检索结果-内蒙古大学图书馆

Credit risk assessment of small and medium-sized enterprises in supply chain finance based on SVM and bp neural network

引用

neural COMPUTING & APPLICATIONS 2022年第15期34卷 12467-12478页

作者： Zhao, Jingfeng Li, Bo North China Univ Water Resources & Elect Power Sch Management & Econ Zhengzhou 450046 Henan Peoples R China

Our country's market economy is composed of enterprises. However, due to their inherent credit deficiencies and high risks of management, it is very difficult for them to obtain financing support. Based on this, this article studies Error Back Propagation (bp) to establish (SMEs). Based on the relevant concepts of the supply chain management budget model, it explores the main factors influencing the financial impact of SMEs and the benefits of the supply chain budget in solving problems expenditure of SMEs, support vector machine is mainly based on solving the main credit risks of small and medium-sized enterprises, such as poor information transparency, low credit and various risk unknown factors. bp neural network is an algorithm that takes into account the components of supply chain financial financing. This article first gives a simple background and theoretical introduction to the under the current supply chain finance model, and then proposes to use SVM and bp neural network algorithms to build and the model has been trained and tested. After collecting relevant references, we will establish authoritative risk assessment rules in accordance with this article according to these standards. These experts are mainly people with many years of experience in the financial industry, and they also have a certain influence in the industry. The risk assessment established for this can be the analysis of factors such as risk indicators and government intervention in this experiment.

关键词： SVM algorithm bp neural network algorithm Supply chain finance Small and medium enterprises Credit risk assessment

来源：评论

学校读者我要写书评

暂无评论

The Prediction of liquid holdup in horizontal pipe with bp neural network

引用

ENERGY SCIENCE & ENGINEERING 2020年第6期8卷 2159-2168页

作者： Xiao, Rongge Li, Kai Sun, Leyuan Zhao, Jiali Xing, Peng Wang, Haifeng Xian Shiyou Univ Coll Petr Engn Shaanxi Key Lab Adv Stimulat Technol Oil & Gas Re Xian 710065 Shaanxi Peoples R China Petrochina West East Gas Pipeline Shanghai Peoples R China

Liquid holdup is one of the most critical factors for the formation of pipe effusion, which is closely related to the efficiency of pipe transportation. Nowadays, liquid holdup is mainly estimated according to empirical or semiempirical correlation. Besides, little has been done concerning the accurate prediction of liquid holdup. Therefore, to obtain more precise forecast, this paper proposed a prediction method concerning liquid holdup in horizontal pipe with bp neural network algorithm. Meanwhile, a sensitivity analysis on the key factors impacting liquid holdup was conducted by the combination of the forecast calculation and orthogonal experiment design. The results showed that compared with the empirical calculation (the smallest standard deviation 8.65%), the bp neural network prediction model had achieved more accurate estimation (the average relative error is 7.38%). In addition, the sensitivity analysis indicated that the main indexes including pipe diameter, gas- and liquid-phase superficial velocities, and temperature have significant influence on the liquid holdup. Pipe diameter, liquid-phase superficial velocity, temperature, and viscosity are positively correlated with the liquid holdup, while pressure and gas-phase superficial velocity are negatively correlated with it.

关键词： bp neural network algorithm gas-liquid two-phase flow influencing factors liquid holdup orthogonal test

来源：评论

学校读者我要写书评

暂无评论

Research on Diagnosis Device of Insulator Pollution Degree Based on bp neural network 3

Research on Diagnosis Device of Insulator Pollution Degree B...

引用

3rd Asia Energy and Electrical Engineering Symposium (AEEES)

作者： Liu, Yunpeng Yang, Jiajun Li, Yonglin Pei, Shaotong Liu, Jiashuo Lai, Tingyu North China Elect Power Univ Coll Elect & Elect Engn Beijing Peoples R China

ISBN: (纸本)9781665425513

In order to realize the real-time diagnosis of local insulator pollution, a kind of local insulator pollution diagnosis device is designed based on bp (Back Propagation) neural network prediction and classification algorithm, which can communicate with domestic ultraviolet imager in real time. According to the obtained photoelectron number, apparent discharge, detection distance and gain from ultraviolet imager, the insulator pollution grade is evaluated by bp neural network algorithm. The research results lay a foundation for the practical engineering application of the local insulator pollution diagnosis device.

