检索结果-内蒙古大学图书馆

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Zhang, Jia Lin, Xiao Hong, Zhixiang Wu, Guiping Li, Jun Chen, Zhen Sun, Weiqiang Lou, Zhilan College of Physics and Information Engineering Fuzhou University Fuzhou China School of Electronic and Information Engineering Soochow University Suzhou China Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai China School of Data Sciences Zhejiang University of Finance and Economics Hangzhou China

A SnF scheduling method is presented to schedule data transfers in the HFL aggregation process across the ECPON. Studies demonstrate that the proposed method outperforms conventional methods in terms of network perfor... 详细信息

ISBN: (纸本)9798350367652

关键词： Edge computing power network hierarchical federated learning model aggregation store-and-forward

来源：评论

学校读者我要写书评

暂无评论

CLIP-HASH: A Lightweight Hashing Network for Cross-Modal Retrieval 26

CLIP-HASH: A Lightweight Hashing Network for Cross-Modal Ret...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Xu, Mengying Lai, Hanjiang Yin, Jian Xu, Mengying Sun Yat-Sen University School of Systems Science and Engineering Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China

ISBN: (纸本)9798350331684

Cross-modal hashing has attracted great interest in the past decades. Due to the traditional hashing retrieval model requiring hand-crafted feature extraction, much research on the end-to-end deep hashing models has been explored. However, this training process of deep models is complex and needs a large number of samples. To address the above issues, we propose a lightweight hashing retrieval network with the pre-trained CLIP model, which is called CLIP-Hash. It can obtain better hash features via the pre-training CLIP model and provide a lightweight fine-tune model which is easily trained and only few training samples are required. First, we obtain the powerful feature representations by the visual and textual encodes. Then, we propose a simple hash encoding module, which is a lightweight network and only few parameters are needed to be trained. With the proposed hash encoding module, we can obtain efficient binary hash codes that can align the images and texts. We conduct experiments on MIRFlickr and NUS-WIDE two benchmark datasets. The results show that the proposed simple method can outperform the SOTA hashing methods. © 2023 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

A review on global spatial distribution,sources and toxicity of perfluoroalkyl acid and prospect in the cryosphere

引用

Journal of Mountain Science 2025年第1期22卷 167-183页

作者： LI Bowen Du Wentao KANG Shichang CHEN Jizu JIANG Youyan YIN Lichen LU Changsheng LIU Hongyi State Key Laboratory of Cryospheric Science and frozen soil engineering Northwest Institute of Eco-Environment and ResourcesChinese Academy of Sciences(CAS)Lanzhou 730000China University of Chinese Academy of Sciences Beijing 100049China Gansu Provincial Industry Technology Center of Intelligent Equipment and Big Data for Disaster Prevention Northwest Institute of Eco-Environment and ResourcesChinese Academy of Sciences(CAS)Lanzhou 730000China Lanzhou Regional Climate Center Lanzhou 730000China School of Earth Sciences and Spatial Information Engineering Hunan University of Science and TechnologyXiangtan 411201China School of Energy and Power Engineering Lanzhou University of TechnologyLanzhou 730000China Zhangye Meteorological Service Zhangye 734000China

Perfluoroalkyl acid analogs(PFAAs)are a class of chemically stable environmentally persistent organic pollutants(POPs)that are difficult to degrade and have a strong capacity to accumulate in the human *** have been found to be biotoxic to humans and have been detected in various environmental media,especially in the cryosphere at trace *** cryosphere,sensitively responds to climate change,plays a crucial role in the global water,carbon and energy ***,researches on cryosphere PFAAs especially in Tibetan Plateau(TP)is ***,we summarize the physicochemical properties,physiological toxicity,spatiotemporal distribution,sources,diffusion and migration pathways,as well as analysis and removal methods of PFAAs in the cryosphere *** results show that PFAAs pollutants are mainly produced and distributed in the more economically developed countries in Europe and the United States,as well as in East Asia,and PFAAs can be transported by atmospheric circulation and water cycle to remote regions including cryosphere *** current detection methods for PFAAs in cryosphere need to be further refined for increased accuracy and *** is also a need to develop more effective removal methods that will reduce the environmental and human threats posed by these ***,we propose key scientific questions for future research in cryosphere including PFAAs redistribution influenced by cryosphere changes,human activities,and the interaction of other spheres.

关键词： Perfluoroalkyl acid Cryosphere Physiological toxicity Analytical method Removal method

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Computing Power Scheduling Scheme for the EDWC Project in china 22

A Dynamic Computing Power Scheduling Scheme for the EDWC Pro...

