检索结果-内蒙古大学图书馆

Decentralized reinforcement learning applied to mobile robots 1

20th Annual RoboCup International Symposium, 2016

作者： Leottau, David L. Vatsyayan, Aashish Ruiz-del-Solar, Javier Babuška, Robert Advanced Mining Technology Center Department of Electrical Engineering Universidad de Chile Av. Tupper 2007 Santiago Chile Delft Center for Systems and Control Delft University of Technology Delft2628 CD Netherlands

ISBN: (数字)9783319687926

ISBN: (纸本)9783319687919

In this paper, decentralized reinforcement learning is applied to a control problem with a multidimensional action space. We propose a decentralized reinforcement learning architecture for a mobile robot, where the individual components of the commanded velocity vector are learned in parallel by separate agents. We empirically demonstrate that the decentralized architecture outperforms its centralized counterpart in terms of the learning time, while using less computational resources. The method is validated on two problems: an extended version of the 3-dimensional mountain car, and a ball-pushing behavior performed with a differential-drive robot, which is also tested on a physical setup. © 2017, Springer International Publishing AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Relation Model of Burden Operation and State Variables of Blast Furnace Based on Low Frequency Feature Extraction*

引用

IFAC-PapersOnLine 2017年第1期50卷 13796-13801页

作者： Zhang, Kexin Wu, Min An, Jianqi Cao, Weihua Liu, Zhentao Ning, Fulong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Faculty of Engineering China University of Geosciences wuhan430074 China Department of Computer Science School of Computing Tokyo Institute of Technology Yokohama226-8502 Japan

In the blast furnace ironmaking process, the running state of the blast furnace can be directly adjusted by the burden operation. Therefore, the explicit relation between the burden operation and the running state variables is vital for the blast furnace operators. However, the state variables of the blast furnace are affected by many factors and the burden matrix is complicated. In this paper, a support vector regression(SVR) predicting model based on low frequency feature extraction is proposed to solve these problems. First, the low frequency components of state variables time series which are mostly affected by the burden operation are extracted. Then, the dimensions of the burden matrix are reduced by a devised simple expression method. Finally, the relation model based on SVR is proposed to predict the values of the expected state variables according to the simplified burden matrix and the value of initial state variables. The simulation on real factory data indicates that the model reflects the accurate quantitative relation between the burden operation and the state variables. © 2017

关键词： Blast furnaces Blast furnace practice Extraction Feature extraction Support vector regression Blast furnace iron making Blast furnace operators burden operation Initial state variables Low frequency components Relation models State variables Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

Log-Data Clustering Analysis for Dropout Prediction in Beginner Programming Classes

引用

Procedia Computer Science 2017年 112卷 614-621页

作者： Shinichi Oeda Genki Hashimoto Department of Information and Computer Engineering National Institute of Technology Kisarazu College Advanced Control and Information Engineering Course National Institute of Technology Kisarazu College 11-1 Kiyomidaihigashi 2-chome Kisarazu City Chiba Japan

Educational data mining (EDM) involves the application of data mining, machine learning, and statistics to information generated from an educational setting. In most school education, one teacher teaches many students. A periodic examination is used as a method to confirm that students have acquired skills. However, it is difficult to grasp the status of the student from each lesson, since examinations cannot be carried out easily. On the other hand, in programming classes, the students’ history of UNIX commands and source-code editing can be easily and automatically stored as log-data. Therefore, attempts have been made to estimate the student’s performance from this log-data, although their estimation accuracy is not high. In this research, we aim to extract those students who cannot keep up with programming lessons, rather than estimating the student’s performance from the log-data. Specifically, we propose a method for predicting dropouts using outlier detection to cluster data with unsupervised learning.

关键词： Educational data mining Dropout prediction Dynamic time warping k-means++ UNIX command history

来源：评论

学校读者我要写书评

暂无评论

Stability and Neimark-Sacker bifurcation analysis for single gene discrete system with delay

Stability and Neimark-Sacker bifurcation analysis for single...

