检索结果-内蒙古大学图书馆

A Parallel Levenberg-Marquardt algorithm for Recursive Neural Network in a Robot Control System

INTERNATIONAL JOURNAL OF COGNITIVE INFORMATICS AND NATURAL INTELLIGENCE 2018年第2期12卷 32-47页

作者： Wang, Wei Pu, Yunming Li, Wang Jimei Univ Coll Comp Engn Xiamen Peoples R China

This article has the purpose of overcoming the shortcomings of the recursive neural network learning algorithm and the inherent delay problem on the manipulator master control system. This is by analyzing the shortcomings of lm learning algorithms based on DRNN network, an improved parallel lm algorithm is proposed. The parallel search of the damping coefficient p is found in order to reduce the number of iterations of the loop, and the algorithm is used to decompose the parameter operation and the matrix operation into the processor (core), thereby improve the learning convergence speed, and control the scale of the delay. The simulation results show that the pro-posed algorithm is feasible.

关键词： Damping Coefficient DRNN lm algorithm Manipulator Control System

来源：评论

学校读者我要写书评

暂无评论

The Prediction of Greenhouse Temperature and Humidity Based on lm-RBF Network

The Prediction of Greenhouse Temperature and Humidity Based ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Youjun Yue Jun Quan Hui Zhao Hongjun Wang Tianjin Key laboratory for Control Theory and Applications in Complicated System Tianjin University of Technology Tianjin China

In order to improve the accuracy of prediction for the temperature and humidity of the northern greenhouse, this paper proposes a model to predict the temperature and humidity of a greenhouse based on improved lm-RBF. The input data of the model were measured in a greenhouse in Tianjin in March. This model uses the inside and outside meteorological data of the greenhouse as input, and the temperature and humidity in a greenhouse as output. The higher prediction accuracy is obtained by the experimental results, which proved the feasibility of this scheme. This model can be used to forecast the temperature and humidity of a greenhouse and guide the control of the temperature and humidity of a greenhouse.

关键词： RBF network lm algorithm Temperature and humidity prediction

来源：评论

学校读者我要写书评

暂无评论

An Improved Calibration Method for a Rotating 2D LIDAR System

引用

SENSORS 2018年第2期18卷 497-497页

作者： Zeng, Yadan Yu, Heng Dai, Houde Song, Shuang Lin, Mingqiang Sun, Bo Jiang, Wei Meng, Max Q. -H. Chinese Acad Sci Quanzhou Inst Equipment Mfg Haixi Inst Jinjiang 362200 Peoples R China North Univ China Coll Elect & Control Engn Taiyuan 030051 Shanxi Peoples R China Harbin Inst Technol Shenzhen Grad Sch Shenzhen 518000 Peoples R China Suzhou SinoGermany Robooster Intelligent Technol Suzhou 215000 Peoples R China Chinese Univ Hong Kong Dept Elect Engn Hong Kong Hong Kong Peoples R China

This paper presents an improved calibration method of a rotating two-dimensional light detection and ranging (R2D-LIDAR) system, which can obtain the 3D scanning map of the surroundings. The proposed R2D-LIDAR system, composed of a 2D LIDAR and a rotating unit, is pervasively used in the field of robotics owing to its low cost and dense scanning data. Nevertheless, the R2D-LIDAR system must be calibrated before building the geometric model because there are assembled deviation and abrasion between the 2D LIDAR and the rotating unit. Hence, the calibration procedures should contain both the adjustment between the two devices and the bias of 2D LIDAR itself. The main purpose of this work is to resolve the 2D LIDAR bias issue with a flat plane based on the Levenberg-Marquardt (lm) algorithm. Experimental results for the calibration of the R2D-LIDAR system prove the reliability of this strategy to accurately estimate sensor offsets with the error range from -15 mm to 15 mm for the performance of capturing scans.

关键词： light detection and ranging (LIDAR) rotating unit Pan-Tilt Unit (PTU) bias angle calibration lm algorithm

来源：评论

学校读者我要写书评

暂无评论

The Application of Levenberg-Marquardt algorithm in Multi-beam Sounding Data 2

The Application of Levenberg-Marquardt Algorithm in Multi-be...

