检索结果-内蒙古大学图书馆

21st Chinese National Conference on Computational Linguistic, CCL 2022

作者： Wang, Yaqiang Li, Kailun Jiang, Yongguang Shu, Hongping College of Software Engineering Chengdu University of Information Technology China Institute for Data Science and Engineering Chengdu University of Information Technology China Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service China Department of Preclinical Medicine Chengdu University of Traditional Chinese Medicine China

Four diagnostic description extraction in clinical records of traditional Chinese medicine (TCM) has important application value in improving the quality and efficiency of TCM clinical syndrome differentiation and treatment. However, the extraction task is yet to be explored, and imbalanced class distribution is one of the key challenges of this task. As a first exploration of this task, we firstly constructed a TCM clinical four diagnostic description extraction corpus and then solved the domain adaptation by fine-tuning the general domain pre-trained language model based on unlabeled TCM clinical records. At last, we trained our proposed four diagnostic description extraction model by utilizing a small labeled dataset through a well-designed batch data oversampling algorithm. The experimental results show that the performance of the proposed method in this paper is better than that of the compared methods, and the proposed method improves the extraction performance F1 score of the rare class by 2.13% on average. © 2022 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

PicT: A SlimWeakly Supervised Vision Transformer for Pavement Distress Classification

arXiv

引用

arXiv 2022年

作者： Tang, Wenhao Huang, Sheng Zhang, Xiaoxian Huangfu, Luwen School of Big Data & Software Engineering Chongqing University Chongqing China School of Big Data & Software Engineering Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Chongqing China Fowler College of Business Center for Human Dynamics in the Mobile Age San Diego State University San DiegoCA United States

Automatic pavement distress classification facilitates improving the efficiency of pavement maintenance and reducing the cost of labor and resources. A recently influential branch of this task divides the pavement image into patches and infers the patch labels for addressing these issues from the perspective of multi-instance learning. However, these methods neglect the correlation between patches and suffer from a low efficiency in the model optimization and inference. As a representative approach of vision Transformer, Swin Transformer is able to address both of these issues. It first provides a succinct and efficient framework for encoding the divided patches as visual tokens, then employs self-attention to model their relations. Built upon Swin Transformer, we present a novel vision Transformer named Pavement Image Classification Transformer (PicT) for pavement distress classification. In order to better exploit the discriminative information of pavement images at the patch level, the Patch Labeling Teacher is proposed to leverage a teacher model to dynamically generate pseudo labels of patches from image labels during each iteration, and guides the model to learn the discriminative features of patches via patch label inference in a weakly supervised manner. The broad classification head of Swin Transformer may dilute the discriminative features of distressed patches in the feature aggregation step due to the small distressed area ratio of the pavement image. To overcome this drawback, we present a Patch Refiner to cluster patches into different groups and only select the highest distress-risk group to yield a slim head for the final image classification. We evaluate our method on a large-scale bituminous pavement distress dataset named CQU-BPDD. Extensive results demonstrate the superiority of our method over baselines and also show that PicT outperforms the second-best performed model by a large margin of +2.4% in P@R on detection task, +3.9% in F 1 on recogni

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered-Based Privacy-Preserving Finite-Time Flocking Control for Networked Multi-Agent Systems

Event-Triggered-Based Privacy-Preserving Finite-Time Flockin...

引用

IEEE Conference on Decision and Control

作者： Jiangfeng Yue Kaiyu Qin Jinliang Shao Mengji Shi Weihao Li Wei Xing Zheng School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing China School of Computer Data and Mathematical Sciences Western Sydney University Sydney NSW Australia

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Drawing inspiration from the dynamics of biological groups, flocking behavior has captivated interest due to its adaptive, self-organizing, and resilient characteristics. However, the presence of numerous agents in an open network environment raises concerns regarding the potential for information leakage during flocking movements. To address this issue, we present a decentralized output mapping function, executed independently by each individual agent, to ensure the maintenance of flocking behavior, including velocity alignment, cohesion and collision avoidance. Additionally, to enhance resource efficiency and convergence speed, an event-triggered mechanism is employed to mitigate the excessive consumption of bandwidth and computation resources in traditional flocking control algorithms. Moreover, the designed finite-time controller facilitates rapid convergence of flocking behavior. Finally, the efficacy of our proposed approach is corroborated through numerical simulation experiments.

