检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Weijie Zhang, Xiaoxi Duan, Jingpu Joe-Wong, Carlee Zhou, Zhi Chen, Xu The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Institute of Future Networks Southern University of Science and Technology Shenzhen518055 China The Department of Communications Peng Cheng Laboratory Shenzhen518066 China Department of Electrical and Computer Engineering Carnegie Mellon University CA94035 United States

Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data. While prior works have focused on analyzing FL convergence with respect to hyperparameters like batch size and aggregation frequency, the joint effects of adjusting these parameters on model performance, training time, and resource consumption have been overlooked, especially when facing dynamic data streams and network characteristics. This paper introduces novel analytical models and optimization algorithms that leverage the interplay between batch size and aggregation frequency to navigate the trade-offs among convergence, cost, and completion time for dynamic FL training. We establish a new convergence bound for training error considering heterogeneous datasets across devices and derive closed-form solutions for co-optimized batch size and aggregation frequency that are consistent across all devices. Additionally, we design an efficient algorithm for assigning different batch configurations across devices, improving model accuracy and addressing the heterogeneity of both data and system characteristics. Further, we propose an adaptive control algorithm that dynamically estimates network states, efficiently samples appropriate data batches, and effectively adjusts batch sizes and aggregation frequency on the fly. Extensive experiments demonstrate the superiority of our offline optimal solutions and online adaptive algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2024年

作者： Lin, Zhenchao He, Li Yang, Hongqiang Sun, Xiaoqun Zhang, Guojin Chen, Weinan Guan, Yisheng Zhang, Hong School of Electromechanical Engineering Guangdong University of Technology Guangzhou China Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China Meituan Technology Co. Ltd Shenzhen China

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling Transformer to deal with large-scale point cloud. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently. The code is available at https://***/Sylva-Lin/SWCF-Net Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SubPipe: A Submarine Pipeline Inspection Dataset for Segmentation and Visual-inertial Localization

SubPipe: A Submarine Pipeline Inspection Dataset for Segment...

引用

OCEANS

作者： Olaya Álvarez-Tuñón Luiza Ribeiro Marnet Martin Aubard László Antal Maria Costa Yury Brodskiy Department of Electrical and Computer Engineering Artificial Intelligence in Robotics Laboratory (AiR-Lab) Aarhus University Aarhus C Denmark EIVA a/s Skanderborg Denmark OceanScan Marine Systems & Technology Matosinhos Portugal RWTH Aachen University Aachen Germany

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

This paper presents SubPipe, an underwater dataset for SLAM, object detection, and image segmentation. SubPipe has been recorded using a lightweight autonomous underwater vehicle (LAUV), operated by OceanScan MST, and carrying a sensor suite including two cameras, a side-scan sonar, and an inertial navigation system, among other sensors. The AUV has been deployed in a pipeline inspection environment with a submarine pipe partially covered by sand. The AUV's pose ground truth is estimated from the navigation sensors. The side-scan sonar and RGB images include object detection and segmentation annotations, respectively. State-of-the-art segmentation, object detection, and SLAM methods are benchmarked on SubPipe to demonstrate the dataset's challenges and opportunities for leveraging computer vision algorithms. To the authors' knowledge, this is the first anno-tated underwater dataset providing a real pipeline inspection scenario. The dataset and experiments are publicly avail-able online at https://***/remaro-network/SubPipe-dataset.

关键词： Location awareness Image segmentation Simultaneous localization and mapping Oceans Pipelines Object detection Inertial navigation

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Menstrual Cycle Prediction Using GAN-Generated Data and Transformer Model for Tabular Data

A Novel Approach to Menstrual Cycle Prediction Using GAN-Gen...

