检索结果-内蒙古大学图书馆

Improved bp Classifier via Distance for Sample Reduction

电脑学刊 2019年第2期30卷 1-13页

作者： Jia Wen Jia Deng Peng-Fei Liu Hong-Jun Wang

The bp neural network algorithm is a commonly used technique in the classification field of pattern recognition, which iterates training samples continuously to obtain the decision boundary, until the error reaches the convergence precision. However, due to the extensive redundancy of training samples, this carpet-like training method can easily lead to slow network convergence and low classification performance. In this paper, from the view of sample, a novel bp training method called improved bp Classifier algorithm using Distance for Sample Reduction (DRbp) is proposed. Through the sample weight to get the new training sample, which are the near of the classification interface like support vector, and then iterative training bp classifier to solve the classification issue. The main function of this method is to keep the original sample information, realize the sample reduction, and improve the generalization ability of the bp neural network. First, point sets is used to visualize the training process. And then use 10 sets of the University of California Irvine (UCI) to verify the effectiveness and superiority of our experiments. Finally through Cross-validation, the classification error rate of 10 sets of UCI datasets tested by DRbp training method is lower than that of standard bp neural network (STbp). So the result of the experiment showed that the method of the combined distance sample reduce with bp network can significantly enhance the generalization ability of bp network.

关键词： bp neural network algorithm classification interface sample reduce support vector

来源：评论

学校读者我要写书评

暂无评论

Design of Low Scale Pressure Sensor Intelligent System with Temperature Compensation Based on STM32 4

Design of Low Scale Pressure Sensor Intelligent System with ...

引用

IEEE 4th International Conference on Control Science and Systems Engineering (ICCSSE)

作者： Li, Yanwen Ma, Shaojie Nanjing Univ Sci & Technol Sch Mech Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538678879

This article designs and implements a pressure sensor intelligent system with temperature compensation, which is based on STM32F103RCT6 microcontroller. The system is used to measure accurate small range signals of pressure sensor. Designing the functional circuit makes the output of the system digitized. Utilizing the improved bp neural network algorithm compensates the digital signal of the pressure sensor to ensure the accuracy of the pressure sensor. The repeated test shows that the intelligent system compensates the temperature drift of low scale pressure sensor effectively and ensures the property and the measurement accuracy of the pressure sensor.

关键词： low scale pressure sensor bp neural network algorithm temperature compensation temperature drift

来源：评论

学校读者我要写书评

暂无评论

Study the therapeutic mechanism of Amomum compactum in gentamicin-induced acute kidney injury rat based on a back propagation neural network algorithm

引用

JOURNAL OF CHROMATOGRAPHY B-ANALYTICAL TECHNOLOGIES IN THE BIOMEDICAL AND LIFE SCIENCES 2017年 1040卷 81-88页

作者： Wang, Xiye Chen, Hongmei Chang, Chun Jiang, Mingyang Wang, Xiulan Xu, Liang Inner Mongolia Univ Nationalities Inner Mongolia Key Lab Nat Prod Chem & Funct Mol Coll Chem & Chem Engn Tongliao 028000 Peoples R China Mongolian Med Engn Technol Res Inst Inner Mongoli Tongliao 028000 Peoples R China Inner Mongolia Univ Nationalities Mongolia Med Dept Tongliao 028000 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Natl Educ Minist Coll Comp Sci & Technol Changchun 130012 Peoples R China Inner Mongolia Univ Nationalities Coll Comp Sci & Technol Tongliao 028000 Peoples R China

Acute kidney injury (AKI) is a major global public health problems, as it causes high morbidity and serious injury to renal function. However, the etiology for AKI is not very clear. In this study, a serum metabolite profile analysis was performed to identify potential biomarkers for gentamicin-induced AKI and to investigate the mechanism of action of Amomum compactum (AC) used for treatment. A metabonomics approach by ultra-performance liquid chromatography together with quadrupole time-of-flight mass spectrometry (UPLC-Q-TOF-MS) was applied to perform the analysis. Back propagation (bp) neural network models were established for classifying data from the control, model, and AC-treated groups. Accuracy rate for classification was 91.7% in positive ion mode and 87.5% in negative ion mode. By orthogonal partial least squares discriminant analysis (OPLS-DA), 29 metabolites were identified as potential biomarkers of gentamicin-induced AKI. Most of them are related to phospholipid metabolism. After treatment with AC, the levels of sphingomyelin, sphingosine, phytosphingosine, and arachidonic acid were restored to normal. The results indicate that AC plays a protective role in rats with gentamicin-induced AKI via regulation of the phospholipid metabolic pathway. In this work, early biomarkers of AKI has been identified and underlying therapeutic mechanism of AC has been understood, therefore, AC can be further investigated and tested for clinical application. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Amomum compactum Metabonomics UPLC-MS Acute kidney injury bp neural network algorithm Gentamicin

