检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Di Liu, Wenjian Gao, Longxiang Qu, Y. Neil. Zhang, Hu Shi, Jihong The Faculty of Data Science City University of Macau Macau China Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Medical Integration and Practice Center Shandong University Jinan China

ISBN: (纸本)9789819615476

Federated Learning (FL) has progressed, providing a distributed mechanism where data need not be consolidated, thereby enhancing the privacy and security of sensitive healthcare data. Recent advancements in multimodal machine learning have empowered the development of accurate and robust AI systems in the medical domain, especially within centralized database systems. Multimodal federated learning (MFL) combines federated learning’s distributed nature with the flexibility to work with various data types. This capability is particularly relevant in medical contexts, where healthcare data can range from electronic health records (EHR) to radiology imaging, genomic data, and wearable device information. The key advantage of MFL in medical settings is the ability to create robust models without centralizing sensitive patient information. However, there are no existent research to comprehensively review the application status of MFL in smart healthcare systems from the modal-centric aspect. Motivated by this, we explore the systematization of knowledge about multimodal federated learning on medical data, find the challenges of this area and related solutions. With this research, we hope to provide a systematical review of this under-explored domain and provide insights for forthcoming researchers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Interference-Aware Routing,Wavelength and Power Allocation in C+L+S Multi-Band Optical Networks

引用

China Communications 2025年第4期22卷 129-142页

作者： Zhang Xu Xie Wang Feng Chuan Zeng Hankun Zhou Shanshan Zhang Fan Gong Xiaoxue School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China Institute of Intelligent Communications and Network Security Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and TelecommunicationsChongqing 400065China

Multi-band optical networks are a potential technology for increasing network ***,the strong interference and non-uniformity between wavelengths in multi-band optical networks have become a bottleneck restricting the transmission capacity of multi-band optical *** overcome these challenges,it is particularly important to implement optical power optimization targeting wavelength ***,based on the generalized Gaussian noise model,we first formulate an optimization model for the problems of routing,modulation format,wavelength,and power allocation in C+L+S multi-band optical *** objective function is to maximize the average link capacity of the network while ensuring that the Optical Signal-to-Noise(OSNR)threshold of the service request is not ***,we propose a NonLinear Interferenceaware(NLI-aware)routing,modulation format,wavelength,and power allocation ***,we conduct simulations under different test *** simulation results indicate that our algorithm can effectively reduce the blocking probability by 23.5%and improve the average link capacity by 3.78%in C+L+S multi-band optical networks.

关键词： multiband optical communications multiband optical networks power allocation wavelength assignment

来源：评论

学校读者我要写书评

暂无评论

Task Prioritization in Multiagent Environments: A Novel Approach Using Nash Q-Learning

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Li, Kexin Hu, Yu Wang, Jielei Li, Lin Zhang, Shuyuan Luo, Guangchun Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of China China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China College of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

—With the rapid proliferation of smartphones and various terminal devices, edge computing has gained increasing importance in overcoming computational limitations and enhancing service quality through task offloading. However, most existing approaches handle tasks on a first-come, first-served basis, neglecting task prioritization, which is critical in real-world scenarios where tasks have different levels of urgency and resource requirements. This paper addresses the challenge of effective task prioritization in multi-agent task offloading by proposing a Nash Q-learning-based strategy. Our methodology involves optimizing task allocation decisions using Nash Q-learning to integrate Nash equilibrium principles, thereby enhancing adaptability and dynamic decision-making capabilities within a multi-agent environment. The proposed algorithm is evaluated through extensive simulations, comparing total delay, resource utilization, and task success rates across various task offloading strategies. The results demonstrate that our Nash Q-learning approach outperforms conventional techniques by dramatically lowering overall latency, optimizing resource allocation, and maintaining high task success rates. This work demonstrates the efficacy of Nash Q-learning for dynamically setting priorities for tasks in multi-agent edge computing environments, providing a robust framework for effective resource management and collaborative task completion. And also highlight the potential of Nash Q-learning in advancing intelligent task management in edge computing, suggesting its applicability in real-world, resource-constrained environments. © 2025 IEEE. All rights reserved,

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity feature intersection learning for visible-infrared person re-identification

引用

Complex and intelligent Systems 2025年第7期11卷 1-14页

作者： Chan, Sixian Wang, Jie Cui, Jiaao Hu, Jie Li, Zhuorong Mao, Jiafa College of Computer Science and Technology Zhejiang University of Technology Hangzhou 310023 China Key Laboratory of Intelligent Informatics for Safety & Emergency of Zhejiang Province Wenzhou University Wenzhou 325035 China School of Computer and Computing Science Hangzhou City University Hangzhou 310015 China

