检索结果-南通市图书馆

Multi-instance partial-label learning: towards exploiting dual inexact supervision

Science China(Information Sciences) 2024年第3期67卷 48-61页

作者： Wei Tang Weijia ZHang Min-ling ZHang School of Computer Science and engineering Southeast University Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Physical Sciences The University of Newcastle

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associated with not only multiple instances but also a candidate label set that contains one groundtruth label and some false positive labels. Specifically, at least one instance pertains to the ground-truth label while no instance belongs to the false positive labels. In this paper, we formalize such problems as multi-instance partial-label learning(MIPL). Existing multi-instance learning algorithms and partial-label learning algorithms are suboptimal for solving MIPL problems since the former fails to disambiguate a candidate label set, and the latter cannot handle a multi-instance bag. To address these issues, a tailored algorithm named MIPLGP, i.e., multi-instance partial-label learning with Gaussian processes, is *** first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes. Experimental results on various datasets validate that MIPLGP is superior to well-established multi-instance learning and partial-label learning algorithms for solving MIPL problems.

关键词： machine learning multi-instance partial-label learning multi-instance learning partial-label learning Gaussian processes

来源：

同方期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Evaluation of 3D crustal seismic velocity models in southwest China:Model performance,limitation,and prospects

引用

Science China Earth Sciences 2024年第2期67卷 604-619页

作者： Xin Wang ling CHEN Qi-Fu CHEN Key Laboratory of Earth and Planetary Physics Institute of Geology and GeophysicsChinese Academy of SciencesBeijing100029China College of Earth and Planetary Sciences University of Chinese Academy of SciencesBeijing100049China State Key Laboratory of Lithospheric Evolution Institute of Geology and GeophysicsChinese Academy of SciencesBeijing100029China

Southwest China is a tectonically and seismically active region,witnessing strong deformation due to the collision between the Indian and Eurasian *** the subsurface velocity structure of this region is thus important in understanding the tectonics and geodynamic processes of continental collision and in mitigating seismic *** studies have provided various 3D seismic velocity models in southwest ***,discrepancies exist among these models,and less effort has been made to quantify the reliability and accuracy of these existing velocity *** this study,we use regional 3D waveform simulation to evaluate the performance of various regional crustal 3D velocity models in reproducing observed *** particularly focus on two recent earthquake sequence in the region,the 2021 Yunnan Yangbi MS_(6.4) earthquake sequence and the 2022 Sichuan Luding MS_(6.8) earthquake *** tested 3D velocity models include the Southwest China Community Velocity model V1.0,the Unified Seismic Tomography Models for Continental China Lithosphere V2.0,the adjoint full waveform tomography model of the crustal and upper mantle beneath Eastern Tibetan Plateau,and the shallow seismic structure model beneath continental *** results show that the tested 3D velocity models generally capture well long-period(<0.2 Hz)waveforms,indicating that the 3D models adequately resolve overall large-scale subsurface ***,the 3D synthetics show discrepancies in higher frequencies(0.05–0.3 Hz)and the performance of the 3D velocity models varies from region to region,suggesting that smaller scale heterogeneities are not well *** shallow velocity structures(<10 km)can improve the waveform fitting,emphasizing the importance of incorporating shallow structures in waveform *** full-waveform tomography model shows a slighter better performance than the other models,especially for the body-waves,highlighting the advantages

关键词： Southwest China Seismic tomography models Shallow Structures Waveform simulation Model evaluation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Applications of mercury stable isotopes for tracing volcanism in the geologic record

引用

Science China Earth Sciences 2024年第5期67卷 1436-1458页

作者： Qing GONG Ming-Xing ling Wang ZHeng State Key Laboratory of Nuclear Resources and Environment East China University of TechnologyNanchang 330013China School of Earth System Science Institute of Surface-Earth System ScienceTianjin UniversityTianjin 300072China

