The Factors Affecting GDP Growth

This paper discusses the factors affecting GDP growth. By processing the data related to GDP, this paper uses AHP method, BP neural network, SVR method and economic policy correction model to quantitatively analyze the impact of different candidate countries on the U.S. economy and China’s economy. Combined with political, economic, social, environmental and other factors, referring to the national policy, the index system is obtained. The judgment matrix is constructed by AHP, and the more important one is extracted as the main index. Then the evaluation is carried out by using neural network. Firstly, the index is combined with the existing GDP standard system, and then network training and simulation are carried out. After substituting the data, we get and analyze the interaction between the indicators of each factor, and determine the positive correlation and negative correlation between the factors in the schematic diagram. As for the influence of policy factors, GDP is indirectly affected through tangible influence.

Download Full-text

A Geometric Perspective on Information Plane Analysis

Entropy ◽

10.3390/e23060711 ◽

2021 ◽

Vol 23 (6) ◽

pp. 711

Author(s):

Mina Basirat ◽

Bernhard C. Geiger ◽

Peter M. Roth

Keyword(s):

Neural Network ◽

Mutual Information ◽

Geometric Interpretation ◽

Neural Network Training ◽

Neural Network Learning ◽

Network Learning ◽

Plane Analysis ◽

Network Training ◽

Hidden Layer ◽

The Impact

Information plane analysis, describing the mutual information between the input and a hidden layer and between a hidden layer and the target over time, has recently been proposed to analyze the training of neural networks. Since the activations of a hidden layer are typically continuous-valued, this mutual information cannot be computed analytically and must thus be estimated, resulting in apparently inconsistent or even contradicting results in the literature. The goal of this paper is to demonstrate how information plane analysis can still be a valuable tool for analyzing neural network training. To this end, we complement the prevailing binning estimator for mutual information with a geometric interpretation. With this geometric interpretation in mind, we evaluate the impact of regularization and interpret phenomena such as underfitting and overfitting. In addition, we investigate neural network learning in the presence of noisy data and noisy labels.

Download Full-text

Research on the hydrographic survey cycle for updating navigational charts

Journal of Navigation ◽

10.1017/s0373463320000776 ◽

2021 ◽

pp. 1-13

Author(s):

Jing Duan ◽

Xiaoxia Wan ◽

Jianan Luo

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Calculation Model ◽

Impact Factors ◽

Factors Affecting ◽

Material Resources ◽

Hydrographic Survey ◽

Survey Planning ◽

The Impact ◽

The Relationship

Abstract Due to the vast ocean area and limited human and material resources, hydrographic survey must be carried out in a selective and well-planned way. Therefore, scientific planning of hydrographic surveys to ensure the effectiveness of navigational charts has become an urgent issue to be addressed by the hydrographic office of each coastal state. In this study, a reasonable calculation model of hydrographic survey cycle is established, which can be used to make the plan of navigational chart updating. The paper takes 493 navigational charts of Chinese coastal ports and fairways as the research object, analyses the fundamental factors affecting the hydrographic survey cycle and gives them weights, proposes to use the BP neural network to construct the relationship between the cycle and the impact factors, and finally establishes a calculation model of the hydrographic survey cycle. It has been verified that the calculation cycle of the model is effective, and it can provide reference for hydrographic survey planning and chart updating, as well as suggestions for navigation safety.

Download Full-text

Study on Elman Neural Networks Algorithms Based on Factor Analysis

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.511-512.945 ◽

2014 ◽

Vol 511-512 ◽

pp. 945-949 ◽

Cited By ~ 1

Author(s):

Shao Xue Jing ◽

Wei Kuan Jia

Keyword(s):

Neural Network ◽

Factor Analysis ◽

Computing Time ◽

Storage Space ◽

Elman Neural Network ◽

Actual Problem ◽

Network Training ◽

The Index System ◽

Hidden Layer ◽

Low Dimensional

When we manipulate high dimensional data with Elman neural network, many characteristic variables provide enough information, but too many network inputs go against designing of the hidden-layer of the network and take up plenty of storage space as well as computing time, and in the process interfere the convergence of the training network, even influence the accuracy of recognition finally. Factor Analysis (FA) concentrates the information that is carried by numerous original indexes which form the index system, and then stores it to the factor, and can according to the precision that the actual problem needs, through controlling the number of the factors, to adjust the amount of the information. In this paper we make full use of the advantages of FA and the properties of Elman neural network structures to establish FA-Elman algorithm. The new algorithm reduces dimensions by FA, and carry on network training and simulation with low dimensional data that we get, which obviously simplifies the network structure, and in the process, improves the training speed and generalization capacity of the Elman neural network.

