检索结果-南通市图书馆

Multi-Task Deep Learning with Task attention for Post-Click Conversion 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

Intelligent Automation & Soft Computing 2023年第6期36卷 3583-3593页

作者： Hongxin Luo Xiaobing Zhou Haiyan Ding Liqing Wang School of Information Science and Engineering Yunnan UniversityKunming650500China

Online advertising has gained much attention on various platforms as a hugely lucrative *** promoting content and advertisements in real life,the acquisition of user target actions is usually a multi-step process,such as impres-sion→click→conversion,which means the process from the delivery of the recommended item to the user’s click to the final *** to data sparsity or sample selection bias,it is difficult for the trained model to achieve the business goal of the target ***-task learning,a classical solution to this pro-blem,aims to generalize better on the original task given several related tasks by exploiting the knowledge between tasks to share the same feature and label *** learned task relations bring better performance to make full use of the correlation between *** train a general model capable of captur-ing the relationships between various tasks on all existing active tasks from a meta-learning *** addition,this paper proposes a Multi-task attention Network(MAN)to identify commonalities and differences between tasks in the feature *** model performance is improved by explicitly learning the stacking of task relationships in the label *** illustrate the effectiveness of our method,experiments are conducted on Alibaba Click and Conversion Pre-diction(Ali-CCP)*** results show that the method outperforms the state-of-the-art multi-task learning methods.

关键词： Multi-task learning recommend system attention meta-learning

Point cloud upsampling generative adversarial network based on residual multi-scale off-set attention

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2023年第1期5卷 81-91页

作者： Bin SHEN Li LI Xinrong HU Shengyi GUO Jin HUANG Zhiyao LIANG School of Computer and Artificial Intelligence Wuhan Textile UniversityHubei 430200China School of Computer Science and Engineering Macao University of Science and TechnologyMacao China

Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.

关键词： Point cloud upsampling Generative adversarial network attention

Prenatal nicotine alters development of the laterodorsal tegmentum:Possible role for attention-deficit/hyperactivity disorder and drug dependence

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

World Journal of Psychiatry 2022年第2期12卷 212-235页

作者： Filip S Polli Kristi A Kohlmeier Drug Design and Pharmacology University of CopenhagenCopenhagen 2100Denmark

As we cycle between the states of wakefulness and sleep,a bilateral cholinergic nucleus in the pontine brain stem,the laterodorsal tegmentum(LDT),plays a critical role in controlling salience processing,attention,behavioral arousal,and electrophysiological signatures of the sub-and microstates of *** involving abnormal alterations in behavioral and motivated states,such as drug dependence,likely involve dysfunctions in LDT *** addition,as the LDT exhibits connectivity with the thalamus and mesocortical circuits,as well as receives direct,excitatory input from the prefrontal cortex,a role for the LDT in cognitive symptoms characterizing attention-deficit/hyperactivity disorder(ADHD)including impulsivity,inflexibility,and dysfunctions of attention is *** nicotine exposure(PNE)is associated with a higher risk for later life development of drug dependence and ADHD,suggesting alteration in development of brain regions involved in these *** has been shown to alter glutamate and cholinergic signaling within the *** glutamate and acetylcholine are major excitatory mediators,these alterations would likely alter excitatory output to target regions in limbic motivational circuits and to thalamic and cortical networks mediating executive ***,PNE alters neuronal development and transmission within prefrontal cortex and limbic areas that send input to the LDT,which would compound effects of differential processing within the PNE *** taken together,alterations in signaling in the LDT are likely to play a role in negative behavioral outcomes seen in PNE individuals,including a heightened risk of drug dependence and ADHD behaviors.

关键词： Prenatal nicotine exposure Pregnancy outcome Addiction risk Laterodorsal tegmentum Arousal attention

The impact of the design of learning spaces on attention and memory from a neuroarchitectural approach:A systematic review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Architectural Research 2022年第3期11卷 542-560页

作者： Mar Llorens-Gamez Juan Luis Higuera-Trujillo Carla Sentieri Omarrementeria Carmen Llinares Department of Architectural Projects Universitat Politecnica de ValenciaValencia 46022Spain Institute for Research and Innovation in Bioengineering(i3B) Universitat Politecnica de ValenciaValencia 46022Spain

