检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Tong, Shilin Wu, Difei Liu, Xiaona Zheng, Le Du, Yuchuan Zou, Difan Department of Computer Science The University of Hong Kong Hong Kong Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University China Institute of IoT Shenzhen Polytechnic University China School of Information and Electronics Beijing Institute of Technology China Department of Computer Science Insitute of Data Science The University of Hong Kong Hong Kong

Pavement distress, manifested as cracks, potholes, and rutting, significantly compromises road integrity and poses risks to drivers. Accurate prediction of pavement distress deterioration is essential for effective road management, cost reduction in maintenance, and improvement of traffic safety. However, real-world data on pavement distress is usually collected irregularly, resulting in uneven, asynchronous, and sparse spatial-temporal datasets. This hinders the application of existing spatial-temporal models, such as DCRNN [1], since they are only applicable to regularly and synchronously collected data. To overcome these challenges, we propose the Spatial-Temporal Graph Autoregression Network (STGAN), a novel graph neural network (GNN) model designed for accurately predicting irregular pavement distress deterioration using complex spatial-temporal data. Specifically, STGAN integrates the temporal domain into the spatial domain, creating a larger graph where nodes are represented by spatial-temporal tuples and edges are formed based on a similarity-based connection mechanism. Furthermore, based on the constructed spatiotemporal graph, we formulate pavement distress deterioration prediction as a graph autoregression task, i.e., the graph size increases incrementally and the prediction is performed sequentially. This is accomplished by a novel spatial-temporal attention mechanism deployed by the proposed STGAN model. Utilizing the ConTrack dataset [2], which contains pavement distress records collected from different locations in Shanghai, we demonstrate the superior performance of STGAN in capturing spatial-temporal correlations and addressing the aforementioned challenges. Experimental results further show that STGAN outperforms baseline models, and ablation studies confirm the effectiveness of its novel modules. Our findings contribute to promoting proactive road maintenance decision-making and ultimately enhancing road safety and resilience. © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Nonlinear Modeling and Control of Switched Reluctance Motor 32

Simulation Research on Nonlinear Modeling and Control of Swi...

引用

32nd Chinese Control and Decision Conference, CCDC 2020

作者： Ru, Luan Zou, Hongjian Guo, Jinru Beijing University of Civil Engineering and Architecture School of Electrical and Information Engineering Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

ISBN: (纸本)9781728158549

The model of a switched reluctance motor (SRM) directly influences it's performance and control effect. However, the doubly salient structure, switching power supply and seriously saturated magnetic circuit, make it difficult to accurately model. Aiming to solve this problem, this paper presents a new simulation method based on BP neural network to establish the current and torque models of a SRM. Using a great deal of current, flux linkage, torque numerical solution data obtained by a finite element software as the sample data, a kind of BP neural network is trained offline, and all the expected data sets, which form a table, are outputted. By looking-up the table the nonlinear models of flux linkage and torque of the SRM are obtained. On the basis of the nonlinear models, the current closed-loop control is formed by using the torque sharing function and the fuzzy switching angles to reduce the torque ripple. The simulation results show that the proposed nonlinear models not only have a fast calculation speed, but also are high precision and can meet the requirements of real-time control. The proposed control method can effectively reduce the torque ripple of the SRM. © 2020 IEEE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

On the Noise Robustness of In-Context Learning for Text Generation

arXiv

引用

arXiv 2024年

作者： Gao, Hongfu Zhang, Feipeng Jiang, Wenyu Shu, Jun Zheng, Feng Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China School of Economics and Finance Xi’an Jiaotong University China National Key Laboratory for Novel Software Technology Nanjing University China School of Mathematics and Statistics Xi’an Jiaotong University China Department of Computer Science and Engineering Southern University of Science and Technology China

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://***/ml-stat-Sustech/Local-Perplexity-Ranking © 2024, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning Fine-Grained Information Alignment for Calibrated Cross-Modal Retrieval

Learning Fine-Grained Information Alignment for Calibrated C...

引用

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

作者： Jianhua Dong Shengrong Zhao Hu Liang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China

Masked Language Modeling (MLM) and Image-Text Matching (ITM) are always used in fusion encoder to learn the joint representation of images and text. In existing methods, the masking strategy of MLM leads to the neglect of image details during the modeling process. Meanwhile, the sampling strategy of ITM struggles to consistently select high-difficulty hard negative instances, reducing the effectiveness of constraints. This leads to challenges in aligning fine-grained information in cross-modal retrieval. In response to this challenge, a fine-grained information alignment-based visual language model (FAM) is proposed in this paper. On one hand, the attribute-based masking strategy is employed in MLM, helping the model focus on the details of objects in images during modeling. On the other hand, the robust hard negative sample generation strategy provides challenging negative samples for ITM by altering the relationships between objects. This enables the model to align relationships between objects in different modalities and thus calibrates cross-modal retrieval. Extensive experiments demonstrate the effectiveness of the model in cross-modal retrieval tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bridging knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal 39

