Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating In...Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.展开更多
Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-g...Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-grained file level detection cannot accurately locate specific defects.(2)Fine-grained line-level defect prediction methods rely solely on local information of a single line of code,failing to deeply analyze the semantic context of the code line and ignoring the heuristic impact of line-level context on the code line,making it difficult to capture the interaction between global and local information.Therefore,this paper proposes a telecontext-enhanced recursive interactive attention fusion method for line-level defect prediction(TRIA-LineDP).Firstly,using a bidirectional hierarchical attention network to extract semantic features and contextual information from the original code lines as the basis.Then,the extracted contextual information is forwarded to the telecontext capture module to aggregate the global context,thereby enhancing the understanding of broader code dynamics.Finally,a recursive interaction model is used to simulate the interaction between code lines and line-level context,passing information layer by layer to enhance local and global information exchange,thereby achieving accurate defect localization.Experimental results from within-project defect prediction(WPDP)and cross-project defect prediction(CPDP)conducted on nine different projects(encompassing a total of 32 versions)demonstrated that,within the same project,the proposed methods will respectively recall at top 20%of lines of code(Recall@Top20%LOC)and effort at top 20%recall(Effort@Top20%Recall)has increased by 11%–52%and 23%–77%.In different projects,improvements of 9%–60%and 18%–77%have been achieved,which are superior to existing advanced methods and have good detection performance.展开更多
The movement of pedestrians involves temporal continuity,spatial interactivity,and random diversity.As a result,pedestrian trajectory prediction is rather challenging.Most existing trajectory prediction methods tend t...The movement of pedestrians involves temporal continuity,spatial interactivity,and random diversity.As a result,pedestrian trajectory prediction is rather challenging.Most existing trajectory prediction methods tend to focus on just one aspect of these challenges,ignoring the temporal information of the trajectory and making too many assumptions.In this paper,we propose a recurrent attention and interaction(RAI)model to predict pedestrian trajectories.The RAI model consists of a temporal attention module,spatial pooling module,and randomness modeling module.The temporal attention module is proposed to assign different weights to the input sequence of a target,and reduce the speed deviation of different pedestrians.The spatial pooling module is proposed to model not only the social information of neighbors in historical frames,but also the intention of neighbors in the current time.The randomness modeling module is proposed to model the uncertainty and diversity of trajectories by introducing random noise.We conduct extensive experiments on several public datasets.The results demonstrate that our method outperforms many that are state-ofthe-art.展开更多
Neuroscientists have emphasized visceral influences on consciousness and attention,but the potential neurophysiological pathways remain under exploration.Here,we found two neurophysiological pathways of heartbrain int...Neuroscientists have emphasized visceral influences on consciousness and attention,but the potential neurophysiological pathways remain under exploration.Here,we found two neurophysiological pathways of heartbrain interaction based on the relationship between oxygen-transport by red blood cells(RBCs)and consciousness/attention.To this end,we collected a dataset based on the routine physical examination,the breaking continuous flash suppression(b-CFS)paradigm,and an attention network test(ANT)in 140 immigrants under the hypoxic Tibetan environment.We combined electroencephalography and multilevel mediation analysis to investigate the relationship between RBC properties and consciousness/attention.The results showed that RBC function,via two independent neurophysiological pathways,not only triggered interoceptive re-representations in the insula and awareness connected to orienting attention but also induced an immune response corresponding to consciousness and executive control.Importantly,consciousness played a fundamental role in executive function which might be associated with the level of perceived stress.These results indicated the important role of oxygen-transport in heart-brain interactions,in which the related stress response affected consciousness and executive control.The findings provide new insights into the neurophysiological schema of heartbrain interactions.展开更多
