检索结果-内蒙古大学图书馆

20th Chinese National Conference on Computational Linguistics, CCL 2021

作者： San, Maocuo Cai, Zhi-Jie Dao, Jizhaxi College of Computer Science and Technology Qinghai Normal University Qinghai Xining810016 China Key Laboratory of Tibetan Informati on Processing Ministry of Education Qinghai Xining810008 China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Qinghai Xining810008 China School of Computer Science and Technology Southwest Minzu University Sichuan Chengdu610041 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China

Text proofreading evaluation set is the basis of spelling research, including traditional text proofreading evaluation set and standard text proofreading evaluation set. The traditional text proofreading evaluation set is a kind of evaluation set obtained by artificial forgery of the correct data set through subjective experience. It is a common text proofreading evaluation method, but it also has many defects. Standard text proofreading evaluation set is an evaluation set obtained by selecting research objects to obtain reliable real data sets. Based on the analysis of the construction methods of English and Chinese text proofreading evaluation set, combined with the characteristics of tibetan, this paper studies the construction methods of tibetan text proofreading evaluation set, constructs a standard text proofreading evaluation set for evaluating the performance of tibetan text proofreading, and analyzes the error types and distribution in the evaluation set, so as to verify the effectiveness of the standard text proofreading evaluation set constructed in this paper Availability and usability. © 2021 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Pulse-Coupled Dual Adversarial Learning Network for Infrared and Visible Image Fusion

引用

Laser and Optoelectronics Progress 2025年第10期62卷 447-458页

作者： Jia, Zhao Yuelan, Xin Jizhao, Liu Qingqing, Wang School of Physical and Electronic Information Engineering Qinghai Normal University Qinghai Xining810001 China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810001 China School of Information Science and Engineering Lanzhou University Gansu Lanzhou730000 China Qinghai Meteorological Information Center Qinghai Xining810001 China

To address the issue of insufficient extraction and fusion of complementary information in infrared and visible image fusion, this study proposes a pulse-coupled dual adversarial learning network. The network utilizes dual discriminators that target infrared objects and visible texture details in the fused images, with the goal of preserving and enhancing modality-specific features. We also introduce a pulse-coupled neural network featuring a combined learning mechanism to effectively extract salient features and detailed information from the images. During the fusion stage, we implement a cross-modality fusion module guided by cross-attention, which further optimizes the complementary information between modalities and minimizes redundant features. We conducted comparative qualitative and quantitative analyses against nine representative fusion methods in the TNO, M3FD, and RoadScene datasets. Results show that the proposed method demonstrates superior performance in evaluation metrics, such as mutual information and sum of correlation differences. The method produces fused images with high contrast and rich detail and achieves better results in target detection tasks. © 2025 Universitat zu Koln. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Modeling human travel and social contact with multi-layer networks for epidemic prediction 9

Modeling human travel and social contact with multi-layer ne...

引用

9th IEEE International Conference on Bioinformatics and Computational Biology, ICBCB 2021

作者： Duan, Wei Wang, Tao Wang, Peng Ju, Rusheng Wang, Xiao Yang, Tian College of Systems Engineering National University of Defense Technology Changsha City China State Key Laboratry of Complex Systems Management and Control Institute of Automation Chinese Academy of Sciences Beijing City China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha City China

ISBN: (纸本)9780738132020

It is a key issue to reasonably represent human travel and social contact in epidemic models. Various measures were applied to develop the models of human mobility and contact in a long range or a short range, such as Brown movement, random walks, spatial networks, gravity models, contact networks. We proposed a method of representing human daily movement and social contact by using multi-layer networks with temporal edge weights. We combined bipartite networks with social networks to describe human daily trip and social contact, respectively. Temporal edge weights of multi-layer networks were employed to denote the propensity of individual movement and contact. We also verified our models and parameters by incorporating human daily travel and contact regularities, as well as comparing experimental results with human behavior statistical laws. At last, we applied a Chinese university campus as a case study to investigate students' daily travel and social contact, and studied the transmission and control strategies of COVID-19 virus. We found stricter control strategies are needed to mitigate the transmission of COVID-19 virus in a university. Once a patient case emerges in a university, it is better to close the campus and quarantine all students. Partial control strategies such as quarantining a part of students and buildings cannot achieve a great effect of mitigating the transmission of COVID-19 virus. Our works are beneficial for the practitioners in the field of computational epidemiology. © 2021 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

