检索结果-内蒙古大学图书馆

A model-free feature extraction procedure for interval-valued time series prediction

Soft Computing 2025年第6期29卷 2727-2741页

作者： Tian, Wan Qin, Zhongfeng Hu, Tao School of Economics and Management Beihang University Beijing100191 China Beijing100191 China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education Shanghai China School of Mathematical Sciences Capital Normal University Beijing100048 China

We present a novel feature extraction procedure to predict interval-valued time series by combing transfer learning and imaging approaches. Initially, we represent interval-valued time series as a bivariate point-valued time series, and then transform each time series into images by employing imaging approaches such as recurrence plot, gramian angular summation/difference field, and Markov transition field, thereby obtaining an image dataset containing four classes. Based on this dataset, we train multiple candidate feature extraction networks, specifically ResNet with varying layers. Then we choose the penultimate layer of the feature extraction networks to extract the most relevant features from the images. To formulate prediction, we integrate the extracted features into a traditional prediction model. The proposed method are evaluated on three data-generating processes as well as the S&P 500 index, and the experimental results demonstrate a notable improvement in prediction performance compared to existing methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Transformer-based multi-level attention integration network for video saliency prediction

引用

Multimedia Tools and Applications 2025年第13期84卷 11833-11854页

作者： Tan, Rui Sun, Minghui Liang, Yanhua Software College Jilin University Qianjin Street Jilin Changchun130012 China College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Qianjin Street Jilin Changchun130012 China

Most existing models for video saliency prediction heavily rely on 3D convolutional operations to extract spatio-temporal features. However, it is worth noting that 3D convolution produces a local receptive field, which may struggle to capture long-range spatio-temporal dependencies effectively. To compensate for such shortage, this paper introduces a novel approach called the Transformer-based Multi-level Attention Integration Network (TMAI-Net) for video saliency prediction. TMAI-Net is designed as a two-stream encoder-decoder model, carefully integrating multi-level features of semantic information. Our model incorporates a Multi-level Interactive Attention(MLIA) module and a Transformer, both implemented based on self-attention mechanism, which are placed at different levels of the model to capture long-range spatio-temporal feature dependencies. Additionally, our model operates on input video frames and attentional patches, allowing the Transformer module to capture structural similarities between related objects in global features and attention features. This, in turn, enables the model to allocate increased attention to salient areas. The efficacy of our proposed approach is validated through extensive experiments conducted on three widely recognized benchmark datasets. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Effective Instruction Parsing Plugin for Complex Logical Query Answering on knowledge Graphs 34

Effective Instruction Parsing Plugin for Complex Logical Que...

引用

34th ACM Web Conference, WWW 2025

作者： Zhuo, Xingrui Wang, Jiapu Wu, Gongqing Pan, Shirui Wu, Xindong Hefei University of Technology Anhui Hefei China Beijing University of Technology Beijing China Griffith University Gold Coast QLD Australia The Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology China

ISBN: (纸本)9798400712746

knowledge Graph Query Embedding (KGQE) aims to embed First-Order Logic (FOL) queries in a low-dimensional KG space for complex reasoning over incomplete KGs. To enhance the generalization of KGQE models, recent studies integrate various external information (such as entity types and relation context) to better capture the logical semantics of FOL queries. The whole process is commonly referred to as Query Pattern Learning (QPL). However, current QPL methods typically suffer from the pattern-entity alignment bias problem, leading to the learned defective query patterns limiting KGQE models’ performance. To address this problem, we propose an effective Query Instruction Parsing Plugin (QIPP) that leverages the context awareness of Pre-trained Language Models (PLMs) to capture latent query patterns from code-like query instructions. Unlike the external information introduced by previous QPL methods, we first propose code-like instructions to express FOL queries in an alternative format. This format utilizes textual variables and nested tuples to convey the logical semantics within FOL queries, serving as raw materials for a PLM-based instruction encoder to obtain complete query patterns. Building on this, we design a query-guided instruction decoder to adapt query patterns to KGQE models. To further enhance QIPP’s effectiveness across various KGQE models, we propose a query pattern injection mechanism based on compressed optimization boundaries and an adaptive normalization component, allowing KGQE models to utilize query patterns more efficiently. Extensive experiments demonstrate that our plug- and-play method¹ improves the performance of eight basic KGQE models and outperforms two state-of-the-art QPL methods. © 2025 Copyright held by the owner/author(s).