Enriched environments in animal models have demonstrated that exposure to an optimal stimulus improves behavior,cognition,and ***,the evidence base for the neurophysiological influence of human environment enrichment has not been extensively *** systematic review compiles indicators about the effect of built,indoor environments on the cognitive processes of memory and attention in *** work pursues two main objectives:(1)to define current knowledge and the methods that are useful and identify whether previously published studies indicate consistencies and(2)to report the approaches and strategies that can be used in evaluating cognitive processes affected by environment *** of this systematic review show that(1)form and geometry,(2)space distribution and context,(3)color and texture,(4)height,width,and enclosure,(5)transition and circulation,and(6)light,sound,and temperature have an impact on memory and/or attention,and they can be assessed *** all the advances in this field,methodological limitations and a lack of cross-validated standard protocols are ***,future research is necessary to provide a deep insight into how human cognition can be heightened by the environment to which it is exposed.

关键词： Built environment Neuroarchitecture Cognition attention Memory Learning spaces

Prediction of cognitive scores by joint use of movie-watching fMRI connectivity and eye tracking via attention-CensNet

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Psychoradiology 2023年第1期3卷 193-202页

作者： Jiaxing Gao Lin Zhao Tianyang Zhong Changhe Li Zhibin He Yaonei Wei Shu Zhang Lei Guo Tianming Liu Junwei Han Xi Jiang Tuo Zhang School of Automation Northwestern Polytechnical UniversityXIi'an 710072China Cortical Architecture Imaging and Discovery Laboratory Department of Computer Science and Bioimaging Research CenterThe University of GeorgiaAthensGA 30602USA School of Computer Science Northwestern Polytechnical UniversityXi'an 710072China School of Life Science and Technology MOE Key Laboratory for NeuroinformationUniversity of Electronic Science and Technology of ChinaChengdu 611731China

Background:Brain functional connectivity under the naturalistic paradigm has been shown to be better at predicting individual behaviors than other brain states,such as rest and doing ***,the state-of-the-art methods have found it difcult to achieve desirable results from movie watching paradigm functional magnetic resonance imaging(mfMRI)-induced brain functional connectivity,especially when there are fewer *** other physical measurements into the prediction method may enhance *** tracking,becoming popular due to its portability and lower expense,can provide abundant behavioral features related to the output of human's cognition,and thus might supplement the mfMRI in observing participants'subconscious ***,there are very few studies on how to effectively integrate the multimodal information to strengthen the performance by a unified ***:A fusion approach with mfMRI and eye tracking,based on convolution with edge-node switching in graph neural networks(CensNet),is proposed in this ***:In this graph model,participants are designated as nodes,mfMRI derived functional connectivity as node features,and different eye-tracking features are used to compute similarity between participants to construct heterogeneous graph *** taking multiple graphs as different channels,we introduce squeeze-and-excitation attention module to CensNet(A-CensNet)to integrate graph embeddings from multiple channels into ***:The proposed model outperforms those using a single modality and single channel,and state-of-the-art ***:The results indicate that brain functional activities and eye behaviors might complement each other in interpreting trait-like phenotypes.

关键词： functional connectivity naturalistic stimulus eye movement CensNet attention

Effects of grade,academic performance,and sex on spatial working memory and attention in primary school children:a cross-sectional observational study

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 Bio-X Research 2022年第2期5卷 90-96页

作者： Nengpeng Zhan Xuelian Fan Fengtao Shen Lulu Song Chenhuan Zhou Jiayi Xiao Xun Wu Leonardo Jiahao Li Jiayao Xi Sophia Jiayi Li Suhua Zeng Can Li Lihui Wang Weidong Li Bio-X Institutes Key Laboratory for the Genetics of Development and Neuropsychiatric Disorders(Ministry of Education)Shanghai Key Laboratory of Psychotic DisordersInstitute of Psychology and Behavioral Scienceand Brain Science and Technology Research CenterShanghai Jiao Tong University Experimental Primary School Affiliated to Shanghai Jiao Tong University ShanghaiChina

Objective:Only a few studies have investigated the development trends in spatial working memory and attention among a large sample of primary school students over a wide range of ages,while the efficiency of learning and memory processes is fundamental to academic performance,particularly for children,who are in a key developmental stage when their life opportunities can be *** aimed to explore how the spatial working memory and attention of primary school children are affected by grade,academic performance,and ***:In this cross-sectional observational study,students(144 boys,139 girls,6–13 years old)were recruited from Experimental Primary School Affiliated to Shanghai Jiao Tong University in Shanghai,China in *** study protocol was reviewed and approved by the Bio-Ethics Board of the Bio-X Institutes,Shanghai Jiao Tong *** on a simple Spatial Working Memory and attention Test on Paired Symbols test,we evaluate 283 participants’working memory and attention ***:attention and working memory performance were enhanced as a positive function of grade in primary school children,and students who showed better academic achievement also performed better on the working memory ***,attention and working memory performance were not affected by ***:attention and working memory performance of primary school students develop with grade and corresponds to Better academic *** and working memory ability do not differ significantly between boys and girls.