STABLE CLASSES OF HARMONIC MAPPINGS

arXiv

引用

arXiv 2023年

作者： Liu, Gang Ponnusamy, Saminathan Starkov, Victor V. College of Mathematics and Statistics Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang Normal University Hunan Hengyang421002 China Department of Mathematics Indian Institute of Technology Madras Chennai600 036 India Lomonosov Moscow State University Moscow Center of Fundamental and Applied Mathematics Moscow Russia Department of Mathematics University of Petrozavodsk ul. Lenina 33 Petrozavodsk185910 Russia

Let H0 denote the set of all sense-preserving harmonic mappings f = h + g in the unit disk D, normalized with h(0) = g(0) = g′(0) = 0 and h′(0) = 1. In this paper, we investigate some properties of certain subclasses of H0, including inclusion relations and stability analysis by precise examples, coefficient bounds, growth, covering and distortion theorems. As applications, we build some Bohr inequalities for these subclasses by means of subordination. Among these subclasses, six classes consist of functions f = h + g ∈ H0 such that h + ǫg is univalent (or convex) in D for each |ǫ| = 1 (or for some |ǫ| = 1, or for some |ǫ| ≤ 1). Simple analysis shows that if the function f = h + g belongs to a given class from these six classes, then the functions h + ǫg belong to corresponding class for all |ǫ| = 1. We call these classes as stable *** Codes Primary: 30A10, 30B10, 30H05, 31A05, 30C62, 30C80, Secondary 30C35, 30C45 Copyright © 2023, The Authors. All rights reserved.

关键词： Harmonic analysis

来源：评论

学校读者我要写书评

暂无评论

A High Precision Refresh Method to Improve The Performance of Flash Storage Devices

A High Precision Refresh Method to Improve The Performance o...

引用

International Symposium on Distributed Computing and applications to Business, Engineering and Science (DCABES)

作者： Peixuan Li Yaofang Zhang Deli Yin Ping Xie College of Computer of Qinghai Normal University Xining P. R. China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining P. R. China The Key Laboratory of Internet of Things of Qinghai Province Xining P. R. China Academy of Plateau Science and Sustainability Xining P. R. China Chuzhou Polytechnic Chuzhou P. R. China

ISBN: (纸本)9781665428903

With the development of flash memory, its storage density has gradually increased, but its reliability has been greatly reduced. Now, flash memory relies on LDPC to solve this problem. Although LDPC (Low Density Parity Check Code) can correct data with a high error rate, it will cause a lot of delays. The refresh operation can cause the LDPC decoding delay. In the work of this article, we propose a precise refresh strategy. On the basis of high latency pages, according to the characteristics of data access frequency, we take the read-hot data in the write-cold data as our refresh target. We test the performance of the precise refresh scheme through different workloads. Compared with ordinary refresh schemes, the average response time of flash memory storage devices is reduced by 16%-49% and the lifetime of flash memory is extended.

关键词： Performance evaluation Error analysis Distributed databases Parity check codes Delays Decoding Reliability

来源：评论

学校读者我要写书评

暂无评论

Improve the Performance of LSM-Tree based on key-Value via Multithreading

Improve the Performance of LSM-Tree based on Key-Value via M...