来源：评论

学校读者我要写书评

暂无评论

The Application of Forecasting algorithms on Electric Vehicle Power Load

The Application of Forecasting Algorithms on Electric Vehicl...

引用

IEEE International Conference on Mechatronics and Automation

作者： Shijun Wang Guobin Xue Chang Ping Dinggang Wang Feng You Tao Jiang Technology Research Institute Gansu Electric Power Company Lanzhou Gansu Province China Electric Transmission &Transformer co. TLD Gansu Electric Power Company Lanzhou Gansu Province China

The autoregressive model algorithm (ARA) of time series analysis and reverse transmission neural network algorithm (bpA) of machine learning were used in this paper, and applied the load forecasting of electric vehicle (EV), through studying and analysising of different algorithms, aiming at certain domestic city electric vehicle charging station has carried on the short-term load forecast, compared of prediction results of the two ways, the simulation results show that different algorithm also have different effects in the short-term load forecasting, therefore, according to different system to select appropriate learning algorithm is particularly important.

关键词： Autoregressive model algorithm bp neural network algorithm Electric car Load forecasting

来源：评论

学校读者我要写书评

暂无评论

Study on inventory control model based on the B2C mode in big data environment

Study on inventory control model based on the B2C mode in bi...

引用

2016 3rd International Conference on Modern Economic Technology and Management(ICMETM 2016)

作者： Zhiping Zhang Meimei Zhang Zixian Zhang Department of Communication Engineering Shijiazhuang Post and Telecommunications Technical College School of Economics and Management North China Electric Power University Network Institute Shijiazhuang Post and Telecommunications Technical College

The current inventory problem has become the key issue in the enterprise survival and *** this paper,we take "Taobao" as an example to conduct a detailed study of the inventory of the high conversion rate based on data ***,by using a funnel model to predict the conversion of the commodities on the critical path,we capture the factors influencing the consumer decision-making on each key point,and propose corresponding solutions of improving the conversion rate;Second,we use bp neural network algorithm to predict the goods traffic,and then obtain the corresponding weights by the relation analysis and the output of the goods traffic by the input of large data sample goods;Third,we can predict the inventory in accordance with the commodity conversion rate and flow prediction,and amend the predicted results to get accurate and real-time inventory forecast,avoiding the economic loss due to the inaccurate inventory.

关键词： big data bp neural network algorithm conversion data mining funnel model inventory

来源：评论

学校读者我要写书评

暂无评论

Research on Food Demand Prediction algorithm Based on Supply Chain Management

引用

Advance Journal of Food Science and Technology 2016年第12期11卷 832-836页

作者： Zhu Jianbin School of Business Administration Research Center of Cluster and Enterprise Development Jiangxi University of Finance and Economics Nanchang Jiangxi 330013 China

An improved bp neural network algorithm for food demand prediction based on supply chain management is presented to realize market and sale management target effectively for food enterprises. First, the working principle of bp neural network algorithm is analyzed to explore the root reasons of its low convergence speed; Second, the paper integrates genetic algorithm with bp algorithm to present a new algorithm, then improves it through encoding chromosome, formatting fitness function, designing selection operator, redesigning crossover operator, designing mutation operator, integrating bp algorithm and optimal individual, improving calculation process step by step; Finally, a supply chain of a food enterprise is taken for experimental sample to illustrate the calculation performance of the improved algorithm and the simulation results indicate that the improved algorithm not only can solve the problem of low convergence speed, but also can improve the demand prediction accuracy and can be used for predicting supply chain demand for food enterprises practically.

