检索结果-内蒙古大学图书馆

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Abdou, Mostafa Ravishankar, Vinit Barrett, Maria Belinkov, Yonatan Elliott, Desmond Søgaard, Anders Department of Computer Science University of Copenhagen Department of Informatics University of Oslo John A. Paulson School of Engineering and Applied Sciences Harvard University Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology

ISBN: (纸本)9781952148255

Large-scale pretrained language models are the major driving force behind recent improvements in performance on the Winograd Schema Challenge, a widely employed test of commonsense reasoning ability. We show, however, with a new diagnostic dataset, that these models are sensitive to linguistic perturbations of the Winograd examples that minimally affect human understanding. Our results highlight interesting differences between humans and language models: language models are more sensitive to number or gender alternations and synonym replacements than humans, and humans are more stable and consistent in their predictions, maintain a much higher absolute performance, and perform better on non-associative instances than associative ones. Overall, humans are correct more often than out-of-the-box models, and the models are sometimes right for the wrong reasons. Finally, we show that fine-tuning on a large, task-specific dataset can offer a solution to these issues. © 2020 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Interfacial magnetic characteristics of nearly compensated gadolinium iron garnet

引用

Physical Review Materials 2024年第4期8卷 044403-044403页

作者： Karthik Srinivasan Alexander J. Grutter Thomas E. Gage P. Quarterman Christy J. Kinane Andrew J. Caruana Guichuan Yu Javier Garcia-Barriocanal Sean Langridge Bethanie J. H. Stadler Department of Electrical and Computer Engineering University of Minnesota 200 Union Street SE Minneapolis Minnesota 55455 USA Department of Electrical and Computer Engineering Boise State University Boise Idaho 83725 USA NIST Center for Neutron Research National Institute of Standards and Technology Gaithersburg Maryland 20878 USA Center for Nanoscale Materials Argonne National Laboratory Lemont Illinois 60439 USA ISIS-Neutron and Muon Source STFC Rutherford Appleton Laboratory Didcot Oxfordshire OX11 0QX United Kingdom Characterization Facility University of Minnesota 100 Union Street SE Minneapolis Minnesota 55455 USA Institute of Informatics University of Minnesota 2231 6th Street SE Minneapolis Minnesota 55455 USA

Reports on spin Hall magnetoresistance, magnonic spin currents from thermal gradients, and spin transfer-torque magnetic random-access memory using compensated ferrimagnets largely discuss bulk magnetization but lack consideration of depth profiles or interfacial characteristics. Here, magnetic and structural characterization of profiles and interfaces was performed for nearly compensated gadolinium iron garnet (GdIG) thin films. X-ray diffraction and reciprocal space maps show that sputter deposited GdIG on Si is polycrystalline with the desired cubic garnet phase, and GdIG on gadolinium gallium garnet (GGG) is epitaxial with <0.06% compressive strain. Temperature-dependent magnetometry confirms the compensation temperatures of GGG/GdIG and Si/GdIG to be 285 and 260 K, respectively, both near room temperature. Interestingly, these measurements suggest the presence of unsaturated rare-earth moments, which result in a characteristic hysteresis between heating and cooling sequences in the magnetization-temperature curves at zero field. Depth-profile measurements from polarized neutron reflectometry (PNR) indicate up to 91% volume fraction in GdIG on Si. At the interface, PNR reveals a region containing magnetized Fe-doped GGG, a low-density GdIG at the GGG/GdIG interface, and a thin magnetically dead layer at the Si/GdIG interface. Cross-sectional transmission electron microscopy and energy dispersive x-ray spectroscopy confirm the assessment of PNR. The magnetic characteristics of interfacial regions are attributed to intermixing of Fe-Ga at the GGG/GdIG interface and the presence of amorphous Fe-Si at the Si/GdIG interface.

关键词： Ferrimagnetism Magnetic insulators Rare-earth magnetic materials Magnetization measurements Neutron reflectometry Scanning transmission electron microscopy Sputtering

来源：评论

学校读者我要写书评

暂无评论

Nonlinear consensus+innovations under correlated heavy-tailed noises: Mean square convergence rate and asymptotics

arXiv

引用

arXiv 2022年

作者： Vukovic, Manojlo Jakovetic, Dusan Bajovic, Dragana Kar, Soummya University of Novi Sad Faculty of Technical Sciences Department of Fundamental Sciences Serbia University of Novi Sad Faculty of Sciences Department of Mathematics and Informatics Serbia University of Novi Sad Faculty of Technical Sciences Department of Power Electronic and Communication Engineering Serbia Department of Electrical and Computer Engineering Carnegie Mellon University United States

