检索结果-内蒙古大学图书馆

Prediction of seasonal variation pollutant sequence based on binomial coupled nonlinear grey Bernoulli model

GREY SYSTEMS-THEORY AND APPLICATION 2025年

作者： Huang, Shuai Ning, Lihua An, Jiayi Wang, Youfan Wang, Yiyang Guilin Univ Elect Technol Guangxi Coll & Univ Key Lab Data Anal & Computat Ctr Appl Math Guangxi Sch Math & Comp Sci Guilin Peoples R China

PurposeThe traditional grey Bernoulli model often faces limitations when applied to pollutant concentration series, which may exhibit complex seasonal trends and varying data types. To address these challenges, we propose a structural extension of the traditional grey Bernoulli model by integrating a binomial equation. This extension allows for a more flexible framework suitable for diverse datasets, especially those related to environmental ***/methodology/approachFirst, the pollutant concentration time series is decomposed into four relatively stable seasonal sub-sequences. Binomial and nonlinear grey Bernoulli models are then integrated to predict these sub-sequences. The prediction formula of the proposed model is derived directly from the definition equation rather than from the solutions of the grey differential equation, thereby minimizing systematic errors. The particle swarm optimization algorithm is used to estimate the nonlinear parameters, while the least squares method is used to estimate the linear parameters of the *** BNGBM(1,1) model is used to forecast the air quality index (AQI), sulfur dioxide (SO2) concentration and particulate matter (PM2.5) concentration for seven major regions in China. The prediction results show that BNGBM(1,1) has superior accuracy compared to four competing models. The model predicts the seasonal variations of these three air pollution indicators in the selected regions for the period 2023-2024. The results show that the concentrations of all three pollution indices will decrease at different ***/valueThe grey Bernoulli model is well suited to sequences exhibiting quasi-exponential growth, whereas the polynomial model is more appropriate for sequences characterized by saturated growth. The integration of these two models extends their applicability. In the empirical study, despite the different development trends of the three air quality indicators in different regions of China, th

关键词： Grey Bernoulli model Particle swarm optimization Pollutant concentration prediction Binomial

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Based on Kernel Local Differential Privacy and Low Gradient Sampling

引用

IEEE ACCESS 2025年 13卷 16959-16977页

作者： Chen, Yi Chen, Dan Tang, Niansheng Yunnan Univ Yunnan Key Lab Stat Modeling & Data Anal Kunming 650500 Peoples R China

Federated learning that is an approach to addressing the "data silo" problem in a collaborative fashion may face the risk of data leakage in real-world contexts. To solve this problem, we introduce the random Fourier feature mapping (RFFM) together with kernel local differential privacy (KLDP) and develop a new privacy protection mechanism, called the RFFM-KLDP mechanism, for high-dimensional context data. Theoretical properties show that the proposed privacy-preserving mechanism has the properties of epsilon -LDP and epsilon -distance-LDP in the federated learning framework. To guarantee the effectiveness of federated learning in the presence of contaminated data, we develop a modified low-gradient sampling technique to sample representative subset of uncontaminated data by incorporating large gradients and unbalanced information. By combining RFFM-KLDP and modified low-gradient sampling technique, we develop a novel and robust federated learning method for classification in the presence of the noisy text data, which can preserve data privacy and largely improve the accuracy of classification algorithm compared to the existing classifiers in terms of the area under curve and classification accuracy. Simulation studies and a context example are used to illustrate the proposed methodologies.

关键词： Protection Kernel Differential privacy Accuracy Statistical learning Privacy data analysis Probability Vectors federated learning low gradient sampling random Fourier feature mapping random Fourier feature mapping

来源：评论

学校读者我要写书评

暂无评论

Error analysis of virtual element method for the Poisson-Boltzmann equation

引用

JOURNAL OF NUMERICAL MATHEMATICS 2025年

作者： Huang, Linghan Shu, Shi Yang, Ying Guilin Univ Elect Technol Guangxi Coll Sch Mathemat & Computat Sci Guilin 541004 Guangxi Peoples R China Guangxi Appl Math Ctr GUET Univ Key Lab Data Anal & Computat Guilin 541004 Guangxi Peoples R China Xiangtan Univ Sch Math & Computat Sci Hunan Key Lab Computat & Simulat Sci & Engn Key Lab Intelligent Comp & Informat ProcMinist Ed Xiangtan 411105 Hunan Peoples R China

The Poisson-Boltzmann equation, which incorporates the source of the Dirac distribution, has been widely applied in predicting the electrostatic potential of biomolecular systems in solution. In this paper we discuss and analyse the virtual element method for the Poisson-Boltzmann equation on general polyhedral meshes. Nearly optimal error estimates, approaching the best possible accuracy, are achieved for the virtual element approximation in both the L 2-norm and H 1-norm, even when the solution of the entire domain has low regularity. The efficiency of the virtual element method and the validity of the proposed theoretical prediction are confirmed through numerical experiments conducted on various polyhedral meshes.

