检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Yichi Chen, Zhuo Guo, Lingbing Xu, Yajing Hu, Binbin Liu, Ziqi Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given knowledge graphs, collaboratively leveraging structural information from the triples and multi-modal information of the entities to overcome the inherent incompleteness. Existing MMKGC methods usually extract multi-modal features with pre-trained models, resulting in coarse handling of multi-modal entity information, overlooking the nuanced, fine-grained semantic details and their complex interactions. To tackle this shortfall, we introduce a novel framework MYGO to tokenize, fuse, and augment the fine-grained multi-modal representations of entities and enhance the MMKGC performance. Motivated by the tokenization technology, MYGO tokenizes multi-modal entity information as fine-grained discrete tokens and learns entity representations with a cross-modal entity encoder. To further augment the multi-modal representations, MYGO incorporates fine-grained contrastive learning to highlight the specificity of the entity representations. Experiments on standard MMKGC benchmarks reveal that our method surpasses 19 of the latest models, underlining its superior performance. Code and data can be found in https://***/zjukg/MyGO. Copyright © 2024, The Authors. All rights reserved.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SCRN: A Spectrogram Convolutional Recurrent Network for AoA Estimation Using Bluetooth 5

SCRN: A Spectrogram Convolutional Recurrent Network for AoA ...

引用

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

作者： Wentao Shi Baoqi Huang Bing Jia Engineering Research Center of Ecological Big Data Ministry of Education China Inner Mongolia Key Laboratory of Wireless Networking and Mobile Computing College of Computer Science Inner Mongolia University Hohhot China

Bluetooth 5 employs Constant Tone Extension (CTE) signals to simulate arrival times of a common signal at multiple antennas, but incurs limited accuracy due to inevitable frequency offsets caused by Gaussian frequency shift keying (GFSK) and time offsets caused by antenna switching. To address this issue, this paper proposes SCRN, an efficient Bluetooth 5 Angle of Arrival(AoA) estimation scheme that combines spectrogram analysis with deep learning co-design. SCRN leverages neural networks to generate a super-resolution spectrogram, effectively eliminating frequency offsets and recovering the true underlying frequency. Subsequently, it utilizes a lightweight convolutional recurrent network to encode the input features into a high-dimensional latent space, so as to alleviate the effect of time offsets. Through extensive experiments conducted in practical indoor settings, the proposed scheme achieves an AoA estimation error of only 1.3 degrees, surpassing traditional algorithms by over 90%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Research of Remote Sensing Process Language based on XML 2

Design and Research of Remote Sensing Process Language based...

引用

2nd IEEE International Conference on Information Technology, big data and Artificial Intelligence, ICIBA 2021

作者： Zuo, Xianyu Li, Heng Zhou, Liming Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781665428767

In the era of rapid development of remote sensing technology, in order to improve the production efficiency of remote sensing data processing flow and further optimize the editing of remote sensing processes in the visual interface. In this paper we have analyzed the characteristics and attributes of remote sensing processes and algorithms. We made the production of processes and algorithms into scripts, and realizes to create remote sensing processes by inputting scripting language in the visual interface. A remote sensing language based on XML is designed to read and store key information. This language will use XML to drive the production of remote sensing process. With the language we design, a remote sensing process customization system has been implemented. It can improve the editing and production efficiency of remote sensing data processing flow. © 2021 IEEE.

关键词： XML

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Azimuth signal reconstruction for hrws-sar from uniform resampling 2

Azimuth signal reconstruction for hrws-sar from uniform resa...

引用

2nd International Conference on Artificial Intelligence, Information Processing and Cloud Computing, AIIPCC 2021

作者： Zhang, Hanqing Wu, Lin Li, Ning Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China College of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9783800756162

Signal reconstruction is a key step in the azimuth multichannel high-resolution wide-swath synthetic aperture radar (HRWS-SAR) imaging algorithms. Krieger’s digital beam-forming (DBF) algorithm is currently one of the commonly used algorithms for processing HRWS-SAR data. However, this algorithm is only suitable for uniform space-time sampling and moderately non-uniform sampling. In the case of highly non-uniform sampling, the imaging performance of Krieger’s DBF algorithm will be seriously deteriorated. In this paper, a uniform resampling algorithm is presented to solve above problem. The proposed algorithm adopts modern sampling theory to reduce the approximate error. This algorithm consists of two key steps: 1. The given signal samples are projected onto a selected intermediate subspace, spanned by integer translations of a compactly supported kernel function. This process generates a sparse set of equations, which can be effectively solved by using a sparse equation solvers. 2. The results are projected onto the subspace where the sampled signal is known to reside. The orthogonal matching pursuit (OMP) algorithm is used to realize the second projection and reconstruction the signal effectively. Simulation results show that the newly proposed algorithm has a significant improvement in imaging performance than Krieger’s DBF algorithm. © 2021 AIIPCC 2021 - 2nd International Conference on Artificial Intelligence, Information Processing and Cloud Computing. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal variability of soil salinity and the driving factors of cultivated land in Xinjiang, China

