检索结果-内蒙古大学图书馆

OpenKG Chain:A Blockchain Infrastructure for Open Knowledge Graphs

data Intelligence 2021年第2期3卷 205-227页

作者： Huajun Chen Ning Hu Guilin Qi Haofen Wang Zhen Bi Jie Li Fan Yang College of Computer Science&AZFT Knowledge Engine Lab Zhejiang UniversityHangzhou 310058China Ontology Foundation Venture Drive#11-31Vision ExchangeSingapore 608526Singapore School of Computer Science and Engineering Southeast UniversityNanjing 211189China Intelligent Big Data Visualization Lab Tongji UniversityShanghai 200092China

The early concept of knowledge graph originates from the idea of the semantic Web,which aims at using structured graphs to model the knowledge of the world and record the relationships that exist between *** publishing knowledge bases as open data on the Web has gained significant *** China,Chinese Information Processing Society of China(CIPS)launched the OpenKG in 2015 to foster the development of Chinese Open Knowledge *** existing open knowledge-based programs,OpenKG chain is envisioned as a blockchain-based open knowledge *** article introduces the first attempt at the implementation of sharing knowledge graphs on OpenKG chain,a blockchain-based trust *** have completed the test of the underlying blockchain platform,and the on-chain test of OpenKG’s data set and tool set sharing as well as fine-grained knowledge crowdsourcing at the triple *** have also proposed novel definitions:K-Point and OpenKG Token,which can be considered to be a measurement of knowledge value and user value.1,033 knowledge contributors have been involved in two months of testing on the blockchain,and the cumulative number of on-chain recordings triggered by real knowledge consumers has reached 550,000 with an average daily peak value of more than 10,*** the first time,we have tested and realized on-chain sharing of knowledge at entity/triple granularity *** present,all operations on the data sets and tool sets at ***,as well as the triplets at OpenBase,are recorded on the chain,and corresponding value will also be generated and assigned in a trusted *** this effort,OpenKG chain looks forward to providing a more credible and traceable knowledge-sharing platform for the knowledge graph community.

关键词： Open knowledge graph Blockchain Decentralized distributed network Decentralized knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Coresets for near-convex functions 34

Coresets for near-convex functions

引用

34th Conference on Neural Information Processing Systems, NeurIPS 2020

作者： Tukan, Murad Maalouf, Alaa Feldman, Dan The Robotics and Big Data Lab. Department of Computer Science University of Haifa Haifa Israel

Coreset is usually a small weighted subset of n input points in Rd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the f-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and z-regression. Experimental results and open source are also provided. © 2020 Neural information processing systems foundation. All rights reserved.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification of Ocular Toxoplasmosis from Fundus Images with Residual Neural Networks

Multiclass Classification of Ocular Toxoplasmosis from Fundu...

引用

Iberian Conference on Information Systems and Technologies (CISTI)

作者： José Luis Vázquez Noguera Rodrigo Parra Verena Ojeda Miguel García-Torres Julio César Mello-Román Cynthia Villaba Olivia Cardozo Universidad Americana Asunción Paraguay Data Science and Big Data Lab Universidad Pablo de Olavide Spain Facultad Politécnica Universidad Nacional de Asunción San Lorenzo Paraguay Department of Ophthalmology Hospital General Pediátrico Niños de AcostaÑu Paraguay

Ocular toxoplasmosis (OT) is usually diagnosed by a specialist through the analysis of fundus images of the eye. Deep learning has been used to perform binary classification of the disease; however, to the best of our knowledge this is the first work that performs a multi-class classification to differentiate between active or inactive OT lesions which gives more information to the clinician when making the diagnosis. Using a predictive model to differentiate healthy eyes from others with different type of lesions can be useful to save time, help diagnose atypical cases and assist specialists with less experience. In this work, we investigate the application of a deep learning model to perform multi-class image classification of eye fundus images. A pretrained residual neural network is fine tuned on a dataset of samples collected at the Hospital de Cl\’inicas and Hospital General Pediátrico Acosta Nu medical centers from Asunci\’on, Paraguay. The proposed model results are highly promising, scoring sensitivity and specificity rates equal to 91% and 98% respectively. In order to replicate the results and continue researching this area an open data set of images of the eye fundus labeled by ophthalmologists is also published as part of this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IMAGINENET: TARGET SPEAKER EXTRACTION WITH INTERMITTENT VISUAL CUE THROUGH EMBEDDING INPAINTING

arXiv

引用

arXiv 2022年

作者： Pan, Zexu Wang, Wupeng Borsdorf, Marvin Li, Haizhou Singapore Department of Electrical and Computer Engineering Nus Singapore Machine Listening Lab University of Bremen Germany Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China

