Annals of Data Science最新文献

In this paper, an intervention analysis approach was applied to daily cases of COVID-19 in Nigeria in order to evaluate the utilization and effect of the COVID-19 vaccine administered in the country. Data on the daily report of COVID-19 cases in Nigeria were collected and subjected to two models: the naïve solution and the interrupted time series (the intervention model). Based on the Alkaike Information Criterion (AIC), sigma², and log likelihood values, the interrupted time series model outperformed the Naïve solution model. ARIMA (4, 1, 4) with exogenous variables was identified as the best model. It was observed that the intervention (vaccination) was not significant at the 5% level of significance in reducing the number of daily COVID-19 cases in Nigeria since the start of the vaccination on March 5, 2021, until March 28, 2022. Also, the ARIMA (4, 1, 4) forecasts indicated that there will be surge in the number of daily COVID-19 cases in Nigeria between January and April 2023. As a result, we recommend strict adherence to COVID-19 protocols as well as further vaccination and sensitization programs to educate people on the importance of vaccine uptake and avoid Corona virus spread in the year 2023 and beyond.

This paper targets the description of the fusion of modeling techniques, such as the GARCH model and the Artificial Neural Network (ANN), for the sake of predicting financial series and precisely the series of the exchange rate in Tunisia, namely the USD/TND, the EUR/TND and the YEN/TND, for a daily frequency extending from 2015 through 2019. To our knowledge, this is the only paper that focuses on the descriptions of the fusion of modeling techniques (GARCH-NN) or hybridization method that applied on Tunisian currency (TND). The empirical results show that the hybrid model (GARCH-NN) outperforms and it is more efficient than the two used models. In fact, this method combines the advantages of two approaches in order to obtain a result more satisfactory for the expectations of the policy-makers in the exchange market in order to take their decisions. The results showed that the model proposed gives better results, so, can be an alternative of standard linear autoregressive model. This result has been joined by many empirical studies that confirm the quality and performance of this methodology, which researchers advise to be retained in all areas.

In regression analysis involving response variable on the bounded unit interval [0, 1], the beta regression model often suffice as a common choice, however, there are many alternatives to the beta regression model. In this article, we add yet another new alternative to the literature called the unit upper truncated Weibull (unit UTW) regression model. We introduce a novel unit UTW distribution as an alternative to the beta distribution and we present some of its mathematical properties. The unit UTW distribution is then extended to build the unit UTW regression model. Through an extensive Monte-Carlo simulation experiments, we show that the method of maximum likelihood can provide good estimate for each parameter in the new models. We give two practical examples were the proposed models performed better than the beta distribution and the beta regression model.

The purpose of this paper is to introduce the adaptive progressive hybrid censored scheme of the bivariate model which expands the limited applicability of failure censored schemes for the bivariate models in several fields of products. Also, the paper discusses a new bivariate model based on an adaptive progressive hybrid censored with more efficacy than the traditional models. Based on the FGM copula function and Odd-Weibull family, we will introduce the bivariate FGM Weibull-Weibull distribution. To estimate the model parameters, maximum likelihood and Bayesian estimation are used. In addition, for the parameter model, asymptotic confidence intervals and credible intervals of the highest posterior density for the Bayesian are calculated. A Monte-Carlo simulation analysis is carried out of the maximum likelihood and Bayesian estimators. Finally, we demonstrate the utility of the suggested bivariate distribution using real data from the medical area, such as diabetic nephropathy data.

In this article, step-stress partially accelerated life testing (SSPALT) with competing risks is studied when the lifetime of test units follows Nadarajah–Haghighi (NH) distribution. The maximum likelihood estimates (MLEs) and Bayes estimates (BEs) of the model parameters are derived under progressive Type-II censoring. Furthermore, the approximate and credible confidence intervals (CIs) of the parameters are computed. A numerical example has been constructed to illustrate the methods used for the study. Finally, simulation studies are performed to demonstrate the accuracy of the MLEs and BEs for the parameters of Nadarajah–Haghighi distribution and the BEs showed better results than MLEs.