Download Full-text

Impact of COronaVirus Disease -2019 (COVID-19) pandemic on Haemodialysis care delivery pattern in Karnataka, India- a cross-sectional, questionnaire based survey.

10.1101/2020.07.25.20151225 ◽

2020 ◽

Author(s):

Anupama Y J ◽

Arvind Conjeevaram ◽

Ravindra Prabhu A ◽

Manjunath Doshetty ◽

Sanjay Srinivasa ◽

...

Keyword(s):

Care Delivery ◽

National Policy ◽

Well Being ◽

Care Providers ◽

Movement Restriction ◽

Online Questionnaire ◽

Cross Sectional ◽

Factors Affecting ◽

Dialysis Facilities ◽

The Impact

The COVID-19 pandemic has disrupted health care delivery globally. Patients on in-centre haemodialysis(HD) are particularly affected due to their multiple hospital visits and the need for uninterrupted care for their well-being and survival. We studied the impact of the pandemic and the national policy for pandemic control on the HD care delivery in Karnataka state in India in April 2020, when the first and second national lockdown were in place. An online, questionnaire based survey of dialysis facilities was conducted and the responses analysed. The questions were pertaining to the key areas such as changes in number of dialysis treatments, frequency, duration, expenses, transportation to and from dialysis units, impact on availability of consumables, effect on dialysis personnel and on machine maintenance. 62 centres participated. Median of dialysis treatments for the months of March and April 2020 were 695.5 and 650 respectively. Reduction in dialysis treatments was noted in 29(46.8%) facilities , decreased frequency reported by 60 centres. In at least 35(56.5%) centres, dialysis patients had to bear increased expenses. Cost and availability of dialysis consumables were affected in 40(64.5%) and 55(88.7%) centres respectively. Problems with transportation and movement restriction were the two key factors affecting both patients and dialysis facilities.This survey documents the collateral impact of COVID -19 on the vulnerable group of patients on HD, even when not affected by COVID. It identifies the key areas of challenges faced by the patients and the facilities and implores the care-providers for finding newer avenues for mitigation of the problems. Key words: COVID-19, India, Haemodialysis , dialysis care delivery, questionnaire-based survey

Download Full-text

Evaluation of Parameter Settings for Training Neural Networks Using Backpropagation Algorithms

International Journal of Operations Research and Information Systems ◽

10.4018/ijoris.2020100104 ◽

2020 ◽

Vol 11 (4) ◽

pp. 62-85

Author(s):

Leema N. ◽

Khanna H. Nehemiah ◽

Elgin Christo V. R. ◽

Kannan A.

Keyword(s):

Neural Network ◽

Neural Networks ◽

Activation Function ◽

Neural Network Training ◽

Network Parameter ◽

Network Parameters ◽

Network Training ◽

Hidden Layer ◽

Function Number ◽

The Impact

Artificial neural networks (ANN) are widely used for classification, and the training algorithm commonly used is the backpropagation (BP) algorithm. The major bottleneck faced in the backpropagation neural network training is in fixing the appropriate values for network parameters. The network parameters are initial weights, biases, activation function, number of hidden layers and the number of neurons per hidden layer, number of training epochs, learning rate, minimum error, and momentum term for the classification task. The objective of this work is to investigate the performance of 12 different BP algorithms with the impact of variations in network parameter values for the neural network training. The algorithms were evaluated with different training and testing samples taken from the three benchmark clinical datasets, namely, Pima Indian Diabetes (PID), Hepatitis, and Wisconsin Breast Cancer (WBC) dataset obtained from the University of California Irvine (UCI) machine learning repository.

