检索结果-内蒙古大学图书馆

International Conference on computer Supported Cooperative Work in Design

作者： Xin Zhang Xueping Peng Weimin Chen Weiyu Zhang Xiaoqiang Ren Wenpeng Luv Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia Shandong Mental Health Center Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Sequential diagnosis prediction (SDP) is a complex and challenging task, aming to predict future diagnoses of patients by analyzing their historical medical records. Although graph neural networks(GNNs) has been applied to successfully address the challenge of heterogeneous data integration in electronic health records, relatively limited work has been done on GNNs for sequential diagnosis prediction. Graph neural network-based methods, aimed at capturing structural and relational patterns of EHR data for sequential diagnosis prediction, explore code-code pairwise relationships, resulting in an inability to learn fine-grained, higher-order interaction relationships among different types medical codes. As a result, they are difficult to effectively model complex, multi-dimensional interactions among different types of medical codes necessary for accurate and nuanced diagnosis predictions. To address these challenges, this paper proposes a novel approach called Multi-Channel Hypergraph Network (MCHN) predictive framework for sequential diagnosis prediction. The proposed method aims to explore the fine-grained higher-order interactions between different types of medical codes via multi-channel hypergraphs. Specifically, MCHN learns two levels of code embeddings from multi-channel hypergraph learning module and line graph learning module, respectively: (i) multi-channel hypergraph learning module, which is to learn multi-channel hypergraph level code embeddings by modeling the higher-order relationships between medical codes in different hypergraphs; and (ii) line graph learning module, which is to learn the line graph level code embeddings by modeling code-code pairwise relationships. In MCHN, we propose a novel channel-level attention mechanism to help our model attend to the informativeness of the different channel for forecasting future patient diagnoses. We also design a code-level attention mechanism, which can to pay more attention to the medical codes that are m

关键词： Codes Attention mechanisms Federated learning Medical services Predictive models Benchmark testing Sequential diagnosis

来源：评论

学校读者我要写书评

暂无评论

Efficient and Scalable Dynamic Graph Replication for Cloud Computing Services

引用

IEEE Transactions on Services Computing 2025年

作者： Javadpour, Amir Ja'fari, Forough Zhang, Weizhe Harbin Institute of Technology School of Computer Science and Technology Guangdong Shenzhen518055 China Peng Cheng Laboratory Department of New Networks Guangdong Shenzhen518055 China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Guangdong518055 China

The cloud environment has garnered significant attention due to its crucial role as a supportive framework in computer science and engineering activities. This ever-growing adoption has increased among users, necessitating ongoing efforts to maintain and enhance cloud performance. A widely recognised approach to improving the user experience in cloud environments is data replication. This article proposes a Locality-Aware Dynamic Data Replication Algorithm (LADRE) designed to balance network load and enhance performance. The proposed model identifies the most appropriate data files for replication and selects optimal storage nodes for placing replicas. Simulations conducted using the CloudSim library demonstrate that LADRE improves cloud network load balancing by 5% compared to prior methods. Furthermore, LADRE outperforms existing approaches regarding network response time, storage efficiency, and the frequency of data removal operations. © 2008-2012 IEEE.

