检索结果-南通市图书馆

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

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

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

Metal-organic framework-derived CoSe_(2)@N-doped carbon nanocubes for high-performance lithium-ion capacitors

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Rare Metals 2024年第5期43卷 2150-2160页

作者： Lei Wang Xiong Zhang Yan-Yan Kong Chen Li Ya-Bin An Xian-Zhong Sun Kai Wang Yan-Wei Ma Institute of Electrical engineering Chinese Academy of SciencesBeijing 100190China school of engineering sciences University of Chinese Academy of SciencesBeijing 100190China Institute of Electrical engineering and Advanced Electromagnetic Drive Technology Qilu ZhongkeJinan 250013China school of Materials science and engineering Zhengzhou UniversityZhengzhou 450001China

Cobalt selenide(CoSe_(2))has garnered considerable attention as a prospective anode candidate for advanced lithium-ion storage,prompting comprehensive ***,CoSe_(2)-based anodes usually suffer from significant volume variation upon lithiation leading to unsatisfactory cycling ***,a versatile synthesis route is proposed for the in-situ fabrication of CoSe2nanoparticles embedded in N-dope carbon skeleton(CoSe_(2)@NC)through annealing treatment and selenization of a metal–organic framework-derived(MOF)*** N-doped carbon derived from the MOF serves not only as an excellent conductive substrate but also as a confined reactor,effectively inhibiting the structural instability and alleviating the inevitable volume change of CoSe_(2).Owing to their unique nanostructure,the as-prepared CoSe_(2)@NC exhibits a high capacity of 745.9mAh·g^(-1)at 0.1 A·g^(-1),while maintaining excellent rate capability and an impressive ***,the assembled lithium-ion capacitor(LIC)based on CoSe_(2)@NC demonstrates an energy density of 130Wh·kg^(-1),a power density of 24.6 kW·kg^(-1),and remarkable capacity retention of 90.8%after 8000 *** results highlight the great potential of CoSe_(2)@NC for practical applications.

关键词： Lithium capacitors Cobalt selenide Metal-organic frameworks N-doped carbon

维普期刊数据库

A model reduction approach for discrete-time linear time-variant systems with delayed inputs

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第4期67卷 197-217页

作者： Ai-Guo WU Guang-Ren DUAN Yu WANG Jie ZHANG school of Mechanical engineering and Automation Harbin Institute of Technology(Shenzhen) HIT Wuhu Robot Technology Research Institute Center for control science and Technology Southern University of Science and Technology

A model reduction approach is presented for discrete-time linear time-variant input-delayed systems. According to this proposed approach, a dynamical variable is constructed by taking advantage of the current state and historical information of input. It is revealed that the behavior of this dynamical variable is governed by a discrete-time linear delay-free system. It is worth noting that the presented variable transformation does not require the system matrix to be invertible. Based on the reduced delay-free models,stabilizing control laws can be easily obtained for the original delayed system. For the case with a single input delay, the constructed variable is an exact prediction for the future state, and thus the stabilizing control law could be designed by replacing the future state with its prediction. Finally, three discrete-time periodic systems with delayed input are employed to illustrate how to utilize the presented model reduction approaches.

关键词： reduction approach predictor-based feedback time-varying systems delayed input periodic system

Machine Learning-Assisted Fabrication of PCBM-Perovskite Solar Cells with Nanopatterned TiO2 Layer

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Energy & Environmental Materials 2024年第4期7卷 223-230页

作者： Siti Norhasanah Sanimu Hwa-Young Yang Jeevan Kandel Ye-Chong Moon Gangasagar Sharma Gaudel Seung-Ju Yu Yong Ju Kim Sejung Kim Bong-Hyun Jun Won-Yeop Rho Graduate school of Integrated Energy-AI Jeonbuk National University school of Energy and Chemical engineering Ulsan National Institute of Science and Technology (UNIST) Department of Herbal Medicine Resources College of Environmental and Bioresource Sciences Jeonbuk National University school of Chemical engineering Jeonbuk National University Department of Bioscience and Biotechnology Konkuk University school of International engineering and science Jeonbuk National University

To unlock the full potential of PSCs,machine learning （ML） was implemented in this research to predict the optimal combination of mesoporous-titanium dioxide （mp-TiO2） and weight percentage （wt%） of phenyl-C61-butyric acid methyl ester （PCBM）,along with the current density(Jsc),open-circuit voltage (Voc),fill factor （ff）,and energy conversion efficiency （ECE）.

