检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Yuan, Ye Li, Junlin Li, Liang Jiang, Frank Tang, Xiuchuan Zhang, Fumin Liu, Sheng Goncalves, Jorge Voss, Henning U. Li, Xiuting Kurths, Jürgen Ding, Han School of Artificial Intelligence and Automation State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan430074 China School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm11428 Sweden School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta30332 United States School of Power and Mechanical Engineering Wuhan University Wuhan430074 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Luxembourg Centre for Systems Biomedicine University of Luxembourg BelvauxL-4367 Luxembourg Citigroup Biomedical Imaging Center Weill Cornell Medical College New York10021 United States Research Domain IV - Transdisciplinary Concepts & Methods Potsdam Institute for Climate Impact Research Potsdam14473 Germany School of Mechanical Science and Engineering State Key Laboratory of Digital Manufacturing Equipments and Technology Huazhong University of Science and Technology Wuhan430074 China

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery (S3d), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning;which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the Complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics. Copyright © 2019, The Authors. All rights reserved.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Sensorless nonlinear control of fed-batch Escherichia coli cultivation bioprocess using the state-dependent approach 12th

引用

12th Portuguese Conference on Automatic Control, CONTROLO 2016

作者： Iratni, Abdelhamid Araújo, Rui Rastegar, Saeid Mostefai, Mohammed Faculty of Science and Technology Electrical Engineering Department University of Bordj Bou Arreridj El Anasser Algeria Department of Electrical and Computer Engineering Institute for Systems and Robotics University of Coimbra Coimbra Portugal Automatic Control Laboratory of Setif Electrical Engineering Department Faculty of Technology University of Setif1 Sétif Algeria

ISBN: (纸本)9783319436708

The cultivation of Escherichia coli bacteria is widely used by geneticists and biopharmaceuticals to produce medicines and vaccines. In such industries, Bioprocesses are known by their harsh environment and very expensive physical sensors. This paper deals with nonlinear estimation and control of fed-batch Escherichia coli bioprocess. Enhancing the process performance and maximizing its efficiency by optimizing the control of Escherichia coli cultures depends on the availability of appropriate online sensors for the main culture components. In this study, an innovative method for nonlinear estimation and control of bioprocesses is designed and assessed. The new algorithm for control and estimation of Escherichia coli bioprocess states, based on the State-Dependent Riccati Equation technique, is validated by numerical simulation. The results obtained clearly demonstrate the effectiveness of the proposed technique for Biosystems in measuring, monitoring, and control of their natural nonlinear dynamics. © Springer International Publishing Switzerland 2017.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Model-Free Iterative Tuning Approach for Smooth and Accurate Tracking

Data-Driven Model-Free Iterative Tuning Approach for Smooth ...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Xiaocong Li Si-Lu Chen Jun Ma Chek Sing Teo Kok Kiong Tan Mechatronics Group Singapore Institute of Manufacturing Technology Singapore Zhejiang Provincial Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Chinese Academy of Sciences Ningbo Zhejiang China Department of Electrical and Computer Engineering National University of Singapore Singapore

The feedback controller tuning for tray indexing can be challenging and time-consuming depending on the experience of the control engineer. Inappropriate tuning of the feedback controller often results in unacceptable tracking accuracy, humming sound, and even chips dislodged. In this paper, we propose a data-driven iterative feedback tuning approach within a three-degree-of-freedom control structure. The penalty function is introduced which takes into account both the tracking accuracy and jerk minimization, and it is particularly suitable for the tray indexing application. In contrast to the traditional model-based control, the proposed approach method makes use of the closed-loop experimental data to fine-tune the controller without system modeling, i.e. a model-less approach. The performance improvement is demonstrated with a case study based on a typical industrial timing-belt setup.