引用

International Symposium on Distributed Computing and applications to Business, Engineering and Science (DCABES)

作者： Yuan Gao Ping Xie Wendi Hua Meng Lv Jiating Lu College of Computer of Qinghai Normal University Xining P. R. China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining P. R. China Key Laboratory of Internet of Things of Qinghai Province Xining P. R. China Academy of Plateau Science and Sustainability Xining P. R. China School of Physical and Electrical Engineering Qinghai Normal University Xining P. R. China

ISBN: (纸本)9781665428903

In the era of big data, key-value storage systems based on Log-Structure Merge tree (LSM-tree) are widely used in numerous industries. LSM-Tree is divided into two parts, one part is in the memory and the other part is on the hard disk. When writing data, first write to the memory, when the Immutable Memtable in the memory is full of data, then write to the disk to output a Sorted String Table (SSTable) file. However, the use of writing data from memory to disk is single-threaded. When the Immutable Memtable writes data to the disk, it will block other threads. This article uses multiple Immutable Memtables and multi-threaded writing to solve the single-thread blocking problem. By running the benchmarks of LevelDB to analyze the experiment, the experimental results indicate a higher improvement.

关键词： Industries Multithreading Instruction sets Writing Big Data Benchmark testing Hard disks

来源：评论

学校读者我要写书评

暂无评论

Face occlusion detection algorithm based on yolov5

引用

Journal of Physics: Conference Series 2021年第1期2031卷

作者： Yuanzhang Zhao Shengling Geng School of Computer Science Qinghai Normal University Xining Qinghai 810016 China A State Key Laboratory of Intelligent Information Processing and Application of Tibetan Language jointly established by the Ministry and the Province Qinghai Normal University Xining Qinghai 810016 China Academy of Plateau Science and Sustainability Qinghai Normal University Xining Qinghai 810016 China

The current face-mask recognition detection algorithm during the epidemic only distinguishes between wearing or not wearing a mask. Such detection often has certain loopholes, such as using other objects to cover their mouths and noses instead of masks to cheat the detection. To address such problems, this paper proposes a YOLOv5 based face occlusion detection algorithm, which is modified based on the YOLOv5 algorithm by improving the loss function as DIoU and increasing the experimental samples by introducing multiple data sets to improve the object detection effect. The experimental results show that the improved YOLOv5 algorithm has improved the object detection effect for different kinds of face occlusions, which verifies the method's effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdaMMS: Model Merging for Heterogeneous Multimodal Large language Models with Unsupervised Coefficient Optimization

arXiv

引用

arXiv 2025年

作者： Du, Yiyang Wang, Xiaochen Chen, Chi Ye, Jiabo Wang, Yiru Li, Peng Yan, Ming Zhang, Ji Huang, Fei Sui, Zhifang Sun, Maosong Liu, Yang Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Tsinghua University Beijing China State Key Laboratory of Multimedia Information Processing Peking University Beijing China School of Software Microelectronics Peking University Beijing China Institute of Intelligent Computing Alibaba Group China Shanghai Artificial Intelligence Laboratory Shanghai China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China ModelTC Open Source Organization Beijing China

Recently, model merging methods have demonstrated powerful strengths in combining abilities on various tasks from multiple Large language Models (LLMs). While previous model merging methods mainly focus on merging homogeneous models with identical architecture, they meet challenges when dealing with Multimodal Large language Models (MLLMs) with inherent heterogeneous property, including differences in model architecture and the asymmetry in the parameter space. In this work, we propose AdaMMS1, a novel model merging method tailored for heterogeneous MLLMs. Our method tackles the challenges in three steps: mapping, merging and searching. Specifically, we first design mapping function between models to apply model merging on MLLMs with different architecture. Then we apply linear interpolation on model weights to actively adapt the asymmetry in the heterogeneous MLLMs. Finally in the hyper-parameter searching step, we propose an unsupervised hyper-parameter selection method for model merging. As the first model merging method capable of merging heterogeneous MLLMs without labeled data, extensive experiments on various model combinations demonstrated that AdaMMS outperforms previous model merging methods on various vision-language benchmarks. 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

