检索结果-内蒙古大学图书馆

3D reconstruction and face recognition using kernel-based ICA and neural networks

EXPERT SYSTEMS WITH APPLICATIONS 2011年第5期38卷 5406-5415页

作者： Kuo, Shye-Chorng Lin, Cheng-Jian Liao, Jan-Ray Natl Chin Yi Univ Technol Dept Comp Sci & Informat Engn Taiping 411 Taichung County Taiwan Natl Chung Hsing Univ Dept Elect Engn Taichung 402 Taiwan

Kernel-based nonlinear characteristic extraction and classification algorithms are popular new research directions in machine learning. In this paper, we propose an improved photometric stereo scheme based on improved kernel-independent component analysis method to reconstruct 3D human faces. Next, we fetch the information of 3D faces for facial face recognition. For reconstruction, we obtain the correct normal vector's sequence to form the surface, and use a method for enforcing integrability to reconstruct 3D objects. We test our algorithm on a number of real images captured from the Yale Face Database B. and use three kinds of methods to fetch characteristic values. Those methods are called contour-based, circle-based, and feature-based methods. Then, a three-layer, feed-forward neural network trained by a back-propagation algorithm is used to realize a classifier. All the experimental results were compared to those of the existing human face reconstruction and recognition approaches tested on the same images. The experimental results demonstrate that the proposed improved kernel independent component analysis (IKICA) method is efficient in reconstruction and face recognition applications. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Independent component analysis 3D human face reconstruction 3D human face recognition back-propagation algorithm Neural networks

来源：评论

学校读者我要写书评

暂无评论

A GIS-based neuro-fuzzy procedure for integrating knowledge and data in landslide susceptibility mapping

引用

COMPUTERS & GEOSCIENCES 2010年第9期36卷 1101-1114页

作者： Vahidnia, Mohammad H. Alesheikh, Ali A. Alimohammadi, Abbas Hosseinali, Farhad KN Toosi Univ Technol Fac Geodesy & Geomat Eng Tehran *** Iran

A significant portion of the Mazandaran Province in Iran is prone to landslides due to climatic conditions, excessive rain, geology, and geomorphologic characteristics. These landslides cause damage to property and pose a threat to human lives. Numerous solutions have been proposed to assess landslide susceptibility over regions such as this one. This study proposes an indirect assessment strategy that shares in the advantages of quantitative and qualitative assessment methods. It employs a fuzzy inference system (FIS) to model expert knowledge, and an artificial neural network (ANN) to identify non-linear behavior and generalize historical data to the entire region. The results of the FIS are averaged with the intensity values of existing landslides, and then used as outputs to train the ANN. The input patterns include both physical landscape characteristics (criterion maps) and landslide inventory maps. The ANN is trained with a modified back-propagation algorithm. As part of this study, the strategy is implemented as a GIS extension using ArcGIS (R). This tool was used to create a four-domain landslide susceptibility map of the Mazandaran province. The overall accuracy of the LSM is estimated at 90.5%. (C) 2010 Elsevier Ltd. All rights reserved.

关键词： Geographic information system (GIS) Landslide susceptibility map (LSM) Fuzzy inference system (FIS) Artificial neural network (ANN) back-propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Neural networks study on the correlation between impact sensitivity and molecular structures for nitramine explosives

引用

STRUCTURAL CHEMISTRY 2006年第5期17卷 501-507页

作者： Zhao, Jun Cheng, Xin-Lu He, Bi Yang, Xiang-Dong Sichuan Univ Inst Atom & Mol Phys Chengdu 610065 Peoples R China China Acad Engn Phys Inst Chem Engn & Mat Mianyang 621900 Peoples R China

In this paper, a back-propagation neural network has been utilized to study on the correlation between impact sensitivity and molecular properties of 33 nitramine molecules. By using density functional theory method B3P86/6-31G**, all the molecular properties have been calculated. Eight different sets of molecular properties, including (HOMO-LUMO)* BDE, E, BDE/E, HOMO-LUMO, BDE*mu, R-2, Delta E, and BDE, have been used to train and test the network. Based on the test results, the correlation order between the molecular properties and impact sensitivity has been achieved. The correlation order shows that the input set with the descriptor Delta E ( atomization energy) can obtain better results than any other descriptor for nitriamines, which surely accounts for a comparatively stronger correlation between Delta E ( atomization energy) and impact sensitivity for nitramines we have studied in this work.

