检索结果-内蒙古大学图书馆

39th IEEE International Conference on data engineering, ICDE 2023

作者： Guan, Renchu Zhang, Hao Liang, Yanchun Giunchiglia, Fausto Huang, Lan Feng, Xiaoyue Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Changchun China University of Trento Disi Trento Italy

ISBN: (纸本)9798350322279

Text clustering is a critical step in text data analysis and has been extensively studied by the text mining community. Most existing text clustering algorithms are based on the bag-of-words model, which faces the high-dimensional and sparsity problems and ignores text structural and sequence information. Deep learning-based models such as convolutional neural networks and recurrent neural networks regard texts as sequences but lack supervised signals and explainable results. In this paper, we propose a deep feature-based text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is based on sequence representations, breaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. Our code is available at https://***/KEAML-JLU/DeepTextClustering. © 2023 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Vertical Traffic Scheduling Control Method Based On Dual Fuzzy Neural Network

Vertical Traffic Scheduling Control Method Based On Dual Fuz...

引用

2023 International Annual Conference on Complex Systems and Intelligent Science, CSIS-IAC 2023

作者： Sun, Xinhao An, Siqi Gao, Xiaoting Cui, Enchang College of Light Industry Liaoning University Shenyang China Jilin University Key Laboratory of Symbolic Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China

ISBN: (纸本)9798350309003

With the complexity of the functions of modern buildings, the problem of vertical traffic in buildings is becoming more and more prominent. As the only vertical transportation, the elevator is a necessary prerequisite for the development of modern buildings to solve its group control distribution problem. In this paper, a vertical traffic scheduling control method is proposed based on dual fuzzy neural network, a recognition strategy is designed to identify the passenger flow models. The dual fuzzy neural network is used to first identify the traffic network model in which the elevator is located, and then combine the corresponding weights and the confidence of the group control allocation to complete the group control scheduling. Finally, the proposed method is verified through a semi-physical simulation platform, proving the correctness and effectivness for traffic pattern recognition and scheduling strategy optimization of group controllers. © 2023 IEEE.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

On the Robustness of Editing Large Language Models

On the Robustness of Editing Large Language Models

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Ma, Xinbei Ju, Tianjie Qiu, Jiyang Zhang, Zhuosheng Zhao, Hai Liu, Lifeng Wang, Yulong School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Baichuan Intelligent Technology China

ISBN: (纸本)9798891761643

Large language models (LLMs) have played a pivotal role in building communicative AI, yet they encounter the challenge of efficient updates. Model editing enables the manipulation of specific knowledge memories and the behavior of language generation without retraining. However, the robustness of model editing remains an open question. This work seeks to understand the strengths and limitations of editing methods, facilitating practical applications of communicative AI. We focus on three key research questions. RQ1: Can edited LLMs behave consistently resembling communicative AI in realistic situations? RQ2: To what extent does the rephrasing of prompts lead LLMs to deviate from the edited knowledge memory? RQ3: Which knowledge features are correlated with the performance and robustness of editing? Our empirical studies uncover a substantial disparity between existing editing methods and the practical application of LLMs. On rephrased prompts that are flexible but common in realistic applications, the performance of editing experiences a significant decline. Further analysis shows that more popular knowledge is memorized better, easier to recall, and more challenging to edit effectively. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

The Impact of Medical Resources and Oral Antiviral Drugs on SARS-CoV-2 Mortality—Hong Kong SAR,China,2022

引用

China CDC weekly 2024年第21期6卷 469-477,I0001-I0005页

作者： Zhiqi Zeng Jingyi Liang Zhijie Lin Wenda Guan Wei He Qianying Li Lixi Liang Weiqi Pan Zige Liu Guibin Lu Xiaoyan Deng Eric HY Lau Chitin Hon Zifeng Yang Guangzhou key laboratory for clinical rapid diagnosis and early warning of infectious diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangzhou CityGuangdong ProvinceChina Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao SARChina Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovative EngineeringMacao University of Science and TechnologyMacao SARChina State Key Laboratory of Respiratory Disease National Clinical Research Center for Respiratory DiseaseGuangzhou Institute of Respiratory Healththe First Affiliated Hospital of Guangzhou Medical UniversityGuangzhou CityGuangdong ProvinceChina School of Public Health The University of Hong KongHong Kong SARChina Laboratory of Data Discovery for Health Hong Kong SARChina Guangzhou Laboratory Guangzhou CityGuangdong ProvinceChina