引用

Chinese control Conference

作者： Feng Liu Qicheng Mei Fenglan Sun Xinmei Wang Hua O. Wang Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Automation China University of Geosciences Wuhan China Research Center of System Theory and Application Chongqing University of Posts and Telecommunications Chongqing China Department of Mechanical Engineering Boston University Boston MA USA

The network structure and functional properties of gene regulatory system and their relationships arc an important research field in systems biology. In this paper, a new improved model is proposed based on the study of gene expression process. The model takes into account the effect of protein concentration on the gene expression, so as to obtain a new bifurcation point and improve the performance of the system. The validity of the model is verified by theoretical analysis and data simulation.

关键词： Mathematical model Proteins Stability analysis Bifurcation Biological system modeling Delays RNA

来源：评论

学校读者我要写书评

暂无评论

AIFORCOVID: Predicting the clinical outcomes in patients with COVID-19 applying AI to chest-X-rays. an Italian multicentre study

arXiv

引用

arXiv 2020年

作者： Soda, Paolo D’Amico, Natascha Claudia Tessadori, Jacopo Valbusa, Giovanni Guarrasi, Valerio Bortolotto, Chandra Akbar, Muhammad Usman Sicilia, Rosa Cordelli, Ermanno Fazzini, Deborah Cellina, Michaela Oliva, Giancarlo Callea, Giovanni Panella, Silvia Cariati, Maurizio Cozzi, Diletta Miele, Vittorio Stellato, Elvira Carrafiello, Gian Paolo Castorani, Giulia Simeone, Annalisa Preda, Lorenzo Iannello, Giulio Bue, Alessio Del Tedoldi, Fabio Alì, Marco Sona, Diego Papa, Sergio Unit of Computer Systems and Bioinformatics Department of Engineering University Campus Bio-Medico of Rome Via Alvaro del Portillo 21 Rome00128 Italy Department of Diagnostic Imaging and Stereotactic Radiosurgey Centro Diagnostico Italiano S.p.A. Via S. Saint Bon 20 Milan20147 Italy Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Via Morego 30 Genoa16163 Italy Bracco Imaging S.p.A. Via Caduti di Marcinelle 13 Milan20134 Italy Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Radiology Institute Fondazione IRCCS Policlinico San Matteo Viale Golgi 19 Pavia27100 Italy Department of Naval Electrical Electronic and Telecommunications Engineering - University of Genova Via All’Opera Pia 11 A Genoa16145 Italy Radiology Department ASST Fatebenefratelli Sacco Piazza Principessa Clotilde 3 Milan20121 Italy Diagnostic and interventional radiology unit ASST Santi Paolo e Carlo - San Paolo Hospital Via Antonio di Rudinì 8 Milan20142 Italy Department of Advanced Diagnostic Technologies - Therapeutic Diagnostic and Radiology Units ASST Santi Paolo e Carlo - San Paolo Hospital Via Antonio di Rudinì 8 Milan20142 Italy Department of Emergency Radiology Careggi University Hospital Largo Piero Palagi 1 Florence50139 Italy Operative Unit of Radiology Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico of Milan Via della Commenda 10 Milan20122 Italy Department of Health Sciences Univeristy of Milan Via Festa del Perdono 7 Milan20122 Italy Diagnostic Imaging Postgraduate Medical School University of Foggia Via Antonio Gramsci 89 Foggia71122 Italy Department of Diagnostic Imaging IRCCS Ospedale Casa Sollievo della Sofferenza Viale Cappuccini 1 San Giovanni Rotondo71013 Italy Radiology Unit Department of Clinical Surgical Diagnostic and Pediatric Sciences University of Pavia Corso Str. Nuova 65 Pavia27100 Italy Neuroinformatics Laboratory Fondazione Bru

Recent epidemiological data report that worldwide more than 53 million people have been infected by SARS-CoV-2, resulting in 1.3 million deaths. The disease has been spreading very rapidly and few months after the identification of the first infected, shortage of hospital resources quickly became a problem. In this work we investigate whether chest X-ray (CXR) can be used as a possible tool for the early identification of patients at risk of severe outcome, like intensive care or death. CXR is a radiological technique that compared to computed tomography (CT) it is simpler, faster, more widespread and it induces lower radiation dose. We present a dataset including data collected from 820 patients by six Italian hospitals in spring 2020 during the first COVID-19 emergency. The dataset includes CXR images, several clinical attributes and clinical outcomes. We investigate the potential of artificial intelligence to predict the prognosis of such patients, distinguishing between severe and mild cases, thus offering a baseline reference for other researchers and practitioners. To this goal, we present three approaches that use features extracted from CXR images, either handcrafted or automatically by convolutional neuronal networks, which are then integrated with the clinical data. Exhaustive evaluation shows promising performance both in 10-fold and leave-one-centre-out cross-validation, implying that clinical data and images have the potential to provide useful information for the management of patients and hospital resources. © 2020, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Inside Cover: A novel in vivo Cerenkov luminescence image-guided surgery on primary and metastatic colorectal cancer (J. Biophotonics 3/2020)