Unveiling optimal SDG pathways: an innovative automated recommendation approach integrating graph pruning, intent graph, and attention mechanism

引用

International Journal of Digital Earth 2025年第1期18卷

作者： Qiang Wang Zhihang Yu Shu Wang Yunqiang Zhu Xiaoliang Dai Zhiqiang Zou Weiming Huang Christophe Claramunt a State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing People’s Republic of Chinad University of Chinese Academy of Sciences Beijing People’s Republic of China b College of Computer Nanjing University of Posts and Telecommunications Nanjing People’s Republic of Chinac Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing People’s Republic of China a State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing People’s Republic of Chinad University of Chinese Academy of Sciences Beijing People’s Republic of Chinae Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing People’s Republic of China f School of Geography University of Leeds Leeds UK a State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing People’s Republic of Chinag Naval Academy Research Institute Lanvéoc France

ABSTRACTThe recommendation of Sustainable Development Pathways (SDPs) is crucial for achieving the United Nations Sustainable Development Goals (SDGs) at regional level. However, traditional recommendation algorithms struggle with two key challenges: spatial heterogeneity and sparse historical interaction records between regions and SDPs. To address these issues, we introduce the Regional Graph-Based Explainable Recommendation (RGB-ER) method. RGB-ER leverages a pruned Regional Graph (RG) to capture regional spatial heterogeneity, incorporating environmental, economic, and social factors into the recommendations. In addition, an Intent Graph models regional preferences across various attributes, bridging historical interactions with the RG and mitigating data sparsity. This dual approach significantly improves recommendation accuracy and interpretability. Extensive experiments show that RGB-ER outperforms state-of-the-art graph-based models, with a maximum improvement of 9.61% in Top-3 recommendation accuracy. A case study in Fujian Province – a region characterized by its mountainous terrain, complex socio-economic landscape, and significant sustainability challenges – illustrates RGB-ER’s practical applicability, aligning well with local government strategies for sustainable development. Furthermore, we assess SDPs at the county level across China, highlighting the method’s potential for guiding region-specific sustainable development planning. In conclusion, RGB-ER provides a robust, explainable framework for data-driven decision-making in sustainable development.

关键词： Sustainable development pathways ecological civilization pattern recommender system knowledge graph pruning intent graph

来源：评论

学校读者我要写书评

暂无评论

Magnetotelluric signal-noise separation method based on SVM–CEEMDWT

引用

Applied Geophysics 2019年第2期16卷 160-170,252-253页

作者： Li Jin Cai Jin Tang Jing-Tian Li Guang Zhang Xian Xu Zhi-Min Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and EngineeringHunan Normal UniversityChangsha 410081China School of Geosciences and Info-Physics Key Laboratory of Metallogenic Prediction of Non-Ferrous Metals and Geological Environment MonitorMinistry of EducationCentral South UniversityChangsha 410083China State Key Laboratory Breeding Base of Nuclear Resources and Environment East China University of TechnologyNanchang 330013China

To better retain useful weak low-frequency magnetotelluric(MT)signals with strong interference during MT data processing,we propose a SVM-CEEMDWT based MT data signal-noise separation method,which extracts the weak MT signal affected by strong ***,the approximate entropy,fuzzy entropy,sample entropy,and Lempel-Ziv(LZ)complexity are extracted from the magnetotelluric ***,four robust parameters are used as the inputs to the support vector machine(SVM)to train the sample library and build a model based on the different complexity of *** on this model,we can only consider time series with strong interference when using the complementary ensemble empirical mode decomposition(CEEMD)and wavelet threshold(WT)for noise *** results suggest that the SVM based on the robust parameters can distinguish the time periods with strong interference well before noise *** with the CEEMD WT,the proposed SVM-CEEMDWT method retains more low-frequency low-variability information,and the apparent resistivity curve is smoother and more ***,the results better reflect the deep electrical structure in the field.

关键词： SVM-CEEMDWT magnetotelluric signal-noise separation MT data processing

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：