检索结果-内蒙古大学图书馆

SSAM: a span spatial attention model for recognizing named entities

Scientific Reports 2025年第1期15卷 1-13页

作者： Wang, Kai Wen, Kunjian Chen, Yanping Qin, Yongbin Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and Technology Guizhou University Guiyang China State Key Laboratory of Public Big Data Guizhou University Guiyang China ByteDance Ltd. Beijing China

Mapping a sentence into a two-dimensional (2D) representation can flatten nested semantic structures and build multi-granular span dependencies in named entity recognition. Existing approaches to recognizing named entities often classify each entity span independently, which ignores the spatial structures between neighboring spans. To address this issue, we propose a Span Spatial Attention Model (SSAM) that consists of a token encoder, a span generation module, and a 2D spatial attention network. The SSAM employs a two-channel span generation strategy to capture multi-granular features. Unlike traditional attention implemented on a sequential sentence representation, spatial attention is applied to a 2D sentence representation, enabling the model to learn the spatial structures of the sentence. This allows the SSAM to adaptively encode important features and suppress non-essential information in the 2D sentence representation. Experimental results on the GENIA, ACE2005, and ACE2004 datasets demonstrate that our proposed model achieves state-of-the-art performance, with F1-scores of 81.82%, 89.04%, and 89.24%, respectively. The code is available at https://***/Gzuwkj/SpatialAttentionForNer. © The Author(s) 2025.

关键词： Named entity recognition Natural language processing Spatial attention

来源：评论

学校读者我要写书评

暂无评论

big data challenge： a data management perspective

引用

Frontiers of Computer Science 2013年第2期7卷 157-164页

作者： Jinchuan CHEN Yueguo CHEN Xiaoyong DU Cuiping LI Jiaheng LU Suyun ZHAO Xuan ZHOU Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China China Beijing 100872

There is a trend that, virtually everyone, rang- ing from big Web companies to traditional enterprisers to physical science researchers to social scientists, is either al- ready experiencing or anticipating unprecedented growth in the amount of data available in their world, as well as new op- portunities and great untapped value. This paper reviews big data challenges from a data management respective. In partic- ular, we discuss big data diversity, big data reduction, big data integration and cleaning, big data indexing and query, and fi- nally big data analysis and mining. Our survey gives a brief overview about big-data-oriented research and problems.

关键词： big data performance databases

来源：评论

学校读者我要写书评

暂无评论

DWMFusion: A lightweight medical image fusion network based on discrete wavelet convolution and selective state space models

引用

Expert Systems with Applications 2025年 286卷

作者： Fan, Chao Yun, Mengyang Chen, Li Zhao, Huijun Peng, Bingcheng School of Artificial Intelligence and Big Data Henan University of Technology Henan Province Zhengzhou City China Ministry of Education Key Laboratory of Grain Information Processing and Control Henan Province Zhengzhou City China School of Information Science and Engineering Henan University of Technology Henan Province Zhengzhou City450001 China

Multimodal medical image fusion improves the accuracy of clinical diagnosis by integrating medical imaging information from different sensors into unified and complementary multi-scale fused information images. However, existing fusion methods still face challenges in capturing modality-specific features, balancing local and global contextual features, and preserving complementary information from different representations. To overcome these shortcomings, this study proposes a lightweight feature complementary fusion network(DWMFusion) to achieve effective fusion of functional and structural medical images under lightweight premise. Specifically, a cross-channel feature extraction unit based on discrete wavelet transform (DWT) and convolutional coupling structure is designed to enhance the modal intrinsic frequency domain features. Meanwhile, a visual state space block (VSSB) and a contextual modeling structure with multiple layers of Mamba are introduced to balance local details with global semantics and reduce computational redundancy. In the image fusion stage, a multilevel cross-fusion unit (CFFM) that introduces position coding is designed to realize deep cross-modal spatio-temporal feature interaction. A joint loss function incorporating wavelet decomposition properties is proposed to effectively adaptively constrain the frequency domain consistency and maintain the structural information. Validation on the Harvard Medical School database shows that DWMFusion is capable of generating visually satisfactory fusion images. And compared with other methods, it improves the SD metrics by an average of 17.59%, the SF metrics by an average of 17.64%, and the AG metrics by an average of 19.96% on the three datasets. These results confirm the robustness and adaptability of the model. © 2025 Elsevier Ltd

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

EDSep: An Effective Diffusion-Based Method for Speech Source Separation

EDSep: An Effective Diffusion-Based Method for Speech Source...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jinwei Dong Xinsheng Wang Qirong Mao School of Computer Science and Communication Engineering Jiangsu University Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi’an China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Zhenjiang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method’s superior performance over existing diffusion and discriminative models, validating its efficacy.