BACKGROUND Attention deficit hyperactivity disorder(ADHD)affects approximately 5%of children worldwide and is associated with significant academic impairment.Parents of children with ADHD experience elevated stress an...BACKGROUND Attention deficit hyperactivity disorder(ADHD)affects approximately 5%of children worldwide and is associated with significant academic impairment.Parents of children with ADHD experience elevated stress and anxiety levels,which may further affect their children's educational outcomes.This prospective study examined the relationship between parental anxiety and academic performance of children with ADHD over a 6-year period.AIM To investigate the longitudinal impact of parental anxiety on academic performance in children with ADHD and explore the mediating and moderating factors over a 6-year follow-up period.METHODS A longitudinal cohort study was conducted from 2018 to 2024,enrolling 118 children with ADHD(aged 6-12 years)and their parents from three specialized educational centers.Parental anxiety was assessed using the Parenting Stress Index-4(PSI-4)and Parental Anxiety Scale.Children's academic performance was measured using the Academic Performance Questionnaire and standardized achievement tests.Assessments were conducted at baseline and every 6 months for 3 years.RESULTS Higher parental anxiety scores were significantly associated with poorer academic performance in children with ADHD(β=-0.42,P<0.001).Children of parents with clinically significant anxiety(PSI-4 scores>85th percentile)showed 1.2 standard deviations lower academic achievement than children of parents with normal anxiety levels.The relationship was partially mediated by parent-child interaction quality(indirect effect=-0.18,95%CI:-0.26 to-0.10)and homework supervision practices(indirect effect=-0.15,95%CI:-0.22 to-0.08).CONCLUSION Parental anxiety could significantly affect the academic outcomes of children with ADHD via multiple pathways.Interventions targeting parental mental health may improve the educational outcomes of children with ADHD.展开更多
针对能量收集无线传感器网络中,能量预测精度不佳、节点能量利用效率过低和网络难以持续运行等问题,提出了一种改进样本卷积交互神经网络(sample convolution and interaction network,SCINet)预测模型,并引入概率稀疏自注意力机制,在...针对能量收集无线传感器网络中,能量预测精度不佳、节点能量利用效率过低和网络难以持续运行等问题,提出了一种改进样本卷积交互神经网络(sample convolution and interaction network,SCINet)预测模型,并引入概率稀疏自注意力机制,在新特征序列的每个时间步上计算注意力权重,捕捉重要特征,提高模型预测精度.最后,根据节点剩余能量、预测未来可收集的太阳能能量,对分簇路由算法进行改进.仿真实验结果表明,该能量预测模型具备更高的预测精度和泛化能力.在能量预测模型的基础上,改进的分簇路由算法,能有效地延长无线传感器网络的生命周期.展开更多
Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the d...Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.展开更多
Attention deficit and hyperactivity disorder（ADHD） is a disorder characterized by behavioral symptoms including hyperactivity/impulsivity among children,adolescents,and adults.These ADHD related symptoms are influen...Attention deficit and hyperactivity disorder（ADHD） is a disorder characterized by behavioral symptoms including hyperactivity/impulsivity among children,adolescents,and adults.These ADHD related symptoms are influenced by the complex interaction of brain networks which were under explored.We explored age-related brain network differences between ADHD patients and typically developing（TD） subjects using resting state f MRI（rs-f MRI） for three age groups of children,adolescents,and adults.We collected rs-f MRI data from 184 individuals（27 ADHD children and 31 TD children;32 ADHD adolescents and 32 TD adolescents;and 31 ADHD adults and 31 TD adults）.The Brainnetome Atlas was used to define nodes in the network analysis.We compared three age groups of ADHD and TD subjects to identify the distinct regions that could explain age-related brain network differences based on degree centrality,a well-known measure of nodal centrality.The left middle temporal gyrus showed significant interaction effects between disease status（i.e.,ADHD or TD） and age（i.e.,child,adolescent,or adult）（P 0.001）.Additional regions were identified at a relaxed threshold（P 0.05）.Many of the identified regions（the left inferior frontal gyrus,the left middle temporal gyrus,and the left insular gyrus） were related to cognitive function.The results of our study suggest that aberrant development in cognitive brain regions might be associated with age-related brain network changes in ADHD patients.These findings contribute to better understand how brain function influences the symptoms of ADHD.展开更多