关键词： insulator pollution degree real-time diagnosis bp neural network algorithm

来源：评论

学校读者我要写书评

暂无评论

A Forecasting Method for Rainfall Distribution at Four Rainfall Stations in Xining Area Based on bp neural network 1

引用

3rd EAI International Conference on Artificial Intelligence for Communications and networks, AICON 2021

作者： Xiong, Zhuang Ma, Jun Zhou, Bingrong Zhang, Lingfei Chen, Bohang Lan, Haiming The Computer College Qinghai Normal University Qinghai Xining810008 China Academy of Plateau Science and Sustainability Qinghai Xining810016 China Institute of Meteorological Science of Qinghai Province Xining810001 China College of XiNing Urban Vocational and Technical Xining Qinghai Xining810000 China

ISBN: (数字)9783030901998

ISBN: (纸本)9783030901981

The recent years have witnessed increasing precipitation in Xining area. This makes the statistics of rainfall particularly important since crucial reference can be provided for mudslides, landslides, and urban waterlogging. The mathematical models constructed based on the improvement or reorganization of neural network algorithms are mainly used to predict rainfall intensity and analyze rainfall data, and there are few studies on the changes in rainfall characteristics and rainfall distribution. This study made full use of 4380 data on rainfall collected from the four stations in Xining area in 2017, 2018, and 2019, analyzed the rainfall distribution at each station;4380 data were used as the dataset, which was reorganized and divided into two parts: the training set and the test set, and a prediction method for rainfall distribution at four stations in Xining area based on the bp neural network was proposed. This forecasting method uses an improved model algorithm for the number of iterations of rainfall data adjustment and neuron nodes in the hidden layer. Through MATLAB programming and debugging, and data comparison and analysis, a stable and reliable identification and classification algorithm model was obtained. The model algorithm can be used to compare and analyze the data of daily rainfall of different regions, latitudes, longitudes, and altitudes in Xining area in the future. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： bp neural network algorithm Daily rainfall Mathematical model MATLAB Neuron node

来源：评论

学校读者我要写书评

暂无评论

Fatigue Driving Detection Method Based on Combination of bp neural network and Time Cumulative Effect

引用

SENSORS 2022年第13期22卷 4717-4717页

作者： Chen, Jian Yan, Ming Zhu, Feng Xu, Jing Li, Hai Sun, Xiaoguang Yangzhou Univ Sch Mech Engn Yangzhou 225127 Jiangsu Peoples R China

Fatigue driving has always received a lot of attention, but few studies have focused on the fact that human fatigue is a cumulative process over time, and there are no models available to reflect this phenomenon. Furthermore, the problem of incorrect detection due to facial expression is still not well addressed. In this article, a model based on bp neural network and time cumulative effect was proposed to solve these problems. Experimental data were used to carry out this work and validate the proposed method. Firstly, the Adaboost algorithm was applied to detect faces, and the Kalman filter algorithm was used to trace the face movement. Then, a cascade regression tree-based method was used to detect the 68 facial landmarks and an improved method combining key points and image processing was adopted to calculate the eye aspect ratio (EAR). After that, a bp neural network model was developed and trained by selecting three characteristics: the longest period of continuous eye closure, number of yawns, and percentage of eye closure time (PERCLOS), and then the detection results without and with facial expressions were discussed and analyzed. Finally, by introducing the Sigmoid function, a fatigue detection model considering the time accumulation effect was established, and the drivers' fatigue state was identified segment by segment through the recorded video. Compared with the traditional bp neural network model, the detection accuracies of the proposed model without and with facial expressions increased by 3.3% and 8.4%, respectively. The number of incorrect detections in the awake state also decreased obviously. The experimental results show that the proposed model can effectively filter out incorrect detections caused by facial expressions and truly reflect that driver fatigue is a time accumulating process.

关键词： fatigue driving detection Adaboost algorithm cascade regression tree bp neural network algorithm time accumulation effect

来源：评论

学校读者我要写书评

暂无评论

Visual prediction of gas diffusion concentration based on regression analysis and bp neural network

引用

JOURNAL OF ENGINEERING-JOE 2019年第13期2019卷 19-23页

作者： Wang, Jing Fang, Jiandong Zhao, Yvdong Inner Mongolia Univ Technol Hohhot Peoples R China Inner Mongolia Autonomous Reg Agr & Anim Husb Inf Hohhot Peoples R China

In order to realise the prediction of the diffusion trend of chemical gases under toxic, flammable, and explosive conditions, this article used a multiple regression model and a back propagation (bp) neural network model, established two kinds of leakage gas diffusion models based on Fluent simulation data. First, the multivariate function relation between multiple influencing factors and diffusion concentration is established by using linear fitting method, i.e. multivariate regression model. Second, according to the large number and non-linearity of Fluent simulation data of leakage gas, a three-layer bp neural network prediction model for leakage gas, wind speed, X-axis diffusion distance, and Y-axis diffusion distance was established by using bp neural network algorithm. Under the same data conditions, the prediction error of bp neural network prediction model is smaller than that of multivariate reversion model, and the fitting degree is high, but the stability of multiple linear regression is better.

