检索结果-内蒙古大学图书馆

arXiv 2024年

作者： de la Rosa, Ezequiel Reyes, Mauricio Liew, Sook-Lei Hutton, Alexandre Wiest, Roland Kaesmacher, Johannes Hanning, Uta Hakim, Arsany Zubal, Richard Valenzuela, Waldo Robben, David Sima, Diana M. Anania, Vincenzo Brys, Arne Meakin, James A. Mickan, Anne Broocks, Gabriel Heitkamp, Christian Gao, Shengbo Liang, Kongming Zhang, Ziji Siddiquee, Md Mahfuzur Rahman Myronenko, Andriy Ashtari, Pooya Van Huffel, Sabine Jeong, Hyun-Su Yoon, Chi-Ho Kim, Chulhong Huo, Jiayu Ourselin, Sebastien Sparks, Rachel Clèrigues, Albert Oliver, Arnau Lladó, Xavier Chalcroft, Liam Pappas, Ioannis Bertels, Jeroen Heylen, Ewout Moreau, Juliette Hatami, Nima Frindel, Carole Qayyum, Abdul Mazher, Moona Puig, Domenec Lin, Shao-Chieh Juan, Chun-Jung Hu, Tianxi Boone, Lyndon Goubran, Maged Liu, Yi-Jui Wegener, Susanne Kofler, Florian Ezhov, Ivan Shit, Suprosanna Hernandez Petzsche, Moritz R. Menze, Bjoern Kirschke, Jan S. Wiestler, Benedikt Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Informatics Technical University Munich Germany Icometrix Leuven Belgium ARTORG Center for Biomedical Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Switzerland University of Bern Bern Switzerland Chan Division of Occupational Science and Occupational Therapy University of Southern California Los AngelesCA United States Stevens Neuroimaging and Informatics Institute Department of Neurology Keck School of Medicine University of Southern California United States University Institute of Diagnostic and Interventional Neuroradiology Inselspital Bern Switzerland University Institute of Diagnostic and Interventional Neuroradiology University Hospital Bern Inselspital University of Bern Bern Switzerland Department of Diagnostic and Interventional neuroradiology University Medical Center Hamburg-Eppendorf Hamburg Germany Department of Medical Imaging Radboud University Medical Center Institute for Health Sciences Nijmegen Netherlands Deepwise AI Lab Beijing China Beijing University of Posts and Telecommunications Bejing China School of Computing and Augmented Intelligence Arizona State University TempeAZ United States NVIDIA Santa ClaraCA United States STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Pohang Korea Republic of School of Biomedical Engineering & Imaging Sciences King’s College London United Kingdom Institute of Computer Vision and Robotics University of Girona Spain Wellcome Centre for Human Neuroimaging University College London London United Kingdom Laboratory of Neuro Imaging Stevens Institute for Neuroimaging and Informatics Keck School of Medicine University of Southern California Los Angeles United States KU Leuven Leuven Belgium CREATIS Université Lyon1 CNRS UMR5220 INSERM U1206 INSA-Lyon Villeurbanne696

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES’22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. By assessing them against a hidden test set, we identified strengths, weaknesses, and potential biases. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model combines the individual algorithms’ strengths and achieved superior ischemic lesion detection and segmentation accuracy (median Dice score: 0.82, median lesion-wise F1 score: 0.86) on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers like lesion types and affected vascular territories. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm’s segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model’s generalizability (median Dice score: 0.82, median lesion-wise F1 score: 0.86). The algorithm’s outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)rad

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

H∞ Model-free Reinforcement Learning with Robust Stability Guarantee

arXiv

引用

arXiv 2019年

作者： Han, Minghao Zhang, Lixian Tian, Yuan Wang, Jun Pan, Wei Department of Control Science and Engineering Harbin Institute of Technology Department of Cognitive Robotics Delft University of Technology Department of Computer Science University College London

Reinforcement learning is showing great potentials in robotics applications, including autonomous driving, robot manipulation and locomotion. However, with complex uncertainties in the real-world environment, it is difficult to guarantee the successful generalization and sim-to-real transfer of learned policies theoretically. In this paper, we introduce and extend the idea of robust stability and H∞ control to design policies with both stability and robustness guarantee. Specifically, a sample-based approach for analyzing the Lyapunov stability and performance robustness of a learning-based control system is proposed. Based on the theoretical results, a maximum entropy algorithm is developed for searching Lyapunov function and designing a policy with provable robust stability guarantee. Without any specific domain knowledge, our method can find a policy that is robust to various uncertainties and generalizes well to different test environments. In our experiments, we show that our method achieves better robustness to both large impulsive disturbances and parametric variations in the environment than the state-of-art results in both robust and generic RL, as well as classic control. Anonymous code is available to reproduce the experimental results at https://***/RobustStabilityGuaranteeRL/RobustStabilityGuaranteeRL. Copyright © 2019, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Anchor-based spatio-temporal attention 3D convolutional networks for dynamic 3D point cloud sequences