In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the ＂interaction points＂ in the collision detectionscene, such as ＂grasp＂ and ＂release＂ and objects ...In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the ＂interaction points＂ in the collision detectionscene, such as ＂grasp＂ and ＂release＂ and objects in the scene, without paying attention to the tracked 3D hand gesture model in the total procedure. Thus in this paper, a visual attention distribution model of operator in the ＂grasp＂, ＂translation＂, ＂release＂ and other basic operation procedures is first studied and a 3D hand gesture tracking algorithm based on this distribution model is proposed. Utilizing the algorithm, in the period with a low degree of visual attention, a pre-stored 3D hand gesture animation can be used to directly visualise a 3D hand gesture model in the interactive scene; in the time period with a high degree of visual attention, an existing ＂frame-by-frame tracking＂ approach can be adopted to obtain a 3D gesture model. The results demonstrate that the proposed method can achieve real-time tracking of 3D hand gestures with an effective improvement on the efficiency, fluency, and availability of 3D hand gesture interaction.展开更多
Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively inv...Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively investigated in this field. Foreground segmentation networks (FgSegNets) are representative deep end-to-endMOS methods proposed recently. This study explores a new mechanism to improve the spatial feature learningcapability of FgSegNets with relatively few brought parameters. Specifically, we propose an enhanced attention(EA) module, a parallel connection of an attention module and a lightweight enhancement module, with sequentialattention and residual attention as special cases. We also propose integrating EA with FgSegNet_v2 by taking thelightweight convolutional block attention module as the attention module and plugging EA module after the twoMaxpooling layers of the encoder. The derived new model is named FgSegNet_v2 EA. The ablation study verifiesthe effectiveness of the proposed EA module and integration strategy. The results on the CDnet2014 dataset,which depicts human activities and vehicles captured in different scenes, show that FgSegNet_v2 EA outperformsFgSegNet_v2 by 0.08% and 14.5% under the settings of scene dependent evaluation and scene independent evaluation, respectively, which indicates the positive effect of EA on improving spatial feature learning capability ofFgSegNet_v2.展开更多
Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which ...Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.展开更多
In recent years,deep learning has been widely applied in the fields of recommendation systems and click-through rate(CTR)prediction,and thus recommendation models incorporating deep learning have emerged.In addition,t...In recent years,deep learning has been widely applied in the fields of recommendation systems and click-through rate(CTR)prediction,and thus recommendation models incorporating deep learning have emerged.In addition,the design and implementation of recommendation models using information related to user behavior sequences is an important direction of current research in recommendation systems,and models calculate the likelihood of users clicking on target items based on their behavior sequence information.In order to explore the relationship between features,this paper improves and optimizes on the basis of deep interest network(DIN)proposed by Ali’s team.Based on the user behavioral sequences information,the attentional factorization machine(AFM)is integrated to obtain richer and more accurate behavioral sequence information.In addition,this paper designs a new way of calculating attention weights,which uses the relationship between the cosine similarity of any two vectors and the absolute value of their modal length difference to measure their relevance degree.Thus,a novel deep learning CTR prediction mode is proposed,that is,the CTR prediction network based on user behavior sequence and feature interactions deep interest and machines network(DIMN).We conduct extensive comparison experiments on three public datasets and one private music dataset,which are more recognized in the industry,and the results show that the DIMN obtains a better performance compared with the classical CTR prediction model.展开更多