关键词： Privacy Event detection System performance Bandwidth Numerical simulation Stability analysis Trajectory Optimization Numerical stability Convergence

来源：评论

学校读者我要写书评

暂无评论

Testing the number of common factors by bootstrapped sample covariance matrix in high-dimensional factor models

arXiv

引用

arXiv 2022年

作者： Yu, Long Zhao, Peng Zhou, Wang School of Statistics and Management Shanghai University of Finance and Economics China School of Mathematics and Statistic Jiangsu Provincial Key Laboratory of Educational Big Data Science and Engineering Jiangsu Normal University Jiangsu Xuzhou China Department of Statistics and Data Science National University of Singapore Singapore

This paper studies the impact of bootstrap procedure on the eigenvalue distributions of the sample covariance matrix under a high-dimensional factor structure. We provide asymptotic distributions for the top eigenvalues of bootstrapped sample covariance matrix under mild conditions. After bootstrap, the spiked eigenvalues which are driven by common factors will converge weakly to Gaussian limits after proper scaling and centralization. However, the largest non-spiked eigenvalue is mainly determined by the order statistics of the bootstrap resampling weights, and follows extreme value distribution. Based on the disparate behavior of the spiked and non-spiked eigenvalues, we propose innovative methods to test the number of common factors. Indicated by extensive numerical and empirical studies, the proposed methods perform reliably and convincingly under the existence of both weak factors and cross-sectionally correlated errors. Our technical details contribute to random matrix theory on spiked covariance model with convexly decaying density and unbounded support, or with general elliptical *** Codes 62H25, 60B20 © 2022, CC BY-NC-SA.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Dissociation mechanism of C2H42+ induced by 18-keV/u Ne8+ impact: Symmetric and isomeric cleavage of the C-C bond

引用

Physical Review A 2022年第1期106卷 012805-012805页

作者： Baihui Ren Pufang Ma Yu Zhang Long Wei Jie Han Zihan Xia Jiarong Wang Tianming Meng Wandong Yu Yaming Zou Chuan-Lu Yang Baoren Wei Institute of Modern Physics Key Laboratory of Nuclear Physics and Ion-Beam Application (MOE) Fudan University Shanghai 200433 China College of Data Science Jiaxing University Jiaxing 314001 China State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-Optoelectronics School of Physics Peking University Beijing 100871 China School of Physics and Optoelectronics Engineering Ludong University Yantai 264025 China

The C-C bond cleavage dissociation of ethylene dication produced by 18-keV/u Ne8+ impact is investigated by combining experimental measurement and theoretical calculation. Using cold target recoil ion momentum spectroscopy, two channels, i.e., the symmetric fragmentation, C2H42+ → CH2++CH2+, and the isomeric one, C2H42+ → CH++CH3+, are clearly identified and thus their kinetic-energy release (KER) distributions are determined. The average KER values are then compared with the theoretical results obtained by quantum chemical calculations, which provide reaction paths of both channels on the potential-energy surfaces of different molecular states. It is found that the hydrogen transfer process and excited-state dynamics still play crucial roles in the formation of C-C bond cleavage channels, but in a different way in comparison with the cases of acetylene C2H2 and ethane C2H6.

关键词： Atomic & molecular structure Chemical reactions Density functional theory Ions Molecules

来源：评论

学校读者我要写书评

暂无评论

A Secure key-Aggregate keyword Retrieval Scheme Over Encrypted data in Cloud Computing

引用

IEEE Access 2024年 1-1页

作者： Lou, Chunwei Cao, Mingsheng Luo, Yaohua Xu, Hua Gao, Yuan Wang, Weiwei Wang, Dong University of Electronic Science and Technology of China Chengdu 611731 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu 611731 China School of Information Science and Technology Chengdu University of Technology Chengdu 610059 China School of Physics and Electronic Engineering Yancheng Teachers University Yancheng 224007 China China Academy of Railway Sciences Beijing 100081 China School of Computer Science and Engineering and the Center for Cyber Security University of Electronic Science and Technology of China Chengdu 611731 China

key-aggregate keyword retrieval primitive enables a cloud server on behalf of delegated users to securely perform a keyword search over the data encrypted with various public keys. However, existing key-aggregate searchable encryption schemes are insecure against keyword guessing attacks, which result in the privacy leakage of keyword ciphertext and trapdoor. In this paper, we for the first time formulate a secure and efficient key-aggregate searchable encryption for cloud-assisted IoT applications, which not only enables a data owner to securely share the selected documents to multiple users, but also supports data users in delegating the capability of keyword search to a cloud server for searching the desired documents without leaking any privacy of keyword ciphertext and trapdoor. Then, the security of the proposed scheme is formally defined and proven to be secure against the indistinguishable selective-file chosen keyword attacks. The flexibility and practicability of the formulated scheme is also demonstrated by theoretical evaluations and experimental simulations. Author

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

arXiv

引用

arXiv 2024年

作者： Zhang, Xiaoqing Nie, Qiushi Xiao, Zunjie Zhao, Jilu Wu, Xiao Guo, Pengxin Li, Runzhi Liu, Jin Wei, Yanjie Pan, Yi Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Actuarial Science The University of Hong Kong 999077 Hong Kong Cooperative Innovation Center of Internet Healthcare Zhengzhou University Zhengzhou450001 China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830046 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