关键词： Tuning Adaptive control Iterative methods Indexing Feedforward systems Cost function Minimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Recurrent Neural Network for Sound Event Detection

Multi-Scale Recurrent Neural Network for Sound Event Detecti...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Rui Lu Zhiyao Duan Changshui Zhang Department of Automation Tsinghua University State Key Lab of Intelligent Technologies and Systems Tsinghua National Laboratory for Information Science and Technology (TNList) Beijing P.R.China Department of Electrical and Computer Engineering University of Rochester Rochester NY USA

ISBN: (纸本)9781538646595

Sound event detection (SED) in real life is an interesting but challenging task due to the polyphonic and long-term dependent nature of sound events. Recently, multi-label recurrent neural networks (RNNs) have shown promises. However, even equipped with long short-term memory (LSTM) or gated recurrent unit (GRU) cells, RNNs are still limited to model the long-term dependency. In this paper, we propose a multiscale RNN to address this issue. By integrating information from different time resolutions, we can better capture both the fine-grained and long-term dependencies of sound events. We experiment on the development sets of Task3 of DCASE2016 and DCASE2017. Compared to our previously proposed single-scale RNN that won the third place among the 13 teams in Task3 of DCASE2017, the proposed multiscale model achieves statistically significantly better performance on the development datasets of both DECASE2016 and DCASE2017.

关键词： Multi-scale model deep learning recurrent neural network sound event detection recurrent neural nets multiscale models Event detection Machine Learning SOUND Vibration Hearing temporal resolution

来源：评论

学校读者我要写书评

暂无评论

The limits and potentials of deep learning for robotics

arXiv

引用

arXiv 2018年

作者： Sünderhauf, Niko Brock, Oliver Scheirer, Walter Hadsell, Raia Fox, Dieter Leitner, Jürgen Upcroft, Ben Abbeel, Pieter Burgard, Wolfram Milford, Michael Corke, Peter Brisbane Australia Robotics and Biology Laboratory Technische Universität Berlin Germany Department of Computer Science and Engineering University of Notre Dame IN United States DeepMind London United Kingdom Paul G. Allen School of Computer Science & Engineering University of Washington WA United States Oxbotica Ltd. Oxford United Kingdom UC Berkeley Department of Electrical Engineering and Computer Sciences CA United States Department of Computer Science University of Freiburg Germany

The application of deep learning in robotics leads to very specific problems and research questions that are typically not addressed by the computer vision and machine learning communities. In this paper we discuss a number of robotics-specific learning, reasoning, and embodiment challenges for deep learning. We explain the need for better evaluation metrics, highlight the importance and unique challenges for deep robotic learning in simulation, and explore the spectrum between purely data-driven and model-driven approaches. We hope this paper provides a motivating overview of important research directions to overcome the current limitations, and help fulfill the promising potentials of deep learning in robotics. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Global control for a class of uncertain upper-triangular nonlinear systems with uncontrollable linearization 36

Global control for a class of uncertain upper-triangular non...

引用

第36届中国控制会议

作者： Zha Wenting Qian Chunjiang Zhai Junyong Fei Shumin School of Mechanical Electronic & Information Engineering China University of Mining & Technology (Beijing) Key Laboratory of Measurement and Control of CSE Ministry of EducationSchool of AutomationSoutheast University Department of Electrical and Computer Engineering The University of Texas at San Antonio

ISBN: (纸本)9781538629185

This paper fucuses on the global control problem for a class of upper-triangular nonlinear systems whose linearization around the origin is not guaranteed to be controllable. Assuming that the nonlinearities satisfy the homogeneous growth conditions, a nonsmooth state-feedback controller is elaborately constructed based on the adding a power integrator technique and the homogeneous domination approach. By introducing the dynamic gain to deal with the input dependent growth rate, it can be proved that all the signals of the closed-loop system are bounded and the system states converge to the origin asymptotically.

关键词： upper-triangular nonlinear systems input dependent growth rate adding a power integrator homogeneous domination approach

