检索结果-内蒙古大学图书馆

Harnessing language models for computational literature review of emerging AI topics

Information Processing and Management 2025年第6期62卷

作者： Chung, Jaemin Jeong, Byeongki Park, Young-Jae Jeong, Hwihun Lee, Jiho Yoon, Janghyeok Choi, Jaewoong Data Curation Center Korea Institute of Science and Technology Information Seoul02456 Korea Republic of Department of Industrial Engineering Konkuk University Seoul05029 Korea Republic of Digital Transformation Office SK Innovation Seoul03188 Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju61005 Korea Republic of Harvard Medical School Brigham and Women's Hospital BostonMA02115 United States AI Lab Neopons Inc. Daegu41260 Korea Republic of Department of Public Administration Korea University Seoul02841 Korea Republic of

As the ability to interpret and anticipate artificial intelligence (AI) research trends is becoming increasingly important, previous studies have highlighted the potential of computational literature review (CLR) within the AI domain. However, existing approaches may be limited in understanding domain-specific terminologies and complex contexts and delivering timely, forward-looking insights within the rapidly evolving AI landscape. As a remedy, this study proposes a systematic approach for effectively exploring AI landscapes using AI-specific pre-trained language model (PLM)-based topic modeling, and emergingness analysis. We newly adopt the PapersWithCode database, considering its credibility based on source codes and venue information, human-crafted tags (e.g., methods), and periodic updatability. The core components of the proposed approach are: (1) constructing a dynamic AI landscape to capture time-varying trends using AI-specific PLMs and unsupervised clustering;(2) assessing the emergingness of individual AI topics to deliver anticipatory insights;and (3) developing an interactive topic evolution map that traces the temporal transitions of key topics from their predecessors to successors. A case study of 18,870 papers on scaled dot-product attention mechanisms demonstrates the effectiveness of the proposed approach in understanding what AI topics can be identified as emerging, along with their defining characteristics, and the evolutionary pathways of a given target topic. Our systematic process and quantitative outcomes are expected to serve as complementary tools for strategic foresight and AI trend monitoring while contributing to academia by proposing the integration of new data sources and perspectives into AI-specific CLR. © 2025 Elsevier Ltd

关键词： AI landscape Attention mechanism Computational literature review Emergingness Pre-trained language model Unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

Visual explanations of machine learning model estimating charge states in quantum dots

arXiv

引用

arXiv 2022年

作者： Muto, Yui Nakaso, Takumi Shinozaki, Motoya Aizawa, Takumi Kitada, Takahito Nakajima, Takashi Delbecq, Matthieu R. Yoneda, Jun Takeda, Kenta Noiri, Akito Ludwig, Arne Wieck, Andreas D. Tarucha, Seigo Kanemura, Atsunori Shiga, Motoki Otsuka, Tomohiro Research Institute of Electrical Communication Tohoku University 2-1-1 Katahira Aoba-ku Sendai980-8577 Japan Department of Electronic Engineering Graduate School of Engineering Tohoku University Aoba 6-6-05 Aramaki Aoba-Ku Sendai980-8579 Japan LeapMind 28-1 Maruyama-cho Shibuya-ku Tokyo150-0044 Japan WPI Advanced Institute for Materials Research Tohoku University 2-1-1 Katahira Aoba-ku Sendai980-8577 Japan Center for Emergent Matter Science RIKEN 2-1 Hirosawa Saitama Wako351-0198 Japan Ruhr University Bochum Universitätsstraße 150 Bochum44801 Germany Unprecedented-scale Data Analytics Center Tohoku University 6-3 Aoba Aramakiaza Aoba-ku Sendai980-8578 Japan RIKEN Center for Advanced Intelligence Project 1-4-1 Nihonbashi Chuo-ku Tokyo103-0027 Japan Graduate School of Information Science Tohoku University 6-3-09 Aoba Aramaki-aza Aoba-ku Sendai980-8579 Japan Center for Science and Innovation in Spintronics Tohoku University 2-1-1 Katahira Aoba-ku Sendai980-8577 Japan