This paper proposes a multi-granularity feature intersection network (MGFINet) for visible-infrared person re-identification (VI-ReID). VI-ReID aims to retrieve images of the same pedestrian from different spectral cameras. The key challenge is to extract pedestrian descriptions with both inter-class discriminability and intra-class similarity. Previous methods ignore the potential loss of details during representation extraction and the presence of data bias in the metric function, limiting further improvements in retrieval performance. Meanwhile, the discrepancy regarding how to calculate the loss for representation learning and metric learning also affects the model’s training. To address the above issues, MGFINet consists of three components: a hierarchical part pooling method (HPP), a hierarchical part restriction method (HPC), and a feature intersection (FI) loss. HPP adopts a hierarchical framework to extract multi-granularity pedestrian representations, and it performs an inter-layer fusion operation to exploit the high-resolution information from shallow layers and the semantic representability from deep layers. Meanwhile, HPP employs part pooling with different step sizes to capture pedestrian details in each layer. Next, HPC spreads the identity loss across all layers to reduce the distance for gradient backpropagation and further optimize fine-grained features in shallow layers. Besides, FI loss combines representation and metric learning by incorporating hyperparameters of classifiers into metric learning, mitigating data bias and reducing the gap between the two learning processes. Finally, extensive experiments evaluated on two public datasets, SYSU-MM01 and RegDB demonstrate the effectiveness of the proposed method. © The Author(s) 2025.

关键词： Metric learning Multi-granularity Representation learning VI-ReID

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Task Offloading for Rotatable STAR-RIS-Enhanced Mobile Edge computing Systems

引用

IEEE Internet of Things Journal 2025年

作者： Yang, Dongdong Li, Bin Niyato, Dusit Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Huzhou Key Laboratory of Urban Multidimensional Perception and Intelligent Computing Huzhou313000 China Nanyang Technological University College of Computing and Data Science Singapore Singapore

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can expand the coverage of mobile edge computing (MEC) services by reflecting and transmitting signals simultaneously, enabling full-space coverage. The orientation of the STAR-RIS plays a crucial role in optimizing the gain of received and transmitted signals, and a rotatable STAR-RIS offers potential enhancement for MEC systems. This paper investigates a rotatable STAR-RIS-assisted MEC system, operated under three protocols, namely energy splitting, mode switching, and time switching. The goal is to minimize energy consumption for multiple moving user devices through the joint optimization of STAR-RIS configurations, orientation, computation resource allocation, transmission power, and task offloading strategies. Considering the mobility of user devices, we model the original optimization problem as a sequential decision-making process across multiple time slots. The high-dimensional, highly coupled, and nonlinear nature makes it a challenging non-convex decision-making problem for traditional optimization algorithms. Therefore, a deep reinforcement learning (DRL) approach is employed, specifically utilizing soft actor-critic algorithm to train the DRL model. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in both convergence speed and energy efficiency, while reducing energy consumption by up to 52.7% compared to the fixed STAR-RIS scheme. Among three operating protocols, the energy splitting yields the best performance. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement

arXiv

引用

arXiv 2025年

作者： Fang, Runnan Wang, Xiaobin Liang, Yuan Qiao, Shuofei Wu, Jialong Xi, Zekun Zhang, Ningyu Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effectively refine their action knowledge in the current environment. Our experiments demonstrate that SynWorld is an effective and general approach to learning action knowledge in new environments.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Federated Hybrid-Supervised Learning for Universal Medical Image Segmentation

Federated Hybrid-Supervised Learning for Universal Medical I...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Shenhai Wen, Sian Li, Congyu Chen, Qing Li, Laquan College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China School of Science Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG. © 2025 IEEE.

关键词： federated learning hybrid-supervised learning medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Improved generative adversarial network with bald eagle search optimization for missing data imputation

引用

Earth science Informatics 2025年第2期18卷 1-18页

作者： Qin, Xiwen Shi, Hongyu Dong, Xiaogang Zhang, Siqi Yuan, Liping Guo, Sijia School of Mathematics and Statistics Changchun University of Technology Jilin Changchun China Jilin Provincial Key Laboratory of Data Science and Intelligent Decision Jilin Changchun China School of Mathematics Sun Yat-Sen University Guangdong Guangzhou China

