检索结果-内蒙古大学图书馆

4th Asia-Pacific Artificial Intelligence and Big data Forum, AIBDF 2024

作者： Zhao, Feng Fan, Wenxuan Han, Zhongwei Chen, Hongyu School of Computer Science and Technology Shandong Technology and Business University Shandong Yantai China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Shandong Yantai China Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China Information Engineering College Yantai Institute of Technology Shandong Yantai China Shandong Technology and Business University Shandong Yantai China

ISBN: (纸本)9798400710865

Functional connectivity networks (FCNs), particularly those utilizing the phase lag index (PLI) method, have been instrumental in elucidating the pathological features of Major Depressive Disorder (MDD) by assessing the synchrony and lag of electroencephalogram (EEG) signal waveforms. Currently, the more prevalent methods are traditional FCNs that quantify phase synchronization as scalar values and dynamic FCNs (D-FCNs) that employ sliding window approaches to capture the instantaneous variations in functional connectivity. However, these two methods merely capture the low-level functional connections between paired regions of interest (ROIs) from both the static and dynamic perspectives, and fail to reflect the high-level functional connections involving multiple ROIs. Moreover, the feature dimension of the dynamic FCN is excessively high, and there exists a phase mismatch issue between different samples, which renders it impossible to be directly applied to the classification task, and no better solution is available at present. To mitigate these issues, we proposed a comprehensive framework that includes segmenting EEG sequences based on PLI to construct dynamic FCNs;employing seventh-order central moments for feature extraction to form low-order FCNs (Lo-FCNs);and establishing high-order FCNs (Ho-FCNs) based on Pearson correlation theory derived from Lo-FCNs. We conducted classification experiments across four distinct EEG frequency bands using our proposed framework while analyzing relevant features through graph theory and brain topological mapping techniques. The experiments showed that the proposed framework has a high classification accuracy rate in the classification experiments of MDD and NC, and proved the importance of high-order features in classification experiments, indicating that they may serve as physiological markers for MDD diagnosis. © 2024 Copyright held by the owner/author(s).

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

arXiv

引用

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Evolution of vegetation phenology and its response to urbanisation in Shaanxi province, China: A fine-scale perspective

引用

Journal of Geographical Sciences 2025年第5期35卷 1024-1048页

作者： Gao, Meiling Ma, Jingjing Li, Zhenhong Yang, Guijun College of Geological Engineering and Geomatics Chang’an University Xi’an China State Key Laboratory of Loess Science Xi’an China Key Laboratory of Ecological Geology and Disaster Prevention Ministry of Natural Resources Xi’an China Big Data Center for Geosciences and Satellites Xi’an China

Shaanxi province in China is rich in vegetation resources, making the study of vegetation phenology crucial for understanding climate change and ecological dynamics. Previous studies on Shaanxi have primarily focused on coarse-scale phenology, which results in the loss of essential spatial details due to the lack of finer-scale analyses. Moreover, the impact of rapid urbanisation on the phenology of various vegetation types in this region remains unclear. To address these gaps, we integrated Landsat and MODIS data to generate a daily 30 m NDVI sequence. Vegetation phenology across Shaanxi from 2000 to 2020 was then extracted and analysed, and the responses of different vegetation types to urbanisation were explored. Results indicated that accurate vegetation phenology can be obtained at a 30 m resolution, which is more precise than conventional coarse-scale investigations. The Start of Season (SOS) and End of Season (EOS) in the province advanced by −0.56 and −0.08 day/year, respectively, from 2000 to 2020. In general, the SOS gradually delays, and the EOS progressively advances with increasing latitude. However, anomalies were identified in regions south of 32.64°N and across the zone from 34.04°N to 37.56°N, which are primarily due to the effects of high elevation and rapid urbanisation, respectively. Further investigation into phenological differences among various vegetation types revealed that forests exhibit the earliest SOS, while grasslands present the latest. In addition, a significant negative correlation was found between the SOS difference and air temperature difference along the urban–rural gradient, with urbanisation having the most significant impact on cropland phenology. This study provides valuable insights into vegetation phenology and its response to urbanisation. These insights offer crucial information for ecological conservation and management strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MCITEBENCH: A Benchmark for Multimodal Citation Text Generation in MLLMs

arXiv

引用

arXiv 2025年

作者： Hu, Caiyu Zhang, Yikai Zhu, Tinghui Ye, Yiwei Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Computer Engineering and Science Shanghai University China

