检索结果-内蒙古大学图书馆

2013 AASRI Conference on Intelligent Systems and Control（ISC 2013）

作者： Amit Choudhary Rahul Rishi Savita Ahlawat Maharaja Surajmal Institute UIET Maharshi Dayanand University Maharaja Surajmal Institute of Technology

The choice of pattern classifier and the technique used to extract the features are the main factors to judge the recognition accuracy and the capability of an Optical Character Recognition（OCR） system. The main focus of this work is to extract features obtained by binarization technique for recognition of handwritten characters of English language. The recognition of handwritten character images have been done by using multi-layered feed forward artificial neural network as a classifier. Some preprocessing techniques such as thinning, foreground and background noise removal, cropping and size normalization etc. are also employed to preprocess the character images before their classification. Very promising results are achieved when binarization features and the multilayer feed forward neural network classifier is used to recognize the off-line cursive handwritten characters.

关键词： OCR Binarization Feature Extraction Character Recognition backpropagation algorithm Neural Network

来源：评论

学校读者我要写书评

暂无评论

IDENTIFICATION OF NONLINEAR DYNAMICS OF NUCLEAR POWER REACTOR USING ADAPTIVE FEEDFORWARD NEURAL NETWORK

IDENTIFICATION OF NONLINEAR DYNAMICS OF NUCLEAR POWER REACTO...

引用

The 2nd Session of 2010 Workshop of Pakistan Academy of Sciences

作者： Arshad H.Malik Aftab A.Memon Muhammad R.Khan Directorate of Post Graduate Studies Mehran University of Engineering and TechnologyJamshoroSindhPakistan Department of Telecommunication Engineering Mehran University of Engineering & TechnologyJamshoroSindh Pakistan Electrical Engineering Pakistan Atomic Energy CommissionPakistan

In this paper,the authors have attempted the identification of real world non-linear time-varying Pressurized Heavy Water Reactor(PHWR) *** nonlinear dynamics is identified using adaptive feedforward neural network *** neural network(ANN) has been introduced to solve PHWR nuclear power plant operation complexity in *** Multi-input single-output(MISO) neural systems are designed for the prediction of control rod reactivity,moderator reactivity,moderator level and actual reactor power based on control rod and moderator level dynamics.A severe transient has been imposed in training and prediction phases with proposed *** proposed ANN is developed in *** essence,the proposed adaptive feedforward neural network mimics and identifies the actual nonlinear time-varying dynamics of PHWR system for an operating PHWR-type nuclear power plant in *** proposed ANN is found highly efficient and *** performance of the proposed ANN is investigated and the predicted results are in good agreement with the measured results.

关键词： Nonlinear Dynamics MISO Identification backpropagation algorithm moderator system control rod system PHWR nuclear power plant

来源：评论

学校读者我要写书评

暂无评论

A novel adaptive momentum method for medical image classification using convolutional neural network

引用

BMC MEDICAL IMAGING 2022年第1期22卷 34-34页

作者： Aytac, Utku Can Gunes, Ali Ajlouni, Naim Istanbul Aydin Univ Fac Comp Engn Comp Engn Dept Inonu Cd 38 TR-34295 Istanbul Turkey Istanbul Aydin Univ Comp Engn Dept Istanbul Turkey Istanbul Atlas Univ Comp Engn Dept Istanbul Turkey

Background AI for medical diagnosis has made a tremendous impact by applying convolutional neural networks (CNNs) to medical image classification and momentum plays an essential role in stochastic gradient optimization algorithms for accelerating or improving training convolutional neural networks. In traditional optimizers in CNNs, the momentum is usually weighted by a constant. However, tuning hyperparameters for momentum can be computationally complex. In this paper, we propose a novel adaptive momentum for fast and stable convergence. Method Applying adaptive momentum rate proposes increasing or decreasing based on every epoch's error changes, and it eliminates the need for momentum hyperparameter optimization. We tested the proposed method with 3 different datasets: REMBRANDT Brain Cancer, NIH Chest X-ray, COVID-19 CT scan. We compared the performance of a novel adaptive momentum optimizer with Stochastic gradient descent (SGD) and other adaptive optimizers such as Adam and RMSprop. Results Proposed method improves SGD performance by reducing classification error from 6.12 to 5.44%, and it achieved the lowest error and highest accuracy compared with other optimizers. To strengthen the outcomes of this study, we investigated the performance comparison for the state-of-the-art CNN architectures with adaptive momentum. The results shows that the proposed method achieved the highest with 95% compared to state-of-the-art CNN architectures while using the same dataset. The proposed method improves convergence performance by reducing classification error and achieves high accuracy compared with other optimizers.