关键词： Complex Query Answering knowledge Graph Pre-trained Language Model Query Pattern Learning

来源：评论

学校读者我要写书评

暂无评论

T2R-GAN: A CGAN-based model for rural thematic road extraction 27th

T2R-GAN: A CGAN-based model for rural thematic road extracti...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ni, Zixiang Zhai, Weixin College of Information and Electrical Engineering China Agricultural University Beijing100083 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Application Ministry of Agriculture and Rural Affairs Beijing100083 China

ISBN: (纸本)9783031783883

Rural roads extracted from agricultural machinery trajectories have significant research value. Due to the intricate network of rural roads and the large difference in the density of agricultural machinery trajectories, traditional road extraction methods struggle to perform effectively on rural roads with complex topology and on agricultural machinery trajectories with obscure road features. Therefore, this paper proposes a CGAN-based model named T2R-GAN (Trajectory to Road-GAN) for rural thematic road extraction, which learns the trajectory-to-road feature mapping through continuous adversarial training between the ELAU-Net generator and the PatchGAN discriminator to adapt to trajectories of various densities. ELAU-Net is an efficient network that utilizes an encoder-decoder structure and ELA modules to enhance the capture of obscure road features between sparse trajectories. To enhance model performance and reduce the risk of overfitting, bilateral hinge loss is designed to train our model to enhances the discriminator’s discriminative ability to facilitate the generator to generate more realistic roads improve the generalization of the model. To verify the effectiveness of T2R-GAN in extracting roads from agricultural trajectory data, this paper selects the real agricultural trajectory data from Henan Province, china in June 2021 as the dataset for verification. The experimental results show that the proposed method achieves 79.23% F1score, which is 5.53% higher than the previous state-of-art. The proposed T2R-GAN provides a novel and effective approach for extracting rural thematic roads from agricultural machinery trajectories for the first time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Stochastic Block Models for Complex Network Analysis: A Survey

引用

ACM Transactions on knowledge Discovery from data 2025年第3期19卷 1-35页

作者： Liu, Xueyan Song, Wenzhuo Musial, Katarzyna Li, Yang Zhao, Xuehua Yang, Bo College of Computer Science and Technology Jilin University Changchun China School of Information Science and Technology Northeast Normal University Changchun China Complex Adaptive Systems Lab Data Science Institute University of Technology Sydney Sydney Australia Aviation University of the Air Force Changchun China School of Digital Media Shenzhen Institute of Information Technology Shenzhen China Key Laboratory of Symbolic Computation and Knowledge Engineer Jilin University Ministry of Education Changchun China

Complex networks enable to represent and characterize the interactions between entities in various complex systems which widely exist in the real world and usually generate vast amounts of data about all the elements, their behaviors and interactions over time. The studies concentrating on new network analysis approaches and methodologies are vital because of the diversity and ubiquity of complex networks. The stochastic block model (SBM), based on Bayesian theory, is a statistical network model. SBMs are essential tools for analyzing complex networks since SBMs have the advantages of interpretability, expressiveness, flexibility and generalization. Thus, designing diverse SBMs and their learning algorithms for various networks has become an intensively researched topic in network analysis and data mining. In this article, we review, in a comprehensive and in-depth manner, SBMs for different types of networks (i.e., model extensions), existing methods (including parameter estimation and model selection) for learning optimal SBMs for given networks and SBMs combined with deep learning. Finally, we provide an outlook on the future research directions of SBMs. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Complex Networks Structural Pattern Discovery Stochastic Block models Learning Methods of SBMs

