检索结果-内蒙古大学图书馆

Multimedia Tools and Applications 2024年第33期83卷 80103-80103页

作者： Bennour, Akram Boudraa, Merouane Siddiqi, Imran Al-Sarem, Mohammed Al-Shabi, Mohammed Ghabban, Fahad Laboratory of Mathematics Informatics and Systems (LAMIS) Echahid Cheikh Larbi Tebessi University Tebessa Algeria Xynoptik Pty Limited. Victoria Australia College of Computer Science and Engineering Taibah University Medina Saudi Arabia Department of Management Information System College of Business Administration Taibah University Medina Saudi Arabia

3DTeethSeg’22: 3D Teeth Scan Segmentation and Labeling Challenge

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ben-Hamadou, Achraf Smaoui, Oussama Rekik, Ahmed Pujades, Sergi Boyer, Edmond Lim, Hoyeon Kim, Minchang Lee, Minkyung Chung, Minyoung Shin, Yeong-Gil Leclercq, Mathieu Cevidanes, Lucia Prieto, Juan Carlos Zhuang, Shaojie Wei, Guangshun Cui, Zhiming Zhou, Yuanfeng Dascalu, Tudor Ibragimov, Bulat Yong, Tae-Hoon Ahn, Hong-Gi Kim, Wan Han, Jae-Hwan Choi, Byungsun van Nistelrooij, Niels Kempers, Steven Vinayahalingam, Shankeeth Strippoli, Julien Thollot, Aurélien Setbon, Hugo Trosset, Cyril Ladroit, Edouard Centre de Recherche en Numérique de Sfax Laboratory of Signals Systems Artificial Intelligence and Networks Technopôle de Sfax Sfax3021 Tunisia Udini 37 BD Aristide Briand Aix-en-Provence13100 France Inria Univ. Grenoble Alpes CNRS Grenoble INP LJK France Department of Computer Science and Engineering Seoul National University Korea Republic of School of Software Soongsil University Korea Republic of University of Michigan Ann Arbor United States University of North Carolina Chapel Hill United States Shandong University China ShanghaiTech University China Department of Computer Science University of Copenhagen Denmark Osstem Implant Co. Ltd. Seoul Korea Republic of Department of Oral and Maxillofacial Surgery Radboud University Nijmegen Medical Centre P.O. Box 9101 Nijmegen6500 HB Netherlands Department of Computing Science Radboud University Nijmegen Netherlands Department of Artificial Intelligence Radboud University Nijmegen Netherlands Berlin Institute of Health at Charité Universitätsmedizin Berlin Charitéplatz 1 Berlin10117 Germany

Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg’22 challenge was organized in conjunction with the International Conference on Medical Image Computing and computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg’22 challenge. The 3DTeethSeg’22 challenge code can be accessed at: https://***/abenhamadou/3DTeethSeg22 challenge. © 2023, CC BY-SA.

关键词： Object detection

Bioinspired double-layer thermogalvanic cells with engineered ionic gradients for high-efficiency waste heat recovery

学校读者我要写书评

暂无评论

Nano Energy 2025年 142卷

作者： Cheng Chi Xingyu Zhang Chen Shen Qi Hu Ze Liu Jiahao Hu Zhi Li Yang Li Xiaoli Yu Hao Xiao Zhaoquan Zhao Yuan Yao Xing Liang Hongwei Wu Xiaoze Du Key Laboratory of Power Station Energy Transfer Conversion and System of Ministry of Education School of Energy Power and Mechanical Engineering North China Electric Power University Beijing 102206 China State Key Laboratory of Clean Energy Utilization Department of Energy Engineering Zhejiang University Hangzhou 310027 China State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou 310027 China School of Computer Science and Mathematics Kingston University London KT1 2EE United Kingdom School of Physics Engineering and Computer Science University of Hertfordshire Hatfield AL10 9AB United Kingdom

Thermogalvanic cells (TGCs) have emerged as a promising technology for harvesting low-grade thermal energy, but their widespread application has been hindered by limited conversion efficiencies. A critical factor in enhancing TGC performance lies in establishing substantial ion concentration gradients, which remains challenging due to the inherent tendency of ion pairing. Here, we present a double-layer thermogalvanic cell (DTGC) architecture that spatially segregates redox pairs into two distinct gel layers, enabling unprecedented control over ion concentration gradients. This innovative design yields a single p-type gelatin-K 4 [Fe(CN) 6 ]/K 3 [Fe(CN) 6 ] DTGC unit with remarkable performance metrics of an open-circuit voltage of 220 mV, a power density of 1.73 mW m −2 K −2 , and a relative Carnot efficiency ( η r ) of 1.34 % at ΔT = 10 K, representing a tenfold improvement over conventional TGCs. Scaling up this technology, we demonstrate a modular thermoelectric generator comprising a 4 × 12 array of alternating p-type and n-type DTGCs, capable of delivering an output voltage exceeding 11.3 V at ΔT = 20 K, sufficient to directly power commercial LED lights and electronic displays. This work establishes a new paradigm for efficient low-grade thermal energy conversion, offering a scalable and practical solution for waste heat recovery applications.