Download Full-text

FORMATION OF TEENAGERS’ LEGAL CULTURE: ESSENCE AND IMPACT FACTORS

Tambov University Review Series Humanities ◽

10.20310/1810-0201-2018-23-177-70-80 ◽

2018 ◽

pp. 70-80

Author(s):

Maksim Viktorovich KHARNIKOV

Keyword(s):

Educational Institution ◽

Legal Education ◽

National Policy ◽

Legal Culture ◽

Impact Factors ◽

Factors Affecting ◽

Other Information ◽

Use Of The Internet ◽

Definition Of ◽

The Impact

We give the definition of the essence of the formation of teenager’s legal culture, which is understood as a purposeful, specially organized, managed social and pedagogical process that provides the assimilation of legal knowledge by teenagers, the manifestation of the legal position in socially useful activities. We also consider the impact factors of formation of legal culture of a modern teenager in society. The leading factors affecting teenager’s legal culture include a single national policy in the field of legal culture (“Fundamentals of State Policy of the Russian Federation in the Field of Legal Literacy and Legal Awareness of Citizens”), the organization of space for the participation of teenagers in socially significant activities and for the implementation of legal education (for example, the program “Do not Stumble!”), socializing the potential of the family in the process of legal education, the impact on the legal culture of the teenager media, first of all, Internet (methodical recommendations about placement on information stands, official Internet sites and other information resources of the educational organizations and bodies exercising management in the sphere of education, information on safe behavior and use of the Internet), legal education of teenagers in educational institution, attraction of the new subjects influencing formation of legal culture (interdepartmental interaction) (it is considered on the example of activity of the Children’s rights ombudsman and legal clinics), influence of features of teenage age.

Download Full-text

The impact of credit risk and macroeconomic factors on profitability: the case of the ASEAN banks

Banks and Bank Systems ◽

10.21511/bbs.15(1).2020.03 ◽

2020 ◽

Vol 15 (1) ◽

pp. 21-29

Author(s):

Myra V. De Leon

Keyword(s):

Credit Risk ◽

Fixed Effects ◽

Inflation Rate ◽

Ordinary Least Squares ◽

Gdp Growth ◽

Fixed Effects Model ◽

Macroeconomic Factors ◽

Factors Affecting ◽

Level Of Significance ◽

The Impact

This study investigates the effect of credit risk and macroeconomic factors on profitability of 20 ASEAN banks, particularly from Indonesia, Malaysia, Thailand and Philippines, covering the period of 2012 to 2017. The unbalanced panel data were tested for heteroscedasticity and normality. A fixed effects model and a random effects model were utilized followed by simple ordinary least squares (OLS) regression. The obtained results show that credit risk and GDP growth negatively affect Return on Equity (ROE) at 5% level of significance. The inflation rate increases ROE by 0.323%. In terms of influence, inflation has the highest impact on ROE followed by GDP growth and credit risk. Credit risk and GDP growth negatively affect Return on Assets (ROA) at 5% level of significance. ROA was also influenced by an increase in inflation rate. Therefore, this study will help banks and bank managers, depositors, investors, policy makers and governments to identify factors affecting bank profitability.

Download Full-text

Impact of Asymmetric Weight Update on Neural Network Training With Tiki-Taka Algorithm

Frontiers in Neuroscience ◽

10.3389/fnins.2021.767953 ◽

2022 ◽

Vol 15 ◽

Author(s):

Chaeun Lee ◽

Kyungmi Noh ◽

Wonjae Ji ◽

Tayfun Gokmen ◽

Seyoung Kim

Keyword(s):

