检索结果-内蒙古大学图书馆

2nd International Conference on Foundation and Large Language Models, FLLM 2024

作者： Mou, Yongli Chen, Hanbin Lode, Gwendolyn Isabella Truhn, Daniel Sowe, Sulayman Decker, Stefan University Hospital RWTH Aachen Department of Diagnostic and Interventional Radiology Germany RWTH Aachen University Computer Science 5 Germany Fraunhofer Institute for Applied Information Technology FIT Germany

ISBN: (纸本)9798350354799

Radiology reports are a critical source of information for patient diagnosis and treatment in the medical domain. However, the vast amount of data contained in these reports is often unstructured, making it challenging to extract and normalize relevant clinical entities. Named Entity Normalization (NEN) is essential for mapping these entities to a standard ontology, facilitating better data integration, retrieval, and analysis. In this paper, we introduce RadLink, a benchmark for NEN in radiology. RadLink builds upon 425 expert-annotated radiology reports from the RadGraph dataset, extending it for NEN by mapping entities to the Unified Medical Language System (UMLS) ontology. We employ a combination of morphological and semantic matching approaches to generate normalization annotations, followed by human review for validation. We aim to set a standard with our benchmark for evaluating NEN methods in the radiology domain, that facilitate interoperability across healthcare systems and accelerate medical research by providing structured, standardized data. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Predicting Chess Puzzle Difficulty with Transformers

arXiv

引用

arXiv 2024年

作者： Milosz, Szymon Kapusta, Pawel Institute of Applied Computer Science Lodz University of Technology Lodz Poland

This study addresses the challenge of quantifying chess puzzle difficulty - a complex task that combines elements of game theory and human cognition and underscores its critical role in effective chess training. We present GlickFormer, a novel transformer-based architecture that predicts chess puzzle difficulty by approximating the Glicko-2 rating system. Unlike conventional chess engines that optimize for game outcomes, GlickFormer models human perception of tactical patterns and problem-solving complexity. The proposed model utilizes a modified ChessFormer backbone for spatial feature extraction and incorporates temporal information via factorized transformer techniques. This approach enables the capture of both spatial chess piece arrangements and move sequences, effectively modeling spatio-temporal relationships relevant to difficulty assessment. Experimental evaluation was conducted on a dataset of over 4 million chess puzzles. Results demonstrate GlickFormer’s superior performance compared to the state-of-the-art ChessFormer baseline across multiple metrics. The algorithm’s performance has also been recognized through its competitive results in the IEEE BigData 2024 Cup: Predicting Chess Puzzle Difficulty competition, where it placed 11th. The insights gained from this study have implications for personalized chess training and broader applications in educational technology and cognitive modeling. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Stream-Based Active Learning for Regression with Dynamic Feature Selection 5

Stream-Based Active Learning for Regression with Dynamic Fea...

引用

5th International Conference on Transdisciplinary AI, TransAI 2023

作者： Cacciarelli, Davide Tyssedal, John Solve Kulahci, Murat Technical University of Denmark Department of Applied Mathematics and Computer Science Denmark Norwegian University of Science and Technology Department of Mathematical Sciences Norway Luleå University of Technology Technology and Social Sciences Department of Business Administration Sweden

ISBN: (纸本)9798350358018

In the era of big data, companies are increasingly driven to amass vast amounts of data, particularly in process industries where advanced sensor technologies are prevalent. However, obtaining accurate labels or product information through quality inspections can be prohibitively expensive. Active learning emerges as a promising approach to optimize data sampling by prioritizing the most informative data points. Nevertheless, active learning strategies heavily rely on predictive models that are iteratively updated. Aligning with the principles of data-centric AI, this study highlights the detrimental effects of passively incorporating all available process variables into a predictive model for guiding data collection. Specifically, in real-time sampling strategies based on online active learning, the inclusion of irrelevant features significantly hampers the efficiency of the learning process. © 2023 IEEE.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

Minimize Resource Cost for Containerized Microservices Under SLO via ML-Enhanced Layered Queueing Network Optimization 14

Minimize Resource Cost for Containerized Microservices Under...