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Chen, Muyao Liu, Hanwen Yang, Yehui Liu, Zhe Wang, Hesheng The Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China The Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China The Department of Computer Science and Technology University of Cambridge

With the rapid development of measurwement technology, LiDAR and depth cameras are widely used in the perception of the 3D environment. Recent learning based methods for robot perception most focus on the image or video, but deep learning methods for dynamic 3D point cloud sequences are underexplored. Therefore, developing efficient and accurate perception method compatible with these advanced instruments is pivotal to autonomous driving and service robots. An Anchor-based Spatio-Temporal Attention 3D Convolution operation (ASTA3DConv) is proposed in this paper to process dynamic 3D point cloud sequences. The proposed convolution operation builds a regular receptive field around each point by setting several virtual anchors around each point. The features of neighborhood points are firstly aggregated to each anchor based on the spatio-temporal attention mechanism. Then, anchor-based 3D convolution is adopted to aggregate these anchors' features to the core points. The proposed method makes better use of the structured information within the local region and learns spatio-temporal embedding features from dynamic 3D point cloud sequences. Anchor-based Spatio-Temporal Attention 3D Convolutional Neural Networks (ASTA3DCNNs) are built for classification and segmentation tasks based on the proposed ASTA3DConv and evaluated on action recognition and semantic segmentation tasks. The experiments and ablation studies on MSRAction3D and Synthia datasets demonstrate the superior performance and effectiveness of our method for dynamic 3D point cloud sequences. Our method achieves the state-of-the-art performance among the methods with dynamic 3D point cloud sequences as input on MSRAction3D and Synthia datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Off-Policy Q-Learning for Anti-Interference control of Multi-Player Systems ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 9189-9194页

作者： Jinna Li Zhenfei Xiao Tianyou Chai Frank. L. Lewis Sarangapani Jagannathan School of Information and Control Engineering Liaoning Shihua University Fushun 113001 China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang 110819 China UTA Research Institute the University of Texas at Arlington Arlington TX 76118 USA Department of Electrical and Computer Engineering Missouri University of Science and Technology Rolla MO 65409 USA

This paper develops a novel off-policy game Q-learning algorithm to solve the anti-interference control problem for discrete-time linear multi-player systems using only data without requiring system matrices to be known. The primary contribution of this paper lies in that the Q-learning strategy employed in the proposed algorithm is implemented in an off-policy policy iteration approach other than on-policy learning due to the well-known advantages of off-policy Q-learning over on-policy Q-learning. All of the players work hard together for the goal of minimizing their common performance index meanwhile defeating the disturbance that tries to maximize the specific performance index, and finally they reach the Nash equilibrium of the game resulting in satisfying disturbance attenuation condition. In order to find the solution to the Nash equilibrium, the anti-interference control problem is first transformed into an optimal control problem. Then an off-policy Q-learning algorithm is proposed in the framework of typical adaptive dynamic programming (ADP) and game architecture, such that control policies of all players can be learned using only measured data. Comparative simulation results are provided to verify the effectiveness of the proposed method.

关键词： H ∞ control off-policy Q-learning game theory Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Accurate object recognition for unmanned aerial vehicle electric power inspection using an improved YOLOv2 algorithm 4

Accurate object recognition for unmanned aerial vehicle elec...

引用

4th IEEE International Conference on Data science in Cyberspace, DSC 2019

作者： Chen, Qiang Gao, Yunyuan Peng, Yun Zhang, Jianhai Sun, Ke Intelligent Control and Robotics Institute Hangzhou Dianzi University Hangzhou China Department of Biomedical Engineering University of Houston Houston United States School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Hangzhou Chuangjiang Information Technology Co. Ltd. Hangzhou China