关键词： neural networks impact sensitivity back-propagation algorithm nitramines molecular descriptors

来源：评论

学校读者我要写书评

暂无评论

Mapping of neural network models onto systolic arrays

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2000年第6期60卷 677-689页

作者： Mahapatra, S Mahapatra, RN Reg Engn Coll Dept Comp Sci Engn & Applicat Rourkela 769008 Orissa India Texas A&M Univ Dept Comp Sci College Stn TX 77843 USA

This paper presents a mapping scheme for the proposed implementation of neural network models on systolic arrays. The mapping technique is illustrated on the multilayer perceptron with back-propagation learning. Dependency graphs have been given that represent the operations in the execution phases of the neural network model and later suitable algorithms are presented to realize the operations in a linear bidirectional systolic array. The speedup metric has been used to evaluate the performance of the proposed implementation. (C) 2000 Academic Press.

关键词： neural net models dependency graph mapping scheme bidirectional systolic array back-propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial neural network analysis of the performance characteristics of a reversibly used cooling tower under cross flow conditions for heat pump heating system in winter

引用

ENERGY AND BUILDINGS 2011年第7期43卷 1685-1693页

作者： Wu, Jiasheng Zhang, Guoqiang Zhang, Quan Zhou, Jin Wang, Yu Hunan Univ Coll Civil Engn Changsha 410082 Hunan Peoples R China

This study deals with predicting the performance characteristics of a reversibly used cooling tower (RUCT) under cross flow conditions for heat pump heating system in winter using artificial neural network (ANN) technique. For this aim, extensive field experimental work has been carried out in order to gather enough data for training and prediction. After back-propagation (BP) training combined with principal component analysis, the three-layer ANN model with a tangent sigmoid transfer function at hidden layer with 11 neurons and a linear transfer function at output layer was obtained. The predictions agreed well with the experimental values with a satisfactory correlation coefficient in the range of 0.9249-0.9988, the absolute fraction of variance in the range of 0.8753-0.9976, and the mean relative error in the range of 0.0008-0.54%, moreover, the root mean square error values for the ANN training and predictions were very low relative to the range of the experiments. The results reveal that ANN model can be used effectively for predicting the performance characteristics of RUCT under cross flow conditions, then providing the theoretical basis on the research of heat and mass transfer inside RUCT, which is important for design and running control of the RUCT system. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Reversibly used cooling tower Heating Artificial neural network back-propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Incorporation of Robust Sliding Mode Control and Adaptive Multi-Layer Neural Network-Based Observer for Unmanned Aerial Vehicles

引用

IEEE ACCESS 2024年 12卷 98107-98120页

作者： Akhtar, Zainab Naqvi, Syed Abbas Zilqurnain Hamayun, Mirza Tariq Ahsan, Muhammad Nadeem, Ahsan Muyeen, S. M. Oshnoei, Arman Univ Engn & Technol Mechatron & Control Engn Dept Lahore 54000 Pakistan COMSATS Univ Islamabad CUI Dept Elect & Comp Engn Lahore Campus Lahore 54000 Pakistan Aalborg Univ Dept Energy DK-9220 Aalborg Denmark Qatar Univ Dept Elect Engn Doha Qatar

