Abstract: Abstract In this article, we develop Bayesian estimation procedure for estimating the stress strength reliability R = P [X > Y ] when X (strength) and Y (stress) are the inverse Chen random variables. First, we study some statistical properties of the inverse Chen distribution such as quantiles, mode, stochastic ordering, entropy measure, order statistics and stress strength reliability. Then, we estimate the stress strength parameters and R using maximum likelihood and Bayesian estimations. A symmetric (squared error loss) and an asymmetric (entropy loss) loss functions are considered for Bayesian estimation under the assumption of gamma prior. Since, joint posterior distribution of the model parameters and R involve multiple integrations and have complex form. So, we do not get analytical solution without using any numerical techniques. Therefore, we propose to use Lindley’s approximation and Markov chain Monte Carlo techniques for Bayesian computation. A simulation study is carried out for the proposed Bayes estimators of unknown parameters and compared with the maximum likelihood estimator on the basis of mean squared error. Finally, an empirical illustration based on failure time data is presented to demonstrate the applicability of inverse Chen stress strength model. PubDate: 2021-01-12
Abstract: Abstract In this paper new formulas for E-Bayesian and hierarchical Bayesian estimations of the parameter and reliability of the inverse Weibull distribution are obtained in closed forms. To illustrate the applicability of the obtained results, simulated and real data are used which illustrate that E-Bayesian estimate gives superior performance much better than hierarchical Bayesian for the estimate of the parameter of the inverse Weibull distribution. PubDate: 2021-01-09
Abstract: Abstract This article concerns the existence of positive solutions for elliptic (p, q)-Kirchhoff type systems with multiple parameters. Our approach is based on the method of sub and super-solutions. The concepts of sub- and super-solution were introduced by Nagumo (Proc Phys-Math Soc Jpn19:861–866, 1937) in 1937 who proved, using also the shooting method, the existence of at least one solution for a class of nonlinear Sturm-Liouville problems. In fact, the premises of the sub- and super-solution method can be traced back to Picard. He applied, in the early 1880s, the method of successive approximations to argue the existence of solutions for nonlinear elliptic equations that are suitable perturbations of uniquely solvable linear problems. This is the starting point of the use of sub- and super-solutions in connection with monotone methods. Picard’s techniques were applied later by Poincaré (J Math Pures Appl 4:137–230, 1898) in connection with problems arising in astrophysics. We refer to Rădulescu (Qualitative analysis ofnonlinear elliptic partial differential equations: monotonicity, analytic, and variational methods, contemporary mathematics and its applications, Hindawi Publishing Corporation, New York, 2008). PubDate: 2021-01-08
Abstract: Abstract In this paper, the idea of the bipolar Pythagorean fuzzy sets (BPFSs) and its activities, which is a generalization of fuzzy sets, bipolar fuzzy sets (BFSs), intuitionistic fuzzy sets and bipolar intuitionistic fuzzy sets is proposed, with the goal that it can deal with dubious data all the more flexibly during the process of decision making. The key objective of this research paper has presented another variant of the Pythagorean fuzzy sets so called BPFSs. In bipolar Pythagorean fuzzy sets, membership degrees are satisfying the condition \(0 \le \left( {\mu_{p}^{ + } \left( x \right)} \right)^{2}\) + \(\left( {v_{p}^{ + } \left( x \right)} \right)^{2} \le 1\) and \(0 \le \left( {\mu_{p}^{ - } \left( x \right)} \right)^{2}\) + \(\left( {v_{p}^{ - } \left( x \right)} \right)^{2} \le 1\) instead of \(0 \le \left( {\mu_{p} \left( x \right)} \right)^{2}\) + \(\left( {v_{p} \left( x \right)} \right)^{2} \le 1\) as is in Pythagorean fuzzy sets and \(0 \le \mu_{p} \left( x \right)\) + \(v_{p} \left( x \right) \le 1\) as is in the intuitionistic fuzzy sets. Here, negative membership degree means the certain counter-property comparing to a bipolar Pythagorean fuzzy set. Also, the BPFSs weighted average operator and the BPFSs weighted geometric operator to aggregate the BPFSs is developed here. Further a multi attribute decision making technique is developed and the proposed aggregation operators are used. Finally, a numerical methodology for execution of the proposed system is introduced. PubDate: 2021-01-04
Abstract: Abstract Stock price prediction is a popular research domain for its complex data structure and confounding factors. The use of Data science tools enormously increased along with the advancement of data mining and artificial intelligence tools. Classification is a famous machine learning tool with vast potential use in the stock market. However, predicting stock price through a perfect classification model is vital as different stock market data have individual patterns and dependencies as precise information about increasing or decreasing the market can significantly influence selling or buying the shares. The linear model of classification including logistic regression classification (LR), linear discriminant analysis (LDA), partial last-square discriminant analysis (PLS-DA), penalized discriminant analysis (PDA), and nearest Shrunken discriminant analysis are considered in this study to compare