检索结果-南通市图书馆

A Lambda Layer-Based Convolutional Sequence Embedding Model for Click-Through Rate Prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural sciences 2024年第3期29卷 198-208页

作者： ZHOU Liliang YUAN Shili FENG Zijian DAI Guilan ZHOU Guofu Tenth Research Institute China Electronics Technology Group CorporationChengdu 610000SichuanChina Department of Computer science Nanjing University of Posts and TelecommunicationsNanjing 210023JiangsuChina Research Institution of information technology Tsinghua UniversityBeijing 100084China school of Computer science Wuhan UniversityWuhan 430072HubeiChina

In the era of intelligent economy, the click-through rate(CTR) prediction system can evaluate massive service information based on user historical information, and screen out the products that are most likely to be favored by users, thus realizing customized push of information and achieve the ultimate goal of improving economic benefits. Sequence modeling is one of the main research directions of CTR prediction models based on deep learning. The user's general interest hidden in the entire click history and the short-term interest hidden in the recent click behaviors have different influences on the CTR prediction results, which are highly important. In terms of capturing the user's general interest, existing models paid more attention to the relationships between item embedding vectors(point-level), while ignoring the relationships between elements in item embedding vectors(union-level). The Lambda layer-based Convolutional Sequence Embedding(LCSE) model proposed in this paper uses the Lambda layer to capture features from click history through weight distribution, and uses horizontal and vertical filters on this basis to learn the user's general preferences from union-level and point-level. In addition, we also incorporate the user's short-term preferences captured by the embedding-based convolutional model to further improve the prediction results. The AUC(Area Under Curve) values of the LCSE model on the datasets Electronic, Movie & TV and MovieLens are 0.870 7, 0.903 6 and 0.946 7, improving 0.45%, 0.36% and 0.07% over the Caser model, proving the effectiveness of our proposed model.

关键词： click-through rate prediction deep learning attention mechanism convolutional neural network

Non-cooperative Game Based Optimal Dispatch Model for Integrated Energy Systems

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

CSEE Journal of Power and Energy Systems 2024年第3期10卷 1195-1207页

作者： Jiandong Duan Qian Sun Chen Wu Yao Yang Siyu Tu school of Electrical Engineering Xi’an University of TechnologyXi’an710056China IEEE CSEE

In order to improve the efficiency of energy utilization,the integrated energy system(IES)has *** IES typically acts as a whole system during operations,the subsystems are separated,and the interests of each system are *** this paper,considering the relationship between the various energy systems,non-cooperative game theory is used to establish the optimal dispatch *** proposed model mainly relies on the relationship between the cooperation and competition among various subsystems to obtain the maximum benefit they can ***,the basic definition is combined with the particle swarm optimization algorithm to solve the *** results show that the optimization strategy proposed in this paper can operate safely and reliably,and effectively distribute the benefits of each energy system.

关键词： Integrated energy system multi-energy complimentarily non-cooperative game theory

Transformation power or development pressure:economic growth targets and urban carbon productivity

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 Journal of Population,Resources and Environment 2024年第2期22卷 176-184页

作者： Longtao Chen Yi Zheng Xianfeng Han Juan Liu school of Management and Economics Kunming University of Science and TechnologyKunming 650500China school of Foreign Languages and Literatures Chongqing Normal UniversityChongqing 401331China

Maintaining moderate economic growth targets(EGTs)is the key for local governments to effectively implement the“carbon peak and carbon neutrality”goals under the refreshed development *** panel data of 276 prefecture-level cities in China's Mainland from 2010 to 2020,and employing methods such as intermediary and threshold models,this study empirically analyzes the internal mechanism of EGT’s impact on urban carbon productivity(UCP).Our findings demonstrate that:①The overall EGT during the analyzed period is not conducive to improving *** conclusion remains valid after a series of robustness *** effect is more pronounced in the central region and resource-based cities than in the east-west region and non resource-based cities.②EGT not only directly suppresses UCP but also exerts indirect negative impacts on UCP from three aspects:delaying the digital economy(DE),constraining financial expansion(FE),and hindering green technology innovation(GTI).This negative indirect effect is similar to or even surpasses the direct effect,suggesting that the internal relationship between EGT and“dual-carbon”goals should be re-evaluated from a new compound perspective.③EGT not only has a simple linear impact on UCP but also significantly exhibits a dynamic evolution pattern in inverted“U”*** is,as EGT continuously upgrades,a nonlinear impact on UCP emerges in the form of“promoting first,suppressing later”.This indicates that surpassing the“degree”limit for EGT will be detrimental to the improvement of *** study broadens the scope of carbon productivity analysis by introducing a new perspective centered on *** insights gleaned from this research offer valuable guidance for local governments to effectively manage economic growth expectations and promote the synchronized achievement of dual-carbon objectives.

