检索结果-内蒙古大学图书馆

33rd ACM Web Conference, WWW 2024

作者： Yue, Linan Liu, Qi Liu, Ye Gao, Weibo Yao, Fangzhou Li, Wenfeng Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Hefei China Douyin Vision Co. Ltd Beijing China

ISBN: (纸本)9798400701719

Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been proposed to address this problem. Among them, one solution is to diversify training distributions in vanilla classification by modifying the data environment, yet accessing the environment information is complex. Besides, another promising approach involves rationalization, extracting invariant rationales for predictions. However, extracting rationales is difficult due to limited learning signals, resulting in less accurate rationales and diminished predictions. To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of theclassification and therationalization module. Specifically, we first assume that multiple environments are available in theclassification module. Then, we introduce diverse training distributions using an environment-conditional generative network, enabling robust graph representations. Meanwhile, therationalization module employs a separator to identify relevant rationale subgraphs while the remaining non-rationale subgraphs are de-correlated with labels. Next, we align graph representations from theclassification module with rationale subgraph representations using the knowledge distillation methods, enhancing the learning signal for rationales. Finally, we infer multiple environments by gathering non-rationale representations and incorporate them into theclassification module for cooperative learning. Extensive experimental results on both benchmarks and synthetic datasets demonstrate the effectiveness of C2R. Code is available at https://***/yuelinan/Codes-of-C2R. © 2024 ACM.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Research on Cloud Health Privacy Information Protection Algorithm Based on data Mining 3rd

Research on Cloud Health Privacy Information Protection Algo...

引用

3rd EAI International Conference on IoT and big data Technologies for Health Care, IotCARE 2022

作者： Wang, Wennan Song, Shiyang Zhu, Linkai Su, Junyu Guo, Te Tang, Jinhai Academy of Management Guangdong University of Science and Technology Dongguan523083 China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai519099 China Information Technology School Hebei University of Economics and Business Shijiazhuang050061 China Institute of Data Science City University of Macau 999078 China

ISBN: (纸本)9783031335440

In the process of selecting privacy evaluation indicators, the original algorithm did not set the degree of protection risk, which resulted in a little error in the protection of privacy information, which affected the efficiency of data operation. A data mining-based cloud health privacy information protection algorithm was studied. Build a differential privacy information protection model, establish the connection relationship between users and information, and use trapezoidal distribution membership function to determine the sensitive attributes of privacy information. Set up health privacy information protection indicators on the cloud, evaluate the risks of privacy information protection, and classify them into three levels: high, medium and low. Based on data mining, the information privacy mode is extracted, and the minimum support threshold is used to judge the support of private information in the database. Set the privacy information protection algorithm in the way of data support estimation. Experimental results: in the given data set, the support error of the algorithm in this paper is within 1.5%, and the error of the traditional algorithm is more than 5%. With the increasing size of the data set, the execution time of the traditional algorithm is much higher than that of the algorithm in this paper, which shows that the design is effective. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Twitter Stance Detection via Neural Production Systems 48

Twitter Stance Detection via Neural Production Systems

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhang, Bowen Ding, Daijun Xu, Guangning Guo, Jinjin Huang, Zhichao Huang, Xu Shenzhen Technology University College of Big Data and Internet Shenzhen China Harbin Institute of Technology Computer Science & Technology Shenzhen China Jd Intelligent Cities Research Beijing China

ISBN: (纸本)9781728163277

Stance detection is an important task, which aims to classify the attitude of an opinionated text toward a given target. In this paper, we develop an interpretable neural production system for stance detection (NPS4SD). NPS4SD is an end-to-end deep learning model, which consists of a set of knowledge rules that are applied by binding with specific entities. NPS4SD consists of two main components: a pretrained model for learning the text representation and a variable binding network (VBN) to bind the knowledge rules with text entities. Extensive experiments are conducted to evaluate the effectiveness of the proposed NPS4SD model on three real-world datasets with in-domain, cross-target and zero-shot setups. Experimental results demonstrate that NPS4SD achieves substantially better performance than the strong competitors for the stance detection task. © 2023 IEEE.