关键词： machine learning nanopatterning PCBM perovskite solar cells prediction

Vehicle Abnormal Behavior Detection Based on Dense Block and Soft Thresholding

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 5051-5066页

作者： Yuanyao Lu Wei Chen Zhanhe Yu Jingxuan Wang Chaochao Yang school of Information science and Technology North China University of TechnologyBeijing100144China school of Electrical and control engineering North China University of TechnologyBeijing100144China

With the rapid advancement of social economies,intelligent transportation systems are gaining increasing *** to these systems is the detection of abnormal vehicle behavior,which remains a critical challenge due to the complexity of urban roadways and the variability of external *** research on detecting abnormal traffic behaviors is still nascent,with significant room for improvement in recognition *** address this,this research has developed a new model for recognizing abnormal traffic *** model employs the R3D network as its core architecture,incorporating a dense block to facilitate feature *** approach not only enhances performance with fewer parameters and reduced computational demands but also allows for the acquisition of new features while simplifying the overall network ***,this research integrates a self-attentive method that dynamically adjusts to the prevailing traffic conditions,optimizing the relevance of features for the task at *** temporal analysis,a Bi-LSTM layer is utilized to extract and learn from time-based data *** research conducted a series of comparative experiments using the UCF-Crime dataset,achieving a notable accuracy of 89.30%on our test *** results demonstrate that our model not only operates with fewer parameters but also achieves superior recognition accuracy compared to previous models.

关键词： Vehicle abnormal behavior deep learning ResNet dense block soft thresholding

Identification of fractional order Hammerstein models based on mixed signals

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

Journal of control and Decision 2024年第1期11卷 132-138页

作者： Mengqi Sun Hongwei Wang Qian Zhang school of control science and engineering Dalian University of TechnologyDalianPeople’s Republic of China school of Electrical engineering Xinjiang UniversityUrumqiPeople’s Republic of China

An algorithm based on mixed signals is proposed,to solve the issues of low accuracy of identification algorithm,immeasurable intermediate variables of fractional order Hammerstein model,and how to determine the magnitude of fractional *** this paper,a special mixed input signal is designed to separate the nonlinear and linear parts of the fractional order Hammerstein model so that each part can be identified *** nonlinear part is fitted by the neural fuzzy network model,which avoids the limitation of polynomial fitting and broadens the application range of nonlinear *** addition,the multi-innovation Levenberg-Marquardt(MILM)algorithm and auxiliary recursive least square algorithm are innovatively integrated into the parameter identification algorithm of the fractional order Hammerstein model to obtain more accurate identification results.A simulation example is given to verify the accuracy and effectiveness of the proposed method.

关键词： Mixed signal fractional order Hammerstein model neural fuzzy network model multi-innovation Levenberg-Marquardt algorithm

Systems science in the new era: intelligent systems and big data

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

science China(Information sciences) 2024年第3期67卷 308-310页

作者： Wenwu YU Duxin CHEN Hongzhe LIU He WANG Jinde CAO Zengru DI Xiaojun DUAN Bin JIA Xiaodong DING Yiguang HONG school of Mathematics Southeast University Purple Mountain Laboratories International Academic Center of Complex Systems Beijing Normal University College of science National University of Defense Technology school of Systems science Beijing Jiaotong University Business school University of Shanghai for Science and Technology Department of control science and engineering Tongji University

This study introduces the emergence, research challenges,and future development of intelligent systems and big data(ISBD) and discusses the significance of ISBD to systems science. To this end, an overview of systems science is first presented, followed by the conclusion that the development of artificial intelligence(AI) has promoted the derivation and development of intelligent systems(ISs).