Introduction:The Omicron variant of severe acute respiratory syndrome coronavirus 2(SARS-CoV-2)demonstrates increased transmissibility compared to earlier strains,contributing to a significant number of fatalities in Hong Kong Special Administrative Region(HKSAR),*** medical resources and medications are essential in mitigating these *** study evaluates the effects of supplementary resources from the Chinese mainland during the fifth wave of the pandemic in ***:Vector autoregression(VAR)was employed to analyze data from the Oxford coronavirus disease 2019(COVID-19)Government Response Tracker to assess the effectiveness of control measures during five waves of the pandemic in ***,a transmission dynamics model was created to investigate the influence of supplementary medical resources from the Chinese mainland and oral medications on ***:In the initial four waves,workplace closures,restrictions on public events,international travel bans,and shielding the elderly significantly influenced pandemic ***,during the fifth wave,these measures showed no notable *** comparing a situation without extra medical resources or COVID-19 oral medication,there was a 17.7%decrease in COVID-19 fatalities with mainland medical resources and an additional 10.2%reduction with oral ***,they contributed to a 26.6%decline in ***:With the rapid spread of the virus,regional reallocation of medical resources may reduce mortality even when the local healthcare system is overstretched.

关键词： mainland Impact travel

来源：评论

学校读者我要写书评

暂无评论

PromptGCN: Bridging Subgraph Gaps in Lightweight GCNs

arXiv

引用

arXiv 2024年

作者： Ji, Shengwei Tian, Yujie Liu, Fei Li, Xinlu Wu, Le The School of Artificial Intelligence and Big Data Hefei University Hefei China The School of Computer Science and Information Engineering Hefei University of Technology Hefei China The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education China

Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consume significant GPU memory, causing out of memory (OOM) errors on mainstream GPUs (e.g., 29GB memory consumption on the Ogbn-products graph with 5 layers). The subgraph sampling methods reduce memory consumption to achieve lightweight GCNs by partitioning the graph into multiple subgraphs and sequentially training GCNs on each subgraph. However, these methods yield gaps among subgraphs, i.e., GCNs can only be trained based on subgraphs instead of global graph information, which reduces the accuracy of GCNs. In this paper, we propose PromptGCN, a novel prompt-based lightweight GCN model to bridge the gaps among subgraphs. First, the learnable prompt embeddings are designed to obtain global information. Then, the prompts are attached into each subgraph to transfer the global information among subgraphs. Extensive experimental results on seven large-scale graphs demonstrate that PromptGCN exhibits superior performance compared to baselines. Notably, PromptGCN improves the accuracy of subgraph sampling methods by up to 5.48% on the Flickr dataset. Overall, PromptGCN can be easily combined with any subgraph sampling method to obtain a lightweight GCN model with higher accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

PriFU: Capturing Task-Relevant Information Without Adversarial Learning 24

PriFU: Capturing Task-Relevant Information Without Adversari...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Bi, Xiuli Hu, Yang Liu, Bo Li, Weisheng Cosman, Pamela Xiao, Bin Chongqing Key Laboratory of Image Cognition Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China Department of Electrical and Computer Engineering University of California San Diego San Diego United States

ISBN: (纸本)9798400706868

As machine learning advances, machine learning as a service (MLaaS) in the cloud brings convenience to human lives but also privacy risks, as powerful neural networks used for generation, classification or other tasks can also become privacy snoopers. This motivates privacy preservation in the inference phase. Many approaches for preserving privacy in the inference phase introduce multi-objective functions, training models to remove specific private information from users' uploaded data. Although effective, these adversarial learning-based approaches suffer not only from convergence difficulties, but also from limited generalization beyond the specific privacy for which they are trained. To address these issues, we propose a method for privacy preservation in the inference phase by removing task-irrelevant information, which requires no knowledge of the privacy attacks nor introduction of adversarial learning. Specifically, we introduce a metric to distinguish task-irrelevant information from task-relevant information, and achieve more efficient metric estimation to remove task-irrelevant features. The experiments demonstrate the potential of our method in several tasks. Our code will be available at: https://***/iwhoyoung/PriFU. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Joint Memory Propagation and Rectification for Video Object Segmentation 12th

Joint Memory Propagation and Rectification for Video Objec...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Wang, Jiale Xu, Hongli yin, Hui Wan, Jin Chen, Jianhuan Key Laboratory of Beijing for Railway Engineering Beijing Jiaotong University Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9783031463136

Spatio-temporal memory matching-based methods have achieved significant breakthroughs in the task of video object segmentation. Nevertheless, they are deficient in exploiting the long-term temporal correlation of frames by performing pixel-wise memory matching with limited reference frames, and tend to segment similar objects incorrectly. In this paper, we propose two novel modules, memory propagation and rectification modules, that are able to execute the memory reading in all proceeding frames while leveraging long-term temporal smoothness. Specifically, the memory propagation module employs the lightweight ConvGRU architecture to integrate abundant temporal cues from the reference frame sequence. Afterwards, the memory rectification module guided by the similarity between frames is proposed to increase the inter-frame consistency constraint to retrieve reliable memory and transfer them to the current frame. Additionally, we adopt a tiny-capacity spatio-temporal matching module to model the pixel relationship with only two reference frames. The experimental results on DAVIS and YouTube-VOS datasets demonstrate that combining memory propagation and rectification can achieve considerable performance gain and maintain constant inference time and memory usage in the sequence segmentation. To facilitate research in this direction, we release the project code at https://***/GDPUCJH/MPRNet. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Research on optimal deep learning-based formation flight positioning of UAV

Research on optimal deep learning-based formation flight pos...