引用

14th International Conference on Cloud Computing, Data science and Engineering, Confluence 2024

作者： Luan, Shao Shen, Hong School of Computer Science and Engineering Sun Yat-sen University China School of Engineering and Technology Central Queensland University Australia Macao Polytechnic University Faculty of Applied Sciences China

ISBN: (纸本)9798350344837

The microservice based architecture is widely used in large software systems. Despite its profound advantages, introduction of microservices brings in many challenges, especially in terms of autoscaling. Layered Queueing Network (LQN) as an effective mathematical formation for representing distributed systems can be used for modeling microservices and predicting microservices' performance. Traditional analysis methods solving LQN requires product-form solution and FCFS service discipline. Complex software design and unstable container environment is likely to prevent microservices from meeting these assumptions. To address this problem, we propose a novel autoscaling method using machine learning enhanced LQN optimization to minimize the total resource cost while satisfying the the requirement of Service Level Objectives (SLO). We adopt Deep Neural Networks (DNNs) to fit the submodels from LQN decomposition and propose a DNN based Method of Layers (MOL) to obtain the average response time metric. It avoids the drawbacks of the existing analytical methods. Applying particle swarm optimization to the DNN enhanced LQN, we present an effective method to search for the optimal resource allocation to containerized microservices that achieves our goal.. Experimental results show that our autoscaling method can reduce total CPU costs by 30% to 50% against baselines. © 2024 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Optimizing Patient Outcomes with AI and Predictive Analytics in Healthcare 65

Optimizing Patient Outcomes with AI and Predictive Analytics...

引用

65th IEEE Annual International Scientific Conference on Power and Electrical Engineering of Riga Technical University, RTUCON 2024

作者： Janjua, Jamshaid Iqbal Ghazal, Taher M. Abushiba, Walid Abbas, Sagheer Lahore Pakistan College of Arts & Science Applied Science University P.O.Box 5055 Manama Bahrain Center for Cyber Security Faculty of Information Science and Technology Selangor Bangi43600 Malaysia College of Engineering Applied Science University Bahrain PMU Department of Computer Science Al Khobar Saudi Arabia

ISBN: (纸本)9798350365771

Healthcare's integration with the emerging artificial intelligence, predictive analytics and health information exchange (HIE) system is currently undergoing a revolution. These emerging technologies are offering better diagnostic accuracies, more personalized treatments, and better patients' outcomes. Artificial Intelligence supported by data from either Electronic Health Records or other big data sources are increasing the accuracy of forecasting critical patient conditions such as disease developments, hospital readmission rates, and mortality risks in patients. These AI-empowered models ensure seamless data sharing between the care providers and promote operational interoperability. Challenges to overcome include issues of privacy of the data, the biases of the prediction algorithms, and the proper integration of the model into the currently established operational environments of healthcare providers. With these technologies combined, it will become possible to optimize patient's outcomes with the provision of data to empower real-time medical interventions. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Data collection of wireless sensor network based on trajectory optimization of laser-charged UAV

引用

High-Confidence Computing 2024年第2期4卷 116-128页

作者： Chuanwen Luo Jian Zhang Jin Qian Yi Hong Zhibo Chen Yunan Hou Xiujuan Zhang Yuqing Zhu School of Information Science and Technology Beijing Forestry UniversityBeijing 100083China Engineering Research Center for Forestry-Oriented Intelligent Information Processing of National Forestry and Grassland Administration Beijing 100083China College of Information Engineering Taizhou UniversityTaizhou 225300China School of Computer Science Qufu Normal UniversityRizhao 276826China Research Center of Applied Mathematics and Machine Intelligence Zhejiang LabHangzhou 311121China Department of Computer Science California State UniversityCA 90032USA

