检索结果-内蒙古大学图书馆

Efficient Model Store and Reuse in an OLML database System

Journal of Computer Science & technology 2021年第4期36卷 792-805页

作者： Jian-Wei Cui Wei Lu Xin Zhao Xiao-Yong Du Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China

Deep learning has shown significant improvements on various machine learning tasks by introducing a wide spectrum of neural network ***,for these neural network models,it is necessary to label a tremendous amount of training data,which is prohibitively expensive in *** this paper,we propose OnLine Machine Learning(OLML)database which stores trained models and reuses these models in a new training task to achieve a better training effect with a small amount of training *** efficient model reuse algorithm AdaReuse is developed in the OLML ***,AdaReuse firstly estimates the reuse potential of trained models from domain relatedness and model quality,through which a group of trained models with high reuse potential for the training task could be selected ***,multi selected models will be trained iteratively to encourage diverse models,with which a better training effect could be achieved by *** evaluate AdaReuse on two types of natural language processing(NLP)tasks,and the results show AdaReuse could improve the training effect significantly compared with models training from scratch when the training data is *** on AdaReuse,we implement an OLML database prototype system which could accept a training task as an SQL-like query and automatically generate a training plan by selecting and reusing trained *** studies are conducted to illustrate the OLML database could properly store the trained models,and reuse the trained models efficiently in new training tasks.

关键词： model selection model reuse OnLine Machine Learning(OLML)database

来源：评论

学校读者我要写书评

暂无评论

Dual-view Label and Feature Supervision Network for Semi-supervised Medical Image Segmentation 24

Dual-view Label and Feature Supervision Network for Semi-sup...

引用

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

IntML-KNN: A Few-Shot Radio Frequency Fingerprint Identification Scheme for Lora Devices

引用

IEEE Signal Processing Letters 2025年 32卷 2259-2263页

作者： Cao, Xin Tan, Weijie Gao, Qiangqiang Hu, Zhilong Li, Chunguo Guizhou University College of Computer Science and Technology Guiyang550025 China Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Ministry of Industry and Information Technology Laboratory of Cryptograph Application Technology Innovation and Testing Verification Beijing100015 China Southeast University School of Information Science and Engineering Nanjing210096 China

Deep learning (DL) is widely used in radio frequency fingerprint identification (RFFI). However, in few-shot case, traditional DL-based RFFI need to construct auxiliary dataset to realize radio frequency fingerprint identification. To address this issue, we propose a few-shot RFFI (FS-RFFI) method based on interpolating metric learning and KNN (IntML-KNN). Specifically, the method first extends the dataset with data augmentation, and CutMix interpolation. Secondly, combining with metric learning to enhance the generalization capacity of the model. Finally, KNN algorithm is designed to realize device classification and detection. The proposed IntML-KNN method is verified on the commercial available LoRa dataset. The experimental results indicate that the proposed scheme exhibits strong classification and generalization performance in FS-RFFI. Meanwhile, the recognition rate of the proposed IntML-KNN reaches 97.00% with only 10% samples. © 1994-2012 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

All-fiber and self-starting Yb-doped Mamyshev oscillator based on nonlinear polarization evolution

引用

Chinese Optics Letters 2024年第12期22卷 74-79页

作者： Zecong Li Kai Wang Zinan Huang Qianqian Huang YanlüLin Weixi Li Zhichao Luo Chengbo Mou Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data ScienceJoint International Research Laboratory of Specialty Fiber Optics and Advanced CommunicationShanghai UniversityShanghai 200444China Key Laboratory of Space Active Opto-Electronics Technology Shanghai Institute of Technical PhysicsChinese Academy of SciencesShanghai 200083China Laboratory of Nanophotonic Functional Materials and Devices School of Information and Optoelectronic Science and EngineeringSouth China Normal UniversityGuangzhou 510006China

We experimentally demonstrate a Yb-doped all-fiber mode-locked laser based on the Mamyshev *** entire experimental setup operates only by injecting pump powers and adjusting polarization controllers(PCs),which realizes *** types of pulse patterns are observed at different pump powers and polarization states,including single pulses and up to eight-pulse bound-state *** operating wavelength of single-pulse mode-locking switching between 1072.3and 1043.1 nm can be realized by increasing the pump power while keeping the PCs in a fixed *** design can provide an attractive experimental model for all-fiber and self-starting Mamyshev oscillators.