关键词： bp neural network algorithm food demand prediction genetic algorithm supply chain management

来源：评论

学校读者我要写书评

暂无评论

An Optimized bp algorithm Based on PLS

An Optimized BP Algorithm Based on PLS

引用

2016 International Conference on Computer, Mechatronics and Electronic Engineering (CMEE 2016)

作者： Na GU Xiao-feng JI Nantong Polytechnic College Nantong Shipping College

Back-propagation(bp) neural network has been widely used for dealing with large-scale nonlinear problems. However, the bp algorithm is powerless, when in the face of singular sample data, which with high characteristic dimensional and small sample size. Too many input makes the network structure is difficult to determine, cause slow convergence rate;fewer number of samples makes the network training is not complete, thereby affecting the recognition precision of the neural network. Aiming at these deficiencies, in this paper proposed the optimized bp neural network algorithm based on the partial least squares(PLS) algorithm(PLS-bp algorithm), firstly the new algorithm reduce feature dimension for singular sample data used PLS method, which can fully take into account the level of correlation characteristic variables and the dependent variables, then get the low-dimensional data is used for network training and simulation. New algorithm simplifies the network structure and improves the network training speed and recognition precision.

关键词： Partial least squares bp neural network algorithm PLS-bp algorithm

来源：评论

学校读者我要写书评

暂无评论

Research of Rice Appearance Quality Recognition 7

Research of Rice Appearance Quality Recognition

引用

Seventh International Conference on Advanced Communication and networking (ACN)

作者： Zhong, Weifeng Ma, Lixia Yin, Yuheng Harbin Univ Sci & Technol Sch Automat Harbin Peoples R China

ISBN: (纸本)9781467379557

Rice is the common food in people's daily life, different grades of rice have a great difference to the influence of taste, therefore, it is important to identify the rice quality. In order to improve the accuracy and real-time performance of the rice quality identification, PCA algorithm (Principal Component Analysis) and bp neural network algorithm are proposed to identify the rice quality. The feature variables of rice are extracted by PCA algorithm, then training the bp neural network parameters with the variables as its input, finally the bp neural network trained is used to identify the rice quality. The algorithm is implemented into MATLAB software. The simulation shows that the PCA-bp algorithm is greatly well than bp algorithm in accuracy and real-time performance.

关键词： Quality identification Rice PCA bp neural network algorithm

来源：评论

学校读者我要写书评

暂无评论

Research and prevention of illegal intrusion of digital television network

Research and prevention of illegal intrusion of digital tele...

引用

2015 International Conference on Electric, Electronic and Control Engineering (ICEECE 2015)

作者： Xiangfeng Hu College of Physics Tonghua Normal University

Digital television is now developing rapidly in *** momentum is thrilling,which also brings numerous network security *** paper carries out a study on illegal intrusion of digital television *** from detection model,it proposes the intrusion detection method based on ESTQ and the intrusion detection method based on expert system and bp neural network algorithm on the basis of the analysis on potential safety hazards of digital television *** also designs a realization approach of linkage alarm in method research and analysis so as to lay a theoretical foundation for the sound development of radio and television undertakings in China.

关键词： illegal intrusion detection alarming device ESTQ four components expert system bp neural network algorithm

来源：评论

学校读者我要写书评

暂无评论

Empirical Research of Evaluating Training Base Teaching for Higher Vocation Education

Empirical Research of Evaluating Training Base Teaching for ...

引用

作者： Zhaohui Zheng Xuehui Pei Mingfu Liao Academic Affairs Office of Jiangxi Vocational and Technical College of Information E-commerce & Management Department of Jiangxi Vocational and Technical College of Information Foreign language college of Jiangxi agriculture university

Training base teaching evaluation of higher vocation education is one of the difficult and hot research fields in higher education management. Using bp neural network algorithm, a new clustering segmentation algorithm is presented. Firstly, According to the characteristics of training base teaching evaluation of higher vocation, a new evaluation indicator system is constructed from the perspectives of training preparation, specific training, training administration, training effects;Second, the paper improves the original bp algorithm through adjusting the value of momentum factor, taking dynamic strategy of momentum factor and adaptive change of algorithm step to speed up the calculation;Finally, the empirical results shows that improved model has high evaluation accuracy when used to evaluate training base teaching of higher vocation education and can improve process stability and speed greatly.

关键词： Higher vocation education Training base teaching evaluation bp neural network algorithm Evaluation indicator system

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：