关键词： Autonomous power generation Double-layer Thermogalvanic Cells Ionic thermoelectric materials Low-grade thermal energy

Synthesis Lectures on Computer Vision

学校读者我要写书评

暂无评论

Preface

Synthesis Lectures on computer Vision 2023年 Part F825卷 v-vi页

作者： Wan, Jun Escalera, Sergio Li, Stan Z. Guo, Guodong Escalante, Hugo Jair State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Mathematics and Informatics University of Barcelona and Computer Vision Center Barcelona Spain AI Lab Westlake University Hangzhou China Department of Computer Science and Electrical Engineering West Virginia University Morgantown China Department of Computer Science Instituto Nacional de Astrofísica Optica y Electrónica Puebla Mexico

Stable Gaussian process tracking control of antagonistic variable stiffness actuators

学校读者我要写书评

暂无评论

Scientific reports 2025年第1期15卷 19762页

作者： Zhigang Zou Wei Li Chenguang Yang Yongping Pan College of Mechatronics Engineering Guangdong Polytechnic Normal University Guangzhou 510665 China. School of Computer Science and Engineering Sun Yat-sen University Guangzhou 510006 China. School of Software Engineering Sun Yat-sen University Guangzhou 510006 China. Department of Computer Science University of Liverpool L69 3BX Liverpool UK. Peng Cheng Laboratory Shenzhen 518057 China. panyp@***. School of Mathematical Sciences Center for Applied Mathematics of Guangxi Guangxi Minzu University Nanning 530006 China. panyp@***.

The control of variable stiffness actuators (VSAs) is challenging because they have highly nonlinear characteristics and are difficult to model accurately. Classical control approaches using high control gains can make VSAs stiff, which alters the inherent compliance of VSAs. Iterative learning control can achieve high tracking accuracy for VSAs but generally lacks sufficient generalization. This study applies Gaussian process (GP) regression to design a stable tracking controller combining feedforward and low-gain feedback control actions for agonistic-antagonistic (AA) VSAs subjected to unknown dynamics. The GP model learns the inverse dynamics of AA-VSAs and provides model fidelity by the predicted variance. The stability analysis of the closed-loop system demonstrates that the tracking error is uniformly ultimately bounded and exponentially converges to a small ball under a given probability. Experiments on an AA-VSA named qbmove Advanced have validated the superiority of the proposed method with respect to tracking accuracy and generalization.

关键词： Compliant actuation Gaussian process Machine learning for control Motion control Variable stiffness actuator

DeepFlame: A deep learning empowered open-source platform for reacting flow simulations

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Mao, Runze Lin, Minqi Zhang, Yan Zhang, Tianhan John Xu, Zhi-Qin Chen, Zhi X. State Key Laboratory of Turbulence and Complex Systems Aeronautics and Astronautics College of Engineering Peking University Beijing100871 China Ai for Science Institute Beijing100080 China Caep Software Center for High Performance Numerical Simulation Beijing100088 China Institute of Applied Physics and Computational Mathematics Beijing100088 China Department of Mechanics and Aerospace Engineering SUSTech Shenzhen518055 China Institute of Natural Sciences School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China MOE-LSC Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai200240 China