Multimodal Large Language Models (MLLMs) have advanced in integrating diverse modalities but frequently suffer from hallucination. A promising solution to mitigate this issue is to generate text with citations, providing a transparent chain for verification. However, existing work primarily focuses on generating citations for text-only content, overlooking the challenges and opportunities of multimodal contexts. To address this gap, we introduce MCITEBENCH, the first benchmark designed to evaluate and analyze the multimodal citation text generation ability of MLLMs. Our benchmark comprises data derived from academic papers and review-rebuttal interactions, featuring diverse information sources and multimodal content. We comprehensively evaluate models from multiple dimensions, including citation quality, source reliability, and answer accuracy. Through extensive experiments, we observe that MLLMs struggle with multimodal citation text generation. We also conduct deep analyses of models’ performance, revealing that the bottleneck lies in attributing the correct sources rather than understanding the multimodal content. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Adaptive Detr: A Framework with Dynamic Sampling Points and Feature-Guided Adaptive Attention Updates

SSRN

引用

SSRN 2025年

作者： Li, Botao Yang, Huguang Xia, Chenglong Zheng, Han Wulamu, Aziguli Zhang, Taohong Beijing100083 China Department of Guangxi Zhuang Autonomous Region Key Laboratory of AI and Information Processing [Hechi University Guangxi546300 China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083 China

In recent years, models based on DETR (Detection Transformer) have made significant progress in the field of object detection. However, the encoder and decoder in DETR and its variants still face several critical challenges. Specifically, the high computational complexity and limited adaptability of the encoder restrict its performance across diverse datasets, while the query initialization process in the decoder leads to slower model *** address this issue, we propose a new framework—Adaptive DETR—that features dynamic adjustment of the number of sampling points and feature-guided adaptive feature *** main innovations include: First, we introduce a new attention update strategy that dynamically calculates weights based on the features of the output image, determining the frequency of features, thereby enhancing detection accuracy. Second, to address the issue of poor model adaptability caused by fixed sampling points in the deformable attention module of the DETR model, we implement dynamic adjustment of the number of sampling points, improving the model's generalization ability in complex scenes. Finally, we optimize the DETR decoder by performing attention calculations between queries responsible for bounding boxes and those responsible for semantic information during the query initialization phase, By effectively injecting semantic information while accelerating the model's convergence speed, the model's localization accuracy can also be *** experimental results demonstrate that Adaptive DETR achieves the best performance on the COCO、UAVDT、VisDrone and RSOD datasets, showcasing its efficiency and adaptability. © 2025, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Exploring Source-Free X-ray Prohibited Item Detection with An Assistant-Teacher Network

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Jia, Wanying Jia, Tong Ma, Bowen Huang, Cunhe Tian, Yixin Wang, Hao Chen, Dongyue Northeastern University College of Information Science and Engineering Shenyang110819 China Northeastern University College of Information Science and Engineering Shenyang China Key Laboratory of Data Analysis and Optimization for Smart Industry Ministry of Education Northeastern University China