The integration of genotypic and environmental data can enhance genomic prediction accuracy for crop field traits.Existing genomic prediction methods fail to consider environmental factors and the real growth environm...The integration of genotypic and environmental data can enhance genomic prediction accuracy for crop field traits.Existing genomic prediction methods fail to consider environmental factors and the real growth environments of crops,resulting in low genomic prediction accuracy.In this work,we developed GEFormer,a genotype-environment interaction genomic prediction method that integrates gating multilayer perceptron(gMLP)and linear attention mechanisms.First,GEFormer uses gMLP to extract local and global features among SNPs.Then,Omni-dimensional Dynamic Convolution is used to extract the dynamic and comprehensive features of multiple environmental factors within each day,taking into consideration the real growth pattern of crops.A linear attention mechanism is used to capture the temporal features of environmental changes.Finally,GEFormer uses a gating mechanism to effectively fuse the genomic and environmental features.We examined the accuracy of GEFormer for predicting important agronomic traits of maize,rice,and wheat under three experimental scenarios:untested genotypes in tested environments,tested genotypes in untested environments,and untested genotypes in untested environments.The results showed that GEFormer outperforms six cutting-edge statistical learning methods and four machine learning methods,especially with great advantages under the scenario of untested genotypes in untested environments.In addition,we used GEFormer for three realworld breeding applications:phenotype prediction in unknown environments,hybrid phenotype prediction using an inbred population,and cross-population phenotype prediction.The results showed that GEFormer had better prediction performance in actual breeding scenarios and could be used to assist in crop breeding.展开更多
Automatically extracting Drug-Drug Interactions (DDIs) from text is a crucial and challenging task, particularly when multiple medications are taken concurrently. In this study, we propose a novel approach, called Enh...Automatically extracting Drug-Drug Interactions (DDIs) from text is a crucial and challenging task, particularly when multiple medications are taken concurrently. In this study, we propose a novel approach, called Enhanced Attention-driven Dynamic Graph Convolutional Network (E-ADGCN), for DDI extraction. Our model combines the Attention-driven Dynamic Graph Convolutional Network (ADGCN) with a feature fusion method and multi-task learning framework. The ADGCN effectively utilizes entity information and dependency tree information from biomedical texts to extract DDIs. The feature fusion method integrates User-Generated Content (UGC) and molecular information with drug entity information from text through dynamic routing. By leveraging external resources, our approach maximizes the auxiliary effect and improves the accuracy of DDI extraction. We evaluate the E-ADGCN model on the extended DDIExtraction2013 dataset and achieve an F1-score of 81.45%. This research contributes to the advancement of automated methods for extracting valuable drug interaction information from textual sources, facilitating improved medication management and patient safety.展开更多
为了充分利用特征间的高阶交互以提升点击率预测模型的预测精度,提出了一种基于图神经网络和注意力的点击率预测模型VBGA (vector-wise and bit-wise interaction model based on GNN and attention),该模型借助图神经网络和注意力机制...为了充分利用特征间的高阶交互以提升点击率预测模型的预测精度,提出了一种基于图神经网络和注意力的点击率预测模型VBGA (vector-wise and bit-wise interaction model based on GNN and attention),该模型借助图神经网络和注意力机制,为每个特征分别学习一个细粒度的权重,并将这种细粒度的特征权重输入到向量级交互层和元素级交互层联合预测点击率.VBGA模型主要由向量级交互层和元素级交互层构成,其中向量级交互层采用有向图来构建向量级的特征交互,实现无重复的显式特征交互,在减少计算量的同时,还可以实现更高阶的特征交叉,以获得更准确的预测精度.此外,本文还提出了一种交叉网络用于构建元素级特征交互.在Criteo和Avazu数据集上,与其他几种最先进的点击率预测模型进行了比较,实验结果表明,VBGA可以获得良好的预测结果.展开更多
文摘Reliable traffic flow prediction is crucial for mitigating urban congestion.This paper proposes Attentionbased spatiotemporal Interactive Dynamic Graph Convolutional Network(AIDGCN),a novel architecture integrating Interactive Dynamic Graph Convolution Network(IDGCN)with Temporal Multi-Head Trend-Aware Attention.Its core innovation lies in IDGCN,which uniquely splits sequences into symmetric intervals for interactive feature sharing via dynamic graphs,and a novel attention mechanism incorporating convolutional operations to capture essential local traffic trends—addressing a critical gap in standard attention for continuous data.For 15-and 60-min forecasting on METR-LA,AIDGCN achieves MAEs of 0.75%and 0.39%,and RMSEs of 1.32%and 0.14%,respectively.In the 60-min long-term forecasting of the PEMS-BAY dataset,the AIDGCN out-performs the MRA-BGCN method by 6.28%,4.93%,and 7.17%in terms of MAE,RMSE,and MAPE,respectively.Experimental results demonstrate the superiority of our pro-posed model over state-of-the-art methods.