关键词： Economic growth target Urban carbon productivity Mediating effects Dynamic evolution

Ground-state mass of ^(22)Al and test of state-of-the-art ab initio calculations

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 C 2024年第3期48卷 72-78页

作者：孙铭泽于越王新鹏王猛李健国张玉虎 K.Blaum 陈祖毅陈瑞九邓涵宇付超义葛文文黄文嘉焦红扬李红蕙李宏福罗胤芳廖挺 YuALitvinov 司敏帅鹏史金阳王茜邢元明徐星徐瑚珊许甫荣袁琪 T.Yamaguchi 颜鑫亮杨建成原有进周小红周旭张敏曾奇 CAS Key Laboratory of High Precision Nuclear Spectroscopy Institute of Modern PhysicsChinese Academy of SciencesLanzhou 730000China school of Nuclear science and technology University of Chinese Academy of SciencesBeijing 100049China Max-Planck-Institut für Kernphysik Saupfercheckweg 169117 HeidelbergGermany GSI Helmholtzzentrum für Schwerionenforschung Planckstraße 164291 DarmstadtGermany Advanced Energy science and technology Guangdong Laboratory Huizhou516007China State Key Laboratory of Nuclear Physics and technology School of PhysicsPeking UniversityBeijing 100871China Department of Physics Saitama UniversitySaitama 338-8570Japan school of Nuclear science and Engineering East China University of TechnologyNanchang 330013China

The ground-state mass excess of the T_(z)=−2 drip-line nucleus ^(22)Al is measured for the first time as 18103(10)keV using the newly-developed Bρ-defined isochronous mass spectrometry method at the cooler storage ring in *** new mass excess value allowed us to determine the excitation energies of the two low-lying 1+states in ^(22)Al with significantly reduced uncertainties of 51 *** compared to the analogue states in its mirror nucleus ^(22)F,the mirror energy differences of the two 1^(+)states in the ^(22)Al-^(22)F mirror pair are determined to be−625(51)keV and−330(51)*** excitation energies and mirror energy differences are used to test the state-of-the-art ab initio valence-space in-medium similarity renormalization group calculations with four sets of interactions derived from the chiral effective field *** mechanism leading to the large mirror energy differences is investigated and attributed to the occupation of theπs_(1/2) orbital.

关键词： nuclear mass Bρ-defined IMS mirror energy difference ab initio VS-IMSRG calculations chiral interactions

Path-Following Control With Obstacle Avoidance of Autonomous Surface Vehicles Subject to Actuator Faults

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

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 956-964页

作者： Li-Ying Hao Gege Dong Tieshan Li Zhouhua Peng the school of Marine Electrical Engineering Dalian Maritime UniversityDalian 116026China the school of Automation Engineering University of Electronic Science and Technology of ChinaChengdu 611731the Navigation CollegeDalian Maritime UniversityDalian 116026 the Yangtze Delta Region Institute(Huzhou) Huzhou 313001China

This paper investigates the path-following control problem with obstacle avoidance of autonomous surface vehicles in the presence of actuator faults,uncertainty and external *** surface vehicles inevitably suffer from actuator faults in complex sea environments,which may cause existing obstacle avoidance strategies to *** reduce the influence of actuator faults,an improved artificial potential function is constructed by introducing the lower bound of actuator efficiency *** nonlinear state observer,which only depends on measurable position information of the autonomous surface vehicle,is used to address uncertainties and external *** using a backstepping technique and adaptive mechanism,a path-following control strategy with obstacle avoidance and fault tolerance is designed which can ensure that the tracking errors converge to a small neighborhood of *** with existing results,the proposed control strategy has the capability of obstacle avoidance and fault tolerance ***,the comparison results through simulations are given to verify the effectiveness of the proposed method.

关键词： Actuator faults autonomous surface vehicle(ASVs) improved artificial potential function nonlinear state observer obstacle avoidance

Text Difficulty Study:Do Machines Behave the Same as Humans Regarding Text Difficulty?

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

Machine Intelligence Research 2024年第2期21卷 283-293页

作者： Bowen Chen Xiao Ding Yi Zhao Bo Fu Tingmao Lin Bing Qin Ting Liu Research Center for Social Computing and information Retrieval Harbin Institute of TechnologyHarbin 150001China Fundamental technology Center China Construction Bank Financial Technology Co.Ltd.Beijing 100033China

With the emergence of pre-trained models,current neural networks are able to give task performance that is comparable to ***,we know little about the fundamental working mechanism of pre-trained models in which we do not know how they approach such performance and how the task is solved by the *** example,given a task,human learns from easy to hard,whereas the model learns ***,difficulty-insensitive learning leads to great success in natural language processing(NLP),but little attention has been paid to the effect of text difficulty in *** propose a human learning matching index(HLM Index)to investigate the effect of text *** results show:1)LSTM gives more human-like learning behavior than ***,UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty *** nine tasks,some tasks’performance is related to text difficulty,whereas others are not.2)Model trained on easy data performs best in both easy and medium test data,whereas trained on hard data only performs well on hard test data.3)Train the model from easy to hard,leading to quicker convergence.