关键词： deep neural network neural production system stance detection

来源：评论

学校读者我要写书评

暂无评论

A Cross-Modal Interactive Memory Network Based on Fine-Grained Medical Feature Extraction for Radiology Report Generation

A Cross-Modal Interactive Memory Network Based on Fine-Grain...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Ma, Xitong Kuang, Yuansen Yuan, Lin Tian, Cheng Zeng, Yijie Liu, Song Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

Radiology report generation is an essential task in the medical field, which aims to automate the generation of medical terminology descriptions of radiology images. However, this task currently suffers from several problems: 1) existing methods need to manually build knowledge graphs or templates (consuming time and effort) to introduce medical or prior knowledge to assist in report generation;2) previous models cannot handle the problem of data bias well (anomaly reports and anomaly descriptions make up only a tiny portion of the dataset), causing the models to ignore the learning of anomaly descriptions easily;3) existing approaches cannot robustly supervise the model, resulting in incomplete and inconsistent reports being generated. To address these issues, we propose a cross-modal interactive memory network based on fine-grained medical feature extraction. In our model, we design a cross-modal interactive memory network to automatically store and remember the required medical text knowledge and use this medical knowledge to help generate reports. Furthermore, we design an abnormal medical knowledge enhancement module to enhance the learning of abnormal fine-grained knowledge through the interaction of disease topics and their states to interact with text features. In addition, we design a cross-modal joint semantic loss unit to reduce semantic differences between different features and improve the visual representation ability of the model. We experimented and evaluated our model on MIMIC-CXR and IU-Xray datasets to compare with other baseline models. © 2024 IEEE.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Dynamic Charging and Path Planning for UAV-Powered Rechargeable WSNs Using Multi-Agent Deep Reinforcement Learning

引用

IEEE Transactions on Automation science and Engineering 2025年 22卷 15610-15626页

作者： Betalo, Mesfin Leranso Leng, Supeng Seid, Abegaz Mohammed Abishu, Hayla Nahom Erbad, Aiman Bai, Xiaoshan Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar Shenzhen University College of Mechatronics and Control Engineering National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Unmanned Aerial Vehicle (UAV)-powered 5G/6G networks integrated with rechargeable wireless sensor networks (RWSNs) offer promising solutions for extending system lifetime, collecting data, and providing computing services and power to sensor nodes (SNs). UAVs offer significant advantages, including exceptional mobility, cost-effective deployment, and the ability to be easily reprogrammed for a wide range of missions. However, the limited onboard power capacity of UAVs, coupled with the lack of dynamic and intelligent charging station (CS) management and inefficient path planning, can lead to SN failure in dynamic mobile environments. To address these challenges, we propose an energy-efficient laser-charged UAV (LCU)-enabled RWSN environment, wherein UAVs, powered by laser beams from ground-based stations, provide services, collect data, and transfer energy to SNs. We formulate a joint optimization problem involving power allocation, dynamic charging strategy (DCS), and path planning to minimize task completion time and sensor node death time. Given the NP-hard nature of the problem, we employ a stochastic game model based on a Markov decision process (MDP) for its solution. To solve this problem, we propose a deep reinforcement learning (DRL) based algorithm that enables real-time charging scheduling decisions while optimizing network performance. We introduce a multi-agent double deep Q-network (MA-DDQN) model to determine the optimal trajectories for all UAVs in large and complex environments. Simulation results demonstrate that the MA-DDQN approach outperforms state-of-the-art techniques, showing significant improvements in terms of average delay, energy consumption, and task completion time. © 2004-2012 IEEE.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

An Entity Relation Extraction Framework Based on Large Language Model and Multi-Tasks Iterative Prompt Engineering

An Entity Relation Extraction Framework Based on Large Langu...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Geng, Haibin Shi, Chenglong Jiang, Xuesong Kong, Zan Liu, Song Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

Document-level entity relation extraction is an important task in the field of natural language processing, which plays an important role in semantic understanding and knowledge graph construction. However, existing deep neural networks and graph neural networks models are limited by their performance and parameters number, which can not capture global semantics and have poor generalization ability. Furthermore, existing methods employing large language model for entity relation extraction do not establish good relationships among multi-tasks of entity relation extraction task, resulting in more information can not be effectively shared and transmitted between tasks. In addition, previous approaches can not effectively eliminate false entities and relationships. To solve these problems, we propose an entity relation extraction framework based on large language model and multi-tasks iterative prompt engineering. In our model, we design an iterative prompt engineering, which can better establish the relationship among multi-tasks, and ensure every task to obtain the optimal results. Moreover, we design semantic merging, group disambiguation and self-verification modules to eliminate the false entity relations and noise nodes. Additionally, we design summary prompts to provide sufficient global semantics for better text segmentation. Finally, we evaluated our model on wikiann, wikineural, ACE2005, CoNLL2003, CoNLL2004, and SciERC datasets and compared it with other baseline models. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Degraded Systems Based on Multiple Performance Indicators Constructed by Multiple Features