引用

2017 IEEE 2nd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC 2017)

作者： Kai MA Weiming XU Jian XU Department of Hydrography and Cartography Dalian Naval Academy

ISBN: (纸本)9781509064151;9781509064144

For reducing seabed topographic distortion,namely, the random error of the multi-beam sounding, which caused by the sound velocity error, Levenberg-Marquardt(lm)algorithm is introduced to sound velocity correction. The algorithm utilizes the relationship between the sound ray and the sound velocity to establish observation equations, i.e., lm equations. Then, the novel sound velocity profiles are inversed from above-mention lm functions based on the indirect adjustment theory. Finally, the distortion terrain of the seabed is corrected by forward calculating with the calculated sound velocity profiles. The results of field experimental data are shown that: the sound profile values computed by the lm algorithm are more closer to the true value of the sound profile than that of the substitutive sound profile measurements contaminated by the random error, and the mean square error(MSE) of depth correction has been reduced more than 70%,which effectively cut down the influence of the sound velocity on seabed topography.

关键词： multi-beam sounding sound velocity profile lm algorithm indirect adjustment

来源：评论

学校读者我要写书评

暂无评论

Research on Robot Calibration Based on Laser Tracker 4th

Research on Robot Calibration Based on Laser Tracker

引用

4th IFToMM Asian Conference on Mechanism and Machine Science (IFToMM Asian MMS) / International Conference on Mechanism and Machine Science (CCMMS)

作者： HuangFu, Yabo Hang, Lubin Cheng, Wushan Yu, Liang Shen, Chengwei Wang, Jun Qin, Wei Wang, Yan Shanghai Univ Engn Sci Shanghai Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China

ISBN: (纸本)9789811028755;9789811028748

With the development of intelligent manufacturing, robot absolute positioning accuracy plays an important role in advanced applications. Aiming at improving the absolute positioning accuracy of serial robot, a calibration experiment is conducted with a laser tracker, the effects of the kinematic calibration are evaluated by comparing the position errors. Firstly, the kinematic model of the robot is established according to the method of Denavit-Harteriberg parameter, and the geometric parameters of the robot to be corrected are selected. Secondly, the error function is established with measurement result of the end reflector position and calculation result by DH matrix of the corresponding position. Thirdly, the actual geometric parameters are obtained by solving the error function using lm algorithm. Finally, the kinematic model of robot system is corrected by these parameters. The result shows that the maximum/ mean/root-mean-square (RMS) position errors are reduced 47.48 %/ 37.98 %/ 40.40 % after calibration.

关键词： Serial robot Laser tracker Robot calibration lm algorithm

来源：评论

学校读者我要写书评

暂无评论

A Web Service QoS Forecasting Approach Based on Multivariate Time Series 24

A Web Service QoS Forecasting Approach Based on Multivariate...

引用

24th IEEE International Conference on Web Services (ICWS)

作者： Zhang, Pengcheng Wang, Liyan Li, Wenrui Leung, Hareton Song, Wei Hohai Univ Coll Comp & Informat Nanjing 211110 Jiangsu Peoples R China Nanjing Xiaozhuang Univ Sch Math & Informat Technol Nanjing 211147 Jiangsu Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Hong Kong Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538607527

In order to accurately forecast Quality of Service (QoS) of different Web Services, this paper proposes a novel QoS forecasting approach called MulA-lmRBF (Multi-step forecasting with Advertisement and Levenberg-Marquardt improved Radial Basis Function) based on multivariate time series. Considering the correlation among different QoS attributes, we use phase-space reconstruction to map historical multivariate QoS data into a dynamic system, use Average Dimension (AD) to estimate the embedding dimension and delay time of reconstructed phase space. We also add the short-term QoS advertisement data of service provider to form a more comprehensive data set. Then, RBF (Radial Basis Function) neural network improved by the Levenberg-Marquardt (lm) algorithm is used to update the weight of the neural network dynamically, which improves the forecasting accuracy and realizes the dynamic multiple-step forecasting. The experimental results demonstrate that MulAlmRBF is better than previous approaches in term of precision and is more suitable for multi-step forecasting.

关键词： Quality of Service Multivariate time series Phase-space reconstruction lm algorithm RBF neural network Dynamic multiple step forecasting

来源：评论

学校读者我要写书评

暂无评论

Research Enterprise Performance Evaluation Based on BP-lm Neural Network

Research Enterprise Performance Evaluation Based on BP-LM Ne...

引用

2017 2nd International Conference on Test, Measurement and Computational Method(TMCM 2017)

作者： Meng-meng YUAN Feng-shan XIONG Xue-quan YANG College of Information Science and Technology Agriculture University of Hebei College of Business Agriculture University of Hebei

[Objective]For the better development of the enterprise, enterprise performance evaluation is the symbol of the overall enterprise success.[Methods]In this study, we use Levenberg Marquardt(lm) algorithm to improve the BP neural network to evaluate the performance of enterprises.[Result]Through the simulation test of the relevant data of a car company in 2010-2016, it is proved that the improved BP neural network can improve the performance of the enterprise more quickly and accurately.[Conclusion]lm-BP neural network of enterprise performance evaluation can make enterprises better understand themselves.