引用

22nd International Conference on Optical Communications and Networks, ICOCN 2024

作者： Hong, Zhixiang Lin, Xiao Wu, Guiping Zhang, Jia Li, Jun Chen, Zhen Sun, Weiqiang Lou, Zhilan College of Physics and Information Engineering Fuzhou University Fuzhou China School of Electronic and Information Engineering Soochow University Suzhou China Shanghai Jiao Tong University State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai China School of Data Sciences Zhejiang University of Finance and Economics Hangzhou China

In this paper, we conduct the cost analysis of the EDWC project. Studies show the current transmission cost is too high. We present a scheme to schedule the computing jobs based on the price fluctuation. © 2024 I... 详细信息

ISBN: (纸本)9798350367652

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Cloud-magnetic resonance imaging system:In the era of 6G and artificial intelligence

引用

Magnetic Resonance Letters 2025年第1期5卷 52-63页

作者： Yirong Zhou Yanhuang Wu Yuhan Su Jing Li Jianyu Cai Yongfu You Jianjun Zhou Di Guo Xiaobo Qu Department of Electronic Science Intelligent Medical Imaging R&D CenterFujian Provincial Key Laboratory of Plasma and Magnetic ResonanceNational Institute for Data Science in Health and MedicineXiamen UniversityXiamen361104China Department of Electronic Science Key Laboratory of Digital Fujian on IoT CommunicationXiamen UniversityXiamen361104China Shanghai Electric Group Co. LtdShanghai200002China China Telecom Group Quanzhou362018China China Mobile Group Xiamen361009China Department of Radiology Zhongshan Hospital(Xiamen)Fudan UniversityXiamen Municipal Clinical Research Center for Medical ImagingFujian Province Key Clinical Specialty Construction Project(Medical Imaging Department)Xiamen Key Laboratory of Clinical Transformation of Imaging Big Data and Artificial IntelligenceXiamen361006China School of Computer and Information Engineering Xiamen University of TechnologyXiamen361024China

Magnetic resonance imaging(MRI)plays an important role in medical diagnosis,generating petabytes of image data annually in large *** voluminous data stream requires a significant amount of network bandwidth and extensive storage ***,local data processing demands substantial manpower and hardware *** isolation across different healthcare institutions hinders crossinstitutional collaboration in clinics and *** this work,we anticipate an innovative MRI system and its four generations that integrate emerging distributed cloud computing,6G bandwidth,edge computing,federated learning,and blockchain *** system is called Cloud-MRI,aiming at solving the problems of MRI data storage security,transmission speed,artificial intelligence(AI)algorithm maintenance,hardware upgrading,and collaborative *** workflow commences with the transformation of k-space raw data into the standardized Imaging Society for Magnetic Resonance in Medicine Raw data(ISMRMRD)***,the data are uploaded to the cloud or edge nodes for fast image reconstruction,neural network training,and automatic ***,the outcomes are seamlessly transmitted to clinics or research institutes for diagnosis and other *** Cloud-MRI system will save the raw imaging data,reduce the risk of data loss,facilitate inter-institutional medical collaboration,and finally improve diagnostic accuracy and work efficiency.

关键词： Magnetic resonance imaging Cloud computing 6G bandwidth Artificial intelligence Edge computing Federated learning Blockchain

来源：评论

学校读者我要写书评

暂无评论

Adaptive Method of Process Flow Parameter Values Setting Based on Remote Sensing Image Metadata

Adaptive Method of Process Flow Parameter Values Setting Bas...

引用

2022 International Conference on Signal Processing, Computer Networks, and Communications, SPCNC 2022

作者： Zhou, Bing Ge, Jian Kang Zuo, Xianyu Key Laboratory of Analysis and Processing of Big Data Henan Kaifeng475004 China School of Computer and Information Engineering Henan University Henan Kaifeng475004 China

ISBN: (纸本)9781510664616

Remote sensing data processing involves many steps. This paper uses process flow to represent these processing steps. This paper combines remote sensing image metadata (RSIM) with case based reasoning (CBR) technology, proposes a parameter value adaptive method based on RSIM, and constructs a remote RSIM case model. It makes the representation of RSIM more intuitive and convenient. This method consists of two parts: case building and case similarity measurement. Case building refers to building RSIM into RSIM cases according to case models, and then classifying and saving each case. Case similarity measurement refers to the similarity measurement of metadata in the production process and each case under the flow. Finally, the parameter values will be configured according to the highest similarity. The method is tested in an actual remote sensing production system, and the experimental results show that the method has good applicability in the parameter value adaptation of remote sensing process production. © 2023 SPIE.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Dental Caries Segmentation Method Based on Dental Bitewings 2

A Dental Caries Segmentation Method Based on Dental Bitewing...

引用

2022 2nd International Conference on Health Big data and Smart Sports, HBDSS 2022

作者： Han, Zhiyuan Yang, Jingyu Wang, Chen Du, Chenxi School of Computer Science and Engineering Beijing Technology and Business University Beijing China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing China

ISBN: (纸本)9783800760428

Computer Aided Diagnosis (CAD) has become a hot research field in oral clinic. Due to the similar contrast between caries and periodontal tissues, especially the proximal caries, it is difficult for general CAD methods to accurately detect the location of caries. Aiming at this problem, an image semantic segmentation algorithm based on U-Net and attention mechanism is proposed. First, the dental bitewings dataset was constructed. Second, the CBAM module is integrated into the U-Net network for focusing on caries-affected areas. Finally, the semantic segmentation accuracy is further improved by multi-scale feature fusion. The experimental results show that the model proposed in this paper has significant improvements in multiple performances compared with algorithms such as PSP-Net. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees 41