引用

IEEE Sensors Journal 2025年第11期25卷 19613-19631页

作者： Wu, Bin Shi, Hui Zeng, Jianchao Zhang, Xiaohong Wang, Zhijian Wang, Zuolu Taiyuan University of Science and Technology School of Electronic Information Engineering Taiyuan030024 China North University of China institute for Big Data and Visual Computing Taiyuan030051 China University of Huddersfield Centre for Efficiency and Performance Engineering HuddersfieldHD1 3DH United Kingdom

The health status assessment of industrial equipment is critical to fault prediction and health management technologies. To fully reflect system degradation and accurately predict the remaining useful life (RUL) of a system, the construction of multiple performance indicators is important. Thus, a new state-space model and RUL prediction method is proposed herein based on multiple indicators, considering the three correlation relationships among features and degradation indicators. First, according to the extracted and selected feature signals, various relationships such as the correlations among multiple features, multiple features and indicators, and multiple indicators are analyzed. Then an intuitive multi-indicator state-space model is established considering the three correlations and the identified degradation patterns. On this basis, three failure modes of the system are defined according to the multi-indicator complex correlation conditions, and the corresponding probability density function of the system RUL is calculated. Finally, the PHM2012 Challenge and XJTU-SY datasets are used as examples for experimental verification. Compared with other prediction methods, the proposed method can intuitively reflect the correlation between features and indicators, to solve the problem caused by the hidden random correlation. © 2001-2012 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

RAUIE: A Relation-Augmented Document-Level Event Extraction Model Based on UIE 5

RAUIE: A Relation-Augmented Document-Level Event Extraction ...

引用

5th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2024

作者： Liang, Yiyuan Jia, Hong Wang, Licai Huang, Yangchen Yang, Zhe Big Data Research and Development Center North China Institute of Computing Technology Beijing China Tsinghua University Department of Computer Science and Technology Beijing China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350385557

In document-level event extraction tasks, multiple event types often coexist within a document (the multi-event problem), and arguments may play different roles across different events (the argument intertwining problem). Existing methods often suffer from significantly reduced event extraction accuracy, mainly when focusing on scenarios with scarce annotated data and imbalanced event-type distributions. This paper emphasizes enhancing the correlation between event triggers and arguments to address these challenges. Therefore, we propose the Relation-Augmented UIE Model (RADIE), which introduces entity relationships into prompts using prompt-based learning and designs a relation-augmentation algorithm to improve the accuracy and completeness of event extraction. Experimental results demonstrate that this approach significantly outperforms baseline methods, mainly showcasing excellent performance on datasets with long-tail distributions. © 2024 IEEE.

关键词： document-level event extraction relation augment Universal Information Extraction

来源：评论

学校读者我要写书评

暂无评论

The Caching and Pricing Strategy for Information-Centric Networking with Advertisers’Participation

引用

China Communications 2024年第3期21卷 283-295页

作者： Zheng Quan Yan Wenliang Wu Rong Tan Xiaobin Yang Jian Yuan Liu Xu Zhenghuan Laboratory for Future Networks Department of AutomationUniversity of Science and Technology of ChinaHefei 230026China Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefei 230088China Institute of Advanced Technology University of Science and Technology of ChinaHefei 230088China Suzhou Nuclear Power Research Institute Suzhou 215004China National Engineering Laboratory for Public Safety Risk Perception and Control by Big Data(NEL-PSRPC) China Academy of Electronics and Information Technology of CETCBeijing 100041China

As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’***,the Information-Centric Networking(ICN)came into *** a technical point of view,ICN is a promising future network *** and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of *** current research on ICN pricing mechanism is focused on paid ***,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to *** this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN *** solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each *** extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.

关键词： advertisers cache free content Information-Centric Networking pricing strategy

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：