来源：评论

学校读者我要写书评

暂无评论

Stochastic SIRS models on networks: mean and variance of infection

引用

Infectious Disease Modelling 2025年第3期10卷 875-896页

作者： Chen, Tingting Liu, Guirong Jin, Zhen School of Mathematics and Statistics Shanxi University Shanxi Taiyuan 030006 China Complex Systems Research Center Shanxi University Shanxi Taiyuan 030006 China Key Laboratory of Complex Systems and Data Science of Ministry of Education Shanxi University Shanxi Taiyuan 030006 China

Due to the heterogeneity of contact structure, it is more reasonable to model on networks for epidemics. Because of the stochastic nature of events and the discrete number of individuals, the spread of epidemics is more appropriately viewed as a Markov chain. Therefore, we establish stochastic SIRS models with vaccination on networks to study the mean and variance of the number of susceptible and infected individuals for large-scale populations. Using van Kampen's system-size expansion, we derive a high-dimensional deterministic system which describes the mean behaviour and a Fokker-Planck equation which characterizes the variance around deterministic trajectories. Utilizing the qualitative analysis technique and Lyapunov function, we demonstrate that the disease-free equilibrium of the deterministic system is globally asymptotically stable if the basic reproduction number R₀ < 1;and the endemic equilibrium is globally asymptotically stable if R₀ > 1. Through the analysis of the Fokker-Planck equation, we obtain the asymptotic expression for the variance of the number of susceptible and infected individuals around the endemic equilibrium, which can be approximated by the elements of principal diagonal of the solution of the corresponding Lyapunov equation. Here, the solution of Lyapunov equation is expressed by vectorization operator of matrices and Kronecker product. Finally, numerical simulations illustrate that vaccination can reduce infections and increase fluctuations of the number of infected individuals and show that individuals with greater degree are more easily infected. © 2025 The Authors

关键词： Fokker-Planck equation Networks Stochastic SIRS models Van Kampen's system-size expansion Variance

来源：评论

学校读者我要写书评

暂无评论

Development of a high-resolution near-surface meteorological forcing dataset for the Third Pole region

引用

Science china Earth Sciences 2025年第4期68卷 1274-1290页

作者： Yaozhi JIANG Wenjun TANG Kun YANG Jie HE Changkun SHAO Xu ZHOU Hui LU Yingying CHEN Xin LI Jiancheng SHI School of Resources and Environment University of Electronic Science and Technology of ChinaChengdu611731China Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing100084China National Tibetan Plateau Data Center State Key Laboratory of Tibetan Plateau Earth SystemEnvironment and ResourcesInstitute of Tibetan Plateau ResearchChinese Academy of SciencesBeijing100101China State Key Laboratory of Hydroscience and Engineering Tsinghua UniversityBeijing100084China Tsinghua University(Department of Earth System Science)-Xi’an Institute of Surveying and Mapping Joint Research Center for Next-Generation Smart Mapping Beijing100084China National Space Science Center Chinese Academy of SciencesBeijing100190China

Recently,the Third Pole(TP)region has experienced rapid environmental *** data are essential for hydrometeorological and ecological applications but still have large uncertainties on the TP owing to the heterogeneous land surface,complex terrain,and sparse weather *** this study,a long-term(1979–2020)high-resolution(1/30°)meteorological forcing dataset for the TP(TPMFD)was developed,as a sister to the widely used china Meteorological Forcing dataset(CMFD).The TPMFD comprises seven components necessary for driving land surface *** have previously contributed precipitation and downward shortwave radiation data for the TPMFD,and this study presents the development of five other components and focuses on validations for all ***,2-meter air temperature,2-meter specific humidity,10-meter wind speed,and surface air pressure were generated by combining the fifth-generation atmospheric reanalysis for European Center for Medium-Range Weather Forecasts(ERA5),a short-term high-resolution atmospheric simulation,and in situ observations,and the downward longwave radiation was calculated using semi-physical *** cross-validation and independent-validation demonstrated that most variables in the developed dataset outperformed those in widely used reanalysis datasets,including ERA5,ERA5-Land,and the Global Land data Assimilation System(GLDAS).This dataset is expected to be beneficial for climate analyses and modeling applications of land-surface processes on the TP.