关键词： Neural network Enterprise performance evaluation lm algorithm Evaluating indicator

来源：评论

学校读者我要写书评

暂无评论

lm-BP based Operation Quality Assessment Method for OTN in Smart Grid 18

LM-BP based Operation Quality Assessment Method for OTN in S...

引用

18th Asia-Pacific Network Operations and Management Symposium (APNOMS)

作者： Wu, Manman Guo, Shaoyong Chen, Xingyu Xing, Ningzhe Zhong, Cheng Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China State Grid Jibei Elect Power Co Ltd Informat & Commun Dispatch Beijing Peoples R China State Grid Heibei Elect Power Co Shijiazhuang Peoples R China

ISBN: (纸本)9784885523045

OTN technology has been widely used in smart grid, which improves transmission speed, transmission efficiency and transmission capacity of the network. In order to supervise the operation of the network in real time and improve quality of service (QoS), we need to make a quantitative assessment of operation quality for OTN in smart grid. In this paper, we propose lm-BP evaluation method to assess the operation quality of OTN in smart grid. At first, we give the evaluation indicator system. Secondly, we introduce lm-BP algorithm. At last we make simulation experiments based on MATLAB with last 10 years network operation data of a province electric power OTN company in smart grid. The simulation results show that BP neutral network optimized by Levenberg-Marquardt (lm) algorithm has shorter training time, faster convergence rate and better prediction accuracy than that standard BP neutral network. Demonstrating a new method of lm-BP network in operation quality evaluation of OTN in Smart grid is feasible, effective and reasonable.

关键词： OTN operation quality BP Neural Network lm algorithm

来源：评论

学校读者我要写书评

暂无评论

Using deep belief networks to extract Chinese entity attribute relation in domain-specific

引用

INTERNATIONAL JOURNAL OF COMPUTING SCIENCE AND MATHEMATICS 2016年第2期7卷 144-155页

作者： Xian, Yantuan Shao, Fa Guo, Jianyi Zhou, Lanjiang Yu, Zhengtao Chen, Wei Kunming Univ Sci & Technol Sch Informat Engn & Automat Kunming Yunnan Peoples R China Yunnan Coll Key Lab Pattern Recognit & Intelligent Comp Kunming Yunnan Peoples R China

The state-of-the-art methods used for entity attribute relation extraction are primarily based on statistical machine learning, and the performance strongly depends on the quality of the extracted features. Deep belief networks (DBN) has been successful in the high dimensional feature space information extraction task, which can without complicated pre-processing. In this paper, the DBN, which consists of one or more restricted Boltzmann machine (RBM) layers and a back-propagation (BP) layer, is presented to extract Chinese entity attribute relation in domain-specific. First, the word tokens are transformed to vectors by looking up word embeddings. Then, the RBM layers maintain as much information as possible when feature vectors are transferred to next layer. Finally, the BP layer is trained to classify the features generated by the last RBM layer, and adopting Levenberg-Marquard (lm) optimisation algorithm to do the training. The experimental results show that the proposed method outperforms state-of-the-art learning models in specific domain entity attribute relation extraction.

关键词： relation extraction Chinese entity attribute deep belief nets combination features lm algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network Modeling of MEMS Cantilever Resonator Using Levenberg Marquardt algorithm 2

Artificial Neural Network Modeling of MEMS Cantilever Resona...

引用

2nd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT)

作者： Sutagundar, Manjula Nirosha, H. Sheeparamatti, B. G. Basaveshwar Engn Coll Dept ECE Bagalkot Karnataka India PESITM Dept ECE Shimoga Karnataka India

ISBN: (纸本)9781509023998

Modeling and simulation are two important stages in the design and development of MEMS devices. Accurate modeling of the device is very essential for the system level simulation. This paper presents the Artificial Neural Network (ANN) modeling of MEMS cantilever resonator. The geometrical parameters (length, thickness, width and gap) of the cantilever resonator and bias voltage are considered as the input parameters. The resonance frequency, displacement and motional current are taken as the output parameters. The variation of the output parameters with the variation in the input parameters is obtained from the MEMS simulation software Coventorware. Using this data an ANN model is developed for the cantilever resonator. The Levenberg-Marquardt (lm) algorithm is used for training the ANN model.

关键词： MEMS Resonator ANN modelling Microcantilever beam lm algorithm

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：