来源：评论

学校读者我要写书评

暂无评论

Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the heichole benchmark

arXiv

引用

arXiv 2021年

作者： Wagner, Martin Müller-Stich, Beat-Peter Kisilenko, Anna Tran, Duc Heger, Patrick Mündermann, Lars Lubotsky, David M. Müller, Benjamin Davitashvili, Tornike Capek, Manuela Reinke, Annika Yu, Tong Vardazaryan, Armine Innocent Nwoye, Chinedu Padoy, Nicolas Liu, Xinyang Lee, Eung-Joo Disch, Constantin Meine, Hans Xia, Tong Jia, Fucang Kondo, Satoshi Reiter, Wolfgang Jin, Yueming Long, Yonghao Jiang, Meirui Dou, Qi Heng, Pheng Ann Twick, Isabell Kirtac, Kadir Hosgor, Enes Bolmgren, Jon Lindström Stenzel, Michael von Siemens, Björn Kenngott, Hannes G. Nickel, Felix von Frankenberg, Moritz Mathis-Ullrich, Franziska Maier-Hein, Lena Speidel, Stefanie Bodenstedt, Sebastian Department for General Visceral and Transplantation Surgery Heidelberg University Hospital Im Neuenheimer Feld 420 Heidelberg69120 Germany Heidelberg Im Neuenheimer Feld 460 Heidelberg69120 Germany Data Assisted Solutions Corporate Research & Technology KARL STORZ SE & Co. KG Dr. Karl-Storz-Str. 34 Tuttlingen78332 Germany Im Neuenheimer Feld 223 Heidelberg69120 Germany Im Neuenheimer Feld 223 Heidelberg69120 Germany Faculty of Mathematics and Computer Science Heidelberg University Im Neuenheimer Feld 205 Heidelberg69120 Germany ICube University of Strasbourg CNRS France 300 bd Sébastien Brant - CS 10413 Illkirch CedexF-67412 France IHU Strasbourg France 1 Place de l'hôpital Strasbourg67000 France Sheikh Zayed Institute for Pediatric Surgical Innovation Children's National Hospital 111 Michigan Ave NW WashingtonDC20010 United States University of Maryland College Park 2405 A V Williams Building College ParkMD20742 United States Fraunhofer Institute for Digital Medicine MEVIS Max-von-Laue-Str. 2 Bremen28359 Germany University of Bremen FB3 Medical Image Computing Group ℅ Fraunhofer MEVIS Am Fallturm 1 Bremen28359 Germany Lab for Medical Imaging and Digital Surgery Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Konika Minolta Inc. JP TOWER 2-7-2 Marunouchi Chiyoda-ku Tokyo100-7015 Japan Wintegral GmbH Ehrenbreitsteiner Str. 36 München80993 Germany Department of Computer Science and Engineering Ho Sin-Hang Engineering Building The Chinese University of Hong Kong Sha Tin NT Hong Kong Caresyntax GmbH Komturstr. 18A Berlin12099 Germany Department of Surgery Salem Hospital of the Evangelische Stadtmission Heidelberg Zeppelinstrasse 11-33 Heidelberg69121 Germany Health Robotics and Automation Laboratory Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Geb. 40.28 KIT Campus Süd Engler-Bunte-Ring 8 Karlsruhe76131 Germany Medical Faculty Heidelberg Uni

PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase the safety of the operation through context-sensitive warnings and semi-autonomous robotic assistance or improve training of surgeons via data-driven feedback. In surgical workflow analysis up to 91% average precision has been reported for phase recognition on an open data single-center video dataset. In this work we investigated the generalizability of phase recognition algorithms in a multi-center setting including more difficult recognition tasks such as surgical action and surgical skill. METHODS: To achieve this goal, a dataset with 33 laparoscopic cholecystectomy videos from three surgical centers with a total operation time of 22 hours was created. Labels included framewise annotation of seven surgical phases with 250 phase transitions, 5514 occurences of four surgical actions, 6980 occurences of 21 surgical instruments from seven instrument categories and 495 skill classifications in five skill dimensions. The dataset was used in the 2019 international Endoscopic Vision challenge, sub-challenge for surgical workflow and skill analysis. Here, 12 research teams trained and submitted their machine learning algorithms for recognition of phase, action, instrument and/or skill assessment. RESULTS: F1-scores were achieved for phase recognition between 23.9% and 67.7% (n=9 teams), for instrument presence detection between 38.5% and 63.8% (n=8 teams), but for action recognition only between 21.8% and 23.3% (n=5 teams). The average absolute error for skill assessment was 0.78 (n=1 team). CONCLUSION: Surgical workflow and skill analysis are promising technologies to support the surgical team, but are not solved yet, as shown by our comparison of machine learning algorithms. This novel HeiChole benchmark can be used for comparable evaluation and validation of future work. In future studies, it is of utmost impo