according to predict the stock market price of top six banks stock prices of Bangladesh. The existing literature recommends that PLS-DA fit well if data contain a high correlation among the predictors. On the contrary, PDA performs better if there is any multicollinearity problem or chance of overfitting; LDA gave better approximation when data got multivariate normality, and the nearest shrunken method fit well if there is any existence of high dimensionality. Interestingly, this study's data contain all the mentioned characteristics; still, LR gives less misclassification rate or apparent error rate. Thus, this study recommends that one may choose LR among the linear classification model if there is a high correlation, multicollinearity, multivariate normality, and high-dimensionality among predictors. PubDate: 2021-01-03
Abstract: Abstract The global solar irradiance data plays a vital role in evaluating the performance of all the solar energy conversion devices. In general there are two methods to predict the performance of such irradiance, namely physical models and the machine learning models. This paper presents a generalized regression neural network model (a machine learning technique) for estimating the global solar irradiance using seasonal and meteorological factors as input parameters. Results obtained from this proposed generalized regression neural network approach are compared with the results estimated by extensively used machine learning based methodologies such as fuzzy and artificial neural network models. Such a comparative results clearly indicate that prediction accuracy of proposed generalized regression neural network model is in good agreement with experimentally measured values. The mean percentage error for using GRNN, fuzzy logic and artificial neural network are 3.55%, 4.64%, and 5.49%. PubDate: 2021-01-03
Abstract: Abstract The choice of variable-selection methods to identify important variables for binary classification modeling is critical for producing stable statistical models that are interpretable, that generate accurate predictions, and have minimal bias. This work is motivated by the availability of data on clinical and laboratory features of dengue fever infections obtained from 51 individuals enrolled in a prospective observational study of acute human dengue infections. Our paper uses objective Bayesian method to identify important variables for dengue hemorrhagic fever (DHF) over the dengue data set. With the selected important variables by objective Bayesian method, we employ a Gaussian copula marginal regression model considering correlation error structure and a general method of semi-parametric Bayesian inference for Gaussian copula model to estimate, separately, the marginal distribution and dependence structure. We also carry out a receiver operating characteristic (ROC) analysis for the predictive model for DHF and compare our proposed model with the other models of Ju and Brasier (Variable selection methods for developing a biomarker panel for prediction of dengue hemorrhagic fever. BMC Res Notes 6:365, 2013) tested on the basis of the ROC analysis. Our results extend the previous models of DHF by suggesting that IL-10, Days Fever, Sex and Lymphocytes are the major features for predicting DHF on the basis of blood chemistries and cytokine measurements. In addition, the dependence structure of these Days Fever, Lymphocytes, IL-10 and Sex protein profiles associated with disease outcomes was discovered by the semi-parametric Bayesian Gaussian copula model and Gaussian partial correlation method. PubDate: 2020-12-01
Abstract: Abstract In the Part I of this paper, we presented the main concept of the proposed comprehensive decision model based on Habitual Domains theory, the concept of wonderful solution for solving challenging decision problems that we called decision making in changeable spaces problem (DMCS). In this Part II of the paper, we complete the construction of the model and show that it is operational and effectively empowers DMs in facing challenges. For this purpose, we present the mental principles “7–8–9 principles” that can be used to restructure decision parameters so that new solutions or alternatives could emerge. Then we provide procedures for finding wonderful solutions as sequences of the 7–8–9 principles by solving optimization in changeable spaces (OCS) problems, a new paradigm in optimization. Finally, we present applications of the model to post data mining analysis and decision making. In fact, the proposed model can be used in any area involving decision making and knowledge discovery such as management, politics, health care, technology and research. PubDate: 2020-12-01
Abstract: Abstract We present results for Shannon entropy from environmental data, such as air temperature, relative humidity, rainfall and wind speed. We use hourly generated time-series hydrological model data covering the whole of Tasmania, a state of Australia, and employ concepts from statistical mechanics in our calculations. We also present enthalpy and heat capacitance equivalent quantities for the environment. The results capture interesting seasonal fluctuations in environmental parameters over time. Our results also present an indication that corresponds to a slight increase in the number of microstates due to air temperature over the duration of data considered in this work. PubDate: 2020-12-01