基金supported by National Natural Science Foundation of China(no.62376240).
文摘Software defect prediction aims to use measurement data of code and historical defects to predict potential problems,optimize testing resources and defect management.However,current methods face challenges:(1)Coarse-grained file level detection cannot accurately locate specific defects.(2)Fine-grained line-level defect prediction methods rely solely on local information of a single line of code,failing to deeply analyze the semantic context of the code line and ignoring the heuristic impact of line-level context on the code line,making it difficult to capture the interaction between global and local information.Therefore,this paper proposes a telecontext-enhanced recursive interactive attention fusion method for line-level defect prediction(TRIA-LineDP).Firstly,using a bidirectional hierarchical attention network to extract semantic features and contextual information from the original code lines as the basis.Then,the extracted contextual information is forwarded to the telecontext capture module to aggregate the global context,thereby enhancing the understanding of broader code dynamics.Finally,a recursive interaction model is used to simulate the interaction between code lines and line-level context,passing information layer by layer to enhance local and global information exchange,thereby achieving accurate defect localization.Experimental results from within-project defect prediction(WPDP)and cross-project defect prediction(CPDP)conducted on nine different projects(encompassing a total of 32 versions)demonstrated that,within the same project,the proposed methods will respectively recall at top 20%of lines of code(Recall@Top20%LOC)and effort at top 20%recall(Effort@Top20%Recall)has increased by 11%–52%and 23%–77%.In different projects,improvements of 9%–60%and 18%–77%have been achieved,which are superior to existing advanced methods and have good detection performance.
基金supported by the National NaturalScience Foundation of China(U1811463)the Fundamental Research Funds for the Central Universities(12060093192)。
文摘The movement of pedestrians involves temporal continuity,spatial interactivity,and random diversity.As a result,pedestrian trajectory prediction is rather challenging.Most existing trajectory prediction methods tend to focus on just one aspect of these challenges,ignoring the temporal information of the trajectory and making too many assumptions.In this paper,we propose a recurrent attention and interaction(RAI)model to predict pedestrian trajectories.The RAI model consists of a temporal attention module,spatial pooling module,and randomness modeling module.The temporal attention module is proposed to assign different weights to the input sequence of a target,and reduce the speed deviation of different pedestrians.The spatial pooling module is proposed to model not only the social information of neighbors in historical frames,but also the intention of neighbors in the current time.The randomness modeling module is proposed to model the uncertainty and diversity of trajectories by introducing random noise.We conduct extensive experiments on several public datasets.The results demonstrate that our method outperforms many that are state-ofthe-art.
基金supported by the National Natural Science Foundation of China(31660274,31771247,and 31600907)the Reformation and Development Funds for Local Region Universities from the Chinese Government in 2020(00060607,ZCJK 2020-11).
文摘Neuroscientists have emphasized visceral influences on consciousness and attention,but the potential neurophysiological pathways remain under exploration.Here,we found two neurophysiological pathways of heartbrain interaction based on the relationship between oxygen-transport by red blood cells(RBCs)and consciousness/attention.To this end,we collected a dataset based on the routine physical examination,the breaking continuous flash suppression(b-CFS)paradigm,and an attention network test(ANT)in 140 immigrants under the hypoxic Tibetan environment.We combined electroencephalography and multilevel mediation analysis to investigate the relationship between RBC properties and consciousness/attention.The results showed that RBC function,via two independent neurophysiological pathways,not only triggered interoceptive re-representations in the insula and awareness connected to orienting attention but also induced an immune response corresponding to consciousness and executive control.Importantly,consciousness played a fundamental role in executive function which might be associated with the level of perceived stress.These results indicated the important role of oxygen-transport in heart-brain interactions,in which the related stress response affected consciousness and executive control.The findings provide new insights into the neurophysiological schema of heartbrain interactions.
