of Technology Beijing100081 China National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China JD Explore Academy Beijing100000 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting, where trivial solution and extremely poor performance may be obtained, especially when only positive data w.r.t. a single class label are provided for each client. This issue can be addressed by adding a specially designed regularizer on the server-side. Although effective sometimes, the label correlations are simply ignored and thus sub-optimal performance may be obtained. Besides, it is expensive and unsafe to exchange user’s private embeddings between server and clients frequently, especially when training model in the contrastive way. To remedy these drawbacks, we propose a novel and generic method termed Federated Averaging by exploring Label Correlations (FedALC). Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training. To further improve the safety and also reduce the communication overhead, we propose a variant to learn fixed class embedding for each client, so that the server and clients only need to exchange class embeddings once. Extensive experiments on multiple popular datasets demonstrate that our FedALC can significantly outperform existing counterparts. Copyright © 2024, The Authors. All rights reserved.

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：