关键词： Cloud environment Data locality Dynamic data replication

来源：评论

学校读者我要写书评

暂无评论

Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data

arXiv

引用

arXiv 2024年

作者： Zhang, Rongyu Chen, Yun Wu, Chenrui Wang, Fangxin Li, Bo The Chinese University of Hong Kong Shenzhen China The Chinese University of Hong Kong Shenzhen China The Guangdong Provincial Key Laboratory of Future Networks of Intelligence China The Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange. Nonetheless, FL implementations often suffer from non-i.i.d. and long-tailed class distributions across mobile applications, e.g., autonomous vehicles, which leads models to overfitting as local training may converge to sub-optimal. In our study, we explore the impact of data heterogeneity on model bias and introduce an innovative personalized FL framework, Multi-level Personalized Federated Learning (MuPFL), which leverages the hierarchical architecture of FL to fully harness computational resources at various levels. This framework integrates three pivotal modules: Biased Activation Value Dropout (BAVD) to mitigate overfitting and accelerate training;Adaptive Cluster-based Model Update (ACMU) to refine local models ensuring coherent global aggregation;and Prior Knowledge-assisted Classifier Fine-tuning (PKCF) to bolster classification and personalize models in accord with skewed local data with shared knowledge. Extensive experiments on diverse real-world datasets for image classification and semantic segmentation validate that MuPFL consistently outperforms state-of-the-art baselines, even under extreme non-i.i.d. and long-tail conditions, which enhances accuracy by as much as 7.39% and accelerates training by up to 80% at most, marking significant advancements in both efficiency and effectiveness. Copyright © 2024, The Authors. All rights reserved.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Synesthesia of Machines (SoM)-Enhanced Wideband Multi-User CSI Learning With LiDAR Sensing

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Haotian Gao, Shijian Cheng, Xiang Yang, Liuqing Peking University State Key Laboratory of Photonics and Communications School of Electronics Beijing100871 China Guangzhou511400 China The Chinese University of Hon g Kong Guangdong Provincial Key Laboratory of Future Networks of Intelligence Shenzhen China Internet of Things Thrust Intelligent Transportation Thrust Guangzhou510000 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong

Light detection and ranging (LiDAR) has been utilized for optimizing wireless communications due to its ability to detect the environment. This paper explores the use of LiDAR in channel estimation for wideband multi-user multiple-input-multiple-output orthogonal frequency division multiplexing systems and introduces a LiDAR-Enhanced Channel State Information (CSI) Learning Network (LE-CLN). By utilizing user positioning information, LE-CLN first calculates user-localized over-complete angular measurements. It then investigates the correlation between LiDAR and CSI, transforming raw LiDAR data into a low-complexity format embedded with signal propagation characteristics. LE-CLN also adapts the use of LiDAR based on channel conditions through attention mechanisms. Thanks to the unique wireless features offered by LiDAR, LE-CLN achieves higher estimation accuracy and spectrum efficiency compared to benchmarks, particularly in latency-sensitive applications where pilot transmissions are expected to be reduced. © 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

Slfusion: A Structure-Aware Infrared and Visible Image Fusion Network for Low-Light Scenes

SSRN

引用

SSRN 2024年

作者： Lv, Guohua Gao, Xiang Dong, Aimei Gao, Yongbiao Zhao, Guixin Cheng, Jinyong Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan250353 China Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications Southeast University Ministry of Education 210000 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250353 China

Infrared and visible image fusion is an image enhancement technique that generates a single image with rich textures and significant objectives in a variety of scenarios, providing great convenience for human discrimination and computer recognition. However, in low-light environments, low-intensity visible images tend to blur valuable information, and these details are often ignored during image fusion, resulting in the loss of important information. Although existing methods take into account the damage of low illumination and highlight the illumination in the fusion process, a large amount of structural information is lost in the process of adjusting illumination, resulting in the lack of texture details and poor performance in high-level vision tasks. To address the above challenges, this paper proposes a structure-aware image fusion method for low illumination scenes, called SLFusion, which enhances the illumination while reducing the loss of structural information, leading to a fused image with richer texture details. We first design an illumination enhancement module to separate the degraded illumination from the scene information in the visible image, and mine more details from the low-intensity regions. Based on the fact that image edge information has a good capability of modeling structures, we design an edge extraction network for low-light visible images to model the structural information, which can accurately highlight important structural information and inject it into the fusion image. The proposed method produces fusion results that not only have good visual perception, but also minimize the loss of structural information. Extensive experiments on benchmark datasets demonstrate that the proposed method outperforms state-of-the-art (SOTA) methods in terms of visual quality, quantitative metrics as well as advanced vision tasks. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Advances in Embodied Navigation Using Large Language Models: A Survey

arXiv

引用

arXiv 2023年

作者： Lin, Jinzhou Gao, Han Feng, Xuxiang Xu, Rongtao Wang, Changwei Zhang, Man Guo, Li Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China Aerospace Information Research Institute Chinese Academy of Science China Qilu University of Technology Shandong Academy of Sciences China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science China