文摘BACKGROUND Attention deficit hyperactivity disorder(ADHD)affects approximately 5%of children worldwide and is associated with significant academic impairment.Parents of children with ADHD experience elevated stress and anxiety levels,which may further affect their children's educational outcomes.This prospective study examined the relationship between parental anxiety and academic performance of children with ADHD over a 6-year period.AIM To investigate the longitudinal impact of parental anxiety on academic performance in children with ADHD and explore the mediating and moderating factors over a 6-year follow-up period.METHODS A longitudinal cohort study was conducted from 2018 to 2024,enrolling 118 children with ADHD(aged 6-12 years)and their parents from three specialized educational centers.Parental anxiety was assessed using the Parenting Stress Index-4(PSI-4)and Parental Anxiety Scale.Children's academic performance was measured using the Academic Performance Questionnaire and standardized achievement tests.Assessments were conducted at baseline and every 6 months for 3 years.RESULTS Higher parental anxiety scores were significantly associated with poorer academic performance in children with ADHD(β=-0.42,P<0.001).Children of parents with clinically significant anxiety(PSI-4 scores>85th percentile)showed 1.2 standard deviations lower academic achievement than children of parents with normal anxiety levels.The relationship was partially mediated by parent-child interaction quality(indirect effect=-0.18,95%CI:-0.26 to-0.10)and homework supervision practices(indirect effect=-0.15,95%CI:-0.22 to-0.08).CONCLUSION Parental anxiety could significantly affect the academic outcomes of children with ADHD via multiple pathways.Interventions targeting parental mental health may improve the educational outcomes of children with ADHD.
文摘针对能量收集无线传感器网络中,能量预测精度不佳、节点能量利用效率过低和网络难以持续运行等问题,提出了一种改进样本卷积交互神经网络(sample convolution and interaction network,SCINet)预测模型,并引入概率稀疏自注意力机制,在新特征序列的每个时间步上计算注意力权重,捕捉重要特征,提高模型预测精度.最后,根据节点剩余能量、预测未来可收集的太阳能能量,对分簇路由算法进行改进.仿真实验结果表明,该能量预测模型具备更高的预测精度和泛化能力.在能量预测模型的基础上,改进的分簇路由算法,能有效地延长无线传感器网络的生命周期.
基金Project(51678075)supported by the National Natural Science Foundation of ChinaProject(2017GK2271)supported by the Hunan Provincial Science and Technology Department,China。
文摘Human-object interaction(HOIs)detection is a new branch of visual relationship detection,which plays an important role in the field of image understanding.Because of the complexity and diversity of image content,the detection of HOIs is still an onerous challenge.Unlike most of the current works for HOIs detection which only rely on the pairwise information of a human and an object,we propose a graph-based HOIs detection method that models context and global structure information.Firstly,to better utilize the relations between humans and objects,the detected humans and objects are regarded as nodes to construct a fully connected undirected graph,and the graph is pruned to obtain an HOI graph that only preserving the edges connecting human and object nodes.Then,in order to obtain more robust features of human and object nodes,two different attention-based feature extraction networks are proposed,which model global and local contexts respectively.Finally,the graph attention network is introduced to pass messages between different nodes in the HOI graph iteratively,and detect the potential HOIs.Experiments on V-COCO and HICO-DET datasets verify the effectiveness of the proposed method,and show that it is superior to many existing methods.
基金supported by the Institute for Basic Science[grant No.IBS-R015-D1]the National Research Foundation of Korea(grant No.NRF-2016R1A2B4008545)
文摘Attention deficit and hyperactivity disorder（ADHD） is a disorder characterized by behavioral symptoms including hyperactivity/impulsivity among children,adolescents,and adults.These ADHD related symptoms are influenced by the complex interaction of brain networks which were under explored.We explored age-related brain network differences between ADHD patients and typically developing（TD） subjects using resting state f MRI（rs-f MRI） for three age groups of children,adolescents,and adults.We collected rs-f MRI data from 184 individuals（27 ADHD children and 31 TD children;32 ADHD adolescents and 32 TD adolescents;and 31 ADHD adults and 31 TD adults）.The Brainnetome Atlas was used to define nodes in the network analysis.We compared three age groups of ADHD and TD subjects to identify the distinct regions that could explain age-related brain network differences based on degree centrality,a well-known measure of nodal centrality.The left middle temporal gyrus showed significant interaction effects between disease status（i.e.,ADHD or TD） and age（i.e.,child,adolescent,or adult）（P 0.001）.Additional regions were identified at a relaxed threshold（P 0.05）.Many of the identified regions（the left inferior frontal gyrus,the left middle temporal gyrus,and the left insular gyrus） were related to cognitive function.The results of our study suggest that aberrant development in cognitive brain regions might be associated with age-related brain network changes in ADHD patients.These findings contribute to better understand how brain function influences the symptoms of ADHD.