FedLMT: Tackling System Heterogeneity of Federated Learning ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jiahao Zhou, Yipeng Wu, Di Hu, Miao Guizani, Mohsen Sheng, Quan Z. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Computing Faculty of Science and Engineering Macquarie University Sydney Australia Abu Dhabi United Arab Emirates

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs. Copyright 2024 by the author(s)

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Tumor microenvironment-responsive modular integrated nanocomposites for magnetically targeted and photothermal enhanced catalytic therapy

引用

Nano Research 2023年第7期16卷 9826-9834页

作者： Yuan Liang Yilin Liu Pengpeng Lei Zhen Zhang Hongjie Zhang State Key Laboratory of Rare Earth Resource Utilization Changchun Institute of Applied ChemistryChinese Academy of Sciences5625 Renmin StreetChangchun 130022China School of Materials Science and Engineering Sun Yat-sen UniversityGuangzhou 510275China School of Rare Earths University of Science and Technology of ChinaHefei 230026China Ganjiang Innovation Academy Chinese Academy of SciencesGanzhou 341000China Department of Chemistry Tsinghua UniversityBeijing 100084China

Achieving efficient integration of cancer diagnosis and therapy is of great significance to human health,but the construction of a multifunctional intelligent therapy system still faces great *** this study,we report an integrated multifunctional nanocomposite constructed by a simple modular assembly *** nanocomposites are composed of three different nanomaterials:Fe_(3)O_(4),Au,and NaErF_(4):0.5%Tm@NaYF_(4)upconversion nanoparticles(UCNPs).In this design,Fe_(3)O_(4)nanoparticles have nanozyme effect of peroxidase-like activity,which can react with H_(2)O_(2)in the tumor microenvironment to generate hydroxyl *** of its magnetic properties,it can help the nanocomposites to aggregate under the induction of magnetic *** nanoparticles exhibit nanozyme effect of glucose oxidase-like *** can catalyze the conversion of glucose to gluconic acid and H_(2)O_(2).Ingeniously,the generated H_(2)O_(2)provides a source of reactants for the reaction of the Fe_(3)O_(4)*** addition,the photothermal effect of Au nanoparticles under 808 nm irradiation further enhanced the nanozyme activity of Fe_(3)O_(4)and Au ***,UCNPs can emit near-infrared(NIR)-II fluorescence under 808 nm irradiation,which can provide imaging-guided during cancer ***,the nanocomposites were further modified by poly(vinylpyrrolidone)(PVP)to obtain UCNPs/Au/Fe_(3)O_(4)-PVP with good biocompatibility and high-efficiency cancer treatment ability.

关键词： modular integrated magnetic induction photothermal effect near-infrared(NIR)-II imaging nanozyme catalyzed reactions

来源：评论

学校读者我要写书评

暂无评论

MMAL: Multi-Modal Analytic Learning for Exemplar-Free Audio-Visual Class Incremental Tasks 24

MMAL: Multi-Modal Analytic Learning for Exemplar-Free Audio-...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yue, Xianghu Zhang, Xueyi Chen, Yiming Zhang, Chengwei Lao, Mingrui Zhuang, Huiping Qian, Xinyuan Li, Haizhou Department of Electrical and Computer and Engineering National University of Singapore Singapore Laboratory for Big Data and Decision National University of Defense Technology Hunan Changsha China School of Electronic Electrical and Communication Engineering University of the Chinese Academy of Sciences Beijing China National Key Laboratory of Information Systems Engineering National University of Defense Technology Hunan Changsha China Shien-Ming Wu School of Intelligent Engineering South China University of Technology Guangdong Guangzhou China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China Shenzhen China

ISBN: (纸本)9798400706868

Class-incremental learning poses a significant challenge under an exemplar-free constraint, leading to catastrophic forgetting and sub-par incremental accuracy. Previous attempts have focused primarily on single-modality tasks, such as image classification or audio event classification. However, in the context of Audio-Visual Class-Incremental Learning (AVCIL), the effective integration and utilization of heterogeneous modalities, with their complementary and enhancing characteristics, remains largely unexplored. To bridge this gap, we propose the Multi-Modal Analytic Learning (MMAL) framework, an exemplar-free solution for AVCIL that employs a closed-form, linear approach. To be specific, MMAL introduces a modality fusion module that re-formulates the AVCIL problem through a Recursive Least-Square (RLS) perspective. Complementing this, a Modality-Specific knowledge Compensation (MSKC) module is designed to further alleviate the under-fitting limitation intrinsic to analytic learning by harnessing individual knowledge from audio and visual modality in tandem. Comprehensive experimental comparisons with existing methods show that our proposed MMAL demonstrates superior performance with the accuracy of 76.71%, 78.98%, and 76.19% on AVE, Kinetics-Sounds, and VGGSounds100 datasets, respectively, setting new state-of-the-art AVCIL performance. Notably, compared to those memory-based methods, our MMAL, being an exemplar-free approach, provides good data privacy and can better leverage multi-modal information for improved incremental accuracy. © 2024 ACM.

关键词： Contrastive Learning

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：