In recent years, the rapid advancement of Large Language Models (LLMs) such as the Generative Pre-trained Transformer (GPT) has attracted increasing attention due to their potential in a variety of practical applications. The application of LLMs with Embodied intelligence has emerged as a significant area of focus. Among the myriad applications of LLMs, navigation tasks are particularly noteworthy because they demand a deep understanding of the environment and quick, accurate decision-making. LLMs can augment embodied intelligence systems with sophisticated environmental perception and decision-making support, leveraging their robust language and image-processing capabilities. This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation. It reviews state-of-the-art models, research methodologies, and assesses the advantages and disadvantages of existing embodied navigation models and datasets. Finally, the article elucidates the role of LLMs in embodied intelligence, based on current research, and forecasts future directions in the field. A comprehensive list of studies in this survey is available at https://***/Rongtao-Xu/Awesome-LLM-EN. Copyright © 2023, 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

Unimodal Training-Multimodal Prediction: Cross-modal Federated Learning with Hierarchical Aggregation

引用

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Rongyu Chi, Xiaowei Zhang, Wenyi Liu, Guiliang Wang, Dan Wang, Fangxin Shenzhen China The Hong Kong Polytechnic University Department of Computing Hong Kong The Hong Kong University of Science and Technology Hong Kong Department of Electrical Engineering and Computer Science University of California Irvine United States Shenzhen China Shenzhen China Guangdong Provincial Key Laboratory of Future Networks of Intelligence China

Multimodal learning has significantly advanced the extraction of features from varied data sources, enhancing model performance. Federated learning (FL) complements this by enabling collaborative training while maintaining data privacy. The fusion of these two fields, multimodal federated learning, offers considerable promise. Yet, standard methods often incorrectly assume that each node in the FL network has a full complement of multimodal data, which is rare in real-world applications. In our study, we present a novel architecture designed to surmount these challenges, termed the Unimodal Training - Multimodal Prediction (UTMP) framework, positioned within the multimodal federated learning paradigm. Our proposed model, the HA-Fedformer, is a transformer-based model crafted to facilitate unimodal training on the client-side using exclusively unimodal datasets and to execute multimodal inference by synthesizing insights from multiple clients. Our HA-Fedformer model effectively handles non-IID data through a novel uncertainty-aware aggregation technique and layer-wise Markov Chain Monte Carlo sampling in local encoders. It also resolves misaligned language sequences via cross-modal decoder aggregation, capturing correlations between decoders trained on different modalities. Our comprehensive evaluations conducted on widely recognized sentiment analysis benchmarks demonstrate the superiority of the HA-Fedformer. The results show that our model achieves a substantial uplift in performance. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Fusion of Dynamic Hypergraph and Clinical Event for Sequential Diagnosis Prediction

Fusion of Dynamic Hypergraph and Clinical Event for Sequenti...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Xin Zhang Xueping Peng Hongjiao Guan Long Zhao Xinxiao Qiao Wenpeng Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia

Sequential diagnosis prediction (SDP) is a challenging task, aiming to predict patients’ future diagnoses based on their historical medical records. While methods based on graph neural networks (GNNs) have proven successful for this task, they typically focus on modeling pairwise diseases using a global disease combination graph. However, these approaches neglect the fine-grained higher-order relations among persistent and emerging diseases within a single visit, which may contain crucial clues to predict the next diagnosis. Additionally, they fail to fully leverage patient-related clinical information present in electronic health records (EHRs). To address these challenges, this paper proposes a novel approach called the fusion of Dynamic Hypergraph and Clinical Event (DHCE) for sequential diagnosis prediction. The proposed method aims to exploit the fine-grained higher-order relations among diagnoses within a visit and leverage clinical event information from EHRs to improve the accuracy of predicting the next diagnosis. Specifically, DHCE categorizes diagnoses within a single visit in a fine-grained granularity into persistent and emerging categories based on a patient’s historical diagnoses. It then constructs dynamic hypergraphs to capture higher-order disease relations within each visit. Next, we design a transition function to extract the transitional context from previous visits in order to generate the visit representation. Furthermore, to fully leverage patient-related clinical events in a visit, we utilize Bio-Clinical BERT to encode them and generate the clinical event representation for each visit. Finally, we combine the visit representation and event representation to generate a comprehensive patient representation, which is then used to predict the patient’s next diagnosis. Experimental results on two benchmark datasets consistently demonstrate that DHCE outperforms state-of-the-art methods 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