Security scanners are important for maintaining long-term social stability and safety. However, different security scanners exist endogenous domain shifts. Traditional unsupervised methods require access to the source domain for adaptation during training. But in practical deployment, data privacy restricts access to data between different security scanners. To exploring the this issue, Assistant-Teacher Network (ATN) is proposed to address the endogenous domain shift of X-ray prohibited item detection in the case of source-free domain adaption. In particular, to suppress the problem of false positives and loss of important information in the source-free domain adaption, we propose a common cognitive mechanism. To further prevent the model from optimizing towards the wrong direction under false positive labels, an external ATN loop is designed. In addition, an image de-stylization mechanism is proposed to alleviate the endogenous domain shift, allowing the network to learn the essential features of the X-ray image. By utilizing internal and external loops, ATN can adaptively apply to multiple security scanners in a source-free domain adaptation. The comprehensive experimental results on X-ray images and natural images indicate that our method is effective. Especially in X-ray prohibited item detection, our method has achieved state of the art results compared to recent methods. Our code will be available on https://***/JiaWanying/***. © 1963-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Increase in global per capita cropland imbalance across countries from 1985 to 2022:A threat to achieving Sustainable Development Goals

引用

Geography and Sustainability 2025年第2期6卷 253-264页

作者： Tingting Zhao Xiao Zhang Wendi Liu Jinqing Wang Zhehua Li Liangyun Liu School of Geography and Ocean Science Nanjing UniversityNanjing 210023China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China Key Laboratory of Digital Earth Science Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China School of Electronic Electrical and Communication EngineeringUniversity of Chinese Academy of SciencesBeijing 100049China

Sustainable Development Goal 2(SDG 2,zero hunger)highlights that global hunger and food insecurity have worsened since 2015,driven in part by growing *** the challenge of achieving SDG 2 in the face of rapid global population growth requires sustained attention to global and national cropland *** quantifying the correlation between population and cropland area(i.e.,SDG 2.4.1 per capita cropland)and analyzing the trends of global cropland imbalance are essential for a comprehensive understanding of SDG *** this study,we utilized a new global 30 m land-cover dynamic dataset(GLC_FCS30D)to analyze cropland dynamics,quantify per capita cropland and its changes across various countries and levels of *** results indicate that the global cropland area expanded by 0.944 million km^(2)from 1985 to 2022,with an average expansion rate of 2.42×10^(4)km^(2)/***,the global per capita cropland area decreased from 0.347 ha in 1985 to 0.217 ha in 2022,mainly due to a higher population increase of nearly 65%in the same *** the context of globalization,cropland expansion and per capita cropland exhibited spatial imbalances globally,particularly in developing *** countries saw an increase in total cropland area by 7.09%but a significant decrease in per capita cropland area by 37.38%.From a temporal perspective,the global imbalance has been steadily increasing with the Gini index rising from 0.895 in 1985 to 0.909 in ***,this study reveals an increasing imbalance of global per capita cropland across various countries,which threatens the attainment of the targets of SDG 2.

关键词： Sustainable Development Goals GLC_FCS30D Cropland changes Population Imbalance

来源：评论

学校读者我要写书评

暂无评论

A Hybrid-Feature-Based Autoencoder Model for Predicting Traffic Flow to Accelerate Ambulance Medical Response Time in Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第9期12卷 11397-11407页

作者： Li, Yongmeng Tian, Yu Liu, Wenjian Gao, Longxiang Tian, Hui Xing, Lumin The First Affiliated Hospital of Shandong First Medical University Shandong Provincial Qianfoshan Hospital Shandong Key Laboratory of Digital Diagnosis and Treatment of Thoracic Oncology Shandong Engineering Research Center of Intelligent Surgery Shandong Jinan250014 China Qilu Hospital of Shandong University Department of Thoracic Surgery Shandong Jinan250012 China City University of Macau Faculty of Data Science China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250000 China The First Affiliated Hospital of Shandong First Medical University Shandong Provincial Qianfoshan Hospital Shandong Key Laboratory of Digital Diagnosis and Treatment of Thoracic Oncology Shandong Jinan250014 China