The speaker extraction technique seeks to single out the voice of a target speaker from the interfering voices in a speech mixture. Typically an auxiliary reference of the target speaker is used to form voluntary attention. Either a pre-recorded utterance or a synchronized lip movement in a video clip can serve as the auxiliary reference. The use of visual cue is not only feasible, but also effective due to its noise robustness, and becoming popular. However, it is difficult to guarantee that such parallel visual cue is always available in real-world applications where visual occlusion or intermittent communication can occur. In this paper, we study the audiovisual speaker extraction algorithms with intermittent visual cue. We propose a joint speaker extraction and visual embedding inpainting framework to explore the mutual benefits. To encourage the interaction between the two tasks, they are performed alternately with an interlacing structure and optimized jointly. We also propose two types of visual inpainting losses and study our proposed method with two types of popularly used visual embeddings. The experimental results show that we outperform the baseline in terms of signal quality, perceptual quality, and intelligibility. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Teaching resource recommendation for OBE based on kernel canonical correlation analysis

Teaching resource recommendation for OBE based on kernel can...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Wu Changqian Li Shaozi Lin Yaojin Yu Xiehua Key Laboratory of Big Data and Artificial Intelligence in University of Fujian Province MinNan Science and Technology University José Rizal University Quanzhou China School of Informatics Xiamen University Xiamen China School of Computer Science Lab of Data Science and Intelligence Application Minnan Normal University Zhangzhou China Key Laboratory of Big Data and Artificial Intelligence in University of Fujian Province MinNan Science and Technology University Quanzhou China

data mining is used to extract information from OBE teaching resources, then the teaching resources and user personality database are established to improve the effectiveness of resources recommendation on the online learning platform. The properties of teaching resources and user personality traits are analyzed using the kernel canonical correlation analysis algorithm, and teaching materials with a high correlation coefficient are chosen to recommend to users. The simulation results demonstrate that this proposed method has higher accuracy and more accurate recommended resources when compared to the widely used teaching resource recommendation techniques.

关键词： Correlation coefficient Correlation databases Simulation Education data mining Kernel

来源：评论

学校读者我要写书评

暂无评论

From General to Specific: Tailoring Large Language Models for Personalized Healthcare

arXiv

引用

arXiv 2024年

作者： Shi, Ruize Huang, Hong Zhou, Wei Yin, Kehan Zhao, Kai Zhao, Yun Huazhong University of Science and Technology Wuhan China Tongji Medical College China Hubei Maternity and Child Health Care Hospital China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

The rapid development of large language models (LLMs) has transformed many industries, including healthcare. However, previous medical LLMs have largely focused on leveraging general medical knowledge to provide responses, without accounting for patient variability and lacking true personalization at the individual level. To address this, we propose a novel method called personalized medical language model (PMLM), which explores and optimizes personalized LLMs through recommendation systems and reinforcement learning (RL). Specifically, by utilizing self-informed and peer-informed personalization, PMLM captures changes in behaviors and preferences to design initial personalized prompts tailored to individual needs. We further refine these initial personalized prompts through RL, ultimately enhancing the precision of LLM guidance. Notably, the personalized prompt are hard prompt, which grants PMLM high adaptability and reusability, allowing it to directly leverage high-quality proprietary LLMs. We evaluate PMLM using real-world obstetrics and gynecology data, and the experimental results demonstrate that PMLM achieves personalized responses, and it provides more refined and individualized services, offering a potential way for personalized medical LLMs. Copyright © 2024, The Authors. All rights reserved.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Container Anomaly Detection System Based on Rule Mining and Matching

Container Anomaly Detection System Based on Rule Mining and ...