We consider distributed recursive estimation of consensus+innovations type in the presence of heavy-tailed sensing and communication noises. We allow that the sensing and communication noises are mutually correlated while independent identically distributed (i.i.d.) in time, and that they may both have infinite moments of order higher than one (hence having infinite variances). Such heavy-tailed, infinite-variance noises are highly relevant in practice and are shown to occur, e.g., in dense internet of things (IoT) deployments. We develop a consensus+innovations distributed estimator that employs a general nonlinearity in both consensus and innovations steps to combat the noise. We establish the estimator’s almost sure convergence, asymptotic normality, and mean squared error (MSE) convergence. Moreover, we establish and explicitly quantify for the estimator a sublinear MSE convergence rate. We then quantify through analytical examples the effects of the nonlinearity choices and the noises correlation on the system performance. Finally, numerical examples corroborate our findings and verify that the proposed method works in the simultaneous heavy-tail communication-sensing noise setting, while existing methods fail under the same noise *** Codes 93E10, 93E35, 60G35, 94A13, 62M05 Copyright © 2022, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge

arXiv

引用

arXiv 2025年

作者： Luo, Gongning Xu, Mingwang Chen, Hongyu Liang, Xinjie Tao, Xing Ni, Dong Jeong, Hyunsu Kim, Chulhong Stock, Raphael Baumgartner, Michael Kirchhoff, Yannick Rokuss, Maximilian Maier-Hein, Klaus Yang, Zhikai Fan, Tianyu Boutry, Nicolas Tereshchenko, Dmitry Moine, Arthur Charmetant, Maximilien Sauer, Jan Du, Hao Bai, Xiang-Hui Raikar, Vipul Pai Montoya-Del-Angel, Ricardo Martí, Robert Luna, Miguel Lee, Dongmin Qayyum, Abdul Mazher, Moona Guo, Qihui Wang, Changyan Awasthi, Navchetan Zhao, Qiaochu Wang, Wei Wang, Kuanquan Wang, Qiucheng Dong, Suyu School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Department of Mathematics Faculty of Science National University of Singapore Singapore National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Laboratory Shenzhen University Shenzhen China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Pohang Korea Republic of Heidelberg Division of Medical Image Computing Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany Department of Biomedical Engineering and Health KTH Royal Institute of Technology Stockholm Sweden France FathomX Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Philips Research University of Girona Spain Department of Robotics and Mechatronics Engineering DGIST Korea Republic of Department of Interdisciplinary Studies of Artificial Intelligence DGIST Korea Republic of National Heart and Lung Institute Faculty of Medicine Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Lab School of Communication and Information Engineering Shanghai University Shanghai China Faculty of Science Mathematics and Computer Science Informatics Institute University of Amsterdam Amsterdam1090 GH Netherlands Department of Biomedical Engineering and Physics Amsterdam UMC Amsterdam1081 HV Netherlands Xi’an Jiaotong-Liverpool University China Department of Ultrasound Harbin Medical University Cancer Hospital No. 150 Haping Road Nangang

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of deaths. Automated 3D Breast Ultrasound (ABUS) is a newer approach for breast screening, which has many advantages over handheld mammography such as safety, speed, and higher detection rate of breast cancer. Tumor detection, segmentation, and classification are key components in the analysis of medical images, especially challenging in the context of 3D ABUS due to the significant variability in tumor size and shape, unclear tumor boundaries, and a low signal-to-noise ratio. The lack of publicly accessible, well-labeled ABUS datasets further hinders the advancement of systems for breast tumor analysis. Addressing this gap, we have organized the inaugural Tumor Detection, Segmentation, and Classification Challenge on Automated 3D Breast Ultrasound 2023 (TDSC-ABUS2023). This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis. In this paper, we summarize the top-performing algorithms from the challenge and provide critical analysis for ABUS image examination. We offer the TDSC-ABUS challenge as an open-access platform at https://***/ to benchmark and inspire future developments in1algorithmic research. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Pre-trained Language Models in Simple Knowledge Graph Question Answering

arXiv

引用

arXiv 2023年

作者： Hu, Nan Wu, Yike Qi, Guilin Min, Dehai Chen, Jiaoyan Pan, Jeff Z. Ali, Zafar School of Computer Science and Engineering Southeast University 2 Dongda Rd Jiangsu Nanjing211189 China Department of Computer Science The University of Manchester Oxford Rd ManchesterM13 9PL United Kingdom School of Informatics The University of Edinburgh 10 Crichton St EdinburghEH8 9AB United Kingdom