关键词： Adaptive momentum methods Nonconvex optimization backpropagation algorithm Convolutional neural networks Medical image classification

来源：评论

学校读者我要写书评

暂无评论

Guide Data Generation for On-Line Learning of DBM-Initialized MLP

Guide Data Generation for On-Line Learning of DBM-Initialize...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Yuya Kaneda Qiangfu Zhao Yong Liu Dept. of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Fukushima Japan

ISBN: (纸本)9781509018987

In this paper, we propose a method for generating guide data, and investigate its efficiency and efficacy for online learning with guide data. On-line learning in this research updates a learning model initialized by the decision boundary making algorithm proposed by us in our earlier study. The problem is that, if the guide data are not properly generated, on-line learning may require high computational cost in terms of time, and the learning process may not converge to good result. To solve this problem, we propose to use k-means to cluster all candidates of guide data, and use one datum from each cluster as the guide datum. We conducted experiments on several public databases, using different settings, and confirmed the performance of the proposed method. Specifically, if k=5, we can obtain good models with low computational cost through on-line learning.

关键词： On-Line Learning Decision Boundary Making Multilayer Perceptron backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Forecasting Indian Stock Market Using Artificial Neural Networks

Forecasting Indian Stock Market Using Artificial Neural Netw...

引用

International Conference on Computing Communication Control and Automation

作者： Ashutosh Kale Prathamesh Kumkar Omkaar Khanvilkar Ishan Madan Hardik Jivani Tanuja Sarode Department of Computer Engineering Thadomal Shahani Engineering College Mumbai India

ISBN: (纸本)9781538652589;9781538652572

The objective of this research is to predict the next day's opening value of Nifty-100 index of the National Stock Exchange (NSE) using Artificial Neural Networks (ANNs). The ANN is trained using Error backpropagation Training algorithm (EBPTA). The multilayer feedforward network is trained using the present day's closing values of seven input parameters which are Gold, Silver, Copper, Crude Oil, Natural Gas and Foreign Exchange (FOREX) rates. In addition to these six rates, the closing value of Nifty-100 index was incorporated as input using Simple Moving Average (SMA) model. The relationship between each input parameter and Nifty-100 index was studied and analyzed using correlation technique. This research proves that Nifty-100 index can be predicted using ANNs.

关键词： Nifty-100 index Artificial neural networks backpropagation algorithm Cross-validation Forecasting indian stock market

来源：评论

学校读者我要写书评

暂无评论

Neural Network Speed Identification Scheme for Speed Sensor-less DTC Induction Motor Drive System

Neural Network Speed Identification Scheme for Speed Sensor-...

引用

The Third International Power Electronics and Motion Control Conference

作者： Xianmin Ma Zhi Na Department of Automation Engineering Of XiE28099an University of Science and Technology Xi'an Shanxi China Department of Automation Engineering Xi''an University of Science and Technology Xi'an Shanxi China

ISBN: (纸本)780003464X

A novel neural network speed identification scheme for the speed sensorless direct torque control (DTC) of an induction motor drive system is presented in the paper. The system uses current and voltage sensors for rotor speed and rotor flux estimation with a digital signal processor (DSP) TMS320F240 in a closed loop control system. Rotor speed identification is based on the model reference adaptive control (MRAC) theory with a neural network using the backpropagation (BP) algorithm. The suggested speed identification method has been validated by a simulation study.

关键词： induction motor drives machine vector control control system synthesis neurocontrollers velocity control torque control machine theory parameter estimation model reference adaptive control systems control system analysis backpropagation neural network speed identification scheme speed sensorless direct torque control induction motor drive control design current sensors voltage sensors rotor speed estimation rotor flux estimation closed loop control system control simulation model reference adaptive control backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep

Electroencephalography Analysis Using Neural Network and Sup...