Unmanned Aerial Vehicle(UAV)can be used as wireless aerial mobile base station for collecting data from sensors in UAV-based Wireless Sensor Networks(WSNs),which is crucial for providing seamless services and improving the performance in the next generation wireless ***,since the UAV are powered by batteries with limited energy capacity,the UAV cannot complete data collection tasks of all sensors without energy replenishment when a large number of sensors are deployed over large monitoring *** overcome this problem,we study the Real-time Data Collection with Lasercharging UAV(RDCL)problem,where the UAV is utilized to collect data from a specified WSN and is recharged using Laser Beam Directors(LBDs).This problem aims to collect all sensory data from the WSN and transport it to the base station by optimizing the flight trajectory of UAV such that realtime data performance is ensured It has been proven that the RDCL problem is *** address this,we initially focus on studying two sub-problems,the Trajectory Optimization of UAV for Data Collection(TODC)problem and the Charging Trajectory Optimization of UAV(CTO)problem,whose objectives are to find the optimal flight plans of UAV in the data collection areas and charging areas,*** we propose an approximation algorithm to solve each of them with the constant ***,we present an approximation algorithm that utilizes the solutions obtained from TODC and CTO problems to address the RDCL ***,the proposed algorithm is verified by extensive simulations.

关键词： Wireless sensor networks Laser-charged UAV Trajectory optimization Data collection

来源：评论

学校读者我要写书评

暂无评论

Message Verification Protocol Based on Bilinear Pairings and Elliptic Curves for Enhanced Security in Vehicular Ad Hoc Networks

引用

computers, Materials & Continua 2024年第10期81卷 1029-1057页

作者： Vincent Omollo Nyangaresi Arkan A.Ghaib Hend Muslim Jasim Zaid Ameen Abduljabbar Junchao Ma Mustafa A.Al Sibahee Abdulla J.Y.Aldarwish Ali Hasan Ali Husam A.Neamah Department of Computer Science and Software Engineering Jaramogi Oginga Odinga University of Science and TechnologyBondo40601Kenya Department of Applied Electronics Saveetha School of EngineeringSIMATSChennaiTamilnadu602105India Information Technology Department Management Technical CollegeSouthern Technical UniversityBasrah61004Iraq Department of Computer Science College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq College of Big Data and Internet Shenzhen Technology UniversityShenzhen518118China Huazhong University of Science and Technology Shenzhen InstituteShenzhen518000China National Engineering Laboratory for Big Data System Computing Technology Shenzhen UniversityShenzhen518060China Computer Technology Engineering Department Iraq University CollegeBasrah61004Iraq Department of Mathematics College of Education for Pure SciencesUniversity of BasrahBasrah61004Iraq Institute of Mathematics University of DebrecenDebrecenH-4002Hungary Department of Electrical Engineering and Mechatronics Faculty of EngineeringUniversity of DebrecenDebrecen4028Hungary

Vehicular ad hoc networks(VANETs)provide intelligent navigation and efficient route management,resulting in time savings and cost reductions in the transportation ***,the exchange of beacons and messages over public channels among vehicles and roadside units renders these networks vulnerable to numerous attacks and privacy *** address these challenges,several privacy and security preservation protocols based on blockchain and public key cryptography have been proposed ***,most of these schemes are limited by a long execution time and massive communication costs,which make them inefficient for on-board units(OBUs).Additionally,some of them are still susceptible to many *** such,this study presents a novel protocol based on the fusion of elliptic curve cryptography(ECC)and bilinear pairing(BP)*** formal security analysis is accomplished using the Burrows–Abadi–Needham(BAN)logic,demonstrating that our scheme is verifiably *** proposed scheme’s informal security assessment also shows that it provides salient security features,such as non-repudiation,anonymity,and ***,the scheme is shown to be resilient against attacks,such as packet replays,forgeries,message falsifications,and *** the performance perspective,this protocol yields a 37.88%reduction in communication overheads and a 44.44%improvement in the supported security ***,the proposed scheme can be deployed in VANETs to provide robust security at low overheads.

关键词： Attacks bilinear elliptic curve cryptography(ECC) privacy security vehicular ad hoc network(VANET)

来源：评论

学校读者我要写书评

暂无评论

Practical Engineering Education: Use of collaborative robots in the context of Industry 5.0

Practical Engineering Education: Use of collaborative robots...

