检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jeong, Minbyul Kang, Jaewoo Department of Computer Science and Engineering Korea University Seoul02841 Korea Republic of Interdisciplinary Graduate Program in Bioinformatics Korea University Seoul Korea Republic of AIGEN Sciences Seoul04778 Korea Republic of

Summary: Named entity recognition (NER) is a fundamental part of extracting information from documents in biomedical applications. A notable advantage of NER is its consistency in extracting biomedical entities in a document context. Although existing document NER models show consistent predictions, they still do not meet our expectations. We investigated whether the adjectives and prepositions within an entity cause a low label consistency, which results in inconsistent predictions. In this paper, we present our method, ConNER, which enhances the label dependency of modifiers (e.g., adjectives and prepositions) to achieve higher label agreement. ConNER refines the draft labels of the modifiers to improve the output representations of biomedical entities. The effectiveness of our method is demonstrated on four popular biomedical NER datasets;in particular, its efficacy is proved on two datasets with 7.5–8.6% absolute improvements in the F1 score. We interpret that our ConNER method is effective on datasets that have intrinsically low label consistency. In the qualitative analysis, we demonstrate how our approach makes the NER model generate consistent predictions. © 2022, CC BY-SA.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Literature Review: Drug Supply Chain and Neural Networks

A Literature Review: Drug Supply Chain and Neural Networks

引用

International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE)

作者： Gunadi Emmanuel Meyliana Achmad Nizar Hidayanto Harjanto Prabowo Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Fakultas Sains dan Teknologi Unika Katolik Musi Charitas Palembang Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Faculty of Computer Science Universitas Indonesia Depok Indonesia Management Departement BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia

The drug supply chain is an important variable that will be asked when there is a shortage of drugs. The distribution and storage of drugs require accurate predictions to support the drug supply chain. Many methods have been studied to obtain a high level of prediction accuracy. One of the methods used is an artificial neural network to recognize the pattern of drug demand. It is important to find breakthroughs in artificial neural network technology to anticipate drug shortages. This study seeks to identify and find challenges from previous research in drug supply management and drug demand prediction by utilizing neural networks over the past five years. From the seven sources used, 34 articles were selected based on inclusion criteria and keyword searches according to Kitchenham's systematic review methodology. The discussion areas of the selected articles are 29% in the Logistics and Inventory area, 20% Risk - Resilience, and 18% for Drug supply chain planning which is a description of the research development area. Integrated development provides room for the use of neural networks in these three correlated areas. The model for implementing neural networks in maintaining the continuity of drug shortages is always associated with policies adopted by all drug supply chain stakeholders to anticipate drug shortages.

关键词： Drugs Training Systematics Supply chains Artificial neural networks Prediction algorithms Planning

来源：评论

学校读者我要写书评

暂无评论

A Universal Framework for Accurate and Efficient Geometric Deep Learning of Molecular Systems

arXiv

引用

arXiv 2023年

作者： Zhang, Shuo Liu, Yang Xie, Lei Department of Computer Science Hunter College The City University of New York New York10065 United States Helen & Robert Appel Alzheimer’s Disease Research Institute Feil Family Brain & Mind Research Institute Weill Cornell Medicine Cornell University New York10065 United States Ph.D. Program in Computer Science The Graduate Center The City University of New York New York10016 United States

Molecular sciences address a wide range of problems involving molecules of different types and sizes and their complexes. Recently, geometric deep learning, especially Graph Neural Networks (GNNs), has shown promising performance in molecular science applications. However, most existing works often impose targeted inductive biases to a specific molecular system, and are inefficient when applied to macromolecules or large-scale tasks, thereby limiting their applications to many real-world problems. To address these challenges, we present PAMNet, a universal framework for accurately and efficiently learning the representations of three-dimensional (3D) molecules of varying sizes and types in any molecular system. Inspired by molecular mechanics, PAMNet induces a physics-informed bias to explicitly model local and non-local interactions and their combined effects. As a result, PAMNet can reduce expensive operations, making it time and memory efficient. In extensive benchmark studies, PAMNet outperforms state-of-the-art baselines regarding both accuracy and efficiency in three diverse learning tasks: small molecule properties, RNA 3D structures, and protein-ligand binding affinities. Our results highlight the potential for PAMNet in a broad range of molecular science applications. © 2023, CC BY.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Nernst-Ettingshausen effect in thin Pt and W films at low temperatures

arXiv

引用

arXiv 2023年

作者： Luo, Renjie Legvold, Tanner J. Chen, Liyang Natelson, Douglas Department of Physics and Astronomy Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Electrical and Computer Engineering Department of Materials Science and NanoEngineering Rice University HoustonTX77005 United States