Large-scale pre-trained language models (PLMs) such as BERT have recently achieved great success and become a milestone in natural language processing (NLP). It is now the consensus of the NLP community to adopt PLMs as the backbone for downstream tasks. In recent works on knowledge graph question answering (KGQA), BERT or its variants have become necessary in their KGQA models. However, there is still a lack of comprehensive research and comparison of the performance of different PLMs in KGQA. To this end, we summarize two basic KGQA frameworks based on PLMs without additional neural network modules to compare the performance of nine PLMs in terms of accuracy and efficiency. In addition, we present three benchmarks for larger-scale KGs based on the popular SimpleQuestions benchmark to investigate the scalability of PLMs. We carefully analyze the results of all PLMs-based KGQA basic frameworks on these benchmarks and two other popular datasets, WebQuestionSP and FreebaseQA, and find that knowledge distillation techniques and knowledge enhancement methods in PLMs are promising for KGQA. Furthermore, we test ChatGPT, which has drawn a great deal of attention in the NLP community, demonstrating its impressive capabilities and limitations in zero-shot KGQA. We have released the code and benchmarks to promote the use of PLMs on KGQA. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Framework for standardizing digital health in resource-constrained settings: a case study of Uganda's digital health communication infrastructure

引用

Oxford open digital health 2024年第2期2卷 oqae018页

作者： Andrew Alunyu Egwar Mercy Rebekah Amiyo Josephine Nabukenya Department of Computer Engineering and Informatics Busitema University Tororo Uganda. Department of Information Systems Makerere University Kampala Uganda.

Uganda has several digital health interventions, but most are not interoperable, failing the goal of digitizing the healthcare environment. One major reason for this failure is that the implementations are not based on a common set of standards formally agreed upon by the country's health ministry. Therefore, Uganda and other countries that have fallen behind in standardizing their health systems need to implement and fast-track the formulation of contextual digital health standards. This study followed a design science approach to develop a framework for standardizing the digital health communication infrastructure. The design went through three cycles of design and improvement. Results show that 17 digital health stakeholders in Uganda who evaluated the framework agreed that they are suitable to guide standardization activities in Uganda. This study argues that other countries with digital health challenges similar to those in Uganda can adopt the framework.

关键词： ICT network communication infrastructure digital health eHealth interoperability standardization framework standards

来源：评论

学校读者我要写书评

暂无评论

WKLM-FA: A Web Application for Automated Human-computer Interaction Modeling of Web Form Filling Tasks 24

WKLM-FA: A Web Application for Automated Human-Computer Inte...

引用

24th Pan-Hellenic Conference on informatics, PCI 2020

作者： Karousos, Nikos Tatsis, Fotios Karousos, Dionisis Katsanos, Christos Xenos, Michalis Tselios, Nikos Hellenic Open University Patras Greece Imis Lab Department of Mechanical Engineering and Aeronautics University of Patras Greece Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Educational Sciences and Early Childhood Education Department University of Patras Greece Computer Engineering and Informatics Department University of Patras Patras Greece

ISBN: (纸本)9781450388979

This paper presents the web-based KLM-Form Analyzer (WKLM-FA), a web application that allows the automated estimation of time that a user needs to fill out a web form. Based on feedback from previous studies, this implementation comes to fulfill the need for a cross-platform application of human-computer interaction models, namely the Keystroke Level Model (KLM) and Fitts's Law. WKLM-FA is a new web-based implementation of the KLM-Form Analyzer (KLM-FA), a desktop application that we have developed in our previous work. WKLM-FA also provides additional functionality compared to KLM-FA, such as a user account mechanism, an evaluation tracking feature, and an admin panel to support multiuser functionality. WKLM-FA is the first online KLM-based time estimation tool for web forms and it can be easily used not only by HCI evaluators but also for educational purposes teaching the KLM and the Fitts's law. © 2020 ACM.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

AI in Industry: Real-World Applications and Case Studies

TechRxiv

引用

TechRxiv 2023年

作者： Rahmaniar, Wahyu Maarif, Alfian ul Haq, Qazi Mazhar Iskandar, Muchammad Edo Institute of Innovative Research Tokyo Institute of Technology Kanagawa226-8503 Japan Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55166 Indonesia International Bachelor Program in Informatics and Computer Science Yuan Ze University Taoyuan320315 Taiwan Ezy Industries Jakarta Indonesia

Artificial intelligence (AI) has advanced rapidly and is becoming a cornerstone technology that drives innovation and efficiency in various industries. This paper examines the real-world application of AI in multiple sectors, including healthcare, finance, agriculture, retail, energy, and automotive. Several case studies are described to understand better the practical applications, results, and challenges of implementing AI. While many industries have reaped enormous benefits from AI, inherent challenges include data privacy, the potential for bias, and the continuing demand for skilled labor. This comprehensive review aims to provide AI application insights to professionals and researchers. Thus, as AI grows, there may be challenges and avenues for future research. © 2023, CC BY.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Mapping and Visualization of Artificial Intelligence for Digital Economy Research: A Bibliometric Approach

Mapping and Visualization of Artificial Intelligence for Dig...

