检索结果-南通市图书馆

FSCIL-EACA: Few-Shot Class-Incremental Learning network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department information network Engineering Research center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Training Adaptation models Visualization Image recognition Prototypes Self-supervised learning Power capacitors

Enhanced cycle stability of aprotic Li-O_(2) batteries based on a self-defensed redox mediator

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2024年第3期35卷 449-452页

作者： Guiru Sun Yan Wang Daming Yang Zexu Zhang Wei Lu Ming Feng Key Laboratory of Functional Materials Physics and Chemistry of the Ministry of Education Jilin Normal UniversityChangchun 130103China College of information Technology Jilin Engineering Research Center of Optoelectronic Materials and DevicesJilin Normal UniversitySiping 136000China

LiBr as a promising redox mediator(RM)has been applied in Li-O_(2)batteries to improve oxygen evolution reaction kinetics and reduce ***,the redox shuttle of Br_(3)^-can induce the unexpected reactions and thus cause the degradation of LiBr and the corrosion of Li anode,resulting in the poor cyclability and the low round-trip ***,MgBr_(2)is firstly employed with dual functions for Li-O_(2)batteries,which can serve as a RM and a SEI film-forming *** Br^(–)is beneficial to facilitating the decomposition of Li_(2)O_(2)and thus decreasing the ***,a uniform SEI film containing Mg and MgO generates on Li anode surface by the in-situ spontaneous reactions of Mg^(2+)and Li anode in an O_(2)environment,which can suppress the redox shuttle of Br_(3)^-and improve the interface stability of Li anode and *** from these advantages,the cycle life of Li-O_(2)battery with MgBr_(2)electrolyte is significantly extended.

关键词： MgBr_(2) Redox mediator Redox shuttle Li anode SEI film

Effectively modulating spatial vortex four-wave mixing in a diamond atomic system

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第4期33卷 473-478页

作者：巴诺姜明奇费金友王丹蒋海林王磊王海华 National Demonstration center for Experimental Physics Education College of PhysicsJilin Normal UniversitySiping 136000China College of Physics Jilin UniversityChangchun 130012China

Due to the spatial characteristics of orbital angular momentum,vortex fields can be applied in the fields of quantum storage and quantum *** study the realization of spatially modulated vortex fields based on four-wave mixing in a four-level atomic system with a diamond *** intensity and spiral phase of the vortex field are effectively transferred to the generated four-wave mixing *** changing the detuning of the probe field,the phase and intensity of the generated vertex four-wave mixing field can be *** the probe field takes a large detuning value,the spatial distribution of the intensity and phase of the vertex four-wave mixing field can be effectively tuned by adjusting the Rabi frequency or detuning value of the coupled *** the same time,we also provide a detailed explanation based on the dispersion relationship,and the results agree well with our simulation results.

关键词： coherent optical effects four-wave mixing orbital angular momentum

Resource Allocation for IRS Assistedmm Wave Wireless Powered Sensor networks with User Cooperation

在线全文

学校读者我要写书评

暂无评论

工程与科学中的计算机建模(英文) 2024年第1期138卷 663-677页

作者： Yonghui Lin Zhengyu Zhu network center Zhengzhou UniversityZhengzhou450001China School of Electrical and information Engineering Zhengzhou UniversityZhengzhou450001China

In this paper,we investigate IRS-aided user cooperation(UC)scheme in millimeter wave(mmWave)wirelesspowered sensor networks(WPSN),where two single-antenna users are wireless powered in the wireless energy transfer(WET)phase first and then cooperatively transmit information to a hybrid access point(AP)in the wireless information transmission(WIT)phase,following which the IRS is deployed to enhance the system performance of theWET *** maximized the weighted sum-rate problem by jointly optimizing the transmit time slots,power allocations,and the phase shifts of the *** to the non-convexity of the original problem,a semidefinite programming relaxation-based approach is proposed to convert the formulated problem to a convex optimization framework,which can obtain the optimal global *** results demonstrate that the weighted sum throughput of the proposed UC scheme outperforms the non-UC scheme whether equipped with IRS or not.

关键词： Intelligent reflecting surface millimeter wave wireless powered sensor networks user cooperation resource allocation

Ghost Module Based Residual Mixture of Self-Attention and Convolution for Online Signature Verification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 695-712页

作者： Fangjun Luan Xuewen Mu Shuai Yuan Department of Computer Technology School of Computer Science and EngineeringShenyang Jianzhu UniversityShenyang110168China Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Jianzhu UniversityShenyang110168China Shenyang Branch of National Special Computer Engineering Technology Research center Shenyang Jianzhu UniversityShenyang110168China

Online Signature Verification (OSV), as a personal identification technology, is widely used in various ***, it faces challenges, such as incomplete feature extraction, low accuracy, and computational heaviness. Toaddress these issues, we propose a novel approach for online signature verification, using a one-dimensionalGhost-ACmix Residual network (1D-ACGRNet), which is a Ghost-ACmix Residual network that combines convolutionwith a self-attention mechanism and performs improvement by using Ghost method. The Ghost-ACmix Residualstructure is introduced to leverage both self-attention and convolution mechanisms for capturing global featureinformation and extracting local information, effectively complementing whole and local signature features andmitigating the problem of insufficient feature extraction. Then, the Ghost-based Convolution and Self-Attention(ACG) block is proposed to simplify the common parts between convolution and self-attention using the Ghostmodule and employ feature transformation to obtain intermediate features, thus reducing computational ***, feature selection is performed using the random forestmethod, and the data is dimensionally reducedusing Principal Component Analysis (PCA). Finally, tests are implemented on the MCYT-100 datasets and theSVC-2004 Task2 datasets, and the equal error rates (EERs) for small-sample training using five genuine andforged signatures are 3.07% and 4.17%, respectively. The EERs for training with ten genuine and forged signaturesare 0.91% and 2.12% on the respective datasets. The experimental results illustrate that the proposed approacheffectively enhances the accuracy of online signature verification.