引用

IEEE International WIE Conference on electrical and computer engineering (WIECON-ECE)

作者： Md Younus Ahamed Md Asif Bin Syed Mafuza Nasrin Tani Tanpia Tasnim Al Zadid Sultan Bin Habib Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown WV USA Department of Industrial and Management Systems Engineering West Virginia University Morgantown WV USA Army Medical College Rangpur Rangpur Bangladesh Green University of Bangladesh Narayanganj Dhaka Bangladesh

ISBN: (数字)9798331535476

ISBN: (纸本)9798331535483

Accurate menstrual cycle prediction is crucial for women's health and fertility management. While prior studies have utilized machine learning models to predict cycle length and classify regularity, they often struggled with the low Observationto-Variable Ratio (OVR) inherent in menstrual cycle data. This study tackles this issue by employing Generative Adversarial Networks (GANs) to generate synthetic data and Transformerbased models for both classification a nd r egression t asks. We evaluated multiple machine learning models for menstrual cycle phase classification a nd l ength p rediction. F or t he classification of regular versus irregular cycles, TabNet significantly outperformed baseline models, including Logistic Regression, Random Forest, and LSTM, achieving 99.67% accuracy, an AUC of 0.96, an F1 score of 0.99, 92.37% specificity, a nd 99.66% sensitivity, with CTGAN-generated synthetic data enhancing its performance. In the regression task of predicting cycle length, TabNet demonstrated strong predictive power, with an MSE of 1.29, RMSE of 1.13, and an R 2 score of 0.87. Although Random Forest performed slightly better with an MSE of 0.958 and an R 2 score of 0.90, TabNet remained competitive. These results highlight the potential of GAN-generated data and advanced models like TabNet in overcoming low OVR challenges and improving menstrual cycle prediction. Future research may incorporate personalized health data to further enhance model accuracy and generalizability.

关键词： Logistic regression Accuracy Sensitivity Medical services Predictive models Transformers Data models Random forests Long short term memory Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Tunable Experimental Testbed for Evaluating Load Coordination Methods

arXiv

引用

arXiv 2023年

作者： Geller, Drew A. Mathieu, Johanna L. Los Alamos National Laboratory Los AlamosNM87544 United States The Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States

Driven by the need to offset the variability of wind and solar generation on the electrical grid, development of load controls is a highly active field in the engineering literature. However, practical use of residential loads for grid balancing and ancillary services remains rare, in part due to the relative cost of communicating with hordes of small loads and also due to the limited experimentation done so far to demonstrate reliable operation. To establish a basis for the safe and reliable use of fleets of small compressor loads as distributed energy resources (DERs), we have constructed an experimental testbed in a laboratory, so that load coordination schemes can be tested at extreme conditions within a laboratory environment. This experiment can be used to tune a simulation testbed to which it can then be linked, thereby augmenting the effective size of the ensemble of loads. Control algorithms can simply be plugged in for testing. Modeling of the system was done both to demonstrate the experimental testbed’s behavior and also to understand how to tune the behavior of each participating model house in the system. Implementing this testbed has been useful for the rapid turnaround of experiments on various control types, and it enables testing year-round without the constraints and limitations arising in seasonal field tests with real human participants. Copyright © 2023, The Authors. All rights reserved.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Microcomb-driven photonic convolutional engine

Microcomb-driven photonic convolutional engine

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Bai, Bowen Yang, Qipeng Shu, Haowen Chang, Lin Wu, Yichen Yang, Fenghe Shen, Bitao Tao, Zihan Xie, Weiqiang Hu, Weiwei Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China Zhangjiang Laboratory Shanghai201210 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

We demonstrate a microcomb-driven chip-based photonic convolutional engine utilizing time-wavelength plane stretching approach. A preeminent photonic-core compute density of 1.04 TOPS/mm2 and a record high weight cont... 详细信息

ISBN: (纸本)9781957171258

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Sustainable Multi-User Computation Offloading for Mobile Edge-Quantum Computing

Learning-Based Sustainable Multi-User Computation Offloading...

引用

IEEE International Conference on Communications (ICC)

作者： Minrui Xu Dusit Niyato Jiawen Kang Zehui Xiong Mingzhe Chen School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Singapore Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables FL USA

In this paper, a novel paradigm of mobile edgequantum computing (MEQC) is proposed, which brings quantum computing capacities to mobile edge networks that are closer to mobile users (i.e., edge devices). First, we propose an MEQC system model where mobile users can offload computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Second, we show that it is NP-hard to obtain a centralized solution to the partial offloading problem in MEQC in terms of the optimal latency and energy cost of classical and quantum computing. Third, we propose a multi-agent hybrid discrete-continuous deep reinforcement learning using proximal policy optimization to learn the long-term sustainable offloading strategy without prior knowledge. Finally, experimental results demonstrate that the proposed algorithm can reduce at least 30% of the cost compared with the existing baseline solutions under different system settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics for Urban Transportation Management

arXiv

引用

arXiv 2024年

作者： Li, Tao Bian, Zilin Lei, Haozhe Zuo, Fan Yang, Ya-Ting Zhu, Quanyan Li, Zhenning Chen, Zhibin Ozbay, Kaan Department of Electrical and Computer Engineering New York University United States Department of Civil and Urban Engineering New York University United States State Key Laboratory of Internet of Things for Smart City University of Macau China Shanghai Key Laboratory of Urban Design and Urban Science NYU Shanghai China