Charge state recognition in quantum dot devices is important in the preparation of quantum bits for quantum information processing. Toward auto-tuning of larger-scale quantum devices, automatic charge state recognition by machine learning has been demonstrated. For further development of this technology, an understanding of the operation of the machine learning model, which is usually a black box, will be useful. In this study, we analyze the explainability of the machine learning model estimating charge states in quantum dots by gradient-weighted class activation mapping, which identified class-discriminative regions for the predictions. The model predicts the state based on the change transition lines, indicating that human-like recognition is realized. We also demonstrate improvements of the model by utilizing feedback from the mapping results. Due to the simplicity of our simulation and pre-processing methods, our approach offers scalability without significant additional simulation costs, demonstrating its suitability for future quantum dot system expansions. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Dynamic analysis and multi-objective optimization of an integrated solar energy system for Zero-Energy residential complexes

引用

Energy Conversion and Management 2025年 341卷

作者： Saleh Mobayen Ehsanolah Assareh Ali Dezhdar Siamak Hoseinzadeh Davide Astiaso Garcia Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu Yunlin 640301 Taiwan Built Environment and Engineering Program College of Sport Health and Engineering (CoSHE) Victoria University Melbourne Australia Strategic Research Institute (SRI) Asia Pacific University of Technology and Innovation (APU) Technology Park Malaysia Kuala Lumpur Malaysia Department of Renewable Energy Technology Materials and Energy Research Center Dezful Branch Islamic Azad University Dezful Iran Department of Planning Design Technology of Architecture Sapienza University of Rome Via Flaminia 72 00196 Rome Italy Department of Astronautical Electrical and Energy Engineering Sapienza University of Rome Via Eudossiana 18 Rome Italy

This study introduces and evaluates a novel, integrated solar energy system for achieving sustainable and zero-energy residential buildings. The proposed system integrates photovoltaic-thermal (PVT) solar panels, heat pumps, electrolyzers, fuel cells, reverse osmosis desalination units, and thermal storage tanks to simultaneously supply electricity, heating, cooling, and potable water. A primary challenge in solar energy systems—the intermittency of energy production—is addressed using energy storage solutions, including hydrogen-based electrolysis and fuel cell systems, which stabilize the supply across day-night cycles. The energy system is designed to meet the energy demands of a 160-unit residential complex in San Diego, each unit covering 110 m 2 . A dynamic simulation over an entire year is performed using TRNSYS software. System optimization is conducted via Response Surface Methodology (RSM), targeting three objective functions: total power capacity, life cycle cost (LCC), and thermal comfort represented by the predicted percentage dissatisfied (PPD) index. Optimization system is based on five key decision variables: solar PVT area, fuel cell capacity, electrolyzer capacity, heat pump capacity, and hydrogen tank size. Results demonstrate that, under optimized configurations, the system achieves an annual electricity output of 29,145.8 kWh/year, an LCC of $894,228, and a PPD index of 6.8 %, fully meeting the residential complex’s electricity demand of 200 MWh/year. The results validate the effectiveness of the hybrid system in enhancing efficiency, ensuring system reliability, and mitigating environmental impacts, thus offering a scalable solution for zero-energy building applications.

关键词： Building Energy Solar PVT Panels Fuel Cell Heat Pump Multi-Objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Tunable schiff-based networks with different bonding sites for enhanced photocatalytic activity under visible-light irradiation: The effects of steric hindrance