关键词： Training Adaptation models Technological innovation Source separation databases Stochastic processes Differential equations Speech enhancement Diffusion models Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal evolution of drought status and its driving factors attribution in China

引用

Science of the Total Environment 2025年 958卷 178131页

作者： Jin, Haoyu Zhang, Ke Zhang, Pengfei Liu, Guoyan Liu, Moyang Chen, Xiaohong Willems, Patrick National Key Laboratory of Water Disaster Prevention Hohai University Jiangsu Nanjing210024 China Yangtze Institute for Conservation and Development Jiangsu Nanjing210024 China College of Hydrology and Water Resources Hohai University Jiangsu Nanjing210024 China China Meteorological Administration Hydro-Meteorology Key Laboratory Hohai University Jiangsu Nanjing210024 China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Jiangsu Nanjing210024 China CanberraACT0200 Australia Zhuhai519082 China Department of Civil Engineering Hydraulics and Geotechnics Section KU Leuven Leuven Belgium

Drought has intensified in China in recent years, and it is urgent to clarify the characteristics of drought evolutions in different regions and its influencing factors. To this end, we selected six main influencing factors and analyzed their impact on drought patterns. The results show that drought is increasing in 78.4 % of China, and more severe droughts have occurred since 2000. From the perspective of drought change distribution, the wet areas in China are getting wetter, and the dry areas are getting drier. The partial correlation coefficient (PACC) between precipitation and standard precipitation evapotranspiration index (SPEI) is the largest in South China (SC), and the PACC between temperature and SPEI is the largest in Northwest China (NWC). Precipitation and temperature have the greatest correlation with drought, accounting for 45.7 % and 30.8 % of China. In 49.9 % of China, temperature contributes the most to the drought trend changes, and in 16.6 % of China, normalized difference vegetation index (NDVI) contributes the most to the drought trend changes. Geographical detector model (GDM) shows temperature has the greatest driving force on SPEI, followed by surface solar radiation (SSR). Principal component analysis (PCA) shows temperature has the greatest positive impact on drought, while soil moisture has the greatest negative impact on drought. This study is helpful to increase the understanding of the diversities in drought drivers in different regions of China. © 2024

关键词： Drought Geographical detector Partial correlation analysis Principal component analysis Trend decomposition

来源：评论

学校读者我要写书评

暂无评论

Quantifying Bubble-Induced Diffusion Resistance Through Real-Time Sam-Assisted Yolo High Density Bubble Detection Algorithm

SSRN

引用

SSRN 2025年

作者： Wang, Bowen Lv, Haoyang Wang, Xun Hao, Minghui Guay, Daniel Kirk, Donald W. Thorpe, Steven Ruan, Zhengsen Zhejiang Key Laboratory of Big data and Future E-Commerce Technology Zhejiang Gongshang University. Zhejiang Hangzhou China Surface Engineering and Electrochemistry Group Department of Material Science and Engineering University of Toronto TorontoON Canada Énergie Matériaux Télécommunications Research Centre INRS VarennesQC Canada Department of Chemical Engineering and Applied Chemistry University of Toronto TorontoON Canada