引用

Journal of Biophotonics 2020年第3期13卷

作者： Zeyu Zhang Yawei Qu Yu Cao Xiaojing Shi Hongbo Guo Xiaojun Zhang Sheng Zheng Haifeng Liu Zhenhua Hu Jie Tian Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and Technology Xidian University Xi'an China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Department of Gastroenterology the Third Medical Centre Chinese PLA General Hospital Beijing China Department of Control Science and Engineering Harbin Institute of Technology Harbin China Department of Anorectal the Third medical Centre Chinese PLA General Hospital Beijing China University of Chinese Academy of Sciences Beijing China School of Information Sciences and Technology Northwest University Xi'an China Department of Nuclear Medicine Chinese PLA General Hospital Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine Beihang University Beijing China

This study presents a novel intraoperative in vivo imaging approach which harnessed Cerenkov luminescence (CL) to detect primary and metastatic colorectal cancer (CRC) using clinically approved radiopharmaceuticals. In the mice and swine experiments, the proposed approach effectively improved the effect of CRC surgery. The approach is believed to be promising for utilizing CL in open surgery. Further details can be found in the article by Zeyu Zhang, Yawei Qu, Yu Cao et al. ( e201960152 )

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Object Recognition with Multi-Directional Features in Urban Scenes

Efficient Object Recognition with Multi-Directional Features...

引用

International Conference on Soft Computing, Intelligent System and Information Technology (ICSIIT)

作者： Ryo Kawanami Kousuke Matsushima Advanced Engineering School National Institute of Technology Kurume Japan Department of Control and Information Systems Engineering National Institute of Technology Kurume Japan

ISBN: (纸本)9781467399005

Recently, object recognition in road scenes is attracting interest to the necessity of advanced Safety Vehicle (ASV). In order to protect Vulnerable Road Users (VRUs) from dangerous vehicles, it is important to identify moving objects quickly and accurately. Motorcycles, one of the dangerous vehicles, are often mistakenly recognized as bicycles because they are similar to bicycles. Motorcycles, however, are faster than bicycles and must be properly distinguished from bicycles considering the danger of collision. According to research on bicycle recognition, Two-Dimensional Histogram of Oriented Gradient (2DHOG) with Variable Window Approach (VWA) shows high accuracy and high processing speed. In this study, 2DHOG with VWA was applied to mixed data including bicycle and motorcycle as Efficient Object Recognition, and the recognition experiment was conducted to confirm whether they can distinguish them. Experimental results distinguished bicycles and motorcycles at a rate of over 90%.

关键词： Bicycles Motorcycles Image recognition Feature extraction Histograms Object recognition Testing

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional super-resolution longitudinal magnetization spot arrays

引用

Light(Science & Applications) 2017年第1期6卷 630-637页

作者： Zhong-Quan Nie Han Lin Xiao-Fei Liu Ai-Ping Zhai Yan-Ting Tian Wen-Jie Wang Dong-Yu Li Wei-Qiang Ding Xue-Ru Zhang Ying-Lin Song Bao-Hua Jia Key Lab of Advanced Transducers and Intelligent Control Systems Ministry of Education of Shanxi ProvinceCollege of Physics and OptoelectronicsTaiyuan University of TechnologyTaiyuan 030024China Centre for Micro-Photonics Faculty of ScienceEngineering and TechnologySwinburne University of TechnologyHawthornVictoria 3122Australia Department of Science Taiyuan Institute of TechnologyTaiyuan 030008China Department of Physics Lingnan Normal UniversityZhanjiang 524048China Department of Physics Harbin Institute of TechnologyHarbin 150001China