关键词： Poisson-Boltzmann equation virtual element method error estimate polyhedral meshes

来源：评论

学校读者我要写书评

暂无评论

Group commonality graph: Multimodal pedestrian trajectory prediction via deep group features

引用

PATTERN RECOGNITION LETTERS 2025年 192卷 36-42页

作者： Zhou, Di Gao, Ying Li, Hui Liu, Xiaoya Lin, Qinghua Qingdao Univ Sci & Technol Sch Data Sci Qingdao 266061 Peoples R China Guangxi Minzu Univ Guangxi Key Lab Hybrid Computat & IC Design Anal Nanning 530006 Peoples R China

Pedestrian trajectory prediction is a challenging task in domains such as autonomous driving and robot motion planning. Existing methods often focus on aggregating nearby individuals into a single group, while neglecting individual differences and the risks of unreliable interactions. Therefore we propose a novel framework termed group commonality graph, which comprises a group feature capture network and a spatial-temporal graph sparse connected network. The previous network can group and pool pedestrians based on their characteristics, capturing and integrating deep features of the group to generate the final prediction. The subsequent network learns pedestrian motion patterns and simulates their interactive relationships. The framework not only addresses the limitations of overly simplistic aggregation methods but also ensures reliable interactions with sparse directionality. Additionally, to evaluate the effectiveness of our model, we introduce a new evaluation metric termed collision prediction error, which incorporates map environment information to assess the comprehensiveness of multimodal prediction results. Experimental results on public pedestrian trajectory prediction benchmark demonstrate that our method outperforms the state-of-the-art methods.

关键词： Pedestrian trajectory prediction Group commonality Map information Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

Crns: CLIP-driven referring nuclei segmentation

引用

JOURNAL OF SUPERCOMPUTING 2025年第1期81卷 1-20页

作者： Yuan, Ruosong Zhang, Wenwen Dong, Xiaokang Zhang, Wanjun Henan Univ Sch Comp & Informat Engn Henan Key Lab Big Data Anal & Proc Kaifeng 475004 Peoples R China

Nuclei segmentation models significantly improve the efficiency of nuclei analysis. Current deep learning models for nuclei segmentation can be divided into single-path and multi-path approaches. Single-path algorithms often underestimate the importance of edge supervision, while multi-path algorithms typically share layers but leading to potential negative impacts on feature extraction due to gradient updates during backpropagation. To address these challenges, we introduced a novel CLIP-Driven Referring model. Specifically, we designed a Class Guidance block that guides the model in distinguishing and aggregating different features by computing the similarity between images and text. We also introduced a Deformable Feature Attention block in the image branch to enhance local modeling abilities. We analyzed DICE, AJI and PQ metrics improvements through cross-dataset validation. Our model achieved increases of 4.14%, 5.69% and 9.06%, respectively, on the CPM when training with MoNuSeg, and 2.16%, 3.85% and 2.86%, respectively, on the MoNuSeg when training with CPM.

关键词： Nuclei segmentation CLIP-driven deep learning Feature aggregation and separation Generalization ability

来源：评论

学校读者我要写书评

暂无评论

Numerical solution of backward problem of distributed order time-space fractional diffusion equation

引用

PHYSICA SCRIPTA 2025年第2期100卷 025252-025252页

作者： Wang, H. M. Li, Y. S. Guilin Univ Elect Technol Guangxi Coll & Univ Key Lab Data Anal & Computat Sch Math & Comp Sci Guilin 541004 Peoples R China Ctr Appl Math Guangxi GUET Guilin 541004 Peoples R China

The main objective of this paper is to address the backward problem in the distributed-order time-space fractional diffusion equation (DTSFDE) with Neumann boundary conditions using final data. We began by employing the Finite Difference Method (FDM) combined with matrix transformation techniques to compute the direct problem of DTSFDE. Subsequently, by using the Tikhonov regularization method, the inverse problem is transformed into a variational problem. With the help of the derived sensitivity and adjoint problems, the conjugate gradient algorithm is employed to find an approximate solution for the initial data. Finally, through numerical examples in one and two dimensions, we demonstrated the effectiveness and stability of this method, further verifying its reliability in practical applications.

关键词： distributed order time space fractional diffusion equation fractional Laplacian backward problem conjugate gradient algorithm

来源：评论

学校读者我要写书评

暂无评论

Determinate node selection for semi-supervised classification oriented graph convolutional networks

引用

INTERNATIONAL JOURNAL OF BIO-INSPIRED computatION 2025年第1期25卷 1-10页

作者： Xiao, Yao Xu, Ji Yang, Jing Li, Shaobo Wang, Guoyin Guizhou Univ State Key Lab Publ Big Data Guiyang 550025 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China

Graph convolutional networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labelled nodes used in GCNs may lead to unstable generalisation performance of GCNs. In this paper, we propose an efficient method for the deterministic selection of labelled nodes: the determinate node selection (DNS) algorithm. The DNS algorithm identifies two categories of representative nodes in the graph through structural analysis of the leading tree information granules: typical nodes and divergent nodes. These labelled nodes are selected by exploring the structure of the graph and determining the ability of the nodes to represent the distribution of data within the graph. The DNS algorithm can be applied quite simply on GCNs, and a wide range of semi-supervised graph neural network models for node classification tasks. Through extensive experimentation, we have demonstrated that the incorporation of the DNS algorithm leads to a remarkable improvement in the average accuracy of the model and a significant decrease in the standard deviation simultaneously, as compared to the vanilla method without a DNS module.