The chemistry and localized structure of materials greatly affect their efficiency in gas evolution reactions leading to cell resistance loses. This work focuses on the role of morphological changes in the nature of the bubble distribution by a comparison of two different surface structures: polished Ni and various porous Ni surfaces fabricated by dynamic hydrogen bubble templating. This study introduces a refined method for counting bubbles in gas evolution reactions, focusing on high-density, overlapping bubble flows. By incorporating the Segment Anything Model (SAM), we significantly reduced the training cost of the You Only Look Once algorithm, maintaining accuracy while improving efficiency. Surface characteristics strongly influenced the bubble distribution, with superaerophobic surfaces exhibiting smaller Sauter Mean Diameter (D32) values than polished ones. A polynomial extrapolation indicated that D32s were roughly one third of the thickness of the bubble layer at higher current densities. Building on the established connection between bubble layer thickness and diffusion resistance through electrochemical impedance spectroscopy (EIS), this study establishes a direct relationship between D32 and diffusion resistance. We have also demonstrated that the characteristics of the bubble layer are independent of the electrochemical surface area (ECSA) beneath the surface. This combined approach uses EIS for broader current coverage and imaging for real-time data, providing a powerful framework for bubble management and performance monitoring in gas evolution applications. © 2025, The Authors. All rights reserved.

关键词： Hydrogen evolution reaction

来源：评论

学校读者我要写书评

暂无评论

Robust Indoor Person Re-Identification with Multimodal Training

引用

IEEE Internet of Things Journal 2025年

作者： Su, Can Xue, Xinlei Ma, Lei Zhang, Xiaolong Yan, Wei Bian, Kaigui Peking University School of Computer Science AI Innovation Center National Engineering Laboratory for Big Data Analysis and Applications Beijing100871 China Peking University School of Computer Science Beijing100871 China Peking University Beijing Academy of Artificial Intelligence National Biomedical Imaging Center College of Future Technology National Key Laboratory for Multimedia Information Processing Beijing100871 China Beihang University Beijing100191 China

Existing person re-identification (ReID) methods mainly rely on images and videos to match persons across cameras, yet visual data captured by cameras are vulnerable to environmental interferences (e.g. illumination and occlusion) or personal appearance changes, leading to performance degradation under such scenes. Meanwhile, the popularization of Wi-Fi networks has allowed probe requests to be captured for mobile sensing applications such as crowd counting and trajectory estimation. However, the MAC address randomization technique adopted by modern devices breaks the association of probe requests and adversely affects the functionality of these applications. In this paper, we propose MaRPA, the first multimodal training approach that incorporates both videos and Wi-Fi probe requests to simultaneously promote tasks of probe requests association and person ReID. MaRPA first distinguishes among pairwise probe request frames through a contrastive learning model. It then matches video and probe request sequences by exploring their similarities from the position and the vision aspects. Matched videos and probe requests provide complementary information and generate more robust features for both tasks. To evaluate MaRPA, we contribute a new dataset containing synchronous videos and probe requests data for probe requests association and person ReID. Experimental results demonstrate the effectiveness of our approach. For probe requests association, it achieves > 85% discrimination accuracy and > 0.90 V-measure score;for person ReID, it achieves 75.8% mAP and 90.6% Rank-1, improving state-of-the-art video-based ReID methods by over 40% © 2014 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation for Underwater Acoustic Sensor Networks With Partial Spectrum Sharing: When Optimization Meets Deep Reinforcement Learning

引用

IEEE Transactions on Network and Service Management 2025年

作者： Tang, Rui Zhang, Ruizhi Xu, Yongjun Liu, Chuan Huang, Chongwen Yuen, Chau China West Normal University School of Electronic Information Engineering Nanchong637002 China China West Normal University of Sichuan Province Key Laboratory of Optimization Theory and Applications Nanchong637002 China Internet of Things Perception and Big Data Analysis Key Laboratory of Nanchong City Nanchong637002 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400064 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Nanyang Technological University School of Electrical and Electronics Engineering Singapore639798 Singapore