关键词： Mamyshev oscillator Yb-doped fiber laser pulse dynamic pattern nonlinear polarization evolution

来源：评论

学校读者我要写书评

暂无评论

The GNSS PWV retrieval using non-observation meteorological parameters based on ERA5 and its relation with precipitation

引用

Geodesy and Geodynamics 2024年第3期15卷 302-313页

作者： Weifeng Yang Zhiping Chen Kaiyun Lv Pengfei Xia Tieding Lu School of Surveying and Geoinformation Engineering East China University of TechnologyNanchang 330013China Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources East China University of TechnologyNanchang 330013China State Key Laboratory of Geodesy and Earth's Dynamics Innovation Academy for Precision Measurement Science and TechnologyChinese Academy of SciencesWuhan 430077China Jiangxi Province Engineering Research Center of Surveying Mapping and Geographic InformationNanchang 330025China School of Geodesy and Geomatics Wuhan UniversityWuhan 430079China

The pressure and temperature significantly influence precipitable water vapor(PWV) retrieval. Global Navigation Satellite System(GNSS) PWV retrieval is limited because the GNSS stations lack meteorological sensors. First, this article evaluated the accuracy of pressure and temperature in 68 radiosonde stations in China based on ERA5 Reanalysis data from 2015 to 2019 and compared them with GPT3model. Then, the accuracy of pressure and temperature calculated by ERA5 were estimated in 5 representative IGS stations in China. And the PWV calculated by these meteorological parameters from ERA5(ERA5-PWV) were analyzed. Finally, the relation between ERA5-PWV and precipitation was deeply explored using wavelet coherence analysis in IGS stations. These results indicate that the accuracy of pressure and temperature of ERA5 is better than the GPT3 model. In radiosonde stations, the mean BIAS and MAE of pressure and temperature in ERA5 are-0.41/1.15 hpa and-0.97/2.12 K. And the mean RMSEs are 1.35 hpa and 2.87 K, which improve 74.77% and 40.58% compared with GPT3 model. The errors of pressure and temperature of ERA5 are smaller than the GPT3 model in bjfs, hksl and wuh2, and the accuracy of ERA5-PWV is improved by 18.77% compared with the GPT3 model. In addition, there is a significant positive correlation between ERA5-PWV and precipitation. And precipitation is always associated with the sharp rise of ERA5-PWV, which provides important references for rainfall prediction.

关键词： ERA5 GNSS Precipitable water vapor Precipitation Wavelet coherence analysis

来源：评论

学校读者我要写书评

暂无评论

REQUIRED NUMBER OF ITERATIONS FOR SPARSE SIGNAL RECOVERY VIA ORTHOGONAL LEAST SQUARES

引用

Journal of Computational Mathematics 2023年第1期41卷 1-17页

作者： Haifeng Li Jing Zhang Jinming Wen Dongfang Li Henan Engineering Laboratory for Big Data Statistical Analysis and Optimal Control College of Mathematics and Information ScienceHenan Normal UniversityXinxiang 453007China College of Information Science and Technology Jinan UniversityGuangzhou 510632China School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China

In countless applications,we need to reconstruct a K-sparse signal x∈R n from noisy measurements y=Φx+v,whereΦ∈R^(m×n)is a sensing matrix and v∈R m is a noise *** least squares(OLS),which selects at each step the column that results in the most significant decrease in the residual power,is one of the most popular sparse recovery *** this paper,we investigate the number of iterations required for recovering x with the OLS *** show that OLS provides a stable reconstruction of all K-sparse signals x in[2.8K]iterations provided thatΦsatisfies the restricted isometry property(RIP).Our result provides a better recovery bound and fewer number of required iterations than those proposed by Foucart in 2013.

关键词： Sparse signal recovery Orthogonal least squares(OLS) Restricted isometry property(RIP)

来源：评论

学校读者我要写书评

暂无评论

Social inequity of park accessibility in Taiyuan:highlighting the unfair layout of parks in second-tier cities of China and the relative role of contributors

引用

地球空间信息科学学报（英文版） 2024年第4期27卷 1118-1140页

作者： Jing He Fu Ren Jiaxin Dong Huihui Zhang Wenhao Yan Jiping Liu School of Resource and Environmental Sciences Wuhan UniversityWuhanChina School of Resource and Environmental Sciences Wuhan UniversityWuhanChina Key Laboratory of Geographic Information Systems Ministry of EducationWuhan UniversityWuhanChina School of Remote Sensing and Information Engineering Wuhan UniversityWuhanChina Guangdong Provincial Department of Natural Resources Land and Resources Technology CenterGuangzhouChina Research Center of Geospatial Big Data Application Chinese Academy of Surveying and MappingBeijingChina

The scarcity of public resources and environmental pollution caused by rapid urbanization highlight the practical significance of parks in ensuring the sustainable development of a ***,the social equity of parks warrants further *** paper proposes a fine-grained comprehensive evaluation framework that combines geographic accessibility models,geo-statistical analysis,and machine learning algorithms to explore social inequity in Taiyuan,*** this framework,gini coefficient and lorentz curve express spatial equality,accessibility shows spatial equity,and ridge regression model handles the interdependence of variables with different dimensions to quantify the relative effects of local participants on changes in park *** this basis,the imbalance between vulnerable groups and park supply is analyzed to further understand the core concept of social *** highlight serious spatial inequality in all three types of parks allocation of six urban areas,especially in commu-nity *** actual access level of people to parks is also stratified by their demographic and socioeconomic characteristics,revealing the social inequity in access to *** distribution is indeed not conducive to some social vulnerable groups,whose contradiction between supply and demand is highly prominent in urban-rural junctions and new urban *** paper also confirms the unfair layout of public facilities can be observed in second-tier cities of China by highlighting the social inequity of parks in *** findings of this work have profound implications for urban planning and sustainable development.

