检索结果-内蒙古大学图书馆

Adaptive H∞ Formation Reconfiguration of Multiple Spacecraft System 37

学校读者我要写书评

暂无评论

Adaptive H∞ Formation Reconfiguration of Multiple Spacecraf...

37th Chinese Control Conference, CCC 2018

作者： Ning, Zhou Riqing, Chen Jie, Huang Guoxing, Wen Sixing, Zhang College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China Faculty of Science and Engineering University of Groningen Groningen9747AG Netherlands College of Electrical Engineering and Automation Fuzhou University Fuzhou350108 China College of Science Binzhou University Binzhou Shandong256600 China School of Automation Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789881563941

The problem of formation reconfiguration for multiple spacecraft is discussed in the presence of external disturbances. To achieve the H∞ performance, an elaborate formation task function is designed by using null-space based behavioral control method, then a predesigned desired velocity is calculated for each spacecraft. By employing variable structure technique associated with the universal approximation property of radial basis function neural networks (RBFNN), an adaptive H∞ coordination control scheme is proposed for each spacecraft to implement the specified formation task. Finally, rigorous theoretical analysis shows that the developed algorithm implements the formation reconfiguration task and satisfies the H∞ performance. © 2018 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Spacecraft

Feature extraction for hyperspectral imagery: The evolution from shallow to deep

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Rasti, Behnood Hong, Danfeng Hang, Renlong Ghamisi, Pedram Kang, Xudong Chanussot, Jocelyn Benediktsson, Jon Atli Machine Learning Group Exploration Division Helmholtz Institute Freiberg for Resource Technology Helmholtz-Zentrum Dresden-Rossendorf Freiberg09599 Germany Univ. Grenoble Alpes CNRS Grenoble INP GIPSAlab Grenoble38000 France Jiangsu Key Laboratory of Big Data Analysis Technology School of Automation Nanjing University of Information Science and Technology Nanjing210044 China Machine Learning Group Exploration Division Helmholtz Institute Freiberg for Resource Technology Helmholtz-Zentrum Dresden-Rossendorf Freiberg09599 Germany College of Electrical and Information Engineering Hunan University Changsha410082 China Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Changsha410082 China Univ. Grenoble Alpes Inria CNRS Grenoble INP LJK GrenobleF-38000 France Faculty of Electrical and Computer Engineering University of Iceland Reykjavik101 Iceland Faculty of Electrical and Computer Engineering University of Iceland Reykjavik107 Iceland

The final version of the paper can be found in IEEE Geoscience and Remote Sensing Magazine. Hyperspectral images provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands) with continuous spectral information that can accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to the conventional techniques (the so-called curse of dimensionality) for accurate analysis of hyperspectral images. Feature extraction, as a vibrant field of research in the hyperspectral community, evolved through decades of research to address this issue and extract informative features suitable for data representation and classification. The advances in feature extraction have been inspired by two fields of research, including the popularization of image and signal processing as well as machine (deep) learning, leading to two types of feature extraction approaches named shallow and deep techniques. This article outlines the advances in feature extraction approaches for hyperspectral imagery by providing a technical overview of the state-of-the-art techniques, providing useful entry points for researchers at different levels, including students, researchers, and senior researchers, willing to explore novel investigations on this challenging topic. In more detail, this paper provides a bird's eye view over shallow (both supervised and unsupervised) and deep feature extraction approaches specifically dedicated to the topic of hyperspectral feature extraction and its application on hyperspectral image classification. Additionally, this paper compares 15 advanced techniques with an emphasis on their methodological foundations in terms of classification accuracies. Furthermore, to push this vibrant field of research forward an impressive amount of codes and libraries is shared at: https://***/Behnoo

关键词： Feature extraction

A hybrid deep-learning approach for complex biochemical named entity recognition

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jian Gao, Lei Guo, Sujie Ding, Rui Huang, Xin Ye, Long Meng, Qinghua Nazari, Asef Thiruvady, Dhananjay HeFei University of Technology Hefei230009 China CSIRO Waite Campus UrrbraeSA5064 Australia Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Shanghai Engineering Center for Microsatellites Shanghai201203 China Xi’an Jiaotong University Xi’an710049 China College of Computer and Information Engineering Tianjin Normal University Tianjin300387 China School of Mechatronic Engineering and Automation Shanghai University Shanghai200072 China Faculty of Business Information Shanghai Business School Shanghai201400 China School of Information Technology Deakin University Geelong Australia Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei Anhui230601 China