引用

2013 International Conference on Biomedical Engineering(ICBE 2013)

作者： JeeEun Lee Sun K.Yoo Graduate School of Biomedical Engineering Yonsei University Department of Medical Engineering College of Medicine Yonsei University

The purpose of this paper is to analyze sleep stages accurately using fast and simple classifiers based on the frequency domain of electroencephalography（EEG） signal. To compare and evaluate system performance, the rules of Recht-schaffen and Kales（R＆K rule） were used. Parameters were extracted from preprocessing process of EEG signal as feature vectors of each sleep stage analysis system through representatives of back propagation algorithm and support vector machine （SVM）. As a result, SVM showed better performance as pattern recognition system for classification of sleep stages. It was found that easier analysis of sleep stage was possible using such simple system. Since accurate estimation of sleep state is possible through combination of algorithms, we could see the potential for the classifier to be used for sleep analysis system.

关键词： Sleep Electroencephalography Neural Network backpropagation algorithm SVM

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Networks Applied in Environmental Quality Assessment

Artificial Neural Networks Applied in Environmental Quality ...

引用

2010 3rd IEEE International Conference on Computer Science and Information Technology—ICCSIT 2010

作者： Liu Yijun,Tang Jiali,Jiang Hongfen,Zhu Guangping,Yu Zhimin School of Computer Engineering Jiangsu Teachers University of Technology Changzhou,China

The problem of environmental quality assessment is a pattern recognition problem,and a well-trained ANN can exploit the underlying nonlinear relationships that determine the environmental rating of a *** this study,we are trying with the neural network model to make an effective analysis for environmental quality assessment.A 4-9-1 threelayer feedforward neural network using the backpropagation and Levenberg-Marquardt algorithms has been used in the proposed artificial neural *** case study shows that this neural network is efficient and forms a useful tool for the prediction of environmental quality.

关键词： artificial neural network backpropagation algorithm Levenberg-Marquardt algorithm environmental quality assessment

来源：评论

学校读者我要写书评

暂无评论

Multinodal Load Forecasting in Power Electric Systems using a Neural Network with Radial Basis Function

Multinodal Load Forecasting in Power Electric Systems using ...

引用

2011 First International Conference on High Performance Structures and Materials Engineering (ICHPSM 2011)

作者： Alessandra Bonato Altran Carlos Roberto Minussi Mara Lucia Martins Lopes Fbio Roberto Chavarette Nelson Jos Peruzzi Faculty of Engeneering UNESP-Univ Estadual PaulistaDepartament of Electrical Engeneering Faculty of Engeneering UNESP-Univ Estadual PaulistaDepartament of Mathematics UNESP-Univ Estadual Paulista Department of Exact Science

In this paper we present the results of the use of a methodology for multinodal load forecasting through an artificial neural network-type Multilayer Perceptron,making use of radial basis functions as activation function and the backpropagation algorithm,as an algorithm to train the *** methodology allows you to make the prediction at various points in power system,considering different types of consumers(residential,commercial,industrial) of the electric grid,is applied to the problem short-term electric load forecasting(24 hours ahead).We use a database(Centralised Dataset- CDS) provided by the Electricity Commission de New Zealand to this work.

关键词： Multinodal Forecast of Electric Load Artificial Neural Networks backpropagation algorithm Radial Basis Function

来源：评论

学校读者我要写书评

暂无评论

HIERARCHICAL TAKAGI-SUGENO TYPE FUZZY SYSTEM FOR DIABETES MELLITUS FORECASTING

HIERARCHICAL TAKAGI-SUGENO TYPE FUZZY SYSTEM FOR DIABETES ME...

引用

2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

作者： ARASH SHARIFI MAHDI ALIYARI SH MOHAMMAD TESHNEHLAB ASIYEH VOSOLIPOUR Computer department of Islamic Azad University Science and Research Branch Tehran Iran Electrical Engineering department of K.N.Toosi University of Technology Tehran Iran

In this study, a new group method of data handling (GMDH) method, based on adaptive neurofuzzy inference system (ANF1S) structure, called ANFIS-GMDH and its application for diabetes mellitus forecasting is presented. Conventional neurofuzzy GMDH (NF-GMDH) uses radial basis network (RBF) as the partial descriptions. In this study the RBF partial descriptions are replaced with two input ANFIS structures and backpropagation algorithm is chosen for learning this network structure. The Prima Indians diabetes data set is used as training and testing sets which consist of 768 data whereby 268 of them are diagnosed with diabetes. The result of this study will provide solutions to the medical staff in determining whether someone is the diabetes sufferer or not which is much easier rather than currently doing a blood test. The results show that the proposed method performs better than the other models such as multi layer perceptron (MLP), RBF and ANFIS structure.

关键词： Hierarchical Takagi-Sugeno fuzzy system ANFIS structure backpropagation algorithm Diabetic mellitus

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：