关键词： Meteorological data Third Pole High-resolution data downscaling and merging

来源：评论

学校读者我要写书评

暂无评论

PFed-NS: An Adaptive Personalized Federated Learning Scheme Through Neural Network Segmentation

引用

IEEE Transactions on Computers 2025年第6期74卷 1936-1948页

作者： Liu, Yuchen He, Ligang Zhang, Zhigao Ren, Shenyuan University of Warwick Department of Computer Science CoventryCV4 7AL United Kingdom Wuhan University School of Computer Science Wuhan430072 China China Hubei Luojia Laboratory Wuhan430072 China Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing100044 China

Federated Learning (FL) is typically deployed in a client-server architecture, which makes the Edge-Cloud architecture an ideal backbone for FL. A significant challenge in this setup arises from the diverse data feature distributions across different edge locations (i.e., non-IID data). In response, Personalized Federated Learning (PFL) approaches have been developed. Network segmentation-based PFL is an important approach to achieving PFL, in which the training network is divided into a global segment for server aggregation and a local segment maintained client-side. Existing methods determine the segmentation before the training, and the segmentation remains fixed throughout the PFL training. However, our investigation reveals that model representations vary as PFL progresses and the fixed segmentation may not deliver best performance across various training settings. To address this, we propose PFed-NS, a PFL framework based on adaptive network segmentation. This adaptive segmentation technique is composed of two elements: a mechanism for assessing divergence of clients’ probability density functions constructed from network layers’ outputs, and a model for dynamically establishing divergence thresholds, beyond which server aggregation is deemed detrimental. Further optimization strategies are proposed to reduce the computation and communication costs incurred by divergence modeling. Moreover, we propose a divergence-based BN strategy to optimize BN performance for network segmentation-based PFL. Extensive experiments have been conducted to compare PFed-NS against recent PFL models. The results demonstrate its superiority in enhancing model accuracy and accelerating convergence. © 1968-2012 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in Talking Head Generation

KAN-Face: Efficient Resource Usage and Precision Lip-Sync in...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Feng, Guanwen Jin, Siyu Qian, Zhihao Li, Yunan Miao, Qiguang School of Computer Science and Technology Xidian University Shaanxi Xi'an710071 China Xi'an Key Laboratory of Big Data and Intelligent Vision Xidian University Shaanxi Xi'an710071 China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi'an710071 China

ISBN: (纸本)9798350368741

Despite significant progress in NeRF-based talking head generation, problems like poor lip synchronization and inefficient resource usage remain. To solve these, we propose KAN-Face, a lightweight framework. In preprocessing, we introduce a Lip-Sync Enhancement Module that uses Wav2Lip to extract high-resolution audio features and map them to an explicit intermediate representation, ensuring precise lip movement alignment with the speaker's identity. These predicted lip-sync features are combined with fundamental audio-extracted lip features and injected into the rendering module to improve synchronization. For rendering, we introduce FastKAN to map spatial points to color values. As a variant of KAN, FastKAN's sensitivity to 3D scenes and efficient structure enable precise, fast color prediction. Our framework reduces resource consumption while enhancing lip-sync accuracy and facial reconstruction, making it ideal for talking head generation tasks in resource-limited settings. Project: https://***/KAN-Face/. © 2025 IEEE.

关键词： Face Animation KAN Network Low Resource Neural Radiance Fields Talking Head Generation

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：