scholarly journals Multi-criteria neural network estimation of correlation coefficients for processing small samples of biometric data

2021 ◽  
Author(s):  
A.I. Ivanov ◽  
◽  
Yu.I. Serikova ◽  
T.A. Zolotareva ◽  
S.A. Polkovnikova ◽  
...  
Keyword(s):  
Neural Network ◽  
Correlation Coefficients ◽  
Small Samples ◽  
Biometric Data ◽  
Network Estimation

scholarly journals Synthesis of four new neuro-statistical tests for testing the hypothesis of independence of small samples of biometric data

2021 ◽  
Vol 2094 (3) ◽  
pp. 032013
Author(s):  
V I Volchikhin ◽  
A I Ivanov ◽  
T A Zolotareva ◽  
D M Skudnev
Keyword(s):  
Statistical Tests ◽  
Correlation Coefficients ◽  
Direct Calculation ◽  
Small Samples ◽  
Classical Formula ◽  
Biometric Data ◽  
Artificial Neuron ◽  
Artificial Neurons ◽  
Statistical Criteria

Abstract The paper considers the analysis of small samples according to several statistical criteria to test the hypothesis of independence, since the direct calculation of the correlation coefficients using the Pearson formula gives an unacceptably high error on small biometric samples. Each of the classical statistical criteria for testing the hypothesis of independence can be replaced with an equivalent artificial neuron. Neuron training is performed based on the condition of obtaining equal probabilities of errors of the first and second kind. To improve the quality of decisions made, it is necessary to use a variety of statistical criteria, both known and new. It is necessary to form networks of artificial neurons, generalizing the number of artificial neurons that is necessary for practical use. It is shown that the classical formula for calculating the correlation coefficients can be modified with four options. This allows you to create a network of 5 artificial neurons, which is not yet able to reduce the probability of errors in comparison with the classical formula. A gain in the confidence level in the future can only be obtained when using a network of more than 23 artificial neurons, if we apply the simplest code to detect and correct errors.

scholarly journals Neural network integration of classical statistical tests for processing small samples of biometrics data

Dependability ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 22-27 ◽  
Author(s):  
A. I. Ivanov ◽  
E. N. Kuprianov ◽  
S. V. Tureev
Keyword(s):  
Neural Network ◽  
Statistical Tests ◽  
Pair Correlation ◽  
Test Sample ◽  
Small Samples ◽  
Network Integration ◽  
Chi Square ◽  
Biometric Data ◽  
Joint Application ◽  
Artificial Neurons

The Aim of this paper is to increase the power of statistical tests through their joint application to reduce the requirement for the size of the test sample. Methods. It is proposed to combine classical statistical tests, i.e. chi square, Cram r-von Mises and Shapiro-Wilk by means of using equivalent artificial neurons. Each neuron compares the input statistics with a precomputed threshold and has two output states. That allows obtaining three bits of binary output code of a network of three artificial neurons. Results. It is shown that each of such criteria on small samples of biometric data produces high values of errors of the first and second kind in the process of normality hypothesis testing. Neural network integration of three tests under consideration enables a significant reduction of the probabilities of errors of the first and second kind. The paper sets forth the results of neural network integration of pairs, as well as triples of statistical tests under consideration. Conclusions. Expected probabilities of errors of the first and second kind are predicted for neural network integrations of 10 and 30 classical statistical tests for small samples that contain 21 tests. An important element of the prediction process is the symmetrization of the problem, when the probabilities of errors of the first and second kind are made identical and averaged out. Coefficient modules of pair correlation of output states are averaged out as well by means of artificial neuron adders. Only in this case the connection between the number of integrated tests and the expected probabilities of errors of the first and second kind becomes linear in logarithmic coordinates.

scholarly journals The Neural Network Analysis of Normality of Small Samples of Biometric Data through Using the Chi-Square Test and Anderson–Darling Criteria

2019 ◽  
pp. 205-217
Author(s):  
Vladimir I. Volchikhin ◽  
Aleksandr I. Ivanov ◽  
Alexander V. Bezyaev ◽  
Evgeniy N. Kupriyanov
Keyword(s):  
Neural Network ◽  
Sample Size ◽  
Single Layer ◽  
Test Sample ◽  
Small Samples ◽  
Chi Square ◽  
Biometric Data ◽  
The Neural Network ◽  
Anderson Darling ◽  
Statistical Criteria