To address the need for secure digital image transmission an algorithm that fulfils all prominent prerequisites of a steganography technique is developed. By incorporating the salient features of fractal cover images, dual-layer encryption using the standard chaotic map and DNA-hyperchaotic cryptography along with DWT-SVD embedding, key aspects like robustness, better perceptual quality and high payload capacity are targeted to build a blind colour image steganography algorithm in this work. A fractal cover image is used to hide a DNA-chaotic encrypted colour image using DWT-SVD embedding method. A two-dimensional standard chaotic map, which exhibits robust chaos for a very large range of parameter, is used to generate the pseudo-random number sequences of cryptographic qualities. One of the core novelty of the proposed method is the 2 layers chaotic encryption method to generate the DNA encrypted secret image which is finally embedded in a fractal cover image using DWT-SVD transform domain technique capable of withstanding the false positive attack. The comprehensive statistical security tests and the standard evaluation benchmarks depict that this efficient yet simple hybrid steganography algorithm is highly robust as well as sustainable against removal, geometrical, image enhancement and histogram attacks, offers better perceptual image quality and also contributes high perceptual quality of the extracted image.

In this paper we present a new G family of probability distributions. Some of its mathematical properties are derived. Based on a special member of the new family, a single acceptance sampling plan is considered. The issue of a single sample plan when the lifetime test is truncated at a pre-determined period is discussed. For certain different acceptance levels, confidence limits and values ratio of time and the sample size is desired to assure the estimated fixed mean life. The results of lowest ratio of actual mean life to fixed mean life that confirms acceptance with a given probability are presented. A case study is presented for this purpose.

The key assumption in accelerated life testing is that the mathematical model concerning the lifetime of the item and the stress is known or can be assumed. In several situations, such life-stress relationships are not known and cannot be assumed, i.e. accelerated life testing information cannot be extrapolated to use situation. So, in such cases, a partially accelerated life test is a more appropriate testing method to be executed for which tested objects are subjected to both normal and accelerated circumstances. Due to continual improvement in manufacturing design, it is more difficult to obtain information about the lifetime of products or materials with high reliability at the time of testing under normal conditions. An approach to accelerate failures is the step-stress partially accelerated life test which increases the load applied to the goods in a particular discrete sequence. In this study, the maximum likelihood estimators of inverse the generalized inverse Lindley distribution parameters and the acceleration factor are investigated in a step-stress partially accelerated life test model utilizing two various types of progressively hybrid censoring systems. Furthermore, the performance of the model parameter estimators with the two progressive hybrid censoring schemes is analyzed and compared in terms of biases and mean squared errors using a Monte Carlo simulation approach.

In this article, we proposed a new extension of the Topp–Leone family of distributions. Some important properties of the model are developed, such as quantile function, stochastic ordering, model series representation, moments, stress–strength reliability parameter, Renyi entropy, order statistics, and moment of residual life. A particular member called new extended Topp–Leone exponential (NETLE) is discussed. Maximum likelihood estimation (MLE), least-square estimation (LSE), and percentile estimation (PE) are used for the model parameter estimation. Simulation studies were conducted using NETLE to assess the MLE, LSE, and PE performance by examining their bias and mean square error (MSE), and the result was satisfactory. Finally, the applications of the NETLE to two real data sets are provided to illustrate the importance of the NETLG families in practice; the data sets consist of daily new deaths due to COVID-19 in California and New Jersey, USA. The new model outperformed many other existing Topp–Leone’s and exponential related distributions based on the real data illustrations.

In recent times, various machine learning approaches have been widely employed for effective diagnosis and prediction of diseases like cancer, thyroid, Covid-19, etc. Likewise, Alzheimer’s (AD) is also one progressive malady that destroys memory and cognitive function over time. Unfortunately, there are no dedicated AI-based solutions for diagnoses of AD to go hand in hand with medical diagnosis, even though multiple factors contribute to the diagnosis, making AI a very viable supplementary diagnostic solution. This paper reports an endeavor to apply various machine learning algorithms like SGD, k-Nearest Neighbors, Logistic Regression, Decision tree, Random Forest, AdaBoost, Neural Network, SVM, and Naïve Bayes on the dataset of affected victims to diagnose Alzheimer’s disease. Longitudinal collections of subjects from OASIS dataset have been used for prediction. Moreover, some feature selection and dimension reduction methods like Information Gain, Information Gain Ratio, Gini index, Chi-Squared, and PCA are applied to rank different factors and identify the optimum number of factors from the dataset for disease diagnosis. Furthermore, performance is evaluated of each classifier in terms of ROC-AUC, accuracy, F1 score, recall, and precision as well as included comparative analysis between algorithms. Our study suggests that approximately 90% classification accuracy is observed under top-rated four features CDR, SES, nWBV, and EDUC.