As spin caloritronic measurements become increasingly common techniques for characterizing material properties, it is important to quantify potentially confounding effects. We report measurements of the Nernst-Ettingshausen response from room temperature to 5 K in thin film wires of Pt and W, metals commonly used as inverse spin Hall detectors in spin Seebeck characterization. Johnson-Nyquist noise thermometry is used to assess the temperature change of the metals with heater power at low temperatures, and the thermal path is analyzed via finite-element modeling. The Nernst-Ettingshausen response of W is found to be approximately temperature-independent, while the response of Pt increases at low temperatures. These results are discussed in the context of theoretical expectations and the possible role of magnetic impurities in Pt. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Enhancing UAV Spraying Efficiency through Payload Sensor Integration

Enhancing UAV Spraying Efficiency through Payload Sensor Int...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Celso O. Barcelos Leonardo A. Fagundes-Júnior Daniel C. Gandolfo Martin Saska Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Núcleo de Especialização em Robótica (NERo) Universidade Federal de Viçosa Viçosa MG Brazil Instituto de Automática National University of San Juan San Juan Argentine Department of Cybernetics Czech Technical University in Prague Prague Czech Republic

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

The use of UAVs has grown in recent years, leading to the prominence of various applications such as monitoring and inspection, search and rescue operations, dam and civil structure inspection, military applications, among others. One of the most relevant applications today is related to Precision Agriculture, which is the subject of this work. Our study analyzes the behavior of an Unmanned Autonomous Vehicle (UAV) used for spraying tasks. The variation of the payload is measured through a load sensor. This information indicates to the UAV the right time to return to the base for refueling or completion of the application. Experimental validation is carried out to assess the functionality of the payload sensor during flight operations. In addition, the dynamic compensation controller improves the navigation of the UAV, even in the presence of payload variations during the entire mission duration.

关键词： Precision agriculture Navigation Spraying Inspection Robot sensing systems Autonomous aerial vehicles Vehicle dynamics Monitoring Payloads Diseases

来源：评论

学校读者我要写书评

暂无评论

Tunable Source of Quantum-Correlated Photons with Integrated Pump Rejection in a Silicon CMOS Platform

Tunable Source of Quantum-Correlated Photons with Integrated...

引用

Frontiers in Optics + Laser science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021

作者： Fargas Cabanillas, Josep M. Kramnik, Danielius Ramesh, Anirudh Gentry, Cale M. Stojanović, Vladimir Kumar, Prem Popović, Miloš A. Department of Electrical and Computer Engineering Photonics Center Boston University BostonMA02215 United States Department of Electrical Engineering and Computer Science UC Berkeley BerkeleyCA94720 United States Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Department of Electrical Computer and Energy Engineering University of Colorado BoulderCO80309 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

ISBN: (纸本)9781557528209

A wavelength-tunable, silicon photon-pair source based on spontaneous four-wave mixing, integrated with a pump rejection filter in a single, flip-chip packaged CMOS chip, is demonstrated with a coincidence-to-accidentals ratio of 9.1 with no off-chip pump filtering. Frontiers in Optics / Laser science © Optica Publishing Group 2021.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Charging Models for MANO-based 5G Core Networks

Charging Models for MANO-based 5G Core Networks

引用

2020 International computer Symposium, ICS 2020

作者： Julien, Jean Jimmy Lin, Fuchun Joseph Yu, Chiao-Hsuan Hu, Wan-Hsun National Chiao Tung University Eecs International Graduate Program Hsinshu Taiwan National Chiao Tung University College of Computer Science Department of Computer Science Hsinshu Taiwan Chunghwa Telecom Chunghwa Telecom Laboratories Taipei Taiwan

ISBN: (纸本)9781728192550

SDN/NFV (Software Defined Network/Network Function Virtualization) are key technology enablers for 5G Core Networks. They will introduce new actors into the telecom ecosystem including Virtual Network Function (VNF) vendor, VNF market place, VNF as a Service (VNFaaS) provider and Network Function Virtualization Infrastructure as a Service (NFVIaaS) provider. These new actors will promote competition hence demand for more flexible pricing with new charging models. This research explores these charging models according to the new charging factors identified in SDN/NFV based on the MANO (MANagement and Orchestration) architecture defined by ETSI NFV Industry Specification Group. The results of our research provide a methodology for service providers and telecom operators to price their SDN/NFV products and services. © 2020 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Transistor placement for automatic cell synthesis through Boolean satisfiability 52

Transistor placement for automatic cell synthesis through Bo...