ISBN: (纸本)9781728145280

With the growing application of Unmanned Aerial Vehicle (UAV) in the electric power inspection, there is an increasing demand for accurate recognition of power tower components from a large number of pictures and videos. Traditional machine learning methods require feature extraction of, such as edge, color, texture, etc., are not suitable for the complex scene of the UAV electric power inspection. The end-toend object detection algorithm YOLOv2, offers overall high recognition accuracy and speed, but is less so in recognizing small targets. In this study, the YOLOv2 was improved by: 1)adding an additional passthrough layer to the original network to fuse more fine-grained features to improve the recognition capability for small targets, and 2) removing the redundant convolutional layers and reducing the number of the filters in the middle convolutional layers to simplify the network structure. The datasets are from Multi-rotor UAV inspection of high voltage transmission lines. Three types of power tower components including the tower, tower base, and signs are selected as recognition targets. Results showed that the mean average precision (mAP) of the improved model for three types of target recognition was increased to 98.19%, higher than that of the original one, and the recognition speed was increased by 35%. © 2019 IEEE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Metaproteomics in the One Health framework for unraveling microbial effectors in microbiomes

引用

Microbiome 2025年第1期13卷 134页

作者： Robert Heyer Maximilian Wolf Dirk Benndorf Sergio Uzzau Jana Seifert Lucia Grenga Martin Pabst Heike Schmitt Bart Mesuere Tim Van Den Bossche Sven-Bastiaan Haange Nico Jehmlich Mariagrazia Di Luca Manuel Ferrer Sergio Serrano-Villar Jean Armengaud Helge B Bode Patrick Hellwig Catherine Robbe Masselot Renaud Léonard Paul Wilmes Multidimensional Omics Analyses Group Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V. Bunsen-Kirchhoff-Straße 11 44139 Dortmund Germany. robert.heyer@ISAS.de. Multidimensional Omics Analyses Group Faculty of Technology Bielefeld University Universitätsstraße 25 33615 Bielefeld Germany. robert.heyer@ISAS.de. Multidimensional Omics Analyses Group Faculty of Technology Bielefeld University Universitätsstraße 25 33615 Bielefeld Germany. Bioprocess Engineering Otto-Von-Guericke University Magdeburg Universitätsplatz 2 39106 Magdeburg Germany. Bioprocess Engineering Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Sandtorstraße 1 39106 Magdeburg Germany. Applied Biosciences and Process Engineering Anhalt University of Applied Sciences Köthen Germany. Department of Biomedical Sciences University of Sassari 07100 Sassari Italy. Institute of Animal Science University of Hohenheim Emil-Wolff-Str Stuttgart Germany. HoLMiR - Hohenheim Center for Livestock Microbiome Research University of Hohenheim Leonore-Blosser-Reisen Weg Stuttgart Germany. Département Médicaments Et Technologies Pour La Santé (DMTS) Université Paris-Saclay CEA INRAE SPI Bagnols-Sur-Cèze France. Department of Biotechnology Delft University of Technology Delft The Netherlands. Institute for Infectious Disease Control National Institute for Public Health and the Environment (RIVM) Bilthoven The Netherlands. Department of Applied Mathematics Computer Science and Statistics Ghent University 9000 Ghent Belgium. VIB - UGent Center for Medical Biotechnology VIB 9052 Ghent Belgium. Department of Biomolecular Medicine Faculty of Medicine and Health Sciences Ghent University 9052 Ghent Belgium. Department of Molecular Toxicology Helmholtz-Centre for Environmental Research - UFZ GmbH Permoserstrasse 15 04318 Leipzig Germany. Department of Biology University of Pisa 56127 Pisa Italy. Instituto de Catalisis y Petroleoquimica (ICP) CSIC 28049 Madrid Sp

One Health seeks to integrate and balance the health of humans, animals, and environmental systems, which are intricately linked through microbiomes. These microbial communities exchange microbes and genes, influencing not only human and animal health but also key environmental, agricultural, and biotechnological processes. Preventing the emergence of pathogens as well as monitoring and controlling the composition of microbiomes through microbial effectors including virulence factors, toxins, antibiotics, non-ribosomal peptides, and viruses holds transformative potential. However, the mechanisms by which these microbial effectors shape microbiomes and their broader functional consequences for host and ecosystem health remain poorly understood. Metaproteomics offers a novel methodological framework as it provides insights into microbial dynamics by quantifying microbial biomass composition, metabolic functions, and detecting effectors like viruses, antimicrobial resistance proteins, and non-ribosomal peptides. Here, we highlight the potential of metaproteomics in elucidating microbial effectors and their impact on microbiomes and discuss their potential for modulating microbiomes to foster desired functions.