引用

Environmental research 2024年 246卷 118200页

作者： Han Wang Piao Xu Eydhah Almatrafi Ziwei Wang Chengyun Zhou Ting Xiong Hong Qin Yangzhuo He Hailan Yang Zhuotong Zeng Guangming Zeng School of Metallurgy and Environment Central South University Changsha 410083 China Department of Dermatology Second Xiangya Hospital Central South University Changsha 410011 China College of Environmental Science and Engineering and Key Laboratory of Environmental Biology and Pollution Control (Ministry of Education) Hunan University Changsha 410082 China Center of Research Excellence in Renewable Energy and Power Systems Center of Excellence in Desalination Technology Department of Mechanical Engineering King Abdulaziz University Jeddah 21589 Saudi Arabia. College of Environmental Science and Engineering and Key Laboratory of Environmental Biology and Pollution Control (Ministry of Education) Hunan University Changsha 410082 China. Institute of Big Data and Internet Innovation Hunan University of Technology and Business Changsha 410205 China. Center of Research Excellence in Renewable Energy and Power Systems Center of Excellence in Desalination Technology Department of Mechanical Engineering King Abdulaziz University Jeddah 21589 Saudi Arabia. Electronic address: zgming@***.

Organic polymers hold great potential in photocatalysis considering their low cost, structural tailorability, and well-controlled degree of conjugation for efficient electron transfer. Among the polymers, Schiff base networks (SNWs) with high nitrogen content have been noticed. Herein, a series of SNWs is synthesized based on the melamine units and dialdehydes with different bonding sites. The chemical and structural variation caused by steric hindrance as well as the related photoelectric properties of the SNW samples are investigated, along with the application exploration on photocatalytic degradation and energy production. The results demonstrate that only SNW-o based on o-phthalaldehyde responds to visible light, which extends to over 550 nm. SNW-o shows the highest tetracycline degradation rate of 0.02516 min, under 60-min visible light irradiation. Moreover, the HO production of SNW-o is 2.14 times higher than that of g-CN. The enhanced photocatalytic activity could be ascribed to the enlarged visible light adsorption and intramolecular electron transfer. This study indicates the possibility to regulate the optical and electrical properties of organic photocatalysts on a molecular level, providing an effective strategy for rational supramolecular engineering to the applications of organic materials in photocatalysis.

关键词： H(2)O(2) production Photocatalytic degradation Schiff-based networks Steric hindrance Structure tunability

来源：评论

学校读者我要写书评

暂无评论

Knowledge-based semantic reasoning for creativity

引用

International Journal of Performability engineering 2020年第5期16卷 800-810页

作者： Jing, Delin Tian, Yingchun Zhang, Chi Yang, Changchun Yang, Hongji School of Information Science and Engineering Changzhou University Changzhou213164 China Aliyun School of Big Data Changzhou University Changzhou213164 China Collaborative Innovation Center of ETourism Tourism College Beijing Union University Beijing100101 China School of Informatics Leicester University LeicesterLE1 7RH United Kingdom

Creativity can be challenging in the idea generation process as it is hard to formalise and control. However, there are requirements for creative ideas in many fields. Generating new and inspirational ideas is mainly manual work, and it usually happens in the individual human mind or a group of persons. There is a lack of software systems to generate creative ideas automatically. In this paper, a prototype software system based on a semantic reasoning method is proposed for assisting creativity in the general idea generation process. The kernel algorithm of the system is a set of inference rules designed on the basis of semantic computing technologies and creativity techniques, which is the core of the semantic reasoning. The fundamental information supporting the inference are domains knowledge managed as ontology bases. Furthermore, a major recommender is designed and implemented by employing the proposed idea creation method to enhance the inspiration level of university choice for teenagers. As a prototype software system, the developed major recommender application proves the feasibility and innovation of the proposed method. © 2020 Totem Publisher, Inc. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

MXenes: MXenes: Synthesis, Optical Properties, and Applications in Ultrafast Photonics (Small 11/2021)

引用

Small 2021年第11期17卷

作者： Bo Fu Jingxuan Sun Cong Wang Ce Shang Lijun Xu Jiebo Li Han Zhang BUAA-CCMU Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine and Engineering Beihang University Beijing 100191 China Key Laboratory of Big Data-Based Precision Medicine Ministry of Industry and Information Technology Interdisciplinary Innovation Institute of Medicine and Engineering Beihang University Beijing 100191 China School of Instrumentation and Optoelectronic Engineering Beihang University Beijing 100191 China Shenzhen Engineering Laboratory of Phosphorene and Optoelectronics Collaborative Innovation Center for Optoelectronic Science and Technology College of Optoelectronic Engineering Shenzhen University Shenzhen 518060 China School of Biological Science and Medical Engineering Beihang University Beijing 100191 China Beijing Advanced Innovation Center for Biomedical Engineering Beihang University Beijing 100191 China

来源：评论

学校读者我要写书评

暂无评论

Distributed Attitude Coordination Control for Multiple Flexible Spacecraft with Communication Delays

Distributed Attitude Coordination Control for Multiple Flexi...