Recent developments in deep learning have brought many inspirations for the scientific computing community and it is perceived as a promising method in accelerating the computationally demanding reacting flow simulations. In this work, we introduce DeepFlame, an open-source C++ platform with the capabilities of utilising machine learning algorithms and pre-trained models to solve for reactive flows. We combine the individual strengths of the computational fluid dynamics library OpenFOAM, machine learning framework Torch, and chemical kinetics program Cantera. The complexity of cross-library function and data interfacing (the core of DeepFlame) is minimised to achieve a simple and clear workflow for code maintenance, extension and upgrading. As a demonstration, we apply our recent work on deep learning for predicting chemical kinetics (Zhang et al. Combust. Flame vol. 245 pp. 112319, 2022) to highlight the potential of machine learning in accelerating reacting flow simulation. A thorough code validation is conducted via a broad range of canonical cases to assess its accuracy and efficiency. The results demonstrate that the convection-diffusion-reaction algorithms implemented in DeepFlame are robust and accurate for both steady-state and transient processes. In addition, a number of methods aiming to further improve the computational efficiency, e.g. dynamic load balancing and adaptive mesh refinement, are explored. Their performances are also evaluated and reported. With the deep learning method implemented in this work, a speed-up of two orders of magnitude is achieved in a simple hydrogen ignition case when performed on a medium-end graphics processing unit (GPU). Further gain in computational efficiency is expected for hydrocarbon and other complex fuels. A similar level of acceleration is obtained on an AI-specific chip - deep computing unit (DCU), highlighting the potential of DeepFlame in leveraging the next-generation computing architecture and hardware. © 202

关键词： Graphics processing unit

Learning offline: Memory replay in biological and artificial reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Roscow, Emma L. Chua, Raymond Costa, Rui Ponte Jones, Matt W. Lepora, Nathan Centre de Recerca Matemàtica Bellaterra Spain McGill University and Mila Montréal Canada Bristol Computational Neuroscience Unit Intelligent Systems Lab Department of Computer Science University of Bristol United Kingdom School of Physiology Pharmacology and Neuroscience University of Bristol Bristol United Kingdom Department of Engineering Mathematics Bristol Robotics Laboratory University of Bristol Bristol United Kingdom

Learning to act in an environment to maximise rewards is among the brain’s key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and artificial intelligence (AI) as a way to optimise decision- making. A common aspect of both biological and machine reinforcement learning is the reactivation of previously experienced episodes, referred to as replay. Replay is important for memory consolidation in biological neural networks, and is key to stabilising learning in deep neural networks. Here, we review recent developments concerning the functional roles of replay in the fields of neuroscience and AI. Complementary progress suggests how replay might support learning processes, including generalisation and continual learning, affording opportunities to transfer knowledge across the two fields to advance the understanding of biological and artificial learning and memory. © 2021, CC BY-SA.

关键词： Reinforcement learning

A unified CPM framework using the least-squares generalized finite difference method for surface PDEs

学校读者我要写书评

暂无评论

engineering with computers 2025年

作者： Tang, Zhuochao Fu, Zhuojia Chen, Meng Ling, Leevan School of Management Science and Engineering Anhui University of Technology Maanshan243002 China Key Laboratory of Multidisciplinary Management and Control of Complex Systems of Anhui Higher Education Institutes Maanshan243002 China Center for Numerical Simulation Software in Engineering and Sciences College of Mechanics and Materials Hohai University Nanjing211100 China Department of Mathematics Nanchang University Nanchang China Institute of Mathematics and Interdisciplinary Sciences Nanchang University Nanchang China Xinjiang Vocational and Technical University of Tianshan Kizilsu Kirgiz Autonomous Prefecture Nanchang China Department of Mathematics Hong Kong Baptist University Kowloon Tong Hong Kong

This paper introduces a novel framework, the unified closest point method (CPM) using the least-squares generalized finite difference method (LS-GFDM), to solve the surface partial differential equations (PDEs). Our approach addresses key limitations of existing embedding methods by unifying the computation of finite difference weights and interpolation into a single step, enabling efficient and reasonably accurate solutions on scattered data points. Unlike traditional CPM frameworks that rely on the finite difference method (FDM) and require interpolation to restrict solutions on the surface, potentially introducing additional errors, our LS-GFDM eliminates the need for interpolation. Furthermore, compared to the orthogonal gradient method (OrG) based on radial basis function (RBF) methods, which requires specialized data point arrangements, our method offers greater flexibility by accommodating any arbitrary point set. Higher-order schemes for LS-GFDM are easily achieved by increasing the order of the Taylor series expansion, and the method can be readily extended to other embedded methods. Numerical experiments demonstrate that the proposed framework is less sensitive to the narrow band domain size and showcases good effectiveness and robustness for solving surface PDEs. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Finite difference method