We demonstrate an all-optical strategy for realizing spherical three-dimensional(3D)super-resolution(∼λ3/22)spot arrays of pure longitudinal magnetization by exploiting a 4πoptical microscopic setup with two high numerical aperture(NA)objective lenses,which focus and interfere two modulated vectorial *** phase filters(MPFs)are designed via an analytical approach derived from the vectorial Debye diffraction theory to modulate the two circularly polarized *** system is tailored to constructively interfere the longitudinal magnetization components,while simultaneously destructively interfering the azimuthal *** a result,the magnetization field is not only purely longitudinal but also super-resolved in all three ***,the MPFs can be designed analytically to control the number and locations of the super-resolved magnetization spots to produce both uniform and nonuniform arrays in a 3D ***,an all-optical control of all the properties of light-induced magnetization spot arrays has been demonstrated for the first *** results open up broad applications in magnetic-optical devices such as confocal and multifocal magnetic resonance microscopy,3D ultrahigh-density magneto-optic memory,and light-induced magneto-lithography.

关键词： inverse Faraday effect longitudinal magnetization magnetic-optical devices magneto-optics vectorial beams vectorial Debye diffraction theory

来源：评论

学校读者我要写书评

暂无评论

Autonomous learning applying for expectancy motivation theory on English education

Autonomous learning applying for expectancy motivation theor...

引用

International Conference on engineering Education (ICEED)

作者： Ibuki Takemoto Ayumi Nagoshi Robert Johnston Yusuke Kunimi Hideki Tenzou Tatsuhiko Miyatake Department of Electronic Systems Engineering National Institute of Technology Kagawa Mitoyo Japan Electronic Systems Course Advanced Couse in Electronic National Institute of Technology Kagawa Mitoyo Japan

The seven-year educational program at KOSEN is suitable for global engineering education although the motivation of KOSEN students is lower than that of other high school students or college students of the same age. It's difficult for English teachers to diversity of students' motivation into account within their restricted time of their classes. We consider that the fundamental solution is to raise learner autonomy. We defined that the meaning of “to teach autonomous learning” is to help a learner to have the ability to take charge of one's own learning by oneself. In this paper, a new education model was proposed to teach autonomous learning by using expectancy motivation theory. A new instructional method suited for the new model was tested to create autonomous English learners over the course of 5 years. In this report, the effectiveness of the education method was also discussed by a comparison of successful learners and general students.

关键词： engineering education Conferences Educational programs Psychology Modeling

来源：评论

学校读者我要写书评

暂无评论

Examination of Treatment Methods for a PEDOT:PSS Transparent Conductive Film Produced Using an Inkjet Method

引用

Advances in Materials Physics and Chemistry 2017年第8期7卷 311-322页

作者： Atsushi Nitta Yuki Imamura Kazuya Kawahara Kazuhiro Takeda Department of Electronic Control Engineering National Institute of Technology Kagoshima College Kirishima Japan Advanced Mechanical and Electronic Systems Engineering National Institute of Technology Kagoshima College Kirishima Japan Department of Information Engineering National Institute of Technology Kagoshima College Kirishima Japan

Flexible devices manufactured using printed electronics have attracted the attention of many researchers. A high-performance transparent conductive film exhibiting high flexibility and elasticity is expected to be developed because of its need for the creation of flexible devices. An indium tin oxide (ITO) thin film, which has generally been used, has weaknesses such as fragility to bending stress and depletion of the resource. This study focused on poly (3, 4-ethy-lenedioxythiophene)/poly (styrenesulfonate) (PEDOT:PSS), a conductive polymer material, and examined improvement in the resistivity and transmittance of the transparent conductive film produced using an inkjet method. The present study improved the electrical and optical characteristics of the thin film by examining the annealing temperature between printing operations and the application method of a polar solvent. As a result, the resistivity and transmittance of a PEDOT:PSS thin film were 1.49 × 10-3 Ω·cm and 89.2%, respectively. This film was obtained by annealing at 90°C for 30 min and applying a polar solvent, using an inkjet printer, between printing operations. The printing was performed three times.

关键词： PEDOT:PSS Inkjet Printing Transparent Conductive Film Flexible Devices

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：