Abstract: Abstract The body mass index (BMI) is calculated as weight in kilograms divided by square height in meters ( \( \frac{\text{kg}}{{{\text{m}}^{2} }} \) ). Its formula was developed by Belgium Statistician Adolphe Quetelet, and was known as the Quetelet Index (Adolphe Quetelet in BMI formula was developed. Belgium Statistician, 1796–1874. http://www.cdc.gov/healthyweight/assessing/bmi/childrens_bmi/about_childrens_bmi.htm). It provides a reliable indicator of body fatness for most people and is used to screen weight categories that may lead to health problems. BMI is an internationally used measure of health status of an individual. This study was modeling of longitudinal factors under-age five children BMI at Bahir Dar Districts using First Order Transition Model. This study was based on data from 1900 pre four visits (475 per individual) children enrolled in the first 4 visits of the 4-year Longitudinal data of children in Bahir Dar Districts. First order transition model was used to describe the relationships between children BMI and some covariates accounting for the correlation among the repeated observations for a given children. There were statistically significant (P value < 0.05) difference among children BMI variation with respect to time, Sachet (plump nut), age, residence, Antiretro-Viral Therapy, diarrhea and pervious BMI. But, fever, cough, Mid-Upper Arm Circumference and sex were statistically insignificant (p value > 0.05) effect on children BMI. According to the findings of this study about 29.28% were normal weight, 67% were under weight, 2.52% were overweight and only 1.21% were obesity. Consequently, the study suggests that concerned bodies should focus on awareness creation to bring enough food to under-age five children in Bahir Dar Districts especially in rural areas. PubDate: 2020-12-01
Abstract: Abstract The main goal of the study was to analyze the total and male entrepreneurial activity. Since it is the highly nonlinear task in this study was applied soft computing approach. Intelligent soft computing scheme support vector regression (SVR) was implemented. The performance of the proposed estimator was confirmed with the simulation results. According to the results, a greater improvement in estimation accuracy can be achieved through the SVR compared to other soft computing methodologies. The new optimization methods benefit from the soft computing capabilities of global optimization and multi-objective optimization rather than choosing a starting point by trial and error. A systematic approach was carried to predict the entrepreneurial activity by the SVR methodology. The performance of the SVR approaches compared to the results from ANN and GP showed interesting improvements in the prediction system. SVR predictions with the polynomial kernel function are superior to other methodologies in terms of root-mean-square error and coefficient of error. PubDate: 2020-12-01
Abstract: Abstract A Maxwell–Weibull distribution was introduced by using Maxwell generalized family of distributions. The distribution, density, survival, hazard and quantile functions of the proposed Maxwell–Weibull distribution were defined. Its statistical properties were derived. The maximum likelihood method of estimation was used to estimate its parameters. A simulation study was carried out to demonstrate the potentiality of the maximum likelihood estimates. Two lifetime data sets were used to assess the performance of the proposed Maxwell–Weibull distribution. Our finding revealed that the Maxwell–Weibull distribution suited the end yearly selling Nigerian Naira to Japanese Yen exchange rates and strengths of glass fibers data sets compared to the other competing distributions as it has maximum value of log-likelihood and least values of statistic criteria including AIC, CAIC and HQIC. PubDate: 2020-12-01
Abstract: Abstract Recently, bivariate inverse Weibull distribution was derived; many of its properties have been discussed. Progressive Type-II censoring for bivariate inverse Weibull distribution has been proposed. The problem of estimating the unknown parameters of this distribution in the presence of progressive Type-II censoring by both Maximum likelihood and Bayesian estimation methods is considered in this paper. Moreover, asymptotic and bootstrap confidence intervals for the model parameters are obtained. Simulation study and a real data set are presented to illustrate the proposed procedure. PubDate: 2020-11-23
Abstract: Abstract The Coronavirus Disease-2019 (COVID-19) pandemic persists to have a mortifying impact on the health and well-being of the global population. A continued rise in the number of patients testing positive for COVID-19 has created a lot of stress on governing bodies across the globe and they are finding it difficult to tackle the situation. We have developed an outbreak prediction system for COVID-19 for the top 10 highly and densely populated countries. The proposed prediction models forecast the count of new cases likely to arise for successive 5 days using 9 different machine learning algorithms. A set of models for predicting the rise in new cases, having an average accuracy of 87.9% ± 3.9% was developed for 10 high population and high density countries. The highest accuracy of 99.93% was achieved for Ethiopia using Auto-Regressive Moving Average (ARMA) averaged over the next 5 days. The proposed prediction models used by us can help stakeholders to be prepared in advance for any sudden rise in outbreak to ensure optimal management of available resources. PubDate: 2020-10-16