Neural Network ◽

Power Efficiency ◽

Calibration Method ◽

Neural Network Training ◽

Systematic Analysis ◽

Training Performance ◽

Actual Weight ◽

Network Training ◽

The Neural Network ◽

The Impact

Recent progress in novel non-volatile memory-based synaptic device technologies and their feasibility for matrix-vector multiplication (MVM) has ignited active research on implementing analog neural network training accelerators with resistive crosspoint arrays. While significant performance boost as well as area- and power-efficiency is theoretically predicted, the realization of such analog accelerators is largely limited by non-ideal switching characteristics of crosspoint elements. One of the most performance-limiting non-idealities is the conductance update asymmetry which is known to distort the actual weight change values away from the calculation by error back-propagation and, therefore, significantly deteriorates the neural network training performance. To address this issue by an algorithmic remedy, Tiki-Taka algorithm was proposed and shown to be effective for neural network training with asymmetric devices. However, a systematic analysis to reveal the required asymmetry specification to guarantee the neural network performance has been unexplored. Here, we quantitatively analyze the impact of update asymmetry on the neural network training performance when trained with Tiki-Taka algorithm by exploring the space of asymmetry and hyper-parameters and measuring the classification accuracy. We discover that the update asymmetry level of the auxiliary array affects the way the optimizer takes the importance of previous gradients, whereas that of main array affects the frequency of accepting those gradients. We propose a novel calibration method to find the optimal operating point in terms of device and network parameters. By searching over the hyper-parameter space of Tiki-Taka algorithm using interpolation and Gaussian filtering, we find the optimal hyper-parameters efficiently and reveal the optimal range of asymmetry, namely the asymmetry specification. Finally, we show that the analysis and calibration method be applicable to spiking neural networks.

Download Full-text

GenotypeTensors: Efficient Neural Network Genotype Callers

10.1101/338780 ◽

2018 ◽

Cited By ~ 1

Author(s):

Joshua Cohen ◽

Manuele Simi ◽

Fabien Campagne

Keyword(s):

Neural Network ◽

Model Development ◽

Confidence Regions ◽

Training Models ◽

True Label ◽

Network Training ◽

Robust Model ◽

Machine Learning Approach ◽

Cloud Applications ◽

The Impact

ABSTRACTWe studied the problem of calling genotypes using neural networks. A machine learning approach to calling genotypes requires a training set, an approach to convert genomic sites into tensors and robust model development and evaluation protocols. We discuss each of these components of our approach and compare four types of neural network training protocols, two fully supervised and two semi-supervised approaches. Semi-supervised approaches use unlabeled data to supplement limited quantities of labeled data. Random hyper-parameter searches identified highly performing models that reach indel F1 of 99.4% on a chromosomes 20, 21, 22 and X of NA12878/HG001. We further validate these models by evaluating performance on HG002, an independent sample used in the PrecisionFDA challenge. We apply GenotypeTensors to evaluate the impact of (1) training with small datasets, (2) training models only with sites inside confidence regions, or (3) training with improved true label annotations. A PyTorch open-source implementation of GenotypeTensors is available at https://github.com/CampagneLaboratory/GenotypeTensors. DNANexus cloud applications are provided to help process new datasets both to train model or call genotypes with trained models.

Download Full-text

Current and future transboundary water cooperation over the YarlungZangbo/Brahmaputra River basin: from an interdisciplinary perspective

Water Policy ◽

10.2166/wp.2021.008 ◽

2021 ◽

Author(s):

Yanmei He

Keyword(s):

River Basin ◽

National Policy ◽

Analytical Framework ◽

Water Diversion ◽

Transboundary Water ◽

Brahmaputra River ◽

Factors Affecting ◽

Water Cooperation ◽

Social Environmental ◽

Transboundary Water Cooperation

Abstract While all riparian states in the YarlungZangbo/Brahmaputra River basin have conducted or planned dam-building, water diversion or other water-related activities to meet their respective national policy goals, they are also undertaking fragmented cooperation to solve conflicts and disputes as they arise. Mainly using a combination of natural, economic, social, environmental, political and legal factors affecting transboundary water cooperation as its analytical framework, this article explores the features of the current cooperation practice among the riparian states, then analyses manifold challenges the practice faces. The author lastly envisions an available path where all riparian states develop multilateral cooperation to address the challenges in the future. This article suggests that the rationale for future cooperation is the policy of preventive diplomacy with the aim of avoiding water conflicts and significant transboundary harm; the basic prerequisite for future potential cooperation is trust building among the riparian states, especially between China–India and between India–Bangladesh; the suitable form of future cooperation is expected to be an inclusive, comprehensive and coordination-oriented River Basin Organization; and the focus areas for future cooperation are supposed to be data sharing and riparian activities that all or most of the riparian states are suffering from.

Download Full-text