关键词： Online signature verification feature selection ACG block ghost-ACmix residual structure

Social network Analysis of COVID-19 Research and the Changing International Collaboration Structure

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 Shanghai Jiaotong university(Science) 2024年第1期29卷 150-160页

作者：秦野陈蓉蓉 Shanghai Discipline Assessment center Ofice of Strategic PlanningShanghai Jiao Tong UniversityShanghai 200240China network and information center Shanghai Jiao Tong UniversityShanghai 200240China

Research in information Science and interdisciplinary areas suggested the formation of a growing network of international research *** massive transmission of COVID-19 worldwide especially after the identification of the Omicron variant could fundamentally alter the factors shaping the network's *** study employs network analysis methods to analyze the structure of the COVID-19 research collaboration from 2020 to 2022,using two major academic publication databases and the VOSviewer software.A novel temporal view is added by examining the dynamic changes of the network,and a fractional counting method is adopted as methodological improvements to previous *** reveals that the COVID-19 research network structure has undergone substantial changes over time,as collaborating countries and regions form and re-form new *** in the network can be partly explained by key developments in the pandemic and other social-political *** as one of the largest pivots in the network formed a relatively distinct cluster,with potential to develop a larger Asia-Pacific collaboration cluster based on its research impact.

关键词： COVID-19 international research collaboration network analysis high interdisciplinary research

A novel graph oversampling framework for node classification in class-imbalanced graphs

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6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of Artificial Intelligence Jilin University College of Computer Science and Technology Jilin University College of Communication Engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

Comprehensive Exergoeconomic Analysis and Optimization of a Novel Zero-Carbon-Emission Multi-Generation System based on Carbon Dioxide Cycle

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 Thermal Science 2024年第3期33卷 1065-1081页

作者： SUN Yan LI Hongwei WANG Di DU Changhe School of Energy and Power Engineering Northeast Electric Power UniversityJilin132012China School of Automation Engineering Northeast Electric Power UniversityJilin132012China Xi’an Institute of Electromechanical information Technology Xi’an710065China

This paper aims to conduct a comprehensive exergoeconomic analysis of a novel zero-carbon-emission multi-generation system and propose a fast optimization method combined with machine *** detailed exergoeconomic analysis of a novel combined power,freshwater and cooling multi-generation system is performed in this *** exergoeconomic analysis model is established by exergy flow theory.A comprehensive exergy,exergoeconomic and environmental analysis is carried *** critical decision variables are researched to bring out effects on the multi-generation system exergoeconomic performance.A novel fast optimization method combining genetic algorithm and Bagging neural network is *** advanced nature comparison is made between the proposed system and four similar *** display that increasing the turbine inlet temperature can improve exergy efficiency and decrease the total product unit *** multi-generation system exergy destruction directly determines exergy efficiency and total exergy destruction cost *** total product unit cost in the cost optimal design case is reduced by 7.7%and 25%,respectively,compared with exergy efficiency optimal design case and basic design *** with four similar cases,the proposed multi-generation system has great advantages in thermodynamic performance and exergoeconomic *** paper can provide research methods and ideas for performance analysis and fast optimization of multi-generation system.

关键词： waste heat recovery exergoeconomic analysis supercritical carbon dioxide optimization machine learning

Optimal replication strategy for mitigating burst traffic in information-centric satellite networks: a focus on remote sensing image transmission

在线全文

学校读者我要写书评

暂无评论

Frontiers of information Technology & Electronic Engineering 2024年第6期25卷 791-808页

作者： Ziyang XING Xiaoqiang DI Hui QI Jing CHEN Jinhui CAO Jinyao LIU Xusheng LI Zichu ZHANG Yuchen ZHU Lei CHEN Kai HUANG Xinghan HUO jilin Key Laboratory of network and information Security Changchun 130022China School of Computer Science and Technology Changchun University of Science and TechnologyChangchun 130022China information center Changchun University of Science and TechnologyChangchun 130022China

information-centric satellite networks play a crucial role in remote sensing applications,particularly in the transmission of remote sensing ***,the occurrence of burst traffic poses significant challenges in meeting the increased bandwidth *** content delivery networks are ill-equipped to handle such bursts due to their pre-deployed *** this paper,we propose an optimal replication strategy for mitigating burst traffic in information-centric satellite networks,specifically focusing on the transmission of remote sensing *** strategy involves selecting the most optimal replication delivery satellite node when multiple users subscribe to the same remote sensing content within a short time,effectively reducing network transmission data and preventing throughput degradation caused by burst traffic *** formulate the content delivery process as a multi-objective optimization problem and apply Markov decision processes to determine the optimal value for burst traffic *** address these challenges,we leverage federated reinforcement learning ***,we use bloom filters with subdivision and data identification methods to enable rapid retrieval and encoding of remote sensing *** software-based simulations using a low Earth orbit satellite constellation,we validate the effectiveness of our proposed strategy,achieving a significant 17%reduction in the average delivery *** paper offers valuable insights into efficient content delivery in satellite networks,specifically targeting the transmission of remote sensing images,and presents a promising approach to mitigate burst traffic challenges in information-centric environments.

关键词： information-centric satellite network Burst traffic Content delivery Federated reinforcement learning Mixed-integer linear programming model Bloom filter Dynamic network