The control and state estimation of Unmanned Aerial Vehicles (UAVs) provide significant challenges due to their complex and nonlinear dynamics, as well as uncertainties arising from factors such as sensor noise, wind gusts, and parameter fluctuations. Neural network-based methods tackle these problems by accurately approximating unknown nonlinearities through training on input-output data. This paper proposes an adaptive Multi-layer Neural Network (MLNN) Luenberger observer-based control for altitude and attitude tracking of a quadrotor UAV. The MLNN observer, employing a modified back-propagation algorithm, is used for the quadrotor's state estimation. The adaptive nature of the proposed observer helps mitigate the effects of parameters such as wind gusts, measurement noise, and parameter variations. Subsequently, a sliding mode controller is designed based on the observed states to track the reference trajectories. Lyapunov stability is ensured by using the modified back-propagation weight update rule for the proposed MLNN observer. Simulation results demonstrate superior tracking performance of the proposed observer compared to the Sliding Mode Observer (SMO) and a Single Hidden Layer Neural Network (SHLNN) observer, even in the presence of the aforementioned parameters.

关键词： Observers Quadrotors Noise measurement Autonomous aerial vehicles Neural networks Kalman filters Uncertainty backpropagation Sliding mode control back-propagation algorithm multiple hidden layers perceptron (MLP) neural network (NN) observer sliding mode controller (SMC) sliding mode observer UAVs

来源：评论

学校读者我要写书评

暂无评论

Application of BPANN for prediction of backward ball spinning of thin-walled tubular part with longitudinal inner ribs

引用

JOURNAL OF MATERIALS PROCESSING TECHNOLOGY 2008年第1-3期196卷 190-196页

作者： Jiang, Shuyong Ren, Zhengyi Xue, Kemin Li, Chunfeng Harbin Engn Univ Engn Training Ctr Harbin 150001 Peoples R China Hefei Univ Technol Sch Mat Sci & Engn Hefei 230000 Peoples R China Harbin Inst Technol Sch Mat Sci & Engn Harbin 150001 Peoples R China

As a successively and locally plastic deformation process, backward ball spinning is applied for the purpose of manufacturing thin-walled tubular part with longitudinal inner ribs. Obtaining the desired inner ribs is one of the most critical tasks in backward ball spinning of thin-walled tubular part with longitudinal inner ribs and the formability of inner ribs depends greatly on the process parameters, such as ball diameter, feed ratio, wall thickness reduction and wall thickness of tubular blank. As a nonlinear dynamics system simulating structure and function of biological neural network in the human brain, back-propagation artificial neural network (BPANN) is used in backward ball spinning of thin-walled tubular part with longitudinal inner ribs. The attractiveness of BPANN comes from its remarkable information processing characteristics pertinent mainly to nonlinearity, adaptability, high parallelism, learning capability, fault and noise tolerance so that it can be more efficient in solving complex and nonlinear optimization problems in backward ball spinning of thin-walled tubular parts with longitudinal inner ribs. Not only can BPANN successfully predict the formability of the inner ribs, but it can simulate the influences of the process parameters on the height of inner ribs as well. In the end, the process parameters are matched so rationally that the desired spun parts can be obtained. (c) 2007 Elsevier B.V. All rights reserved.

关键词： power spinning ball spinning artificial neural networks longitudinal inner ribs back-propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Estimating the fracture gradient coefficient using neural networks for a field in the Middle East

引用

JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING 2005年第3-4期49卷 193-211页

作者： Malallah, A Nashawi, IS Coll Engn & Petr Dept Petr Engn Safat 13060 Kuwait

Fracture gradient constitutes an essential parameter in the pre-design stage of drilling operations, reservoir exploitation and stimulation. Over the years, fracture gradient has been acknowledged to be one of the most important key element that needs to be accurately determined in order to achieve optimum operation results. Several calculation methods have been presented in the literature for different regions of the world. All of these techniques were based on either parametric or empirical correlations, which require a prior knowledge of the functional form. Moreover, these methods are only valid at the area where they were developed. This paper presents an artificial neural network model to predict the fracture gradient for the Middle East region. The data set used in the study consists of more than 21,000 points with fracture gradient measurements taken from 16 wells drilled in seven geological prospects covering more than 200 sq mi. The excellent results obtained from the developed model establish a new simple mechanism for fracture gradient prediction that is based on readily obtainable parameters. The proposed neural network model predicts the fracture gradient as a function of pore pressure, depth and rock density. A detailed comparison between the results predicted by this method and those predicted by other techniques is presented. (c) 2005 Elsevier B.V. All rights reserved.