Mercury(Hg)enrichments in ancient sediments have been used as a proxy of volcanism,especially large igneous province(LIP)***,considering the existence of other potential Hg sources besides volcanoes and the diverse factors(e.g.,organic matters,clay minerals,sulfide minerals and Fe oxides)that can affect Hg sequestration,there are considerable uncertainties to simply regard sedimentary Hg anomalies as signatures of volcanic *** stable isotopes,a promising tool for tracing the origins and transformations of Hg,have been increasingly used for determining the causes of Hg spikes and understanding the geochemical behavior of Hg in the geologic *** date,lots of researches have applied Hg concentrations and Hg isotopes to identify LIP volcanisms linking with significant geological events such as mass extinctions,ocean anoxic events and other environmental perturbations that mainly occurred in the ***,the results in previous studies clearly show that not all Hg enrichments are derived from volcanic inputs,which emphasize the need for more caution in using Hg as a fingerprint of *** a better understanding of Hg isotopes in the future,there will be important implications for Hg isotopes to reconstruct volcanic activities in the rock records and their impacts on biological evolution.

关键词： Mercury stable isotopes Large igneous province Mass extinction event Ocean anoxic event

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 919-931页

作者： Fei Ming Wenyin Gong ling Wang Yaochu Jin the School of Computer Science China University of GeosciencesWuhan 430074China the Department of Automation Tsinghua UniversityBeijing 100084China the Faculty of Technology Bielefeld UniversityNorth Rhine-Westphalia33619 BielefeldGermany

Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable *** constrained multi-objective optimization evolutionary algorithms(CMOEAs)have been developed with the use of different algorithmic strategies,evolutionary operators,and constraint-handling *** performance of CMOEAs may be heavily dependent on the operators used,however,it is usually difficult to select suitable operators for the problem at ***,improving operator selection is promising and necessary for *** work proposes an online operator selection framework assisted by Deep Reinforcement *** dynamics of the population,including convergence,diversity,and feasibility,are regarded as the state;the candidate operators are considered as actions;and the improvement of the population state is treated as the *** using a Q-network to learn a policy to estimate the Q-values of all actions,the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic *** framework is embedded into four popular CMOEAs and assessed on 42 benchmark *** experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs.

关键词： Constrained multi-objective optimization deep Qlearning deep reinforcement learning(DRL) evolutionary algorithms evolutionary operator selection

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Optimized the vanadium electrolyte with sulfate-phosphoric mixed acids to enhance the stable operation at high-temperature

引用

Frontiers of Chemical Science and engineering 2024年第2期18卷 13-26页

作者： ling Ge Tao Liu Yimin Zhang Hong Liu School of Resource and Environmental engineering Wuhan University of Science and TechnologyWuhan 430081China State Environmental Protection Key Laboratory of Mineral Metallurgical Resources Utilization and Pollution Control Wuhan University of Science and TechnologyWuhan 430081China Hubei Collaborative Innovation Center for High Efficient Utilization of Vanadium Resources Wuhan University of Science and TechnologyWuhan 430081China Hubei Provincial engineering Technology Research Center of High Efficient Cleaning Utilization for Shale Vanadium Resource Wuhan University of Science and TechnologyWuhan 430081China School of Resource and Environmental engineering Wuhan University of TechnologyWuhan 430070China

Herein, the influence of the concentration design and comprehensive performance of the sulfate-phosphoric mixed acid system electrolyte is investigated to realize an electrolyte that maintains high energy density and stable operation at high temperatures. Static stability tests have shown that VOPO4 precipitation occurs only with vanadium(V) electrolyte. The concentration of vanadium ion of 2.0–2.2 mol·L^(–1), phosphoric acid of 0.10–0.15 mol·L^(–1), and sulfuric acid of 2.5–3.0 mol·L^(–1) are suitable for a vanadium redox flow battery in the temperature range from –20 to 50 ℃. The equations for predicting the viscosity and conductivity of electrolytes are obtained by the response surface method. The optimized electrolyte overcomes precipitation generation. It has 2.8 times higher energy density than the non-phosphate electrolyte, and a coulomb efficiency of 94.0% at 50 ℃. The sulfate-phosphoric mixed acid system electrolyte promotes the electrode reaction process, increases the current density, and reduces the resistance. This work systematically optimizes the concentrations of composition of positive and negative vanadium electrolytes with mixed sulfate-phosphoric acid. It provides a basis for the different valence states and comprehensive properties of sulfate-phosphoric mixed acid system vanadium electrolytes under extreme environments, guiding engineering applications.