关键词： Cognition inspired natural language processing psycholinguistics explainability text difficulty curriculum learning

Gyroscope Dynamic Balance Counterweight Prediction Based on Multi-Head ResGAT Networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & sciences 2024年第6期139卷 2525-2555页

作者： Wuyang Fan Shisheng Zhong school of Mechanical Engineering Harbin Institute of TechnologyHarbin150000China

The dynamic balance assessment during the assembly of the coordinator gyroscope significantly impacts the guidance accuracy of precision-guided *** dynamic balance debugging,reliance on rudimentary counterweight empirical formulas persists,resulting in suboptimal debugging accuracy and an increased repetition *** mitigate this challenge,we present a multi-head residual graph attention network(ResGAT)model,designed to predict dynamic balance counterweights with high *** this research,we employ graph neural networks for interaction feature extraction from assembly graph *** SDAE-GPC model is designed for the assembly condition classification to derive graph data inputs for the ResGAT regression model,which is capable of predicting gyroscope counterweights under small-sample *** results of our experiments demonstrate the effectiveness of the proposed approach in predicting dynamic gyroscope counterweight in its assembly *** approach surpasses current methods in mitigating repetition rates and enhancing the assembly efficiency of gyroscopes.

关键词： Gyroscope counterweight assembly small-sample ResGAT repetition rate

Fine-Grained Ship Recognition Based on Visible and Near-Infrared Multimodal Remote Sensing Images: Dataset,Methodology and Evaluation

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6期79卷 5243-5271页

作者： Shiwen Song Rui Zhang Min Hu Feiyao Huang Department of Aerospace science and technology Space Engineering UniversityBeijing101416China

Fine-grained recognition of ships based on remote sensing images is crucial to safeguarding maritime rights and interests and maintaining national ***,with the emergence of massive high-resolution multi-modality images,the use of multi-modality images for fine-grained recognition has become a promising ***-grained recognition of multi-modality images imposes higher requirements on the dataset *** key to the problem is how to extract and fuse the complementary features of multi-modality images to obtain more discriminative fusion *** attention mechanism helps the model to pinpoint the key information in the image,resulting in a significant improvement in the model’s *** this paper,a dataset for fine-grained recognition of ships based on visible and near-infrared multi-modality remote sensing images has been proposed first,named Dataset for Multimodal Fine-grained Recognition of Ships(DMFGRS).It includes 1,635 pairs of visible and near-infrared remote sensing images divided into 20 categories,collated from digital orthophotos model provided by commercial remote sensing *** provides two types of annotation format files,as well as segmentation mask images corresponding to the ship ***,a Multimodal information Cross-Enhancement Network(MICE-Net)fusing features of visible and near-infrared remote sensing images,has been *** the network,a dual-branch feature extraction and fusion module has been designed to obtain more expressive *** Feature Cross Enhancement Module(FCEM)achieves the fusion enhancement of the two modal features by making the channel attention and spatial attention work cross-functionally on the feature map.A benchmark is established by evaluating state-of-the-art object recognition algorithms on ***-Net conducted experiments on DMFGRS,and the precision,recall,mAP0.5 and mAP0.5:0.95 reached 87%,77.1%,83.8%and 63.9%,*** experiments demons

关键词： Multi-modality dataset ship recognition fine-grained recognition attention mechanism

AVM:A Manually Curated Database of Aerosol-transmitted Virus Mutations,Human Diseases,and Drugs

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Genomics, Proteomics & Bioinformatics 2024年第3期22卷 133-138页

作者： Lan Mei Yaopan Hou Jiajun Zhou Yetong Chang Yuwei Liu Di Wang Yunpeng Zhang Shangwei Ning Xia Li College of Bioinformatics science and technology Harbin Medical UniversityHarbin 150081China

Aerosol-transmitted viruses possess strong infectivity and can spread over long distances,earning the difficult-to-control *** cause various human diseases and pose serious threats to human *** can increase the transmissibility and virulence of the strains,reducing the protection provided by vaccines and weakening the efficacy of antiviral *** this study,we established a manually curated database(termed AVM)to store information on aerosol-transmitted viral mutations(VMs).The current version of the AVM contains 42,041 VMs(including 2613 immune escape mutations),45 clinical information datasets,and 407 drugs/antibodies/***,we recorded 88 human diseases associated with viruses and found that the same virus can target multiple organs in the body,leading to diverse ***,the AVM database offers a straightforward user interface for browsing,retrieving,and downloading *** database is a comprehensive resource that can provide timely and valuable information on the transmission,treatment,and diseases caused by aerosol-transmitted viruses(http://***/AVM).

关键词： Aerosol Viral mutation Immune escape mutation Human disease Drug