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Mobile robot localisation and navigation using LEGO NXT and ultrasonic sensor

arXiv

引用

arXiv 2018年

作者： Liu, Yanan Fan, Rui Yu, Bin Junaid Bocus, M. Liu, Ming Ni, Hepeng Fan, Jiahe Mao, Shixin Bristol Robotics Laboratory University of Bristol Bristol United Kingdom Robotics and Multi-Perception Laboratory Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Department of Electrical and Electronic Engineering University of Bristol BristolBS8 1UB United Kingdom School of Mechanical Engineering Shandong University Jinan250061 China School of Communication Engineering Jilin University Changchun130000 China Shenzhen Sanhang Industrial Technology Research Institute Shenzhen518000 China

Mobile robots are becoming increasingly important both for individuals and industries. Mobile robotic technology is not only utilised by experts in this field but is also very popular among amateurs. However, implementing a mobile robot to perform tasks autonomously can be expensive because of the need for various types of sensors and the high price of robot platforms. Hence, in this paper we present a mobile robot localisation and navigation system which uses a LEGO ultrasonic sensor in an indoor map based on the LEGO MINDSTORM NXT. This provides an affordable and ready-to-use option for most robot fans. In this paper, an effective method is proposed to extract useful information from the distorted readings collected by the ultrasonic sensor. Then, the particle filter is used to localise the robot. After robot's position is estimated, a sampling-based path planning method is proposed for the robot navigation. This method reduces the robot accumulative motion error by minimising robot turning times and covering distances. The robot localisation and navigation algorithms are implemented in MATLAB. Simulation results show an average accuracy between 1 and 3 cm for three different indoor map locations. Furthermore, experiments performed in a real setup show the effectiveness of the proposed methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Preventive Soot Blowing Strategy based on State of Health Prediction for Coal-fired Power Plant Boiler

Preventive Soot Blowing Strategy based on State of Health Pr...

引用

第37届中国控制会议

作者： Yuanhao Shi Jie Wen Xiaoqiong Pang Jianfang Jia Fangshu Cui Jianchao Zeng Jingcheng Wang North University of China School of Electrical and Control Engineering North University of China School of Computer Science and Technology North University of ChinaSchool of Computer Science and Technology Shanghai Jiao Tong University Department of Automationand Key Laboratory of System Control and Information ProcessingMinistry of Education of China

This paper seeks the optimization of soot-blowing operations for heat transfer surfaces in coal-fired power plant boiler.A preventive soot blowing strategy based on state of health prediction for heat transfer surface was *** average state of health of heat transfer surface was forecasted as the threshold to draft preventive soot blowing *** to the theory of renewal process,an optimization model with the system prediction interval and the threshold of preventive soot blowing operation as the optimization variables and minimize average energy losses as the target function was *** using Particle Swarm Optimization（PSO）,the optimal preventive cycle and soot-blowing threshold were obtained,and the long-run average cost rate was the *** model is validated with experiment data of a 300 MW coal-fired power plant boiler and the parameters of prediction model are *** results can verify the feasibility of proposed *** can be used as the guide for the optimization of soot blowing in coal-fired power plant to improve the energy conservation level.

关键词： Coal-fired Boiler Heat Transfer Surface Soot-blowing State of Health（SOH） Prediction

来源：评论

学校读者我要写书评

暂无评论

Some recent results on distributed control of nonlinear systems

Some recent results on distributed control of nonlinear syst...

引用

International workshop on Nonlinear Systems in honor of Henk Nijmeijer’s 60th birthday, 2016

作者： Liu, Tengfei Jiang, Zhong-Ping State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Department of Electrical and Computer Engineering Tandon School of Engineering New York University BrooklynNY11201 United States

ISBN: (纸本)9783319303567

The spatially distributed structure of complex systems motivates the idea of distributed control. In a distributed control system, the subsystems are controlled by local controllers through information exchange with neighboring agents for coordination purposes. One of the major difficulties of distributed control is due to the complex characteristics such as nonlinearity, dimensionality, uncertainty, and information constraints. This chapter introduces small-gain methods for distributed control of nonlinear systems. In particular, a cyclic-small-gain result in digraphs is presented as an extension of the standard nonlinear small-gain theorem. It is shown that the new result is extremely useful for distributed control of nonlinear systems. Specifically, this chapter first gives a cyclic-small-gain design for distributed outputfeedback control of nonlinear systems. Then, an application to formation control problem of nonholonomic mobile robots with a fixed information exchange topology is presented. © Springer International Publishing Switzerland 2017.

关键词： Distributed parameter control systems

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：