引用

International Journal of Agricultural and Biological engineering 2025年第2期18卷 197-207页

作者： Yue Zhang Huichun Ye Ronghao Liu Chaojia Nie Mingyao Tang Yuanfang Huang Hongye Wang Xiaoshu Zhao Weini Wang Zhijun Lyu 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 College of Water Resources Science and Engineering Taiyuan University of TechnologyTaiyuan 030024China Lab of Big Earth Data and Sustainable Development Goal(BASL) Kashi Aerospace Information Research InstituteKashgar 844000China Xinjiang Soil and Fertilizer Station Urumqi 830006China College of Land Science and Technology China Agricultural UniversityBeijing 100193China Cultivated Land Quality Monitoring and Protection Center Ministry of Agriculture and Rural AffairsBeijing 100125China Ordos Agriculture and Animal Husbandry Ecology and Resource Protection Center Ordos 017001Inner MenguliaChina Agricultural and Animal Husbandry Technology Extension Center Dalat BannerOrdos 014300Inner MenguliaChina

Soil salinization poses a major challenge to agricultural production,food security,and sustainability in arid and semi-arid regions *** addressing this issue requires a thorough understanding of the spatiotemporal variations in soil salinity and its driving *** study investigates soil salinity in Xinjiang,China,using geostatistical methods to analyze its spatial distribution in cultivated lands across the region and its southern and northern sub-regions in ***,it examines the spatiotemporal changes in soil salinity from 2011 to 2021 in Bachu County(southern Xinjiang)and Nileke County(northern Xinjiang),which serve as representative *** results showed that in 2021,soil salinity across Xinjiang ranged from 0.1 to 27.7 g/kg,with an average of 2.8 g/kg and a coefficient of variation of 130.4%,indicating significant *** salinity levels were higher in southern Xinjiang(3.8 g/kg)compared to northern Xinjiang(2.0 g/kg),showing a spatial trend of“increasing salinity from north to south.”key drivers of spatial variation included available potassium,mean annual precipitation,alkali-hydrolyzable nitrogen,elevation,and soil *** 2011 and 2021,soil salinity in cultivated lands increased significantly by 2.0 g/kg in Bachu County,while it decreased by 4.2 g/kg in Nileke County,with these changes mainly influenced by climatic factors such as precipitation,evapotranspiration,and surface *** findings provide critical insights and data support for monitoring and managing soil salinization in Xinjiang,offering valuable guidance for improving agricultural sustainability in the region.

关键词： soil salinization spatial-temporal variation driving factors Xinjiang

来源：评论

学校读者我要写书评

暂无评论

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

arXiv

引用

arXiv 2025年

作者： Chen, Jiali Hei, Xusen Xue, Yuqi Wu, Zihan Xie, Jiayuan Cai, Yi Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China School of Software Engineering South China University of Technology China The Hong Kong Polytechnic University Hong Kong

Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children’s reading preferences (i.e., vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters’ personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children’s reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Mapping of Global 30-m Tidal Flats Using Time-Series Landsat Imagery:Algorithm and Products

Journal of Remote Sensing

引用

Journal of Remote Sensing 2023年第1期3卷 362-377页

作者： Xiao Zhang Liangyun Liu Jinqing Wang Tingting Zhao Wendi Liu Xidong Chen 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 College of Geomatics Xi’an University of Science and TechnologyXi’an 710054China North China University of Water Resources and Electric Power Zhengzhou 450046China