基金Supported by the National Natural Science Foundation of China(61472163)the National Key Research&Development Plan of China(2016YFB1001403)the Science and Technology Project of Shandong Province(2015GGX101025)
文摘In the majority of the interaction process, the operator often focuses on the tracked 3D hand gesture model at the ＂interaction points＂ in the collision detectionscene, such as ＂grasp＂ and ＂release＂ and objects in the scene, without paying attention to the tracked 3D hand gesture model in the total procedure. Thus in this paper, a visual attention distribution model of operator in the ＂grasp＂, ＂translation＂, ＂release＂ and other basic operation procedures is first studied and a 3D hand gesture tracking algorithm based on this distribution model is proposed. Utilizing the algorithm, in the period with a low degree of visual attention, a pre-stored 3D hand gesture animation can be used to directly visualise a 3D hand gesture model in the interactive scene; in the time period with a high degree of visual attention, an existing ＂frame-by-frame tracking＂ approach can be adopted to obtain a 3D gesture model. The results demonstrate that the proposed method can achieve real-time tracking of 3D hand gestures with an effective improvement on the efficiency, fluency, and availability of 3D hand gesture interaction.
基金the National Natural Science Foundation of China(No.61702323)。
文摘Moving object segmentation (MOS) is one of the essential functions of the vision system of all robots,including medical robots. Deep learning-based MOS methods, especially deep end-to-end MOS methods, are actively investigated in this field. Foreground segmentation networks (FgSegNets) are representative deep end-to-endMOS methods proposed recently. This study explores a new mechanism to improve the spatial feature learningcapability of FgSegNets with relatively few brought parameters. Specifically, we propose an enhanced attention(EA) module, a parallel connection of an attention module and a lightweight enhancement module, with sequentialattention and residual attention as special cases. We also propose integrating EA with FgSegNet_v2 by taking thelightweight convolutional block attention module as the attention module and plugging EA module after the twoMaxpooling layers of the encoder. The derived new model is named FgSegNet_v2 EA. The ablation study verifiesthe effectiveness of the proposed EA module and integration strategy. The results on the CDnet2014 dataset,which depicts human activities and vehicles captured in different scenes, show that FgSegNet_v2 EA outperformsFgSegNet_v2 by 0.08% and 14.5% under the settings of scene dependent evaluation and scene independent evaluation, respectively, which indicates the positive effect of EA on improving spatial feature learning capability ofFgSegNet_v2.
基金the National Natural Science Foundation of China(No.61975015)the Research and Innovation Project for Graduate Students at Zhongyuan University of Technology(No.YKY2024ZK14).
文摘Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.
文摘In recent years,deep learning has been widely applied in the fields of recommendation systems and click-through rate(CTR)prediction,and thus recommendation models incorporating deep learning have emerged.In addition,the design and implementation of recommendation models using information related to user behavior sequences is an important direction of current research in recommendation systems,and models calculate the likelihood of users clicking on target items based on their behavior sequence information.In order to explore the relationship between features,this paper improves and optimizes on the basis of deep interest network(DIN)proposed by Ali’s team.Based on the user behavioral sequences information,the attentional factorization machine(AFM)is integrated to obtain richer and more accurate behavioral sequence information.In addition,this paper designs a new way of calculating attention weights,which uses the relationship between the cosine similarity of any two vectors and the absolute value of their modal length difference to measure their relevance degree.Thus,a novel deep learning CTR prediction mode is proposed,that is,the CTR prediction network based on user behavior sequence and feature interactions deep interest and machines network(DIMN).We conduct extensive comparison experiments on three public datasets and one private music dataset,which are more recognized in the industry,and the results show that the DIMN obtains a better performance compared with the classical CTR prediction model.