QoE-Aware Latency Optimization in Semantic Transmission Empowered Edge Assisted AR

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Li, Yang Wu, Yuan Xing, Huanlai Feng, Li Wang, Tian Jia, Weijia Southwest Jiaotong University School of Computer and Artificial Intelligent Chengdu611756 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Macau China Beijing Normal University Institute of Artificial Intelligence and Future Networks Zhuhai519087 China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China

Augmented reality (AR) enhances human perception by overlaying digital information in the real environment and can be applied to various fields such as education, healthcare, and industry. To relieve the computing pressure of resourcelimited AR devices, edge assisted AR has attracted significant attention in recent years. It enables AR devices to offload the computation-intensive environment analysis tasks to the edge server and to download the point-based 3D virtual objects for rendering. Although this method can effectively reduce the processing latency, it may introduce a long transmission latency. To address this issue, this work proposes a semantic communication empowered edge assisted AR to reduce the quality of experience (QoE)-aware latency. To this end, the AR devices first utilize an image encoder to extract semantic features of source images. Due to the importance difference of extracted features and limited communication resources, the feature selection and bandwidth allocation are explored to improve transmission efficiency. In addition, when the edge server completes the generation of pointbased 3D virtual objects, it employs a transformer-based encoder to mask a proportion of points and learn a high-level representation of unmasked points. In this way, low-complexity semantic information of 3D objects is sent to the AR devices, which can reduce the transmission overhead of 3D objects. Moreover, the mask ratio of the point encoder is further optimized to balance the reconstructed quality and transmission latency of 3D objects. Therefore, this work aims to minimize the overall QoE-aware latency of edge assisted AR by jointly optimizing the semantic feature selection, mask ratio, and bandwidth allocation. A convexbased improved Harris Hawks optimization algorithm is designed to solve the formulated problem. Experimental results demonstrate that our semantic communication empowered edge assisted AR can effectively reduce the overall latency and outperform

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients

Learning Cautiously in Federated Learning with Noisy and Het...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Chenrui Wu Zexi Li Fangxin Wang Chao Wu The Future Network of Intelligence Institute The Chinese University of Hong Kong Shenzhen School of Science and Engineering The Chinese University of Hong Kong Shenzhen College of Computer Science and Technology Zhejiang University The Guangdong Provincial Key Laboratory of Future Networks of Intelligence Peng Cheng Laboratory School of Public Affairs Zhejiang University

Federated learning (FL) is a distributed framework for collaborative training with privacy guarantees. In real-world scenarios, clients may have Non-IID data (local class imbalance) with poor annotation quality (label noise). The co-existence of label noise and class imbalance in FL’s small local datasets renders conventional FL methods and noisy-label learning methods both ineffective. To address the challenges, we propose FEDCNI without using an additional clean proxy dataset. It includes a noise-resilient local solver and a robust global aggregator. For the local solver, we design a more robust prototypical noise detector to distinguish noisy samples. Further to reduce the negative impact brought by the noisy samples, we devise a curriculum pseudo labeling method and a denoise Mixup training strategy. For the global aggregator, we propose a switching re-weighted aggregation method tailored to different learning periods. Extensive experiments demonstrate our method can substantially outperform state-of-the-art solutions in mix-heterogeneous FL environments.

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：