Traditional mobility management strategies emphasize macro-level mobility oversight from traffic-sensing infrastructures, often overlooking safety risks that directly affect road users. To address this, we propose a Digital Twin-based Driver Risk-Aware Intelligent Mobility Analytics (DT-DIMA) system. The DT-DIMA system introduces four novel services that extract real-time traffic information from pan-tilt-cameras (PTCs), synchronize this data into a digital twin to accurately replicate the physical world, and predict network-wide mobility and safety risks in real time. The system’s innovation lies in its integration of advanced machine learning, simulation, and online control modules, including Spatial-Temporal Traffic Estimation (STTE) for real-time traffic data fusion and prediction, Mesoscopic Traffic Safety Simulation (MTSS) for real-time safety risk prediction, and Risk-Constrained Correlated Online Learning (RiCCOL) for real-time PTC control. Tested and evaluated under normal traffic conditions and incidental situations (e.g., unexpected accidents, pre-planned work zones) in a simulated testbed in Brooklyn, New York, DT-DIMA demonstrated mean absolute percentage errors (MAPEs) ranging from 8.40% to 15.11% in estimating network-level traffic volume and MAPEs from 0.85% to 12.97% in network-level safety risk prediction. In addition, the highly accurate safety risk prediction enables PTCs to preemptively monitor road segments with high driving risks before incidents take place. Such proactive PTC surveillance creates around a 5-minute lead time in capturing traffic incidents. The DT-DIMA system enables transportation managers to understand mobility not only in terms of traffic patterns but also driver-experienced safety risks, allowing for proactive resource allocation in response to various traffic situations. To the authors’ best knowledge, DT-DIMA is the first urban mobility management system that considers both mobility and safety risks based on digital twin

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Ultrasound Image Denoiser Using Parallel Attention Modules and Capsule Generative Adversarial Network

引用

Informatics in Medicine Unlocked 2024年 50卷

作者： Sivaanpu, Anparasy Punithakumar, Kumaradevan Thanikasalam, Kokul Noga, Michelle Zheng, Rui Ta, Dean Lou, Edmond H.M. Le, Lawrence H. Department of Radiology and Diagnostic Imaging University of Alberta Edmonton Alberta Canada Department of Computer Science University of Jaffna Jaffna Sri Lanka School of Information Science and Technology ShanghaiTech University Shanghai 201210 China Department of Biomedical Engineering School of Information Science and Technology Fudan University Shanghai China Department of Electrical and Computer Engineering University of Alberta Edmonton Alberta Canada State Key Laboratory of Integrated Chips and Systems Fudan University Shanghai China

The quality of ultrasound (US) imaging has been constrained by its limited contrast and resolution, inherent speckle noise, and the presence of other artifacts. Existing traditional and deep learning-based US denoising approaches have many limitations, such as reliance on manual parameter configurations, poor performance for unknown noise levels, the requirement for a large number of training data, and high computational expense. To address these challenges, we propose a novel Generative Adversarial Network (GAN) based denoiser. Capsule networks are utilized in both the generator and discriminator of the proposed GAN to capture intricate sparse features with less complexity. In addition, bias components are removed from all neurons of the generator to handle the unknown noise levels. A parallel attention module is also included in the proposed model to further enhance denoising performance. The proposed approach is trained in a semi-supervised manner and can thus be trained with fewer labeled images. Experimental evaluation on publicly available HC18 and BUSI datasets showed that the proposed approach achieved state-of-the-art denoising performance, with PSNR values of 33.86 and 34.16, and SSIM indices of 0.91 and 0.90, respectively. Moreover, experiments showed that the proposed approach is lightweight and more than twice as fast as similar denoisers. © 2024

关键词： Capsule Network Generative Adversarial Network Image denoising Semi-supervision Ultrasound image

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：