关键词： academic performance attention grade primary school student spatial working memory

attention Matters: An Exploration of Relationship Between Google Search Behaviors and Crude Oil Prices

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

Journal of Systems Science & Complexity 2019年第5期32卷 1438-1459页

作者： LI Xin ZHANG Xun WANG Shouyang MA Jian Donlinks School of Economics and Management University of Science and Technology BeijingBeijing 100083China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Department of Information Systems City University of Hong KongTat Chee AvenueKowloonHong KongChina.

Extant studies have suggested that Google search volume data can serve as a new and direct measure of investor attention in various research fields such as economy, financial and energy markets. However, it is not clear that whether investor attention influences prices in the same direction in different market states(prices increase or decrease). In this paper, the authors propose a measure of speculative attention, demonstrate its advantages by comparing it with several existing ones, and then adopt a Markov switching autoregressive model and an EGARCH model to examine its influences on crude oil prices in two market states. It is argued that the responses of crude oil prices to investor attention are asymmetrical in the two states of crude oil prices. The empirical study shows that one increase in searches causes a significant positive increase in crude oil prices during oil price surges, and a more significant reduction of prices during oil price collapses. The authors also conduct robustness checks by limiting the sample periods and using other measures, and the results support the asymmetric effect of web search behaviors on crude oil prices.

关键词： Asymmetric response crude oil prices Google search investor attention Markov switching autoregressive model

attention based simplified deep residual network for citywide crowd flows prediction

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

Frontiers of Computer Science 2021年第2期15卷 51-62页

作者： Genan DAI Xiaoyang HU Youming GE Zhiqing NING Yubao LIU School of Data and Computer Science Sun Yat-Sen UniversityGuangzhou510006China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006China

Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the *** practice,emergency applications often require less training ***,there is a little work on how to obtain good prediction performance with less training *** this paper,we propose a simplified deep residual network for our *** using the simplified deep residual network,we can obtain not only less training time but also competitive prediction performance compared with the existing similar ***,we adopt the spatio-temporal attention mechanism to further improve the simplified deep residual network with reasonable additional time *** on the real datasets,we construct a series of experiments compared with the existing *** experimental results confirm the efficiency of our proposed methods.

关键词： crowd flows prediction spatio-temporal data mining attention

Prediction and cause investigation of ozone based on a double-stage attention mechanism recurrent neural network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2023年第2期17卷 83-95页

作者： Yuanxin Zhang Fei Li Chaoqiong Ni Song Gao Shuwei Zhang Jin Xue Zhukai Ning Chuanming Wei Fang Fang Yongyou Nie Zheng Jiao School of Environmental and Chemical Engineering Shanghai UniversityShanghai 200444China Shanghai Jinshan Environmental Monitoring Station Shanghai 201500China School of Economics Shanghai UniversityShanghai 200237China

Ozone is becoming a significant air pollutant in some regions,and VOCs are essential for ozone prediction as necessary ozone *** this study,we proposed a recurrent neural network based on a double-stage attention mechanism model to predict ozone,selected an appropriate time series for prediction through the input attention and temporal attention mechanisms,and analyzed the cause of ozone generation according to the contribution of feature *** experimental data show that our model had an RMSE of 7.71μg/m3 and a mean absolute error of 5.97μg/m3 for 1-h *** DA-RNN model predicted ozone closer to observations than the other *** on the importance of the characteristics,we found that the ozone pollution in the Jinshan Industrial Zone mainly comes from the emissions of petrochemical enterprises,and the good generalization performance of the model is proved through testing multiple *** experimental results demonstrate the validity and promising application of the DA-RNN model in predicting atmospheric pollutants and investigating their causes.

关键词： Ozone prediction Deep learning Time series attention Volatile organic compounds