关键词： graph convolutional networks granular computing semi-supervised learning node classification

来源：评论

学校读者我要写书评

暂无评论

A Directional Connectivity Feature Enhancement Network for Pavement Crack Detection

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第1期26卷 1039-1054页

作者： Qu, Zhong Wang, Jian-Dong Yin, Xue-Hui Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongqing Key Lab Computat Intelligence Key Lab Cyberspace Big Data Intelligent SecurMini Chongqing 400065 Peoples R China Chongqing Univ Posts & Telecommun Key Lab Big Data Intelligent Comp Chongqing 400065 Peoples R China

Crack detection is a fundamental effort to ensure road driving safety, aiming to detect potential safety hazards and avoid serious accidents. However, cracks can not be extracted completely and accurately due to problems such as low contrast, high noise, and complex topology of pavement cracks. To address these issues, we propose a directional connectivity feature enhancement network for pavement crack detection. In this network, we build multi-directional enhanced convolution to capture the complex topology of cracks, which is more sensitive to long cracks. To leverage both low-level detail information and high-level semantic information in the network, a novel multi-scale fusion attention is constructed to strengthen the mutual guidance of crack information between channels. The directional connectivity is introducted to establish loss module, which enhances the position and direction information between neighbouring pixels and further refines the crack edge features. To validate the effectiveness and accuracy of the proposed method, we experiment on six publicly available crack datasets, DeepCrack, Crack500, CFD, DCD, EdmCrack600 and DCCE. Compared to other networks, our network achieves 2.2% improvement in ODS and 1.8% improvement in MIoU on the DeepCrack dataset, and 1.2% improvement in ODS and 0.9% improvement in MIoU on the Crack500 dataset. Sufficient experimental results show that our network has better crack detection performance.

关键词： Crack detection multi-directional enhanced convolution multi-scale fusion attention directional connectivity

来源：评论

学校读者我要写书评

暂无评论

Dual-referenced assistive network for action quality assessment

引用

NEUROCOMPUTING 2025年 614卷

作者： Huang, keyi Tian, Yi Yu, Chen Huang, Yaping Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing Key Lab Traff Data Anal & Min Beijing 100044 Peoples R China

Action quality assessment (AQA) aims to evaluate the performing quality of a specific action. It is a challenging task as it requires to identify the subtle differences between the videos containing the same action. Most of existing AQA methods directly adopt a pretrained network designed for other tasks to extract video features, which are too coarse to describe fine-grained details of action quality. In this paper, we propose a novel Dual-Referenced Assistive (DuRA) network to polish original coarse-grained features into fine-grained quality-oriented representations. Specifically, we introduce two levels of referenced assistants to highlight the discriminative quality-related contents by comparing a target video and the referenced objects, instead of obtrusively estimating the quality score from an individual video. Firstly, we design a Rating-guided Attention module, which takes advantage of a series of semantic-level referenced assistants to acquire implicit hierarchical semantic knowledge and progressively emphasize quality-focused features embedded in original inherent information. Subsequently, we further design a couple of Consistency Preserving constraints, which introduce a set of individual-level referenced assistants to further eliminate score-unrelated information through more detailed comparisons of differences between actions. The experiments show that our proposed method achieves promising performance on the AQA-7 and MTL-AQA datasets.

关键词： Action quality assessment Human action understanding

来源：评论

学校读者我要写书评

暂无评论

Low-Resource Event Causality Identification With Global Consistency Constraints 13th

Low-Resource Event Causality Identification With Global Cons...

引用

13th International Conference on Natural Language Processing and Chinese Computing

作者： Ning, Kangyun Liu, Jian Xu, Jinan Beijing Jiaotong Univ Beijing Key Lab Traff Data Anal & Min Beijing Peoples R China

ISBN: (纸本)9789819794300;9789819794317

Event causality identification (ECI) primarily involves discerning causal relations between pairs of events within sentences. However, previous methods heavily rely on large volumes of high-quality annotated data, making them impractical in low-resource scenarios. Moreover, traditional methods often make independent predictions about event pairs, ignoring the influence between these relations, leading to incorrect predictions. We propose a low-resource ECI method with global consistency constraints to address these challenges. Our approach consists of two strategies: first, we efficiently utilize high-quality data through combined domain adaptation adversarial training and semi-supervised methods with external data sources. Second, we incorporate global consistency constraints into the training process, enhancing the model's ability to learn chain causal relations. Our method significantly improves the F1 score on the 10% Event Storyline Corpus (ESC) and 5% ESC extending the manually annotated relations within document event co-reference chains with external Causal News Corpus (CNC) and noisy causal data from Wikipedia (WNC) compared to the baseline. The addition of global consistency constraints further increases the model's prediction consistency.

关键词： Event Causality Identification Low Resources Consistency Constraints

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：