引用

第三十八届中国控制会议

作者： Yongxia Shi Qinglei Hu School of Automatic Science and Electrical Engineering Beihang University Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University

This paper addresses the attitude synchronization problem for multiple flexible spacecraft subject to directed communication topology. Taking the time delays of communication network into account, a distributed attitude coordination control scheme is proposed only through local information exchange. It is shown that the control law can not only guarantee that all spacecraft within a formation can track a common reference attitude synchronously, but also ensure the undesirable vibration induced by flexible attachments are perfectly suppressed even when only a subset of formation members have access to the reference attitude. The result is rigorously proved by resorting to the Lyapunov stability analysis and algebraic graph theory. Finally,simulation examples for attitude synchronization among three flexible spacecraft are provided to demonstrate the effectiveness of the proposed control algorithm.

关键词： Spacecraft Formation Flying Flexible Spacecraft Distributed Attitude Synchronization Communication Delays

来源：评论

学校读者我要写书评

暂无评论

Roadmap on data-Centric Materials science

arXiv

引用

arXiv 2024年

作者： Bauer, Stefan Benner, Peter Bereau, Tristan Blum, Volker Boley, Mario Carbogno, Christian Catlow, C.A. Richard Dehm, Gerhard Eibl, Sebastian Ernstorfer, Ralph Fekete, Ádám Foppa, Lucas Fratzl, Peter Freysoldt, Christoph Gault, Baptiste Ghiringhelli, Luca M. Giri, Sajal K. Gladyshev, Anton Goyal, Pawan Hattrick-Simpers, Jason Kabalan, Lara Karpov, Petr Khorrami, Mohammad S. Koch, Christoph Kokott, Sebastian Kosch, Thomas Kowalec, Igor Kremer, Kurt Leitherer, Andreas Li, Yue Liebscher, Christian H. Logsdail, Andrew J. Lu, Zhongwei Luong, Felix Marek, Andreas Merz, Florian Mianroodi, Jaber R. Neugebauer, Jörg Pei, Zongrui Purcell, Thomas A.R. Raabe, Dierk Rampp, Markus Rossi, Mariana Rost, Jan-Michael Saal, James Saalmann, Ulf Sasidhar, Kasturi Narasimha Saxena, Alaukik Sbailò, Luigi Scheidgen, Markus Schloz, Marcel Schmidt, Daniel F. Teshuva, Simon Trunschke, Annette Wei, Ye Weikum, Gerhard Xian, R. Patrick Yao, Yi Yin, Junqi Zhao, Meng Scheffler, Matthias School of Computation Information and Technology Technical University of Munich & Helmholtz AI Munich Germany Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Germany Institute for Theoretical Physics Heidelberg University Heidelberg Germany Thomas Lord Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States Monash University Department of Data Science and AI Melbourne Australia The NOMAD Laboratory The FHI of the Max-Planck-Gesellschaft IRIS-Adlershof of the Humboldt-Universität zu Berlin Berlin Germany School of Chemistry Cardiff University Cardiff United Kingdom Max-Planck-Institut für Eisenforschung GmbH Düsseldorf Germany Max Planck Computing and Data Facility Garching Germany Institute for Optics and Atomic Physics Technical University of Berlin Berlin Germany Physics Department and IRIS-Adlershof Humboldt Universität zu Berlin Berlin Germany Max Planck Institute of Colloids and Interfaces Potsdam Germany Department of Materials Imperial College London United Kingdom Department of Materials Science and Engineering Friedrich-Alexander Universität Erlangen-Nürnberg Germany Department of Chemistry Northwestern University Illinois United States Humboldt-Universität zu Berlin Department of Physics Berlin Germany Department of Materials Science and Engineering University of Toronto Toronto Canada STFC Hartree Centre Daresbury Laboratory Daresbury Warrington United Kingdom Molecular Simulations from First Principles e.V. Berlin Germany Humboldt-Universität zu Berlin Department of Computer Science Berlin Germany Max Planck Institute for Polymer Research Mainz Germany ICFO-Institut de Ciencies Fotoniques The Barcelona Institute of Science and Technology Castelldefels Barcelona Spain Lenovo HPC Innovation Center Stuttgart Germany New York University New York United States University of Arizona Biochemistry Department Arizona United States Max Planck Institute for the Structure an