关键词： backpropagation neural nets diffusion regression analysis toxicology chemical engineering computing finite element analysis explosive conditions multiple regression model bp neural network model leakage gas diffusion models Fluent simulation data multivariate function relation multiple influencing factors linear fitting method nonlinearity three-layer bp neural network prediction model diffusion distance bp neural network algorithm data conditions prediction error multivariate reversion model multiple linear regression visual prediction gas diffusion concentration regression analysis diffusion trend chemical gases toxic conditions flammable conditions

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

Research on the rapid design technology of automotive inspection structure based on MBD model

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING 2022年第8期236卷 1670-1686页

作者： Wang, Shuchun Cheng, Qi Wang, Lina Xu, Jingying Fang, Xifeng Kang, Jie Key Lab Adv Mfg Technol Jiangsu Prov Zhenjiang Jiangsu Peoples R China Jiangsu Univ Sci & Technol Sch Mech Engn 666 Changhui Rd Zhenjiang 212100 Jiangsu Peoples R China Sanjiang Univ Sch Mech & Elect Engn Nanjing Peoples R China

In view of the specificity and low efficiency of the design of automobile inspection fixture, a deformation design method of inspection fixture based on bp neural network algorithm is proposed. bp neural network algorithm is used to realize the learning and classification of case knowledge, and FCM (fuzzy c-means) algorithm and kernel principal component analysis are used to optimize the information source to improve the retrieval efficiency and accuracy. Based on the analysis of the existing fixture design case structure, the case structure is skeletonized to increase the applicability of the case structure. At the same time, the case frame structure is associated with the size chain, the priority deformation rule is proposed, and the relationship of each size chain is established to realize the mutual adjustment of each size chain. From the similarity of retrieval cases, the paper proposes the design scheme of inspection tools to improve the design efficiency. Finally, taking the front bumper model as the experimental object, the deformation rules are compared, and the priority deformation rule is more accurate than the ordinary basic rule. Compared with the manual design, the design efficiency of this method is improved by 55.71%, which proves the feasibility of this method.

关键词： bp neural network algorithm FCM clustering algorithm skeleton structure automobile inspection fixture deformation design

来源：评论

学校读者我要写书评

暂无评论

Large-Signal Behavior Modeling of GaN P-HEMT Based on GA-ELM neural network

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2022年第4期41卷 1834-1847页

作者： Wang, Shaowei Zhang, Jincan Liu, Min Liu, Bo Wang, Jinchan Yang, Shi Henan Univ Sci & Technol Elect Engn Coll Luoyang 471023 Peoples R China Novaco Microelect Technol Ltd Nantong 226000 Peoples R China

The Genetic algorithm-Extreme Learning Machine (GA-ELM) neural network algorithm is proposed to model the relevant characteristics of GaN pseudomorphic high electron mobility transistor (P-HEMT) large signal. This algorithm solves the over-fitting problem of the Back Propagation (bp) neural network algorithm in the prediction data. It has the characteristics of fast calculation speed, so it can greatly save calculation processing time. It can also randomly generate the connection weights of the input layer, the hidden layer and the threshold of the hidden layer neurons, avoiding errors in parameter selection. In order to verify the superiority of the algorithm, the modeling effects of the bp neural network algorithm model, the Genetic algorithm-Back Propagation (GA-bp) neural network algorithm model and the GA-ELM neural network algorithm model are compared in this paper. The results show that the proposed GA-ELM neural network algorithm model has the highest accuracy.

关键词： bp neural network algorithm GA-bp neural network algorithm GA-ELM neural network algorithm GaN large-signal model

来源：评论

学校读者我要写书评

暂无评论

Multiple Kinds of Pesticides Detection Based on Back-Propagation neural network Analysis of Fluorescence Spectra

IEEE PHOTONICS JOURNAL

引用

IEEE PHOTONICS JOURNAL 2020年第2期12卷 1-9页

作者： Bian, Haiyi Yao, Hua Lin, Guohua Yu, Yinshan Chen, Ruiqiang Wang, Xiaoyan Ji, Rendong Yang, Xiao Zhu, Tiezhu Ju, Yongfeng Huaiyin Inst Technol Fac Elect Informat Engn Huaian 223003 Jiangsu Peoples R China Jiangsu Engn Lab Lake Environm Remote Sensing Tec Huaian 223003 Jiangsu Peoples R China

Fluorescence spectroscopy attracted more and more attention in pesticide residue detection field because of its advantages of non-destructive, non-contact, high speed and no requirement of complex pre-process procedure. However, given that the concentration of the pesticide detected via fluorescence spectroscopy is calculated in accordance with the Beer-Lambert law, this method can only be used to detect samples containing a single kind of pesticide or several kinds of pesticides with completely different fluorescence which is not in accordance with practical cases. In this article, to overcome this disadvantage, back-propagation (bp) neural network algorithm was introduced to detect multiple kinds of pesticides via fluorescence spectroscopy. The results from four kinds of pesticides which are usually used for fruits and vegetables indicated the effectiveness of bp neural network algorithm.

关键词： Pesticide residue fluorescence spectroscopy bp neural network 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：