关键词： all vanadium redox flow battery mixed-acid vanadium electrolyte concentration optimization response surface methodology high-temperature stability

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Unmanned Ship Identification Based on Improved YOLOv8s Algorithm

引用

Computers, Materials & Continua 2024年第3期78卷 3071-3088页

作者： Chun-Ming Wu Jin Lei Wu-Kai Liu Mei-ling Ren ling-Li Ran Key Laboratory of Modern Power System Simulation and Control&Renewable Energy Technology School of Electrical EngineeringNortheast Electric Power UniversityJilin132012China School of Biomedical engineering Taiyuan University of TechnologyTaiyuan030600China

Aiming at defects such as low contrast in infrared ship images,uneven distribution of ship size,and lack of texture details,which will lead to unmanned ship leakage misdetection and slow detection,this paper proposes an infrared ship detection model based on the improved YOLOv8 algorithm(R_YOLO).The algorithm incorporates the Efficient Multi-Scale Attention mechanism(EMA),the efficient Reparameterized Generalized-feature extraction module(CSPStage),the small target detection header,the Repulsion Loss function,and the context aggregation block(CABlock),which are designed to improve the model’s ability to detect targets at multiple scales and the speed of model *** algorithm is validated in detail on two vessel *** comprehensive experimental results demonstrate that,in the infrared dataset,the YOLOv8s algorithm exhibits improvements in various performance ***,compared to the baseline algorithm,there is a 3.1%increase in mean average precision at a threshold of 0.5(mAP(0.5)),a 5.4%increase in recall rate,and a 2.2%increase in mAP(0.5:0.95).Simultaneously,while less than 5 times parameters,the mAP(0.5)and frames per second(FPS)exhibit an increase of 1.7%and more than 3 times,respectively,compared to the CAA_YOLO ***,the evaluation indexes on the visible light data set have shown an average improvement of 4.5%.

关键词： Unmanned ships R_YOLO EMA CSPStage YOLOv8s

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An overview and perspective of identifying lunar craters

引用

Science China Earth Sciences 2024年第5期67卷 1395-1416页

作者： Yan JIang Changyi Xu ling CHEN State Key Laboratory of Lithospheric Evolution Institute of Geology and GeophysicsChinese Academy of SciencesBeijing 100029China College of Earth and Planetary Sciences University of Chinese Academy of SciencesBeijing 100029China Key Laboratory of Earth and Planetary Physics Institute of Geology and GeophysicsChinese Academy of SciencesBeijing 100049China

The spatiotemporal evolution of lunar impact craters is crucial for investigating lunar interior structure,internal and external dynamic processes,and interplanetary impact *** in lunar crater identification are reviewed based on topography and gravity data,and the features and mechanisms of topographic or buried craters are analyzed regarding morphology,gravity anomalies,gravity gradients,and the underlying crust-mantle interface *** on the compiled crater catalog,the early lunar impact flux and thermal evolution are further discussed according to the basin ages and their interior *** some ancient impact basins,the crater size-frequency distribution measurements revealed age discrepancies from previous studies,suggesting that the lunar late heavy bombardment event started at~3.95 *** degraded bulge structures of the crust-mantle interface beneath mare basins reveal that these basins formed on the lunar crust surface under high-temperature conditions and underwent prolonged relaxation compared to highland ***,we reveal that the up-to-date identification of lunar buried craters remains inaccurate and incomplete,preventing us from accurately reconstructing lunar and interplanetary impact ***,we propose that a gravity model constructed using localized orthogonal basis functions can be useful for identifying lunar craters.