Abstract: Abstract In this paper, we investigate the literature around deep learning to identify its usefulness in different application domains. Our paper identifies that the effectiveness of deep learning is highly visible in the medical imaging area. Other application domains are yet to make any significant progress using deep learning. Therefore, we conclude that deep learning is a good solution for medical imaging analysis. However, its benefits are yet to be realized in other domains and researchers are pursuing to explore its effectiveness to solve problems in these domains. Our initial critical evaluation suggests that deep learning may be a hype in most domains. In order to probe this further, we call for a deeper engagement with prior literature in different application domains of deep learning. PubDate: 2020-09-01
Abstract: Abstract It is a great challenge of identification as well as formation of groups of infectious disease data set. Data mining, a process of uncovering silent characteristics of big data is one of such techniques which have nowadays become more popular for treating massive volume of infectious disease data set. In the current study, we apply cluster analysis, one of the data mining techniques to classify real groups of infectious disease “novel corona virus disease (COVID-19)” data set of different states and union territories (UTs) in India according to their high similarity to each other. The results obtained permit us to have a sense of clusters of affected Indian states and UTs. The main objective of clustering in this study is to optimize monitoring techniques in affected states and UTs in India which will be very valuable to the government, doctors, the police and others involved in understanding seriousness of the spread of novel coronavirus (COVID-19) to improve government policies, decisions, medical facilities (ventilators, testing kits, masks etc.), treatment etc. to reduce number of infected and deceased persons. PubDate: 2020-09-01
Abstract: Abstract In this paper, an endeavor has been made to fit three distributions Marshall–Olkin with exponential distributions, Marshall–Olkin with exponentiated exponential distributions and Marshall–Olkin with exponentiated extension distribution keeping in mind the end goal to actualize Bayesian techniques to examine visualization of prognosis of women with breast cancer and demonstrate through utilizing Stan. Stan is an abnormal model dialect for Bayesian displaying and deduction. This model applies to a genuine survival controlled information with the goal that every one of the ideas and calculations will be around similar information. Stan code has been created and enhanced to actualize a censored system all through utilizing Stan technique. Moreover, parallel simulation tools are also implemented and additionally actualized with a broad utilization of rstan. PubDate: 2020-09-01
Abstract: Abstract Transmuted distributions belong to the skewed family of distributions which are more flexible and versatile than the simple probability distributions. The focus of this article is the Bayesian estimation of three-parameter Transmuted Pareto distribution. In particular, we assumed noninformative and informative priors to obtain the posterior distributions. Bayesian point estimators and the associated precision measures are investigated under squared error loss function, precautionary loss function, and quadratic loss function. In addition to this, the Bayesian credible intervals are also computed under different priors. A simulation study using a Markov Chain Monte Carlo algorithm assuming uncensored and censored data in terms of different sample sizes and censoring rates is also a part of this study. The performance of Bayesian point estimators is assessed in term of posterior risks. Finally, two real life data sets of cardiovascular disease patients and of exceedances of Wheaton River flood are discussed in this article. PubDate: 2020-07-29
Abstract: Abstract Prediction of financial time series is a great challenge for statistical models. In general, the stock market times series present high volatility due to its sensitivity to economic and political factors. Furthermore, recently, the covid-19 pandemic has caused a drastic change in the stock exchange times series. In this challenging context, several computational techniques have been proposed to improve the performance of predicting such times series. The main goal of this article is to compare the prediction performance of five neural network architectures in predicting the six most traded stocks of the official Brazilian stock exchange B3 from March 2019 to April 2020. We trained the models to predict the closing price of the next day using as inputs its own previous values. We compared the predictive performance of multiple linear regression, Elman, Jordan, radial basis function, and multilayer perceptron architectures based on the root of the mean square error. We trained all models using the training set while hyper-parameters such as the number of input variables and hidden layers were selected using the testing set. Moreover, we used the trimmed average of 100 bootstrap samples as our prediction. Thus, our approach allows us to measure the uncertainty associate with the predicted values. The results showed that for all times series, considered all architectures, except the radial basis function, the networks tunning provide suitable fit, reasonable predictions, and confidence intervals. PubDate: 2020-07-13