检索结果-内蒙古大学图书馆

HOFD: An Outdated Fact Detector for Knowledge Bases

IEEE Transactions on Knowledge and Data Engineering 2023年第10期35卷 10775-10789页

作者： Hao, Shuang Chai, Chengliang Li, Guoliang Tang, Nan Wang, Ning Yu, Xiang Beijing Jiaotong University School of Computer and Information Technology Beijing100044 China Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing100044 China Beijing Institute of Technology School of Computer Science and Technology Beijing100811 China Beijing100190 China Qatar Computing Research Institute Hbku Doha34110 Qatar Huawei Company Gauss Department Beijing100031 China

Knowledge bases (KBs), which store high-quality information, are crucial for many applications, such as enhancing search results and serving as external sources for data cleaning. Not surprisingly, there exist outdated facts in most KBs due to the rapid change of information. Naturally, it is important to keep KBs up-to-date. Traditional wisdom has investigated the problem of using reference data (such as new facts extracted from the news) to detect outdated facts in KBs. However, existing approaches can only cover a small percentage of facts in KBs. In this paper, we propose HOFD, a novel human-in-the-loop approach for outdated fact detection in KBs. HOFD trains a binary classifier using features such as historical update frequency and update time of a fact to compute the likelihood of a fact in a KB to be outdated. Then, HOFD interacts with humans to verify whether a fact with high likelihood is indeed outdated. In addition, HOFD also uses logical rules to detect more outdated facts based on human feedback. The outdated facts detected by the logical rules will also be fed back to train the ML model further for data augmentation. Extensive experiments on real-world KBs, such as Yago and DBpedia, show the effectiveness of our solution. © 1989-2012 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Simulation of Computer Network information Security Assessment Model Based on Data Mining 2

Simulation of Computer Network Information Security Assessme...

引用

2nd International Conference on Artificial Intelligence and Autonomous Robot Systems, AIARS 2023

作者： Liu, Yanjia Yong, Xi Hua, Baojian Yang, Jianhua Institute of Computing Technology Chinese Academy of Sciences Beijing100086 China Ministry of Water Resources Information Centre Beijing100053 China University of Science and Technology of China School of Software Engineering Jiangsu Suzhou215123 China Beijing Sinohonour Computing Technology Beijing100029 China

ISBN: (纸本)9798350324358

With the continuous growth of scie & tech, network technology has been widely used, which has brought great convenience to people's life and work. However, the rapid improvement of network technology has also given network viruses an opportunity, which has caused harm to the information security of computer users. In order to improve the adaptability to the network environment, it is more effective to use data mining (DM) to prevent and control viruses. Through the use of this technology, the control effect of network security management can be improved, and the effective support for the later network security development can be realized. This article will discuss the related modes of DM, study the practical application of DM to computer network virus defense, and build a computer network information security assessment model based on DM. The simulation results show that the proposed model can achieve a recall rate of 94.8% and an accuracy rate of 95.5%, both of which are better than the random forest model. DM has been effectively applied in the stage of protecting computer network virus, which greatly improves the security of computer network system, and then ensures the stability of computer system operation. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Double Cancelable Hashing for Protecting Biometrics of Users in Crowd 18

Double Cancelable Hashing for Protecting Biometrics of Users...

引用

18th INDIAcom;11th International Conference on computing for Sustainable Global Development, INDIACom 2024

作者： Almutairi, Mishaal M. Apostolopoulou, Dimitra Stupples, David Sen, Adnan Ahmed Abi Yamin, Mohammad Halikias, George City University of London School of Science and Technology Dept. of Electrical and Electronic Engg London United Kingdom Islamic University Deanship of Information Technology Madinah Saudi Arabia The Australian National University School of Computing College of Engineering and Computer Science Canberra Australia University of Athens Department of Mathematics Greece

ISBN: (纸本)9789380544519

Smart gates are considered one of the most important methods for managing crowds. Often, methods of authentication and verification of users depend on the user's biometric fingerprints, such as hand or eye prints. Sending a picture of the fingerprint or eye to the server for verification is deemed unacceptable, especially in crowds, as it will significantly impact service performance in addition to imposing a heavy load on the network. Another, more serious challenge is related to the security and privacy of this data. If a user's fingerprint is stolen, it implies that all systems and services related to it, whether financial, medical, or otherwise, will be vulnerable to hacking. Unfortunately, the use of the traditional hash function is not sufficiently strong against a Replay Attack, and integration with blockchain requires substantial resources and suffers from delays that may impact the quality of sensitive services. In this paper, a Hash Function is proposed to enhance the level of privacy and security of biometric information. The hashing process will be doubled on one hand, and fog computing will be employed as an intermediary and additional protection on the other hand. Finally, the proposed technology will provide a solution to the problem of Relay Attack. The effectiveness and applicability of the proposed approach will be implemented and assessed. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Crowd management data privacy data security encryption hackers