关键词：

Nd^(3)+:YAG-Al_(2)O_(3) nanocrystalline transparent ceramics with high inflexion concentration quenching of Nd^(3+) prepared by amorphous crystallization

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Advanced Ceramics 2024年第8期13卷 1242-1253页

作者： Xiujuan Wan Guangfan Tan Liang Cai Jie Fu Jianqiang Li Yingchun Zhang school of Materials science and engineering University of Science and Technology BeijingBeijing 100083China State Key Laboratory of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijing 100080China State Key Lab for Mesoscience and engineering Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China

Rare earth ion-doped Y_(3)Al_(5)O_(12)(YAG)-based transparent ceramics have been used as important laser gain media for a long time,yet the doping concentration of active ions is limited due to concentration quenching,wherein the inflexion concentration quenching of Nd^(3+)is recognized as 1.0 at%.In this work,YAG-Al_(2)O_(3) nanocrystalline transparent ceramics with a concentration of Nd^(3+)(O-5.0 at%)were fabricated via amorphous crystallization,and the crystal structure evolution,morphology,and optical properties were systematically investigated by differential scanning calorimetry(DSC),X-ray powder diffraction(XRD),transmission electron microscopy(TEM),magnetic resonation(MAS),nuclear magnetic resonation(NMR),and fluorescence *** doping of Nd^(3+)can promote the transition of Al[5]and Al[6]to Al[14],indicating improvements in the ability of the amorphous material to form Nd^(3+):Y_(2)O_(3)-Al_(2)O_(3) vitrified beads,and 1.5 at%Nd^(3+):YAG-Al_(2)O_(3) nanocrystalline transparent ceramics can be obtained by crystallization at 1050℃ with a matrix composed of YAG and concomitant δ-Al_(2)O_(3) and θ-Al_(2)O_(3).The nanocrystalline transparent ceramics show an internal transmitance of 89.56%at 1064 nm,and the strongest emission peak corresponds to the energy transfer from 4F_(3/2) to 4l_(11/2) of Nd^(3+)with a fluorescence lifetime of 231μs when pumped by an 808 nm ***,spectral broadening begins to occur,indicating the onset of concentration quenching,when the concentration of Nd^(3+)exceeds 1.5 at%,substantially higher than the 1.0 at% observed in YAG ***-Al_(2)O_(3) nanocrystalline transparent ceramics obtained by amorphous crystalization can be utilized as the matrix to increase the inflexion point of doping concentration quenching of Nd^(3+),and this material may have great potential as a laser gain medium.

关键词： Y_(3)Al_(5)O_(12)(YAG)-Al_(2)O_(3) nanocrystalline transparent ceramics laser gain medium Nd^(3+)

Impact of different interaction behavior on epidemic spreading in time-dependent social networks

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

Chinese Physics B 2024年第3期33卷 190-195页

作者：黄帅陈杰李梦玉徐元昊胡茂彬 school of engineering science University of Science and Technology of ChinaHefei 230026China school of Mathematics Southeast UniversityNanjing 210096China

We investigate the impact of pairwise and group interactions on the spread of epidemics through an activity-driven model based on time-dependent *** effects of pairwise/group interaction proportion and pairwise/group interaction intensity are explored by extensive simulation and theoretical *** is demonstrated that altering the group interaction proportion can either hinder or enhance the spread of epidemics,depending on the relative social intensity of group and pairwise *** the group interaction proportion decreases,the impact of reducing group social intensity *** ratio of group and pairwise social intensity can affect the effect of group interaction proportion on the scale of infection.A weak heterogeneous activity distribution can raise the epidemic threshold,and reduce the scale of *** results benefit the design of epidemic control strategy.

关键词： epidemic transmission complex network time-dependent networks social interaction

维普期刊数据库