Tidal flats are an important part of coastal ecosystems and play an important role in shoreline protection and biodiversity *** many efforts have been made in tidal flat mapping,an accurate global tidal flat product covering all coasts globally is still lacking and urgently *** this study,a novel method is proposed for the automated mapping of global tidal flats at 30 m(GTF30)in 2020 based on the Google Earth Engine,which is also the first global tidal flat dataset covering the high latitudes(>60°N).Specifically,we first propose a new spectral index named the LTideI index through a sensitivity analysis,which is robust and can accurately capture low-tide ***,globally distributed training samples are automatically generated by combining multisource datasets and the spatiotemporal refinement ***,the global coasts are divided into 5885°×5°geographical tiles,and the local adaptive classification strategy is used to map tidal flats in each 5°×5°region by using multisourced training features and the derived globally distributed training *** statistical results show that the total global area of tidal flats is about 140,922.5 km2,with more than 75% distributed on 3 continents in the Northern Hemisphere,especially in Asia(approximately 43.1% of the total).Finally,the GTF30 tidal flat dataset is quantitatively assessed using 13,994 samples,yielding a good overall accuracy of 90.34%.Meanwhile,the intercomparisons with several existing tidal flat datasets indicate that the GTF30 products can greatly improve the mapping accuracy of tidal ***,the novel method can support the automated mapping of tidal flats,and the GTF30 dataset can provide scientific guidance and data support for protecting coastal ecosystems and supporting coastal economic and social *** GTF30 tidal flat dataset in 2020 is freely accessible via https://***/10.5281/zenodo.7936721.

关键词： tidal coastal Tidal

来源：评论

学校读者我要写书评

暂无评论

Attribute Reduction Method Based on Improved Granular Ball Neighborhood Rough Set 7

Attribute Reduction Method Based on Improved Granular Ball N...

引用

7th International Conference on Cloud Computing and big data Analytics, ICCCBDA 2022

作者： Xia, Han Chen, Zizhong Wu, Yanmin Qi, Jinli Chongqing Key Laboratory of Computer Science and Technology Chongqing University of Posts and Telecommunications ChongQing China ChongQing College of Electronic Engineering Department of Artificial Intelligence and Big Data ChongQing China ChongQing College of Electronic Engineering Department of General Education and International Studies ChongQing China

ISBN: (纸本)9781665487115

Feature reduction is an important aspect of big data analytics today, and neighborhood rough set is a classic attribute reduction method. The traditional neighborhood rough set finds out the radius suitable for problem solving by specifying the radius of the neighborhood or using a grid search method. There are a lot of overlapping calculations in the neighborhood calculation, and the calculation complexity is high. The granular ball neighbor-hood rough set can adaptively generate different neighborhood radius, and obtains better algorithm efficiency and learning effect than the traditional neighborhood rough set. However, due to the overlap problem in the process of granular ball generation, the granular ball neighborhood rough set still exists the overlap calculation of neighborhoods. For this reason, this paper solves the problem of granular ball overlap by detecting heterogeneous ball overlap and splitting, and thus designs an improved granular ball neighbor-hood rough set attribute reduction method. Experiments show that the improved granular ball neighborhood rough set has higher classification accuracy on the public benchmark dataset than the classic neighborhood rough set and the standard granular ball neighborhood rough set. © 2022 IEEE.

关键词： Cloud computing Costs Search methods Rough sets big data Benchmark testing Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

MetaDb:a database for metabolites and their regulation in plants with an emphasis on medicinal plants

引用

Molecular Horticulture 2024年第1期4卷 376-379页

作者： Qingqing Gao Jiajin Zhang Juntao Cao Chunfan Xiang Chengxiao Yuan Xia Li Juan Wang Pinhan Zhou Lesong Li Jia Liu Hongchun Xie Ruolan Li Guilin Huang Chaohui Li Guanghui Zhang Shengchao Yang Yan Zhao Key Laboratory of Medicinal Plant Biology of Yunnan Province National&Local Joint Engineering Research Center on Germplasms Innovation&Utilization of Chinese Medicinal Materials in Southwest ChinaYunnan Agricultural UniversityKunming 650201China Yunnan Characteristic Plant Extraction Laboratory Kunming 650106YunnanChina College of Agricultural Honghe Vocational and Technical CollegeHonghe 661199China College of Big Data Yunnan Agricultural UniversityKunming 650201China College of Agronomy&Biotechnology Yunnan Agricultural UniversityKunming 650201China

Natural product biosynthesis in medicinal plants has always been a research focus in ***,phenolics,and alkaloids,all of which have medicinal value for humans,are the three most prominent natural products found in medicinal plants(Cravens et al.2019;Li et al.2023;Zhao et al.2023).Many medicinal plants produce natural products that have special biological functions,such as regulating plant growth and resisting stress.

关键词： biology medicinal alkaloids

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：