来源：评论

学校读者我要写书评

暂无评论

Developing Algorithms for Adaptive Network Coding and Its Impact on Wireless Network Performance 5th

Developing Algorithms for Adaptive Network Coding and Its Im...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Garg, Aanchal Poornima, Selvaraj Savita Nachappa, M.N. Department of Electronic & Communication Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Adaptive network coding (ANC) is a recent technique used in Wi-Fi networks that utilizes coded transmissions to boost community performance. The concept at the back of ANC is to find the ideal combination of coded packets, considering channel conditions and network topology. By adjusting encoding techniques in response to converting environmental situations, ANC helps to maximize throughput and reduce overhead and latency. This paper proposes a set of rules for ANC that considers the evolution of channel situations to alter its encoding strategy dynamically. The proposed set of rules works by using remarks from previously transmitted packets to determine whether modifications to the current transmission scheme want to be made, which will improve community performance. The algorithm's effectiveness is then tested through simulations wherein the network's overall performance is compared to widespread Wi-Fi structures. Outcomes show that the set of rules can achieve sizable upgrades in network performance… © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Multi-Target Distributed Maximum Correntropy Kalman Filter 24

Multi-Target Distributed Maximum Correntropy Kalman Filter

引用

12th International Conference on Communications and Broadband Networking, ICCBN 2024

作者： Deng, Xingyu Han, Hongyu Zhang, Sheng Xu, Yin College of Computer Science and Visual Computing Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu610066 China The School of Information Science and Technology Southwest Jiaotong University Chengdu611756 China

ISBN: (纸本)9798400717109

Multi-target tracking in sensor networks is a challenging problem, especially in scenarios where sensor observations are limited. Conventional centralized Kalman filters and distributed Kalman filters (DKFs) require each sensor to observe all targets, which is often difficult to achieve in practical distributed applications. With this in mind, and inspired by the promising robustness of the maximum correntropy criterion in non-Gaussian noise environments, this paper proposes a novel multi-target distributed maximum correntropy Kalman filter, named MT-DMCKF. The proposed algorithm can operate effectively in distributed multi-target scenarios and provide accurate and consistent tracking performance even when the number of sensors mounted on targets is limited. Within a single period, the algorithm requires only one exchange of information among sensors, thus reducing communication overhead compared to existing distributed Kalman filters. Simulation experiments validate the effectiveness and robustness of the proposed MT-DMCKF. © 2024 ACM.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Characterizing Text Revisions to Better Support Collaborative

Characterizing Text Revisions to Better Support Collaborativ...

引用

2022 International Conference on Digital Transformation and Intelligence, ICDI 2022

作者： Ping, Tan Ping Verspoor, Karin Miller, Timothy Universiti Malaysia Sarawak Faculty of Computer Science and Information Technology Sarawk Malaysia School of Computing Technologies Royal Melbourne Institute of Technology Melbourne Australia School of Computing and Information Systems University of Melbourne Melbourne Australia

ISBN: (纸本)9798350397000

Despite advancement in collaborative writing tools, the track changes capability in modern editors remains limited to highlighting syntactic changes, with authors still required to manually read through each of the revisions. We envision a collaborative authoring system where an author could accept all minor edits first and then focus on the substantial changes. To support this, we define the task of significant revision identification as the task of identifying the revisions between two versions of a text according to one of four categories, i.e. formal, meaning preserving, micro-and macro-structure. Micro-structure change corresponds to minor meaning change while macro-structure change corresponds to major meaning change. Our main contribution is to define a computational approach to this task, by framing the task as bi-directional entailment between the original and revised sentences. An existing recognition of textual entailment (RTE) system is applied to evaluate whether the revised texts entails. We evaluate the approach through a novel corpus consisting of multiple versions of drafts of academic papers written by multiple authors, which were annotated with the four revision types by both authors and non-authors of the papers. The proposed bi-directional textual entailment approach performs better than baseline edit distance approaches, which is similar to the current track changes capability built into most word processors. © 2022 IEEE.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration 38

What Factors Affect Multi-Modal In-Context Learning? An In-D...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Qin, Libo Chen, Qiguang Fei, Hao Chen, Zhi Li, Min Che, Wanxiang School of Computer Science and Engineering Central South University China Research Center for Social Computing and Information Retrieval China Harbin Institute of Technology China Tsinghua University China ByteDance China

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: "What factors affect the performance of MM-ICL?" To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Missing Data Recovery for Downstream Learning in Low-Cost Environmental Sensor Networks 9

Missing Data Recovery for Downstream Learning in Low-Cost En...