Introduction. The aim of the work is to reduce the requirements to test sample size when testing the hypothesis of normality. Materials and Methods. A neural network generalization of three well-known statistical criteria is used: the chi-square criterion, the Anderson–Darling criterion in ordinary form, and the Anderson–Darling criterion in logarithmic form. Results. The neural network combining of the chi-square criterion and the Anderson–Darling criterion reduces the sample size requirements by about 40 %. Adding a third neuron that reproduces the logarithmic version of the Andersоn–Darling test leads to a small decrease in the probability of errors by 2 %. The article deals with single-layer and multilayer neural networks, summarizing many currently known statistical criteria. Discussion and Conclusion. An assumption has been made that an artificial neuron can be assigned to each of the known statistical criteria. It is necessary to change the attitude to the synthesis of new statistical criteria that previously prevailed in the 20th century. There is no current need for striving to create statistical criteria for high power. It is much more advantageous trying to ensure that the data of newly synthesized statistical criteria are low correlated with many of the criteria already created.

scholarly journals The Effectiveness of Ensemble-Neural Network Techniques to Predict Peak Uplift Resistance of Buried Pipes in Reinforced Sand

2021 ◽  
Vol 11 (3) ◽  
pp. 908
Author(s):  
Jie Zeng ◽  
Panagiotis G. Asteris ◽  
Anna P. Mamou ◽  
Ahmed Salih Mohammed ◽  
Emmanuil A. Golias ◽  
...  
Keyword(s):  
Neural Network ◽  
Numerical Models ◽  
Correlation Coefficients ◽  
Network Models ◽  
Small Scale ◽  
Offshore Platforms ◽  
Neural Network Models ◽  
Buried Pipes ◽  
Ensemble Techniques ◽  
Uplift Resistance

Buried pipes are extensively used for oil transportation from offshore platforms. Under unfavorable loading combinations, the pipe’s uplift resistance may be exceeded, which may result in excessive deformations and significant disruptions. This paper presents findings from a series of small-scale tests performed on pipes buried in geogrid-reinforced sands, with the measured peak uplift resistance being used to calibrate advanced numerical models employing neural networks. Multilayer perceptron (MLP) and Radial Basis Function (RBF) primary structure types have been used to train two neural network models, which were then further developed using bagging and boosting ensemble techniques. Correlation coefficients in excess of 0.954 between the measured and predicted peak uplift resistance have been achieved. The results show that the design of pipelines can be significantly improved using the proposed novel, reliable and robust soft computing models.

Sobol′ Sensitivity Analysis Using a Neural Network Model of a LB-LOCA in the ZION Nuclear Power Plant With CATHARE-2 V2.5 Code

2013 ◽  
Author(s):  
Fabrice Fouet ◽  
Pierre Probst
Keyword(s):  
Neural Network ◽  
Sensitivity Analysis ◽  
Nuclear Power ◽  
Uncertainty Propagation ◽  
Correlation Coefficients ◽  
Computer Code ◽  
Numerical Application ◽  
Loss Of Coolant Accident ◽  
Input Parameters ◽  
Artificial Neural Network Ann

In nuclear safety, the Best-Estimate (BE) codes may be used in safety demonstration and licensing, provided that uncertainties are added to the relevant output parameters before comparing them with the acceptance criteria. The uncertainty of output parameters, which comes mainly from the lack of knowledge of the input parameters, is evaluated by estimating the 95% percentile with a high degree of confidence. IRSN, technical support of the French Safety Authority, developed a method of uncertainty propagation. This method has been tested with the BE code used is CATHARE-2 V2.5 in order to evaluate the Peak Cladding Temperature (PCT) of the fuel during a Large Break Loss Of Coolant Accident (LB-LOCA) event, starting from a large number of input parameters. A sensitivity analysis is needed in order to limit the number of input parameters and to quantify the influence of each one on the response variability of the numerical model. Generally, the Global Sensitivity Analysis (GSA) is done with linear correlation coefficients. This paper presents a new approach to perform a more accurate GSA to determine and to classify the main uncertain parameters: the Sobol′ methodology. The GSA requires simulating many sets of parameters to propagate uncertainties correctly, which makes of it a time-consuming approach. Therefore, it is natural to replace the complex computer code by an approximate mathematical model, called response surface or surrogate model. We have tested Artificial Neural Network (ANN) methodology for its construction and the Sobol′ methodology for the GSA. The paper presents a numerical application of the previously described methodology on the ZION reactor, a Westinghouse 4-loop PWR, which has been retained for the BEMUSE international problem [8]. The output is the first maximum PCT of the fuel which depends on 54 input parameters. This application outlined that the methodology could be applied to high-dimensional complex problems.