science is and always has been based on data, but the terms ‘data-centric’ and the ‘4th paradigm’ of materials research indicate a radical change in how information is retrieved, handled and research is performed. It signifies a transformative shift towards managing vast data collections, digital repositories, and innovative data analytics methods. The integration of Artificial Intelligence (AI) and its subset Machine Learning (ML), has become pivotal in addressing all these challenges. This Roadmap on data-Centric Materials science explores fundamental concepts and methodologies, illustrating diverse applications in electronic-structure theory, soft matter theory, microstructure research, and experimental techniques like photoemission, atom probe tomography, and electron microscopy. While the roadmap delves into specific areas within the broad interdisciplinary field of materials science, the provided examples elucidate key concepts applicable to a wider range of topics. The discussed instances offer insights into addressing the multifaceted challenges encountered in contemporary materials research. © 2024, CC BY.

关键词： data Analytics

来源：评论

学校读者我要写书评

暂无评论

Information Interaction based Two-stream Neural Networks for Fatigue Detection

Information Interaction based Two-stream Neural Networks for...

引用

作者： Rui Huang Yan Wang School of Automation Science and Electrical Engineering Beihang University Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University

Fatigue driving is the primary cause of traffic *** fatigue detection has the characteristics of high real-time requirements and low complexity,shallow convolutional neural networks are often chosen as the deep learning framework for common fatigue detection ***,the capability of feature learning and abstraction of shallow network is limited by the depth of the *** this paper,multiple information interaction modules based on cross fully connected layer or bidirectional recurrent neural network are added to dual-stream neural networks for fatigue detection without changing the network *** results demonstrate the proposed information interaction modules greatly improve the accuracy of shallow network in fatigue detection while the additional time loss can be ***,these modules can be regarded as a way of information fusion and extended to behavior recognition and other deep learning tasks using multi-stream networks to alleviate the inconsistent distribution and representation of different streams.

关键词： Fatigue detection information interaction shallow networks deep learning behavior recognition

来源：评论

学校读者我要写书评

暂无评论

Research and Experiment on Dynamic Weight Pseudo-Inverse Control Allocation for Spacecraft Attitude Control System

Research and Experiment on Dynamic Weight Pseudo-Inverse Con...

引用

第三十八届中国控制会议

作者： Haoyang Yang Qinglei Hu School of Automation Science and Electrical Engineering Beihang University Beijing Advanced Innovation Center for Big-Data Based Precision Medicine Beihang University

This paper presents a control and allocation method to avoid the angular momentum and torque saturation of the reaction wheels. Due to the reaction wheels are hard to provide the acceleration torque at the maximum rotational speed, a novel dynamic weight pseudo-inverse allocation method based on the rotational speed of the reaction wheels is proposed ***, the proposed method is also able to reduce power usage by preventing the sustained high speed. To handle the torque saturation, a geometric saturated control law is proposed, and the system's asymptotical stability is proof by Lyapunov *** simulations and hardware-in-loop experiments validation are conducted to illustrate the effectiveness of the proposed method.

关键词： Attitude Control Allocation Strategy Reaction Wheels Angular Momentum Saturation Torque Saturation

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：