引用

9th International Conference on information technology Trends, ITT 2023

作者： Agbo, Benjamin Al-Aqrabi, Hussain Alsboui, Tariq Hussain, Muhammad Hill, Richard Keele University School of Computing and Mathematics Keele United Kingdom Higher Colleges of Technology Faculty of Computer Information Science Sharjah United Arab Emirates University of Huddersfield School of Computing and Engineering Huddersfield United Kingdom

ISBN: (纸本)9798350327502

The development of low-cost sensor networks (LCSNs) has facilitated the generation of vast amounts of environmental monitoring data in air quality monitoring stations. State-of-the-art research has focused on developing robust models to detect and mitigate events which may impact societies. Making adequate predictions is important for meeting the sustainability needs of future generations. Therefore, quality data is required to produce accurate results for downstream analytics and visualisations. When dealing with large amounts of data, it is however common to observe numerous amounts of missing data. This is a challenge for data miners because various methods for data analysis only work well on complete datasets. A traditional approach to handling missing data is to discard instances of missing values and only use complete cases for analysis. However, research has shown that this approach is not practical especially when large amounts of data are missing. This led to an increased need to develop strategies for replacing missing values with plausible values through imputation. This study presents an imputation strategy called k-BFMVI for recovering missing values before training downstream regression models for low cost sensor calibration. Experiments simulated missingness from 10% to 40% using MCAR and MAR mechanisms and the performance of the proposed technique was measured against state-of-the-art techniques. Overall, the proposed algorithm recorded the best imputation accuracy as opposed to existing techniques and showed significant improvements on downstream learning. © 2023 IEEE.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Prediction Empowered with Federated Machine Learning

引用

Computers, Materials & Continua 2024年第4期79卷 963-981页

作者： Muhammad Umar Nasir Omar Kassem Khalil Karamath Ateeq Bassam SaleemAllah Almogadwy M.A.Khan Khan Muhammad Adnan Department of Computer Sciences Bahria University Lahore CampusLahore54000Pakistan Faculty of Information Technology Liwa CollegeAbu Dhabi20009UAE Department of Computing Skyline University CollegeSharjah999041UAE Department of Computer Science Taibah UniversityMedina42315Saudi Arabia Riphah School of Computing and Innovation Faculty of ComputingRiphah International UniversityLahore54000Pakistan Department of Software Faculty of Artificial Intelligence and SoftwareGachon UniversitySeongnam13120Korea

Cervical cancer is an intrusive cancer that imitates various women around the world. Cervical cancer ranks in thefourth position because of the leading death cause in its premature stages. The cervix which is the lower end of thevagina that connects the uterus and vagina forms a cancerous tumor very slowly. This pre-mature cancerous tumorin the cervix is deadly if it cannot be detected in the early stages. So, in this delineated study, the proposed approachuses federated machine learning with numerous machine learning solvers for the prediction of cervical cancer totrain the weights with varying neurons empowered fuzzed techniques to align the neurons, Internet of MedicalThings (IoMT) to fetch data and blockchain technology for data privacy and models protection from hazardousattacks. The proposed approach achieves the highest cervical cancer prediction accuracy of 99.26% and a 0.74%misprediction rate. So, the proposed approach shows the best prediction results of cervical cancer in its early stageswith the help of patient clinical records, and all medical professionals will get beneficial diagnosing approachesfrom this study and detect cervical cancer in its early stages which reduce the overall death ratio of women due tocervical cancer.

关键词： Cervical cancer federated machine learning neurons blockchain technology

来源：评论

学校读者我要写书评

暂无评论

Exploring Representations Learned via Self-Supervised Transfer Learning for Medical Image Classification 5th

Exploring Representations Learned via Self-Supervised Transf...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Devadas, Raghavendra M. Alam, Intekhab Raghavendra, R. Nautiyal, Kapish School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Electronic and Communication Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India

ISBN: (纸本)9789819780426

This paper gives a singular self-supervised transfer new technique for clinical image segmentation. The proposed method entails a deep state-of-the-art structure capable of learning strong feature representations by leveraging unlabelled records from a supply domain thru self-supervised techniques and then shifting those representations to a target domain. Experiments were conducted on medical photo segmentation datasets: manual mind tumor segmentation and chest X-ray segmentation. The proposed technique has improved the version's overall performance compared to the present baseline processes. It significantly improved over the self-supervised strategies, especially in the brain tumor segmentation dataset. The paper highlights capacity destiny guidelines for research in self-supervised transfer brand new for clinical picture segmentation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

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：