Named entity recognition (NER) of chemicals and drugs is a critical domain of information extraction in biochemical research. NER provides support for text mining in biochemical reactions, including entity relation extraction, attribute extraction, and metabolic response relationship extraction. However, the existence of complex naming characteristics in the biomedical field, such as polysemy and special characters, make the NER task very challenging. Here, we propose a hybrid deep learning approach to improve the recognition accuracy of NER. Specifically, our approach applies the Bidirectional Encoder Representations from Transformers (BERT) model to extract the underlying features of the text, learns a representation of the context of the text through Bi-directional Long Short-Term Memory (BILSTM), and incorporates the multi-head attention (MHATT) mechanism to extract chapter-level features. In this approach, the MHATT mechanism aims to improve the recognition accuracy of abbreviations to efficiently deal with the problem of inconsistency in full-text labels. Moreover, conditional random field (CRF) is used to label sequence tags because this probabilistic method does not need strict independence assumptions and can accommodate arbitrary context information. The experimental evaluation on a publicly-available dataset shows that the proposed hybrid approach achieves the best recognition performance;in particular, it substantially improves performance in recognizing abbreviations, polysemes, and low-frequency entities, compared with the state-of-the-art approaches. For instance, compared with the recognition accuracies for low-frequency entities produced by the BILSTM-CRF algorithm, those produced by the hybrid approach on two entity datasets (MULTIPLE and IDENTIFIER) have been increased by 80% and 21.69%, respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Random processes

Updating an electric propulsion UAV device for long range missions

学校读者我要写书评

暂无评论

Updating an electric propulsion UAV device for long range mi...

International Symposium on Electrical and Electronics engineering (ISEEE)

作者： Gabriel Murariu Mihai Dragu Bogdan Roşu Silviu Epure Ciprian Vlad European Center of Excellence for the Environment “Dunarea de Jos” University of Galaţi 47 Domneasca Street Galati Romania Faculty of Automation Computer Sciences Electronics and Electrical Engineering “Dunărea de Jos” University of Galaţi 47 Domneasca Street Galati Romania

ISBN: (数字)9781728129068

ISBN: (纸本)9781728129075

This paper presents the actual method used in upgrading an electric propulsion UAV (Unmanned Aerial Vehicle) (commonly known as drones) device with 2.45 m wingspan and weighing 8 kg. The device, endowed with a ROXXY Brushless Outrunner D63-72 230kV engine and a 14-inch propeller, has been successfully tested in various test flights. The paper explicitly presents the electric and electronic layouts, as well as the solutions identified for increasing its range by including a telemetry system based on the national GSM network.