关键词： Moon Gravity field Craters Impact flux Early evolution

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Trotter–Kato Approximations of Impulsive Neutral SPDEs in Hilbert Spaces

引用

Acta Mathematica Sinica,english Series 2024年第5期40卷 1229-1243页

作者： Ming LIU Xia ZHang ling Fei DAI School of Mathematical Sciences Tiangong UniversityTianjin 300387P.R.China

This paper studies a class of impulsive neutral stochastic partial differential equations in real Hilbert *** main goal here is to consider the Trotter-Kato approximations of mild solutions of such equations in the pth-mean(p≥2).As an application,a classical limit theorem on the dependence of such equations on a parameter is *** novelty of this paper is that the combination of this approximating system and such equations has not been considered before.

关键词： Impulsive neutral stochastic partial diferential equation Trotter-Kato approximations classical limit theorem

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Exploring the potential of constructing a hybrid supercapacitor with FeCoNi-LDH porous material containing oxygen vacancies for high-performance energy storage applications

引用

Nano Research 2024年第9期17卷 8134-8144页

作者： Jihao Su ling Yang Dengbin Yu Shaojun Dong State Key Laboratory of Electroanalytical Chemistry Changchun Institute of Applied ChemistryChinese Academy of SciencesChangchun 130022China College of Chemistry Jilin UniversityChangchun 130022China University of Science and Technology of China Hefei 230026China

A significant challenge in developing high-performance hybrid supercapacitors(HSCs)is the need to reasonably construct advanced architectures that consist of various components and exhibit superior electrochemical capacitance *** FeCoNi-layered double hydroxide(FeCoNi-LDH)porous material has a specific capacitance of 1960 F·g^(-1)when used as the anode material at 1 A·g^(-1).The FeCoNi-LDH material exhibits nanoplates with a distinct spindle morphology on their *** to the combined action of the three metals and abundant oxygen vacancies,they exhibit unique rate performance and cycle *** electronic structure of LDH and the regulation of oxygen vacancy were confirmed by density functional theory(DFT)*** suggests that the strength of hydroxide can reduce the energy required for oxygen vacancy formation in FeCoNi-LDH nanosheets and enhance ion and charge transfer,as well as electrolyte adsorption on the electrode *** FeCoNi-LDH//activated carbon(AC)HSC has an energy density of 53.2 Wh·kg^(-1)at a power density of 800 W·kg^(-1),surpassing other devices composed of comparable materials during the same *** study made significant advances in the design and synthesis of a ternary LDH porous structure with distinct oxygen vacancies,as well as its potential application in electrochemical energy storage.

关键词： oxygen vacancy FeCoNi-layered double hydroxide(FeCoNi-LDH) theory calculation electrode material hybrid supercapacitor

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Online Pareto optimal control of mean-field stochastic multi-player systems using policy iteration

引用

Science China(Information Sciences) 2024年第4期67卷 21-37页

作者： Xiushan JIang Yanshuang Wang Dongya ZHAO ling SHI College of New Energy China University of Petroleum(East China) Department of Electronic and Computer engineering Hong Kong University of Science and Technology

In this study, the Pareto optimal strategy problem was investigated for multi-player mean-field stochastic systems governed by It? differential equations using the reinforcement learning(RL) method.A partially model-free solution for Pareto-optimal control was derived. First, by applying the convexity of cost functions, the Pareto optimal control problem was solved using a weighted-sum optimal control problem. Subsequently, using on-policy RL, we present a novel policy iteration(PI) algorithm based on the Hrepresentation technique. In particular, by alternating between the policy evaluation and policy update steps,the Pareto optimal control policy is obtained when no further improvement occurs in system performance,which eliminates directly solving complicated cross-coupled generalized algebraic Riccati equations(GAREs).Practical numerical examples are presented to demonstrate the effectiveness of the proposed algorithm.

关键词： mean-field stochastic systems Pareto optimal control policy iteration scheme $\mathcal{H}$-representation

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：