关键词： Metaproteomics Microbial community Bacteriophages Microbiome Microbial effectors

来源：评论

学校读者我要写书评

暂无评论

Discrete Fourier Transform based Virtual Constraint control of Powered Ankle-Foot Prosthesis

Discrete Fourier Transform based Virtual Constraint Control ...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Awais Naeem Mohsin Rizwan Hafiz Farhan Maqbool Muhammad Ahsan Ali Raza Syed Abbas Zilqurnain Naqvi Al-Khwarizmi Institute of Computer Science UET Lahore HCR Lab National Center of Robotics and Automation Lahore Pakistan Department of Mechatronics and Control Engineering National Center of Robotics and Automation Lahore Pakistan Department of Mechatronics and Control Engineering UET Lahore Lahore Pakistan

Active prosthetic devices have been controlled using several methods such as Echo control, EMG signal based Position control and Finite State Machine (FSM) based Impedance/Compliance control. This manuscript proposes Virtual Constraint control of active prosthesis which obviates any need for the classification of EMG signals, identification of the gait phase for state switching and potentially avoids an exhaustive procedure for the tuning of impedance parameters. In this paper, a Discrete Fourier Transform (DFT) based Virtual Constraint control is presented to characterize the ankle-foot joint trajectory as a function of the human-inspired phase variable in a unified manner. An optimization-based algorithm is employed for the robust generation of continuously monotonic and linear phase variable for DFT based Virtual Constraint control. The results are generalized across various walking speeds for a specific user during the level ground walking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of patient groups with sleep related disorders using bio-signal processing and deep learning

arXiv

引用

arXiv 2021年

作者： Jarchi, Delaram Andreu-Perez, Javier Kiani, Mehrin Vysata, Oldrich Kuchynka, Jiri Prochazka, Ales Sanei, Saeid Smart Health Technologies Group School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Embedded and Intelligent Systems Laboratory School of Computer Science and Electronics University of Essex ColchesterCO4 3SQ United Kingdom Department of Computing and Control Engineering University of Chemistry and Technology in Prague Prague 6166 28 Czech Republic Department of Neurology Faculty of Medicine in Hradec Králové Charles University Hradec Králové500 05 Czech Republic Czech Institute of Informatics Robotics and Cybernetics Czech Technical University in Prague Prague 6160 00 Czech Republic School of Science and Technology Nottingham Trent University NottinghamNG11 8NS United Kingdom

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem. © 2021, CC BY-NC-ND.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization

arXiv

引用

arXiv 2020年

作者： Yi, Xinlei Zhang, Shengjun Yang, Tao Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Department of Electrical Engineering University of North Texas DentonTX76203 United States The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China

The distributed nonconvex optimization problem of minimizing a global cost function formed by a sum of n local cost functions by using local information exchange is considered. This problem is an important component of many machine learning techniques with data parallelism, such as deep learning and federated learning. We propose a distributed primal–dual stochastic gradient descent (SGD) algorithm, suitable for arbitrarily connected communication networks and any smooth (possibly nonconvex) cost functions. We show that the proposed algorithm achieves the linear speedup convergence rate O(1/√nT) for general nonconvex cost functions and the linear speedup convergence rate O(1/(nT)) when the global cost function satisfies the Polyak–Lojasiewicz (P–L) condition, where T is the total number of iterations. We also show that the output of the proposed algorithm with constant parameters linearly converges to a neighborhood of a global optimum. We demonstrate through numerical experiments the efficiency of our algorithm in comparison with the baseline centralized SGD and recently proposed distributed SGD algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Front Cover: Micrometer-Sized Liposome-Based Systems: A Hierarchical Breakdown (ChemSystemsChem 3/2025)

ChemSystemsChem

引用

ChemSystemsChem 2025年第3期7卷

作者： Prof. Dr. Shogo Hamada Dr. Hironori Sugiyama Prof. Dr. Yiting Zhang Prof. Dr. Shoji Iwabuchi Soichiro Hiroi Toshiki Maruyama Yuktesh Balaji Sota Kumagai Prof. Dr. Satoshi Murata Prof. Dr. Taro Toyota Department of Computer Science School of Computing & Department of Systems and Control Engineering School of Engineering Institute of Science Tokyo 4259 Nagatsuta-cho Midori-ku Yokohama-city Kanagawa 226-8501 Japan These authors contributed equally. Department of Applied Chemistry Graduate School of Engineering The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-8656 Japan Department of Chemistry College of Science Rikkyo University 3-34-1 Nishi-Ikebukuro Toshima-ku Tokyo 171-8501 Japan Department of Biotechnology and Life Science Tokyo University of Agriculture and Technology 2-24-16 Naka-cho Koganei-shi Tokyo 185-8588 Japan Department of Basic Science Graduate School of Arts and Sciences The University of Tokyo 3-8-1 Komaba Meguro-ku Tokyo 153-8902 Japan Department of Robotics Graduate School of Engineering Tohoku University 6-6-01 Aramaki-Aza Aoba Aoba-ku Sendai Miyagi 980-8579 Japan Universal Biology Institute The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo 113-0033 Japan

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：