用于糖尿病培训的大型语言模型:一项前瞻性研究（英文）

学校读者我要写书评

暂无评论

science Bulletin 2025年第6期 934-942页

作者：李灏萱江泽铧管洲榆包玉倩刘月星胡婷婷李佳佳刘茹涵吴量程棣纪宏伟王勇王亚星 Carol Y.Cheung 郑颖丰王继红李震吴卫兵 Cynthia Ciwei Lim Yong Mong Bee Hong Chang Tan Elif I.Ekinci David C.Klonoff Justin B.Echouffo-Tcheugui Nestoras Mathioudakis Leonor Corsino Rafael Simó Charumathi Sabanayagam Gavin Siew Wei Tan 程景煜黄天荫李华婷蔡淳毛丽娟 Lee-Ling Lim 覃宇宗盛斌贾伟平 Shanghai University of Sport School of Clinical Medicine Beijing Tsinghua Changgung Hospital Tsinghua Medicine Tsinghua University Beijing Visual Science and Translational Eye Research Institute(BERI) Tsinghua Medicine Tsinghua University Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes MoE Key Lab of Artificial Intelligence Artificial Intelligence Institute Shanghai Jiao Tong University Department of Cardiology the Affiliated Hospital of Qingdao University CEMS NCMIS HCMS MADIS Academy of Mathematics and Systems Science Chinese Academy of Sciences School of Mathematics University of Chinese Academy of Sciences Chinese Academy of Sciences Key Laboratory of Systems Health Science of Zhejiang Province School of Life Science Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Beijing Institute of Ophthalmology Beijing Tongren Hospital Capital Medical University Beijing Ophthalmology and Visual Sciences Key Laboratory Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual ScienceGuangdong Provincial Clinical Research Center for Ocular Diseases Department of Renal Medicine Singapore General Hospital Sing Health-Duke Academic Medical Centre Department of Endocrinology Singapore General Hospital Department of Endocrinology Austin Health Department of Medicine The University of Melbourne(Austin Health) Australian Centre for Accelerating Diabetes Innovations(ACADI) The Univ

Diabetes poses a considerable global health challenge, with varying levels of diabetes knowledge among healthcare professionals, highlighting the importance of diabetes training. Large Language Models(LLMs)provide new insights into diabetes training, but their performance in diabetes-related queries remains uncertain, especially outside the English language like Chinese. We first evaluated the performance of ten LLMs: Chat GPT-3.5, Chat GPT-4.0, Google Bard, Lla MA-7B, Lla MA2-7B, Baidu ERNIE Bot, Ali Tongyi Qianwen, Med GPT, Huatuo GPT, and Chinese Lla MA2-7B on diabetes-related queries, based on the Chinese National Certificate Examination for Primary Diabetes Care in China(NCE-CPDC) and the English Specialty Certificate Examination in Endocrinology and Diabetes of Membership of the Royal College of Physicians of the United Kingdom. Second, we assessed the training of primary care physicians(PCPs) without and with the assistance of Chat GPT-4.0 in the NCE-CPDC examination to ascertain the reliability of LLMs as medical assistants. We found that Chat GPT-4.0 outperformed other LLMs in the English examination, achieving a passing accuracy of 62.50%, which was significantly higher than that of Google Bard, Lla MA-7B, and Lla MA2-7B. For the NCE-CPFC examination, Chat GPT-4.0, Ali Tongyi Qianwen, Baidu ERNIE Bot, Google Bard, Med GPT, and Chat GPT-3.5 successfully passed, whereas Lla MA2-7B, Huatuo GPT,Chinese LLa MA2-7B, and Lla MA-7B failed. Chat GPT-4.0(84.82%) surpassed all PCPs and assisted most PCPs in the NCE-CPDC examination(improving by 1%–6.13%). In summary, LLMs demonstrated outstanding competence for diabetes-related questions in both the Chinese and English language, and hold great potential to assist future diabetes training for physicians globally.

关键词：

Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ahmad, Muhammad Shabbir, Sidrah Roy, Swalpa Kumar Hong, Danfeng Wu, Xin Yao, Jing Khan, Adil Mehmood Mazzara, Manuel Distefano, Salvatore Chanussot, Jocelyn Department of Computer Science National University of Computer and Emerging Sciences Islamabad Chiniot-Faisalabad Campus Chiniot35400 Pakistan Dipartimento di Matematica e Informatica-MIFT University of Messina Messina98121 Italy Pakistan The Department of Computer Science and Engineering Jalpaiguri Government Engineering College West Bengal 735102 India The Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China The School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Fractional Signals and Systems Beijing100081 China The Institute of Data Science and Artificial Intelligence Innopolis University Innopolis 420500 Russia Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia The Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab Grenoble38000 France

Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies of the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral-features, spatial-features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines. © 2021, CC BY.

关键词： Surveys