关键词： Parks social inequity spatial equality accessibility social vulnerable groups Taiyuan

来源：评论

学校读者我要写书评

暂无评论

Temporal Refinement Graph Convolutional Network for Skeleton-Based Action Recognition

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1586-1598页

作者： Zhuang, Tianming Qin, Zhen Ding, Yi Deng, Fuhu Chen, Leduo Qin, Zhiguang Raymond Choo, Kim-Kwang University of Electronic Science and Technology of China Network and Data Security Key Laboratory of Sichuan Province Chengdu Sichuan610054 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu Sichuan610054 China School of Advanced Technology Suzhou Jiangsu215123 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

Human skeleton data, which has served in the aspect of human activity recognition, ought to be the most representative biometric characteristics due to its intuitivity and visuality. The state-of-the-art approaches mainly focus on improving modeling spatial correlations within graph topologies. However, the interframes motional representations are also of vital importance, and we argue that they are worth paying attention to and exploring. Therefore, a temporal refinement module with contrastive learning mechanism is proposed, fuzing as a complementary to the conventional spatial graph convolution layer. In addition, in order to further exploiting the interframe variances and generalizing graph convolutional network (GCN) operation to temporal dimension, a temporal-correlation matrix is introduced to effectively capture dynamic dependencies within frame-pairs, enhancing semantic feature representation. Moreover, since GCN is a typical local operator which lacks of capability to fully model the long-term relations along spatial and temporal variation, to move beyond the limitation, a spatial-temporal cascaded aggregation (STCA) module is designed to enlarge the receptive filter scale. The overall recognition framework consists of three above novelties, which is capable of achieving remarkable performance by evaluating on benchmark datasets (i.e., NTU RGB+D 60, NTU RGB+D 120, PKU-MMD, and Kinetics Skeleton 400). Extensive experiments demonstrate the effectiveness of the proposed framework, e.g., performing recognition accuracy rate of 90.9% and 96.8% on NTU RGB+D 60, 87.9% and 88.9% on NTU RGB+D 120. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Decomposition-based Multi-objective Genetic Programming for Feature Learning in Image Classification

Decomposition-based Multi-objective Genetic Programming for ...

引用

2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

作者： Zhang, Tuo Bi, Ying Liang, Jing Xue, Bing Zhang, Mengjie School of Electrical and Information Engineering Zhengzhou University China State Key Laboratory of Intelligent Agricultural Power Equipment School of Electrical and Information Engineering Zhengzhou University Luoyang China School of Electrical and Information Engineering Zhengzhou University School of Electrical Engineering and Automation Henan Institute of Technology State Key Laboratory of Intelligent Agricultural Power Equipment China School of Engineering and Computer Science Centre for Data Science and Artificial Intelligence Victoria University of Wellington New Zealand

ISBN: (纸本)9798400704956

Image classification is challenging due to the high dimensionality and large variations of the image data. As an effective method in image classification, feature learning can be considered a multiobjective problem of maximizing the classification accuracy and minimizing the number of learned features. Existing multi-objective genetic programming (MOGP) methods directly apply the multiobjective techniques to GP without considering the characteristics of feature learning tasks. Therefore, this paper proposes a decomposition-based MOGP approach with a global replacement strategy to feature learning in image classification. The proposed approach is compared with existing MOGP methods and the experimental results demonstrate the effectiveness of the proposed approach. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Differential Privacy Protection Protocol Based on Location Entropy

引用

Tsinghua Science and technology 2023年第3期28卷 452-463页

作者： Ping Guo Baopeng Ye Yuling Chen Tao Li Yixian Yang Xiaobin Qian Xiaomei Yu State Key Laboratory of Public Big Data School of Computer Science and TechnologyGuizhou UniversityGuiyang 550025China Information Technology Innovation Service Center of Guizhou Province Guiyang 550025China School of Cyberspace Security Beijing University of Posts and TelecommnuicationsBeijing 100000China Guizhou CoVision Science&Technology Co. Ltd.Guiyang 550025China School of Information Science and Engineering Shandong Normal UniversityJinan 250000China

A Location-Based Service(LBS)refers to geolocation-based services that bring both convenience and *** an increase in the scale and value of data,most existing location privacy protection protocols cannot balance privacy and *** solve the revealing problems in LBS,we propose a differential privacy protection protocol based on location ***,we design an algorithm of the best-assisted user selection for constructing anonymity ***,we employ smart contracts to evaluate the credibility of participants,which ensures the honesty of ***,we provide a comprehensive experiment;the theoretical analysis and experiments show that the proposed protocol effectively resists background knowledge ***,our protocol improves data ***,it realizes user-controllable privacy protection,which improves privacy protection and strengthens security.

关键词： Location-Based Services(LBS) smart contract location entropy differential privacy privacy protection

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：