Missing data imputation is a critical task, as incomplete datasets can negatively impact model performance. Traditional imputation methods often fail to capture the intricate relationships within data, resulting in poor representations of complex patterns and reduced predictive accuracy. Generative Adversarial Network (GAN)-based imputation methods frequently encounter challenges, such as hyperparameter tuning difficulties and mode collapse. In this paper, we propose a improved GAN-based imputation framework, termed BESGAIN. To be concrete, BESGAIN introduces the Bald Eagle Search (BES) optimization algorithm to dynamically adjust hyperparameters, ensuring high-quality data imputation. Additionally, we incorporate an enhanced loss function that leverages cosine similarity to improve data diversity. This helps prevent performance degradation caused by overfitting to a single data mode. As a result, BESGAIN achieves a richer and more accurate set of imputed values. We validate the performance of BESGAIN across seven real-world datasets and compare it against state-of-the-art and widely used imputation methods. The experimental results demonstrate that BESGAIN outperforms existing techniques in terms of accuracy, robustness, and generalizability, particularly in datasets with high missing rates. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Bald eagle search optimization algorithm Generative adversarial imputation networks Missing data Mode collapse

来源：评论

学校读者我要写书评

暂无评论

An enhanced sparse subset selection model based on adaptive projection distance

引用

Evolutionary Intelligence 2025年第3期18卷 1-15页

作者： Feng, Feng Gao, Erwei Zhi, Xiaobin Zhao, Yichuan School of Science and Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an 710121 China School of Communication and Information Engineering Xi’an University of Posts and Telecommunications Xi’an 710121 China School of Science and Research Center for Intelligent Systems and Data Science Xi’an University of Posts and Telecommunications Xi’an 710121 China Department of Mathematics and Statistics Georgia State University Atlanta 30303 GA United States

Subset selection focuses on identifying representative samples from a large dataset to produce a data subset that can represent the main features of the original data and also reduce the data size in an effective way. Sparse representation theory puts emphasis on enhancing the data sparsity, while subset selection aims to reduce the data size. Sparse subset selection is an important branch of subset selection that incorporates sparse representation theory into the exploration of subset selection. Sparse modeling representative selection model has demonstrated outstanding performance in data classification and video summarization. Nonetheless, it suffers from the issue of poor typicality of the selected representatives. Although some recent works have addressed this problem to some extent by introducing the concept of clustering coding terms, most of the clustering coding terms constructed by these existing methods are implicit, and the model structure is complicated, inefficient, and difficult to be understood. To overcome these difficulties, we propose an adaptive projection distance-based sparse subset selection model. This model constructs a clustering coding item by adaptively calculating the projection distance between data. It can not only eliminate redundant and noisy features in the original data but also ensure that the selected representatives are more typical. To solve the proposed model, an efficient algorithm is developed by virtue of the alternating direction method of multipliers. Extensive experiments with comparative analysis demonstrate that the proposed model outperforms several state-of-the-art models in various tasks including subset selection, cluster analysis, classification, and face image representative selection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Adaptive projection distance Classification Cluster analysis Sparse representation Subset selection

来源：评论

学校读者我要写书评

暂无评论

Multiscale Temporal-Convolution and Attention Improved Neural Network for Biased Mental State Recognition 17th

Multiscale Temporal-Convolution and Attention Improved Neur...

引用

17th International Conference on Brain Informatics, BI 2024

作者： Zuo, Guoyu Xiao, Erjun Zhang, Tielin Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing University of Technology Beijing100124 China Center for Excellence in Brain Science and Intelligence Technology University of Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9789819632930

Accurate detection of mental state is vital for sleep assessment and anesthesia monitoring. However, challenges exist, including 1) limited data sources caused by few modalities, few channels, biased sample distribution, or large individual differences;2) multiscale dynamic feature of mental state signals, containing complex and dynamic fluctuations. In this paper, we proposed a multiscale temporal convolution and attention improved neural network (MTA-NN) to handle these two challenges, including: a preprocessing method using a clustering-first and label-generation approach for data augmentation involves filtering the production samples to mitigate the impact of noise on model performance;multiscale temporal-convolution module for detecting different scales of temporal and frequency features;an attention module for decoding key features in different spatial and temporal channels, and for setting the importance of historical dependencies;a full-connection layer is designed to recognize different sleep stage. The proposed MTA-NN is then verified in three typical sleep-state recognition tasks, including SleepEDF-20, SleepEDF-78, and ISRUC3. Compared to some state-of-the-art algorithms, the proposed MTA-NN achieves higher performance. Further ablation experiments show the necessary and importance of these designed sub modules in MTA-NN. We consider the same algorithm can also be extended to further similar mental state recognition tasks such as anesthesia monitoring. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anesthesiology

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

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

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：