引用

2023 IEEE IFEES World Engineering Education Forum and Global Engineering Deans Council, WEEF-GEDC 2023

作者： Vogel, Christian Lindner, Fabian Kratzsch, Alexander Zittau/Görlitz University of Applied Science Faculty of Electrical Engineering and Computer Science Zittau Germany Zittau/Görlitz University of Applied Science Faculty of Business Administration and Engineering Zittau Germany Zittau/Görlitz University of Applied Science Institute of Process Technology Process Automation and Measuring Technology Zittau Germany

ISBN: (纸本)9798350316025

This scientific paper examines the use of collaborative robots in the context of Industry 5.0 and its impact on practical engineering education. The aim of this paper is to highlight the importance as well as the challenges of using robots in Industry 5.0 and to analyze how this can be integrated into engineering education. The paper discusses various aspects such as the technological advances, the need for interaction between humans and robots, and the competencies that engineers need in an increasingly digitalized working world. Furthermore, practical methods and approaches in engineering education at the Zittau/Görlitz University of applied sciences are presented to prepare students for the requirements of Industry 5.0. Additionally, a draft of a future interdisciplinary learning factory 5.0 will be presented, in which networked technologies with the focus on robotics run through various scenarios in the context of Industry 5.0 at different locations. © 2023 IEEE.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Application Research of computer Neural Network in Face Recognition Lending System of Library

Application Research of Computer Neural Network in Face Reco...

引用

2022 IEEE International Conference on Advances in Electrical Engineering and computer Applications, AEECA 2022

作者： Huang, Changjiang Zhan, Liuchun The College of Computer Science Guangzhou College of Applied Science and Technology Guangdong Guangzhou China The College of Computer and Information Engineering Guangzhou Huali College Guangdong Guangzhou China

ISBN: (数字)9781665480901

ISBN: (纸本)9781665480901

From the perspective of demand-driven knowledge flow, this paper constructs a combined structure model of three kinds of knowledge flows in university libraries: users and machines, users and librarians, and users and resources. At the same time, it analyzes the value characteristics of smart information services. On the basis of this, the overall structure of the intelligent information service platform of the university library is designed. The test results show that the intelligent face recognition borrowing system based on cloud computing has good accuracy, real-time performance and stability, reduces the burden and cost of local storage, and better meets the needs of users for intelligent borrowing. © 2022 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of State-of-the-Art Deep Learning Models for Road Surface Type Classification

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1275-1291页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayao56000Thailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research InstituteKing Mongkut’s University of Technology North BangkokBangkok10800Thailand

In recent years,as intelligent transportation systems(ITS)such as autonomous driving and advanced driver-assistance systems have become more popular,there has been a rise in the need for different sources of traffic situation *** classification of the road surface type,also known as the RST,is among the most essential of these situational data and can be utilized across the entirety of the ITS ***,the benefits of deep learning(DL)approaches for sensor-based RST classification have been demonstrated by automatic feature extraction without manual *** ability to extract important features is vital in making RST classification more *** work investigates the most recent advances in DL algorithms for sensor-based RST classification and explores appropriate feature extraction *** used different convolutional neural networks to understand the functional architecture better;we constructed an enhanced DL model called SE-ResNet,which uses residual connections and squeeze-and-excitation mod-ules to improve the classification *** experiments with a publicly available benchmark dataset,the passive vehicular sensors dataset,have shown that SE-ResNet outperforms other state-of-the-art *** proposed model achieved the highest accuracy of 98.41%and the highest F1-score of 98.19%when classifying surfaces into segments of dirt,cobblestone,or asphalt ***,the proposed model significantly outperforms DL networks(CNN,LSTM,and CNN-LSTM).The proposed RE-ResNet achieved the classification accuracies of asphalt roads at 98.98,cobblestone roads at 97.02,and dirt roads at 99.56%,respectively.

关键词： Road surface type classification deep learning inertial sensor deep pyramidal residual network squeeze-and-excitation module

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：