关键词： artificial neural network back-propagation algorithm feed-forward fracture gradient pore pressure gradient

来源：评论

学校读者我要写书评

暂无评论

Robust adaptive fuzzy neural tracking control for a class of unknown chaotic systems

引用

PRAMANA-JOURNAL OF PHYSICS 2011年第6期76卷 887-900页

作者： Kadir, Abdurahman Wang, Xing-Yuan Zhao, Yu-Zhang Dalian Univ Technol Fac Elect Informat & Elect Engn Dalian 116024 Peoples R China Xinjiang Univ Finance & Econ Sch Engn & Comp Sci Urumqi 830012 Peoples R China

In this paper, an adaptive fuzzy neural controller (AFNC) for a class of unknown chaotic systems is proposed. The proposed AFNC is comprised of a fuzzy neural controller and a robust controller. The fuzzy neural controller including a fuzzy neural network identifier (FNNI) is the principal controller. The FNNI is used for online estimation of the controlled system dynamics by tuning the parameters of fuzzy neural network (FNN). The Gaussian function, a specific example of radial basis function, is adopted here as a membership function. So, the tuning parameters include the weighting factors in the consequent part and the means and variances of the Gaussian membership functions in the antecedent part of fuzzy implications. To tune the parameters online, the back-propagation (BP) algorithm is developed. The robust controller is used to guarantee the stability and to control the performance of the closed-loop adaptive system, which is achieved always. Finally, simulation results show that the AFNC can achieve favourable tracking performances.

关键词： Chaos control adaptive control adaptive identifier fuzzy neural network back-propagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial potential field neuro-fuzzy controller for autonomous navigation of mobile robots

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING 2021年第7期235卷 1179-1192页

作者： Imrane, Mahamat Loutfi Melingui, Achille Ahanda, Joseph Jean Baptiste Mvogo Motto, Frederic Biya Merzouki, Rochdi Univ Yaounde I Dept Phys Fac Sci Yaounde Cameroon Univ Yaounde I Dept Elect & Telecommun Engn Ecole Natl Super Polytech Yaounde 8390 Cameroon Univ Bamenda Dept Elect & Power Engn Bamenda Cameroon Univ Lille CRIStAL Lab CNRS UMR Nord France

Some autonomous navigation methods, when implemented alone, can lead to poor performance, whereas their combinations, when well thought out, can yield exceptional performances. We have demonstrated this by combining the artificial potential field and fuzzy logic methods in the framework of mobile robots' autonomous navigation. In this article, we investigate a possible combination of three methods widely used in the autonomous navigation of mobile robots, and whose individual implementation still does not yield the expected performances. These are as follows: the artificial potential field, which is quick and easy to implement but faces local minima and robustness problems. Fuzzy logic is robust but computationally intensive. Finally, neural networks have an exceptional generalization capacity, but face data collection problems for the learning base and robustness. This article aims to exploit the advantages offered by each of these approaches to design a robust, intelligent, and computationally efficient controller. The combination of the artificial potential field and interval type-2 fuzzy logic resulted in an interval type-2 fuzzy logic controller whose advantage over the classical interval type-2 fuzzy logic controller was the small size of the rule base. However, it kept all the classical interval type-2 fuzzy logic controller characteristics, with the major disadvantage that type-reduction remains the main cause of high computation time. In this article, the type-reduction process is replaced with two layers of neural networks. The resulting controller is an interval type-2 fuzzy neural network controller with the artificial potential field controller's outputs as auxiliary inputs. The results obtained by performing a series of experiments on a mobile platform demonstrate the proposed navigation system's efficiency.

关键词： Mobile robots autonomous navigation type-2 fuzzy logic neural networks back-propagation algorithm artificial potential field

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：