To utilize the limited acoustic spectrum while combating the harsh underwater propagation, we incorporate partial spectrum sharing into an underwater acoustic sensor network and aim to maximize the minimum data collection rate among all underwater sensor nodes through joint power allocation and spectrum assignment. To cope with the non-convex optimization problem, we propose a Hybrid Model-based and data-based Resource Allocation (HMDRA) scheme: 1) Under any given spectrum assignment strategy, we analyze the impact of the partial spectrum sharing and imperfect successive interference cancellation on baseband signal processing, and formulate a power allocation problem that is solved by the bisection method and Lagrange dual theory. 2) Based on the optimal power allocation strategy, the gradient-free genetic algorithm (GA) is first adopted to approach the optimal solution of the model-less spectrum assignment problem by nearly enumerating the solution space. To reduce complexity, we further propose a deep reinforcement learning (DRL)-based algorithm and obtain an efficient solution by traversing a deep neural network-based policy learned from the training stage. Simulation results show that compared with the GA-based algorithm, the average execution time of the DRL-based algorithm is substantially reduced by 5 orders of magnitude to 0.7076 seconds at the cost of approximately 6 percent performance loss. © 2004-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Causal Adversarial Graph Neural Network for Multi-Center Autism Spectrum Disorder Identification

SSRN

引用

SSRN 2025年

作者： Zhang, Zhuan Wang, Lihui Chen, Qijian Wang, Li Jian, Caiqing Zhu, Yue-Min Wei, Hongjiang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China University Lyon INSA Lyon CNRS Inserm IRP Metislab CREATIS UMR5220 U1206 Lyon69621 France

Due to the heterogeneous distributions of multi-center rs-fMRI data, currently it is still challenging to identify accurately autism spectrum disorder (ASD) patients from these heterogenous data. To deal with the influence of heterogeneous distributions on multi-center ASD diagnosis, a novel causal adversarial graph neural network (CAG) for multi-center ASD prediction is proposed in this work. CAG mainly consists of a graph filtering (GF) module and a learnable causal graph predictor (CGP). Specifically, the brain connection graph is first constructed from rs-fMRI data, after passing a GF module, the filtered graph is further divided by a causal subgraph and causally irrelevant subgraph. The ground-truth environmental labels and ASD labels are predicted from causal subgraph by a clustering method and a classification block, respectively. In addition, from the filtered graph and causally irrelevant subgraph, the environmental labels are predicted, while from the causally irrelevant subgraph the ASD labels are predicted. Assuming that the predicted environmental labels are independent to causal subgraph, while the predicted ASD labels are independent to causally irrelevant subgraph, accordingly, several adversarial losses are implemented by reversing the gradient. Through this adversarial learning strategy, the derived causal graph can predict multi-center ASD. The comparison experiments on both ABIDE-I and ABIDE-II datasets demonstrate that, the ACC and AUC of CAG has been improved by 3.78\% and 7.38\% at least comparing against the existing methods. Moreover, some abnormal functional connectivities in ASD group are identified from the causal subgraph which may provide useful imaging biomarkers for the early diagnosis of ASD. © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

6D Movable Antenna Enhanced Interference Mitigation for Cellular-Connected UAV Communications

引用

IEEE Wireless Communications Letters 2025年

作者： Ren, Tianshi Zhang, Xianchao Zhu, Lipeng Ma, Wenyan Gao, Xiaozheng Zhang, Rui The School of Information and Electronics Beijing Institute of Technology Beijing100081 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore The Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems China The Engineering Research Center of Intelligent Human Health Situation Awareness of Zhejiang Province Jiaxing University Jiaxing314001 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of HongKong Guangdong Shenzhen518172 China

Cellular-connected unmanned aerial vehicle (UAV) communications is an enabling technology to transmit control signaling or payload data for UAVs through cellular networks. Due to the line-of-sight dominant air-to-ground channels, efficient interference mitigation is crucial to UAV communications, while the conventional fixed-position antenna (FPA) arrays have limited degrees of freedom to suppress the interference between the UAV and its non-associated co-channel base stations (BSs). To address this challenge, we propose in this letter a new approach by utilizing the six-dimensional movable antenna (6DMA) arrays to enhance the interference mitigation for the UAV. Specifically, we propose an efficient block coordinate descent algorithm to iteratively optimize the antenna position vector, array rotation vector, receive beamforming vector, and associated BS of the UAV to maximize its signal-to-interference-plus-noise ratio. Numerical results show that the proposed 6DMA enhanced cellular-connected UAV communication can significantly outperform that with the traditional FPA arrays and other benchmark schemes in terms of interference mitigation. © 2025 IEEE. All rights reserved.

关键词： Aircraft communication

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：