Classification and Prediction of Goldfish Population and Water Quality Using a Potentiometric E-Tongue

2017 ◽  
Vol 60 (4) ◽  
pp. 1037-1044
Author(s):  
Zhenbo Wei ◽  
Yu Zhao ◽  
Jun Wang
Keyword(s):  
Neural Network ◽  
Water Quality ◽  
Pattern Recognition ◽  
Comprehensive Evaluation ◽  
Back Propagation ◽  
Correlation Coefficients ◽  
Principal Component ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Pattern Recognition Methods

Abstract. In this study, a potentiometric E-tongue was employed for comprehensive evaluation of water quality and goldfish population with the help of pattern recognition methods. Four water quality parameters, i.e., pH and concentrations of dissolved oxygen (DO), nitrite (NO2-N), and ammonium (NH3-N), were tested by conventional analysis methods. The differences in water quality parameters between samples were revealed by two-way analysis of variance (ANOVA). The cultivation days and goldfish population were classified well by principal component analysis (PCA) and canonical discriminant analysis (CDA), and the distribution of each sample was clearer in CDA score plots than in PCA score plots. The cultivation days, goldfish population, and water parameters were predicted by a T-S fuzzy neural network (TSFNN) and back-propagation artificial neural network (BPANN). BPANN performed better than TSFNN in the prediction, and all fitting correlation coefficients were >0.90. The results indicated that the potentiometric E-tongue coupled with pattern recognition methods could be applied as a rapid method for the determination and evaluation of water quality and goldfish population. Keywords: Classify, E-tongue, Goldfish water, Prediction.

scholarly journals ОПТИМІЗАЦІЯ ПРОГНОЗУВАННЯ РОЗВИТКУ АРТЕРІАЛЬНОЇ ГІПЕРТЕНЗІЇ НА ОСНОВІ КОМПЛЕКСНОГО ЗАСТОСУВАННЯ ІНФОРМАЦІЙНИХ МЕТОДИК ІЗ РОЗРОБКОЮ ДИФЕРЕНЦІАЛЬНО-ДІАГНОСТИЧНИХ КРИТЕРІЇВ ПРИ НАДАННІ ПЕРВИННОЇ МЕДИЧНОЇ ДОПОМОГИ

2016 ◽  
Author(s):  
V. P. Martsenyuk ◽  
P. R. Selskyy ◽  
B. P. Selskyy
Keyword(s):  
Neural Network ◽  
Health Care ◽  
Primary Health Care ◽  
Roc Analysis ◽  
Correlation Coefficients ◽  
Network Clustering ◽  
Care Level ◽  
Primary Health ◽  
Initial Survey

The paper describes the optimization of the prediction of disease at the primary health care level with a complex phased application of information techniques. The approach is based on analysis of the average values of indicators, correlation coefficients, using multi-parameter neural network clustering, ROC-analysis and decision tree.The data of 63 patients with arterial hypertension obtained at teaching and practical centers of primary health care were used for the analysis. It has been established that neural network clasterization can effectively and objectively allocate patients into the appropriate categories according to the level of average indices of patient examination results. Determination of the sensitivity and specificity of hemodynamic parameters, including blood pressure, and repeated during the initial survey was conducted using ROC-analysis.The diagnostic criteria of decision-making were developed to optimize the prediction of disease at the primary level in order to adjust examination procedures and treatment based on the analysis of indicators of patient examination with a complex gradual application of information procedures.

scholarly journals Abnormal Detection to Big Data Using Deep Neural Networks

2021 ◽  
Vol 2068 (1) ◽  
pp. 012025
Author(s):  
Jian Zheng ◽  
Zhaoni Li ◽  
Jiang Li ◽  
Hongling Liu
Keyword(s):  
Neural Network ◽  
Big Data ◽  
Risk Model ◽  
Small Sample ◽  
Small Samples ◽  
Small Data ◽  
Data Segmentation ◽  
Sample Data ◽  
Segmentation Algorithms ◽  
The Common

Abstract It is difficult to detect the anomalies in big data using traditional methods due to big data has the characteristics of mass and disorder. For the common methods, they divide big data into several small samples, then analyze these divided small samples. However, this manner increases the complexity of segmentation algorithms, moreover, it is difficult to control the risk of data segmentation. To address this, here proposes a neural network approch based on Vapnik risk model. Firstly, the sample data is randomly divided into small data blocks. Then, a neural network learns these divided small sample data blocks. To reduce the risks in the process of data segmentation, the Vapnik risk model is used to supervise data segmentation. Finally, the proposed method is verify on the historical electricity price data of Mountain View, California. The results show that our method is effectiveness.

Sign in / Sign up

Export Citation Format

Share Document