引用

52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020

作者： Cardoso, Maicon Bubolz, Andrei Cortadella, Jordi Rosa, Leomar Marques, Felipe Graduate Program in Computing Federal University of Pelotas Pelotas Brazil Department of Computer Science Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (纸本)9781728133201

This paper presents a new transistor placement method applied to the ASTRAN EDA tool, an open-source solution for the automatic design of complex digital gates. Although it currently reaches an optimized solution through a Threshold Accepting approach, ASTRAN does not guarantee a minimum-width placement. In this paper, a method based on Boolean satisfiability is proposed, ensuring an optimal solution for the transistor placement task through modeling the problem into a set of Boolean variables and clauses aware of four design rule constraints. Experiments comparing the proposed method and the current ASTRAN placement technique have shown reductions in the layout area. Furthermore, our method achieved a significant improvement regarding runtime, an essential feature for designing digital circuits and systems on-demand. © 2020 IEEE

关键词： Transistors

来源：评论

学校读者我要写书评

暂无评论

Computational Adoption in Cultural Heritage: A Systematic Literature Review

Computational Adoption in Cultural Heritage: A Systematic Li...

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Hendro Nindito Meyliana Harjanto Prabowo Achmad Nizar Hidayanto BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Faculty of Computer Science University of Indonesia Jakarta Indonesia

ISBN: (数字)9781728170718

ISBN: (纸本)9781728170725

Indonesia is a country that consists of islands and has various ethnic groups and customs in it. This condition causes Indonesia to have cultural heritage that must be maintained. On the one hand, the rapid advancement of computing technology has affected all aspects of life including the cultural field. This Systematic Literatur Review aims to determine the use of adoption technological or computing that are widely applied by cultural observers in Indonesia in order to maintain the heritage of the nation's ancestors. Published articles used in this research came from the process of filtering in five online databases based on a keyword search pattern then carried out with a content analysis process, the results filtered out as many as 25 relevant articles. The next process is to analyze the content of articles in the role of ICTs that are relevant to preserve cultural heritage. The findings contribute to a better understanding on recent research in cultural heritage and adoption of technologies to maintain cultural heritage in Indonesia.

关键词： Cultural differences computer science Information systems Databases Buildings Global communication Education

来源：评论

学校读者我要写书评

暂无评论

State of the Art Models for Fake News Detection Tasks

State of the Art Models for Fake News Detection Tasks

引用

2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020

作者： Antoun, Wissam Baly, Fady Achour, Rim Hussein, Amir Hajj, Hazem American University of Beirut Electrical and Computer Engineering Department Beirut Lebanon Graduate Program in Computational Science American University of Beirut Beirut Lebanon

ISBN: (数字)9781728148212

ISBN: (纸本)9781728148212

This paper presents state of the art methods for addressing three important challenges in automated fake news detection: fake news detection, domain identification, and bot identification in tweets. The proposed solutions achieved first place in a recent international competition on fake news. For fake news detection, we present two models. The winning model in the competition combines similarity between the embedding of each article's title and the embedding of the top five corresponding google search results. The new model relies on advances in Natural Language Understanding (NLU) end to end deep learning models to identify stylistic differences between legitimate and fake news articles. This second model was developed after the competition and outperforms the winning approach. For news domain detection, the winning model is a hybrid approach composed of named entity features concatenated with semantic embeddings derived from end to end models. For twitter bot detection, we propose to use the following features: duration between account creation and tweet date, presence of a tweet's link, presence of user's location, other tweet's features, and the tweets' metadata. Experiments include insights into the importance of the different features and the results indicate the superior performances of all proposed models. © 2020 IEEE.

关键词： Competition

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：