Traffic congestion during ambulance travel can delay medical response times. With the growing availability of traffic data, computational methods for traffic flow prediction are attracting significant attention. However, current computational prediction models have the following shortcomings. Fully connected networks require extensive feature engineering yet struggle to capture local traffic flow features. Their high parameter count increases training time and overfitting risk, while varying traffic conditions hinder model generalization. Therefore, in this work, we propose a hybrid-feature-based autoencoder (HFAE) model to predict traffic flow and accelerate ambulance medical response time in Internet of Vehicles. Specifically, the HFAE model simultaneously considers local features from the convolutional neural network and global features from the fully connected neural network. Additionally, the HFAE model uses an autoencoder to reconstruct the original input, capturing the intrinsic structure of the traffic flow data. Specifically, the root mean-squared error and mean absolute error scores of the HFAE model are better than those of the three mainstream models. © 2014 IEEE.

关键词： Ambulances

来源：评论

学校读者我要写书评

暂无评论

A Frequency and Polarization Reconfigurable Transparent Water Antenna

引用

Progress in Electromagnetics Research C 2025年 152卷 177-186页

作者： Li, Lei Gao, Jing Nan, Jingchang School of Electronics and Information Engineering Liaoning Technical University Huludao125105 China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Huludao125105 China

A novel frequency and polarization reconfigurable water patch antenna is proposed for radio communication in the UHF band. Based on theoretical analysis and simulation results, water is an ideal material for designing transparent liquid ground. Water enhances outstanding transparency, excellent aesthetics, and high optical stealth performance for a wider range of application scenarios. The entire structure is made with polyvinyl chloride material and distilled water, except for the feed structure. By filling different cavities with liquid water, five different operating states are obtained in 1.924–2.5 GHz (26.1%), 1.67–2.33 GHz (33%), 0.644–2.288 GHz (112.1%), 1.975–2.54 GHz (25%), and 1.748–2.108 GHz (18.7%), achieving frequency reconfigurability. The antenna can be flexibly switched between linear polarization (LP) and two right-handed circular polarization (RHCP) states. The results show that the 3 dB axial ratio (AR) bandwidth covers 1.93–2.08 GHz (7.5%) and 2.06–2.132 GHz (3.5%). The antenna achieves high optical transparency of 100% and a peak gain of 7.97 dBi. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Dual-Network Cross-Learning for Metabolite-Disease Association Prediction

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 545-556页

作者： Yanxin Chen Qiao Ning Yitong Zhang Hui Li Shikai Guo Department of Information Science and Technology Dalian Maritime University Dalian China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Dalian Key Laboratory of Artificial Intelligence Dalian China

In recent years, increasing evidence has demonstrated a close association between metabolites and various complex human diseases, providing valuable insights for disease diagnosis, treatment, and prevention. Although deep learning-based approaches have achieved certain success in predicting metabolic disease associations, challenges remain in enriching graph information and effectively integrating metabolic and disease features. To address these issues, this paper proposes a model named DCMDA, which extracts deep features of both metabolites and diseases using Dual-network Cross-learning for Metabolite- Disease Association prediction. DCMDA consists of three parts. The data processing module integrates similarity networks with association networks to construct a heterogeneous network. The feature extraction module extracts features from the metabolite-disease association network based on the non-negative matrix factorization method and from the heterogeneous network using graph autoencoder techniques. The feature fusion module combines the association matrix feature with the heterogeneous network feature through a Cross-Attention mechanism, thereby obtaining deep representations of metabolites and diseases. These features are then used to train the model to predict association scores between metabolites and diseases. Experimental results demonstrate that in 5-fold cross-validation, DCMDA achieves an area under the receiver operating characteristic curve (AUC) of 97.8% and an area under the precision-recall curve (AUPR) of 97.9%, outperforming state-of-the-art prediction methods.

关键词： Diseases Feature extraction data mining Semantics Deep learning Kernel Information entropy Prediction algorithms Noise Nearest neighbor methods

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：