引用

International Conference of computer Science and Information Technology

作者： Fairuz Iqbal Maulana Agung Purnomo Andi Pramono Mohammad Nazir Arifin Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Entrepreneurship Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Informatics Engineering Study Program University of Madura Pamekasan Indonesia

ISBN: (纸本)9798350399080

Artificial Intelligence (AI) seems to be a disruptive technology that defines and reshapes the economy, more efficient industrial processes, new business models, and the service sector, becoming the development of different practices than before. The literature shows that it will be included in all fields and people's lives, as is the case in the digital economy. Artificial Intelligence for Digital Economy has not been studied significantly. This study uses bibliometric analysis to graphically map scientific publications and research trends in the Artificial Intelligence for Digital Economy sector around the world in the last ten years. The Scopus database was used to collect metadata information for this study, and VOSViewer was used to demonstrate bibliometric network mapping. We use an article selection procedure starting with the searched keywords and year constraints and then exporting the database to a RIS file format. Over the last ten years, we retrieved 540 scientific publications published between 2012 and 2021 from the Scopus database. From the data obtained, researchers at the Russian Federation have the most published papers indexed by Scopus among the most productive countries (N=131), the most productive authors are Petrenko, S.A. (N=4), and the most subject area is computer Science (N=246). We also use VOSViewer to map the Network Theme. This study recommends incorporating research subjects Artificial Intelligence for Digital Economy: Thing, Education, Platform, Global Economy, abbreviated as TEPGE research theme.

关键词： computer science Databases Bibliometrics Taxonomy Education Metadata Market research

来源：评论

学校读者我要写书评

暂无评论

SmartCHANGE: AI-based long-term health risk evaluation for driving behaviour change strategies in children and youth 3

SmartCHANGE: AI-based long-term health risk evaluation for d...

引用

3rd International Conference on Applied Mathematics and computer Science, ICAMCS 2023

作者： Rescic, Nina Alberts, Janna Altenburg, Teatske M. Chinapaw, Mai J. M. De Nigro, Antonio Fenoglio, Dario Gjoreski, Martin Gradisek, Anton Jurak, Gregor Kiourtis, Athanasios Kyriazis, Dimosthenis Langheinrich, Marc Mancuso, Elena Mavrogiorgou, Argyro Pechenizkiy, Mykola Pratola, Roberto Ribeiro, Jose Soric, Maroje Taj, Fawad Tammelin, Tuija H. Vastenburg, Martijn Vilanova, Anna Vrijkotte, Tanja G. M. Lustrek, Mitja Jožef Stefan Institute Department of Intelligent Systems Ljubljana Slovenia ConnectedCare Research & Development Nijmegen Netherlands Vrije Universiteit Amsterdam Amsterdam Public Health Research Institute Department of Public and Occupational Health Amsterdam Umc Amsterdam Netherlands Informatica S.p.A. Engineering Ingegneria Rome Italy Università della Svizzera Italiana Faculty of Informatics Lugano Switzerland University of Ljubljana Faculty of Sports Ljubljana Slovenia University of Piraeus Department of Digital Systems Piraeus Greece Eindhoven University of Technology Department of Mathematics and Computer Science Eindhoven Netherlands University of Porto Faculty of Sport Porto Portugal Jamk University of Applied Sciences Likes School of Health and Social Studies Jyväskylä Finland

ISBN: (纸本)9798350324266

The SmartCHANGE project, a Horizon-Europe Research & Innovation project that has been ongoing since May 2023 and is scheduled to conclude in April 2027, aims to develop AI-driven decision-support tools to identify and reduce the long-term risk of non-communicable chronic diseases (NCDs) in children and youth. NCDs have become a significant public health burden in developed countries, with common risk factors including obesity, low physical fitness, and unhealthy lifestyle habits. Childhood and adolescence are critical periods for establishing healthy habits, and early intervention can prevent or delay the onset of NCDs later in life. However, current tools for identifying high-risk individuals mainly focus on adults, leading to missed opportunities for early detection. The SmartCHANGE project aims to address this gap by creating trustworthy AI tools that accurately assess risk factors in children and youth and promote optimised strategies for risk reduction. The paper outlines the plan for the project from the project's proposed methodologies, including dataset utilisation, data cleaning, risk prediction models (basic and complex), and the implementation of federated learning. Additionally, it discusses user experience aspects such as participatory design, suggested applications, and the evaluation of project outcomes. © 2023 IEEE.

关键词： Health risks

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：