关键词：

Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Kaiyuan Musio, Fabio Ma, Yihui Juchler, Norman Paetzold, Johannes C. Al-Maskari, Rami Höher, Luciano Li, Hongwei Bran Hamamci, Ibrahim Ethem Sekuboyina, Anjany Shit, Suprosanna Huang, Houjing Prabhakar, Chinmay de la Rosa, Ezequiel Waldmannstetter, Diana Kofler, Florian Navarro, Fernando Menten, Martin Ezhov, Ivan Rueckert, Daniel Vos, Iris Ruigrok, Ynte Velthuis, Birgitta Kuijf, Hugo Hämmerli, Julien Wurster, Catherine Bijlenga, Philippe Westphal, Laura Bisschop, Jeroen Colombo, Elisa Baazaoui, Hakim Makmur, Andrew Hallinan, James Wiestler, Bene Kirschke, Jan S. Wiest, Roland Montagnon, Emmanuel Letourneau-Guillon, Laurent Galdran, Adrian Galati, Francesco Falcetta, Daniele Zuluaga, Maria A. Lin, Chaolong Zhao, Haoran Zhang, Zehan Ra, Sinyoung Hwang, Jongyun Park, Hyunjin Chen, Junqiang Wodzinski, Marek Müller, Henning Shi, Pengcheng Liu, Wei Ma, Ting Yalçin, Cansu Hamadache, Rachika E. Salvi, Joaquim Llado, Xavier Estrada, Uma Maria Lal-Trehan Abramova, Valeriia Giancardo, Luca Oliver, Arnau Liu, Jialu Huang, Haibin Cui, Yue Lin, Zehang Liu, Yusheng Zhu, Shunzhi Patel, Tatsat R. Tutino, Vincent M. Orouskhani, Maysam Wang, Huayu Mossa-Basha, Mahmud Zhu, Chengcheng Rokuss, Maximilian R. Kirchhoff, Yannick Disch, Nico Holzschuh, Julius Isensee, Fabian Maier-Hein, Klaus Sato, Yuki Hirsch, Sven Wegener, Susanne Menze, Bjoern Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Center for Computational Health Zurich University of Applied Sciences Zurich Switzerland Department of Neuroradiology University Hospital of Zurich Zurich Switzerland Department of Neurosurgery Zhongnan Hospital of Wuhan University Wuhan China Department of Computing Imperial College London London United Kingdom Helmholtz Center Munich Germany Athinoula A. Martinos Center for Biomedical Imaging Harvard Medical School Boston United States School of Medicine Technical University of Munich Munich Germany Department of Informatics Technical University of Munich Munich Germany Helmholtz AI Helmholtz Munich Munich Germany Image Sciences Institute UMC Utrecht Utrecht Netherlands Department of Neurology UMC Utrecht Utrecht Netherlands Department of Radiology UMC Utrecht Utrecht Netherlands Department of Clinical Neurosciences Division of Neurosurgery Geneva University Hospitals Geneva Switzerland Department of Neurology University Hospital of Zurich Zurich Switzerland Department of Physiology University of Toronto Toronto Canada Department of Neurosurgery University Hospital of Zurich Zurich Switzerland Department of Diagnostic Imaging National University Hospital Singapore Department of Diagnostic and Interventional Neuroradiology University Hospital Berne University of Berne Berne Switzerland Montreal Canada Universitat Pompeu Fabra Barcelona Spain EURECOM Biot France Institute of Medical Technology Peking University Health Science Center Beijing China Hangzhou Genlight Medtech Co. Ltd. Hangzhou China Department of Artificial Intelligence Sungkyunkwan University Seoul Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Seoul Korea Republic of Shanghai MediWorks Precision Instruments Co. Ltd. Shanghai China Institute of Informatics HES-SO Valais-Wallis Switzerland Department of Measurement and Electronics AGH University

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically. © 2023, CC BY-NC-ND.

关键词： Large datasets

Design of stable and new polysaccharide nanoparticles composite and their interaction with solid cellulose surfaces

学校读者我要写书评

暂无评论

Nano-Structures and Nano-Objects 2020年 24卷

作者： Czabany, Ivana Hribernik, Silvo Bračič, Matej Kurečič, Manja Thomas, Sabu Stana Kleinschek, Karin Mohan, Tamilselvan Institute of Chemistry University of Graz Heinrichstrasse 28 Graz 8010 Austria Institute of Automation Faculty of Electrical Engineering and Computer Science University of Maribor Koroska cesta 46 Maribor 2000 Slovenia Laboratory for Characterisation and Processing of Polymers Faculty of Mechanical Engineering University of Maribor Smetanova 17 Maribor 2000 Slovenia School of Energy Materials International and Inter University Centre for Nanoscience and Nanotechnology School of Chemical Sciences Mahatma Gandhi University Priyadarshini Hills P.O. Kottayam 686560 Kerala India Institute for Chemistry and Technology of Biobased Systems (IBioSys) Graz University of Technology Stremayrgasse 9 Graz 8010 Austria

This study presents a simple and straightforward method for the preparation of aqueous-based stable polysaccharide-metal oxide nanoparticles composites — composed of carboxymethyl cellulose (CMC) and titanium dioxide nanoparticles (TiO₂ NPs), and their interaction with the cellulose surface, is presented. Using a combination of anionic polysaccharide CMC as a stabilizer agent and ultrasound probe sonication technique as an agitation tool, a highly stable dispersion of CMC/TiO₂ NPs composites is prepared in water, with and without the presence of calcium chloride electrolyte, at various pH values. The results of the dynamic light scattering and the zeta-potential measurements showed that the quality, the stability of the dispersions and the hydrodynamic radius of the particles (ca, 200–300 nm) remain well-preserved for several weeks under normal storage conditions. The transmission electron microscope revealed that the morphology and size of the dry particles size (ca. 25–50 nm) remain unchanged and are not influenced by the addition of the stabilizer CMC, the electrolyte or the pH value of the solution. The presence of electrolyte and the low pH of the dispersions strongly favored an irreversible and enhanced deposition of CMC/TiO₂ NPs on cellulose surface as showed by a quartz crystal microbalance with dissipation. A linear correlation between the concentration of CMC and the adsorbed mass of polymer and NPs, and the water content of the adsorbed layers is observed. X-ray photoelectron spectroscopy and atomic force microscopy are combined to prove the successful immobilization of polymer and NPs on the cellulose surface. The knowledge gained from this study can be extended not only for the stabilization of various metal oxide nanoparticles but also for the development of green polymer/NPs composites, that may have the potential to be used as functional coatings in biomedical (e.g. wound dressing) applications. © 2020