Bridging Knowledge Gap Between Image Inpainting and Large-Ar...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Leng, Yicheng Fang, Chaowei Chen, Junye Fang, Yixiang Li, Sheng Li, Guanbin School of Artificial Intelligence Xidian University Xi’an China School of Data Science The Chinese University of HongKong Shenzhen China School of Computer Science and Engineering Research Institute of Sun Yat-sen University in Shenzhen Sun Yat-sen University Guangzhou China Afirstsoft Shenzhen China GuangDong Province Key Laboratory of Information Security Technology China

ISBN: (纸本)157735897X

Visible watermark removal which involves watermark cleaning and background content restoration is pivotal to evaluate the resilience of watermarks. Existing deep neural network (DNN)-based models still struggle with large-area watermarks and are overly dependent on the quality of watermark mask prediction. To overcome these challenges, we introduce a novel feature adapting framework that leverages the representation modeling capacity of a pre-trained image inpainting model. Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model. We establish a dual-branch system to capture and embed features from the residual background content, which are merged into intermediate features of the inpainting backbone model via gated feature fusion modules. Moreover, for relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process. This contributes to a visible image removal model which is insensitive to the quality of watermark mask during testing. Extensive experiments on both a large-scale synthesized dataset and a real-world dataset demonstrate that our approach significantly outperforms existing state-of-the-art methods. The source code is available in the supplementary materials. © 2025, Association for the Advancement of Artificial Intelligence (***). 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

A Cloud Framework for High Spatial Resolution Soil Moisture Mapping from Radar and Optical Satellite Imageries

引用

Chinese Geographical Science 2023年第4期33卷 649-663页

作者： GUO Tianhao ZHENG Jia WANG Chunmei TAO Zui ZHENG Xingming WANG Qi LI Lei FENG Zhuangzhuang WANG Xigang LI Xinbiao KE Liwei Northeast Institute of Geography and Agroecology Chinese Academy of SciencesChangchun 130102China College of Resources and Environment University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Black Soils Conservation and Utilization Northeast Institute of Geography and AgroecologyChinese Academy of SciencesChangchun 130102China Changchun Jingyuetan Remote Sensing Test Site Changchun 130102China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China China Centre for Resources Satellite Data and Application China Aerospace Science and Technology CorporationBeijing 100094China College of Geoexploration Science and Technology Jilin UniversityChangchun 130026China School of Geomatics and Prospecting Engineering Jilin Jianzhu UniversityChangchun 130118China

Soil moisture plays an important role in crop yield estimation,irrigation management,*** sensing technology has potential for large-scale and high spatial soil moisture ***,offline remote sensing data processing is time-consuming and resource-intensive,and significantly hampers the efficiency and timeliness of soil moisture *** to the high-speed computing capabilities of remote sensing cloud platforms,a High Spatial Resolution Soil Moisture Estimation Framework(HSRSMEF)based on the Google Earth Engine(GEE)platform was developed in this *** functions of the HSRSMEF include research area and input datasets customization,radar speckle noise filtering,optical-radar image spatio-temporal matching,soil moisture retrieving,soil moisture visualization and *** paper tested the performance of HSRSMEF by combining Sentinel-1,Sentinel-2 images and insitu soil moisture data in the central farmland area of Jilin Province,*** Normalized Difference Vegetation Index(NDVI)based on the Savitzky-Golay algorithm conforms to the crop growth cycle,and its correlation with the original NDVI is about 0.99(P<0.001).The soil moisture accuracy of the random forest model(R 2=0.942,RMSE=0.013 m3/m3)is better than that of the water cloud model(R 2=0.334,RMSE=0.091 m3/m3).HSRSMEF transfers time-consuming offline operations to cloud computing platforms,achieving rapid and simplified high spatial resolution soil moisture mapping.

关键词： soil moisture(SM) Google Earth Engine(GEE) Cloud Computing Platform High Spatial Resolution Soil Moisture Estimation Framework(HSRSMEF) remote sensing Sentienl-1 Sentinel-2 Northeast China

来源：评论

学校读者我要写书评

暂无评论

A small first-order DPA resistant AES implementation with no fresh randomness

引用

Science China(Information Sciences) 2022年第6期65卷 261-263页

作者： Man WEI Siwei SUN Zihao WEI Zheng GONG Lei HU State Key Laboratory of Information Security Institute of Information EngineeringChinese Academy of Sciences Data Assurance and Communication Security Research Center Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences School of Compute Science South China Normal University

Dear editor,Cryptographic algorithms exist in the form of software or hardware components inside security-critical information systems, which are often deployed in a hostile ***, other than guaranteeing the security of the cryptographic algorithms in the black-box model, ensuring the security of the software or hardware components against the attacks exploiting the physical leakage of the underlying devices is considerably important. Among these attacks,