引用

作者： Lu, Jing Li, Yongyi Faculty of Science Beibu Gulf University Qinzhou China Qinzhou Key Laboratory of Big Data Resource Utilization College of Electronic and Information Engineering Beibu Gulf University Qinzhou China

The article examines the positional relationships and transmission/reception signal direction information within unmanned aerial vehicle (UAV) cluster formations. Considering the distinctive characteristics of various formation shapes (such as circle and cone), a study is conducted on the polar and Cartesian coordinate systems in neural network models to address position deviation issues arising in UAV formation flights. The passive receiving signal UAV positioning model is established by applying the triangular cosine theorem. Additionally, the position relationship model of the UAV is formulated using optimization theory. The article introduces a deep learning-based deviated UAV adjustment algorithm designed to automatically adjust UAV positions. This is achieved by establishing a triangular relationship between the passive signal receiving UAV and other UAVs. The implementation involves C# programming and MATLAB visualization. The proposed method not only resolves UAV positioning and position adjustment challenges but also optimizes the adjustment strategy. This optimization leads to maximum savings in time and distance costs associated with sending and receiving signals among UAVs, thereby enhancing the overall performance of UAVs during flights. © 2024 John Wiley & Sons Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Asymmetric scattering behaviors of spin wave dependent on magnetic vortex chirality

引用

Chinese Physics B 2023年第10期32卷 635-640页

作者：张雪枫沈帝虎马晓萍宋成于海明朴红光 Hubei Engineering Research Center of Weak Magnetic-Field Detection China Three Gorges UniversityYichang 443002China Department of Physics College of ScienceYanbian UniversityYanji 133002China Key Laboratory of Advanced Materials(MOE) School of Materials Science and EngineeringTsinghua UniversityBeijing 100084China Fert Beijing Institute School of Integrated Circuit Science and EngineeringBeijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China

We investigate asymmetric spin wave scattering behaviors caused by vortex chirality in a cross-shaped ferromagnetic system by using the micromagnetic *** the system,four scattering behaviors are found:(i)asymmetric skew scattering,depending on the polarity of vortex core,(ii)back scattering(reflection),depending on the vortex core stiffness,(iii)side deflection scattering,depending on structural symmetry of the vortex circulation,and(iv)geometrical scattering,depending on waveguide *** first and second scattering behaviors are attributed to nonlinear topological magnon spin Hall effect related to magnon spin-transfer torque effect,which has value for magnonic exploration and application.

关键词： magnonics magnetic vortex spin wave magnetic chirality

来源：评论

学校读者我要写书评

暂无评论

Robust Watermarking Algorithm for Medical Volume data Based on Polar Cosine Transform and 3D-DCT

引用

Computers, Materials & Continua 2023年第6期75卷 5853-5870页

作者： Pengju Zhang Jingbing Li Uzair Aslam Bhatti Jing Liu Yen-wei Chen Dekai Li Lei Cao School of Information and Communication Engineering Hainan UniversityHaikou570100China State Key Laboratory of Marine Resource Utilization in the South China Sea Hainan UniversityHaikou570100China Research Center for Healthcare Data Science Zhejiang LabHangzhou311121China Graduate School of Information Science and Engineering Ritsumeikan UniversityKyoto5258577Japan

The amount of 3D data stored and transmitted in the Internet of Medical Things(IoMT)is increasing,making protecting these medical data increasingly ***,there are relatively few researches on 3D data ***,due to the particularity of medical data,strict data quality should be considered while protecting data *** solve the problem,in the field of medical volume data,we proposed a robust watermarking algorithm based on Polar Cosine Transform and 3D-Discrete Cosine Transform(PCT and 3D-DCT).Each slice of the volume data was transformed by PCT to obtain feature row vector,and then the reshaped three-dimensional feature matrix was transformed by *** on the contour information of the volume data and the detail information of the inner slice,the visual feature vector was obtained by applying the per-ceptual *** addition,the watermark was encrypted by a multi-sensitive initial value Sine and Piecewise linear chaotic Mapping(SPM)system,and embedded as a zero *** key was stored in a third *** the same experimental conditions,when the volume data is rotated by 80 degrees,cut 25%along the Z axis,and the JPEG compression quality is 1%,the Normalized Correlation Coefficient(NC)of the extracted watermark is 0.80,0.89,and 1.00 respectively,which are significantly higher than the comparison algorithm.

关键词： Volume data watermark zero watermark SPM PCT and 3D-DCT

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：