关键词： Adsorption Carboxmethyl cellulose QCM-D Thin films Titanium dioxide nanoparticles Water content Zeta potential

Super-resolution fluorescence polarization microscopy

学校读者我要写书评

暂无评论

Journal of Innovative Optical Health Sciences 2018年第1期11卷 1-12页

作者： Karl Zhanghao Juntao Gao Dayong Jin Xuedian Zhang Peng Xi Department of Biomedical Engineering College of Engineering Peking UniversityP.R.China School of Optical-Electronic and Computer Engineering Shanghai University of Science and Technology P.R.China Department of Automation Tsinghua University Beijing 100084P.R.China Bioinfomatics Division TNLIST MOE Key Laboratory of Bioinformatics and Center for Synthetic&System Biology Tsinghua UniversityBeijing 100084P.R.China Faculty of Science Institute for Biomedical Materials and Devices(IBMD)University of TechnologyAustralia

Fluorescence polarization is related to the dipole orientation of chromophores,making fuores-cence polarization microscopy possible to_reveal structures and functions of tagged cellularorganelles and biological *** recent super resolution techniques have beenapplied to fluorescence polarization microscopy,achieving dipole measurement at *** this review,we summarize both difraction limited and super resolution fluorescence polari-zation microscopy techniques,as well as their applications in biological imaging.

关键词： Fluorescence polarization microscopy super resolution fluorescence anisotropy linear dichroism polarization modulation

Advances in Intelligent Systems and Computing

学校读者我要写书评

暂无评论

Preface

Advances in Intelligent Systems and Computing 2020年 1049卷 xiii页

作者： Jain, Lakhmi C. Balas, Valentina E. Tsihrintzis, George A. Sharma, Dilip Kumar Faculty of Engineering and IT University of Technology Sydney Broadway NSW Australia Department of Automation and Applied Informatics "Aurel Vlaicu" University of Arad Arad Romania Department of Informatics University of Piraeus Piraeus Greece Department of Computer Engineering and Applications Institute of Engineering and Technology GLA University Mathura India

Forecasting time series for power consumption data in different buildings using the fractional Brownian motion

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bondarenko, Valeria Filipova-Petrakieva, Simona Taralova, Ina Andreev, Desislav University of Beira Covilha Portugal Bulgarian Section Technical University of Sofia Bulgaria Department "Theory of Electrical Engineering" Faculty of Automation Sofia Bulgaria Laboratoire des Sciences du Numerique de Nantes Ecole Centrale de Nantes Nantes France Technical University of Sofia Bulgaria Department "Computer Science" Faculty of Computer Systems and Technologies "Advance Driver Assistance Systems" Company Visteon Electronics Bulgaria Sofia Bulgaria

In the present paper will be discussed the problem related to the individual household electric power consumption of objects in different areas - industry, farmers, banks, hospitals, theaters, hostels, supermarkets, universities. The main goal of the directed research is to estimate the active P and full S power consumptions for all studied buildings. The defined goal is achieved by solving of the following three problems. The first problem studies which buildings increase their power consumption. The second one finds which objects have the greatest increase of power consumption. And the third problem regards if it is possible to make a short-term forecast, based on the solutions of previous two problems. The present research and solving of the aforementioned problems is conducted using fractional Brownian motion theory. The applicability of this approach is illustrated on the example with 20 real objects in different areas. The paper ends with conclusion notes about possibilities to make short-term forecasts about power consumption of the considered buildings. Copyright © 2019, The Authors. All rights reserved.

关键词： Electric power utilization