关键词： side channel analysis DPA threshold implementation domain-oriented masking AES

来源：评论

学校读者我要写书评

暂无评论

Parameters Compressing in Deep Learning

引用

Computers, Materials & Continua 2020年第1期62卷 321-336页

作者： Shiming He Zhuozhou Li Yangning Tang Zhuofan Liao Feng Li Se-Jung Lim School of Computer and Communication Engineering Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on TransportationChangsha University of Science and TechnologyChangsha410114China Liberal Arts&Convergence Studies Honam UniversityGwangju62399Korea

With the popularity of deep learning tools in image decomposition and natural language processing,how to support and store a large number of parameters required by deep learning algorithms has become an urgent problem to be *** parameters are huge and can be as many as *** present,a feasible direction is to use the sparse representation technique to compress the parameter matrix to achieve the purpose of reducing parameters and reducing the storage *** methods include matrix decomposition and tensor *** let vector take advance of the compressing performance of matrix decomposition and tensor decomposition,we use reshaping and unfolding to let vector be the input and output of Tensor-Factorized Neural *** analyze how reshaping can get the best compress *** to the relationship between the shape of tensor and the number of parameters,we get a lower bound of the number of *** take some data sets to verify the lower bound.

关键词： Deep neural network parameters compressing matrix decomposition tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Secrets Behind Advanced Artificial Intelligence Language Models in Deidentifying Chinese-English Mixed Clinical Text: Development and Validation Study

引用

Journal of Medical Internet Research 2024年第1期26卷 e48443页

作者： Lee, You-Qian Chen, Ching-Tai Chen, Chien-Chang Lee, Chung-Hong Chen, Peitsz Wu, Chi-Shin Dai, Hong-Jie Dialogue System Technical Department Asustek Computer Inc Taipei Taiwan Intelligent System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Bioinformatics and Medical Engineering Asia University Taichung Taiwan Center for Precision Health Research Asia University Taichung Taiwan Electromagnetic Sensing Control and AI Computing System Laboratory Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Knowledge Discovery and Data Mining Lab Department of Electrical Engineering College of Electrical Engineering and Computer Science National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Chemical Engineering Feng Chia University Taichung Taiwan National Center for Geriatrics and Welfare Research National Health Research Institutes Zhunan Taiwan National Institute of Cancer Research National Health Research Institutes Tainan Taiwan School of Post-Baccalaureate Medicine College of Medicine Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan

Background: The widespread use of electronic health records in the clinical and biomedical fields makes the removal of protected health information (PHI) essential to maintain privacy. However, a significant portion of information is recorded in unstructured textual forms, posing a challenge for deidentification. In multilingual countries, medical records could be written in a mixture of more than one language, referred to as code mixing. Most current clinical natural language processing techniques are designed for monolingual text, and there is a need to address the deidentification of code-mixed text. Objective: The aim of this study was to investigate the effectiveness and underlying mechanism of fine-tuned pretrained language models (PLMs) in identifying PHI in the code-mixed context. Additionally, we aimed to evaluate the potential of prompting large language models (LLMs) for recognizing PHI in a zero-shot manner. Methods: We compiled the first clinical code-mixed deidentification data set consisting of text written in Chinese and English. We explored the effectiveness of fine-tuned PLMs for recognizing PHI in code-mixed content, with a focus on whether PLMs exploit naming regularity and mention coverage to achieve superior performance, by probing the developed models’ outputs to examine their decision-making process. Furthermore, we investigated the potential of prompt-based in-context learning of LLMs for recognizing PHI in code-mixed text. Results: The developed methods were evaluated on a code-mixed deidentification corpus of 1700 discharge summaries. We observed that different PHI types had preferences in their occurrences within the different types of language-mixed sentences, and PLMs could effectively recognize PHI by exploiting the learned name regularity. However, the models may exhibit suboptimal results when regularity is weak or mentions contain unknown words that the representations cannot generate well. We also found that the availability of cod

关键词： ChatGPT code mixing deidentification electronic health record large language model pretrained language model

来源：评论

学校读者我要写书评

暂无评论

HyperDiff: Masked Diffusion Model with High-efficient Transformer for Hyperspectral Image Cross-Scene Classification

HyperDiff: Masked Diffusion Model with High-efficient Transf...

引用

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

作者： Pei Zhang Dong Wang Chanyue Wu Jing Yang Lei Kang Zongwen Bai Ying Li Qiang Shen School of Computer Science Northwestern Polytechnical University Xi’an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan’an University Yan’an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd Qingdao China Department of Computer Science Aberystwyth University UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques.

关键词： Training Transfer learning Self-supervised learning Transformers Diffusion models Real-time systems Decoding Computational efficiency Speech processing Hyperspectral imaging

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：