The HuaBiao project:whole-exome sequencing of 5000 Han Chinese individuals

引用

Journal of Genetics and Genomics 2021年第11期48卷 1032-1035页

作者： Meng Hao Weilin Pu Yi Li Shaoqing Wen Chang Sun Yanyun Ma Hongxiang Zheng Xingdong Chen Jingze Tan Guoqing Zhang Menghan Zhang Shuhua Xu Yi Wang Hui Li Jiucun Wang Li Jin State Key Laboratory of Genetic Engineering Collaborative Innovation Center for Genetics and DevelopmentHuman Phenome InstituteFudan UniversityShanghai 200433China State Key Laboratory of Genetic Engineering Collaborative Innovation Center for Genetics and DevelopmentHuman Phenome InstituteInstitute for Six-sector EconomyFudan UniversityShanghai 200433China Ministry of Education Key Laboratory of Contemporary Anthropology Department of Anthropology and Human GeneticsSchool of Life SciencesInstitute of Archaeological ScienceFudan UniversityShanghai 200433China Ministry of Education Key Laboratory of Contemporary Anthropology Department of Anthropology and Human GeneticsSchool of Life SciencesFudan UniversityShanghai 200433China Ministry of Education Key Laboratory of Contemporary Anthropology Department of Anthropology and Human GeneticsSchool of Life SciencesInstitute for Six-sector EconomyFudan UniversityShanghai 200433China Taizhou Institute of Health and Sciences Fudan UniversityTaizhouJiangsu 225300China Key Laboratory of Computational Biology Bio-Med Big Data CenterShanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China Ministry of Education Key Laboratory of Contemporary Anthropology Department of Anthropology and Human GeneticsSchool of Life SciencesHuman Phenome InstituteFudan UniversityShanghai 200433China

Next-generation sequencing technologies have significantly accelerated the identification of disease-causing mutations and facilitated the emergence of personalized medicine(Genomes Project Consortium et al.,2015;Goodwin et al.,2016;Sirugo et al.,2019).In comparison with whole-genome sequencing,whole-exome sequencing(WES),which covers the coding regions of the genome,offers a cost-efficacy *** provides deeper sequencing depth(>100)and allows the more accurate detection of rare variants that are tailored for clinical applications(Lek et al.,2016).

关键词： exo cost rare

来源：评论

学校读者我要写书评

暂无评论

Heterogenous multi-source fusion for ship trajectory complement and prediction with sequence modeling 5

Heterogenous multi-source fusion for ship trajectory complem...

引用

5th IEEE International Conference on data Science in Cyberspace, DSC 2020

作者： Zheng, Changmeng Peng, Qi Xu, Xuemiao South China University of Technology Key Laboratory of Big Data and Intelligent Robot School of Software Engineering Guangzhou China South China University of Technology School of Computer Science Engineering Guangzhou China

ISBN: (纸本)9781728195582

Effectively monitoring ships and discovering abnormal ship trajectory in time is necessary for marine traffic supervision. The basic work of discovering the ship's abnormal trajectory is to predict the ship's navigation dynamically. Previous works in ship trajectory prediction are basically concern on single-source data, for example, the AIS data. These methods ignore the relations between different sources which may improve the performance of predicting ship trajectory. We propose a neural sequence model based on heterogeneous multisource fusion for ship trajectory completion and prediction. Our method makes better utilization of AIS, GPS and ARPA radar information to predict ship trajectory precisely. We construct a dataset which contains about 8 million ship trajectory samples and the experiments demonstrate that our multi-source fusion model gains promising results. © 2020 IEEE.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Monocular Depth Estimation with Multi-constraints

Self-Supervised Monocular Depth Estimation with Multi-constr...

引用

第40届中国控制会议

作者： Xinpeng Yang Sen Zhang Baoyong Zhao School of Automation and Electrical Engineering University of Science and Technology Beijing Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical EngineeringUniversity of Science and Technology Beijing

For the self-supervised image depth estimation algorithm based on deep learning,the characteristics of self-supervised methods cause some problems such as visual shadow and infinity *** paper tackles these problems by adopting the spatial consistency loss and multiple loss *** this paper,the depth estimated network and pose estimated network are trained by binocular image *** the depth estimated problem is transformed into image reconstruction and scene reconstruction to realize self-supervised *** on the Deep Convolutional Neural Networks（DCNN）,the depth estimated network introduces the Deep Atrous Convolution（DAC） and the Atrous Spatial Pyramid Pooling（ASPP） modules to extract the multi-scale feature and increase the receptive field of the *** spatial consistency of scene reconstruction strategy greatly reduces the estimated error of pose *** quantitative and qualitative evaluation on the KITTI dataset shows that the proposed algorithm outperforms the existing self-supervised depth estimation algorithms in accuracy and error,even exceeds most of the sumervised algorithms.

关键词： self-supervised depth estimation ASPP photometric loss spatial loss

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：