基金supported by the Biological Breeding-National Science and Technology Major Project(2023ZD04076)the Hubei Provincial Natural Science Foundation(2023AFB832)+2 种基金the Natural Science Foundation of Guizhou Province Science and Technology Agency(ZK[2025]096)the Major Project of Hubei Hongshan Laboratory(2022HSZD031)the Yingzi Tech&Huazhong Agricultural University Intelligent Research Institute of Food Health(IRIFH202209).
文摘The integration of genotypic and environmental data can enhance genomic prediction accuracy for crop field traits.Existing genomic prediction methods fail to consider environmental factors and the real growth environments of crops,resulting in low genomic prediction accuracy.In this work,we developed GEFormer,a genotype-environment interaction genomic prediction method that integrates gating multilayer perceptron(gMLP)and linear attention mechanisms.First,GEFormer uses gMLP to extract local and global features among SNPs.Then,Omni-dimensional Dynamic Convolution is used to extract the dynamic and comprehensive features of multiple environmental factors within each day,taking into consideration the real growth pattern of crops.A linear attention mechanism is used to capture the temporal features of environmental changes.Finally,GEFormer uses a gating mechanism to effectively fuse the genomic and environmental features.We examined the accuracy of GEFormer for predicting important agronomic traits of maize,rice,and wheat under three experimental scenarios:untested genotypes in tested environments,tested genotypes in untested environments,and untested genotypes in untested environments.The results showed that GEFormer outperforms six cutting-edge statistical learning methods and four machine learning methods,especially with great advantages under the scenario of untested genotypes in untested environments.In addition,we used GEFormer for three realworld breeding applications:phenotype prediction in unknown environments,hybrid phenotype prediction using an inbred population,and cross-population phenotype prediction.The results showed that GEFormer had better prediction performance in actual breeding scenarios and could be used to assist in crop breeding.
基金supported by the National Natural Science Foundation of China(No.62476025)the Shaanxi Provincial Department of Science and Technology Projects(No.2013K06-39).
文摘Automatically extracting Drug-Drug Interactions (DDIs) from text is a crucial and challenging task, particularly when multiple medications are taken concurrently. In this study, we propose a novel approach, called Enhanced Attention-driven Dynamic Graph Convolutional Network (E-ADGCN), for DDI extraction. Our model combines the Attention-driven Dynamic Graph Convolutional Network (ADGCN) with a feature fusion method and multi-task learning framework. The ADGCN effectively utilizes entity information and dependency tree information from biomedical texts to extract DDIs. The feature fusion method integrates User-Generated Content (UGC) and molecular information with drug entity information from text through dynamic routing. By leveraging external resources, our approach maximizes the auxiliary effect and improves the accuracy of DDI extraction. We evaluate the E-ADGCN model on the extended DDIExtraction2013 dataset and achieve an F1-score of 81.45%. This research contributes to the advancement of automated methods for extracting valuable drug interaction information from textual sources, facilitating improved medication management and patient safety.
文摘为了充分利用特征间的高阶交互以提升点击率预测模型的预测精度,提出了一种基于图神经网络和注意力的点击率预测模型VBGA (vector-wise and bit-wise interaction model based on GNN and attention),该模型借助图神经网络和注意力机制,为每个特征分别学习一个细粒度的权重,并将这种细粒度的特征权重输入到向量级交互层和元素级交互层联合预测点击率.VBGA模型主要由向量级交互层和元素级交互层构成,其中向量级交互层采用有向图来构建向量级的特征交互,实现无重复的显式特征交互,在减少计算量的同时,还可以实现更高阶的特征交叉,以获得更准确的预测精度.此外,本文还提出了一种交叉网络用于构建元素级特征交互.在Criteo和Avazu数据集上,与其他几种最先进的点击率预测模型进行了比较,实验结果表明,VBGA可以获得良好的预测结果.