引用

2022 International Conference on Blockchain Technology and Information Security, ICBCTIS 2022

作者： Yu, Daisong Xie, Yulai Long, Huachao Jin, Minpeng Li, Xuan School of Cyber Science and Engineering Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan China Wuhan National Lab for Optoelectronics F311 Wuhan China School of Computer Science Huazhong University of Science and Technology Wuhan China Nsfocus Inc. A9-3/F Optical Valley Software Park Wuhan China

ISBN: (数字)9781665496919

ISBN: (纸本)9781665496919

Compared with virtual machine technology, container technology is more and more popular by virtue of its excellent convenience and reliable security isolation. Containers will encounter various anomalies during operation. For maintenance personnel, a large number of abnormal logs makes the work of anomaly analysis very difficult, so anomaly detection technology is needed. In this paper, a container anomaly detection system based on rule mining and matching is proposed, which collects and simplifies the container's logs generated in the abnormal time period, then delivers them to association rule mining algorithm for rule mining and display rules to the maintainer who makes a decision after a simple analysis. The experimental results show that the rule mining algorithm can process log entries in less time consumption compared with traditional association rule mining algorithm, and container anomaly detection system can effectively help system administrator to locate anomalies. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

arXiv

引用

arXiv 2023年

作者： Zhang, Hangtao Yao, Zeming Zhang, Leo Yu Hu, Shengshan Chen, Chao Liew, Alan Li, Zhetao School of Cyber Science and Engineering Huazhong University of Science and Technology China Swinburne University of Technology Australia Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China RMIT University Australia Xiangtan University China

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks. © 2023, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning Approach for Multi-Topic Twitter Summarization 7

Multimodal Learning Approach for Multi-Topic Twitter Summari...

引用

7th International Conference on Cloud Computing and big data Analytics, ICCCBDA 2022

作者： Cao, Yangyang Wu, Yanmin Qi, Jinli Chen, Zizhong Chongqing Key Lab. of Compl. Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China ChongQing College of Electronic Engineering Department of Artificial Intelligence and Big Data ChongQing401331 China University of California Riverside Department of Computer Science and Engineering RiversideCA United States

ISBN: (纸本)9781665487115

Twitter summary is designed to filter out the content summary from lots of noisy tweets, which can be used for Twitter search, public opinion analysis, hot topic discovery, etc. But the existing Twitter summary methods mostly focus on individual topics or hot events, and there are few studies on Twitter summary with multi-Topic posts. For the sake of resolve this problem, we propose a Twitter summary method based on social network information and manifold learning, which can extract tweets covering multiple topics, and better integrates the topic information and structural information of the tweets. First, the multi-modal manifold learning method is improved, and the social network information is integrated. Second, in order to test the relevance of the tweet summary and the topic, a test method of topic membership is designed. What's more, due to the lack of evaluation data sets, the author built a manual evaluation dataset. Our experiments on large-scale real tweets demonstrate the effectiveness of our framework. © 2022 IEEE.

关键词： Cloud computing Social networking (online) Blogs Manuals big data Manifold learning Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Generalizable Black-Box Adversarial Attack with Meta Learning

arXiv

引用

arXiv 2023年

作者： Yin, Fei Zhang, Yong Wu, Baoyuan Feng, Yan Zhang, Jingyi Fan, Yanbo Yang, Yujiu Tsinghua Shenzhen International Graduate School Tsinghua University Beijing100190 China The School of Data Science Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen518172 China Tencent AI Lab Guangdong Shenzhen518057 China The Center for Future Media The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610056 China

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback information, existing query-based black-box attack methods often require many queries for attacking each benign example. To reduce query cost, we propose to utilize the feedback information across historical attacks, dubbed example-level adversarial transferability. Specifically, by treating the attack on each benign example as one task, we develop a meta-learning framework by training a meta generator to produce perturbations conditioned on benign examples. When attacking a new benign example, the meta generator can be quickly fine-tuned based on the feedback information of the new task as well as a few historical attacks to produce effective perturbations. Moreover, since the meta-train procedure consumes many queries to learn a generalizable generator, we utilize model-level adversarial transferability to train the meta generator on a white-box surrogate model, then transfer it to help the attack against the target model. The proposed framework with the two types of adversarial transferability can be naturally combined with any off-the-shelf query-based attack methods to boost their performance, which is verified by extensive experiments. The source code is available at https://***/SCLBD/MCG-Blackbox. Copyright © 2023, The Authors. All rights reserved.

关键词： Budget control

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：