Browsing by Author "Reema Sharma"

Now showing 1 - 9 of 9

A bayes analysis and comparison of weibull and lognormal based accelerated test models with actual lifetimes unknown
(Gnedenko Forum, 2018) S.K. Upadhyay; Reema Sharma
The paper considers an accelerated test situation where the actual lifetimes of the items are not directly observable rather their status are known in the form of binary outcomes. By assuming two widely entertained models, namely the Weibull and the lognormal distributions, for the actual lifetimes, the paper provides full Bayesian analysis of the entertained models when both scale and shape parameters of the models are allowed to vary over the covariates involved in the study, thus giving rise to corresponding accelerated test models. The Bayes implementation is based on sample based approaches, namely the Metropolis algorithm and the Gibbs sampler using proper priors of the parameters where the prior elicitation is based on the expert testimonies. The situation involving missing items where actual status is also unknown is additionally entertained using the same modelling assumption. A comparison between the two entertained models is carried out using some standard Bayesian model comparison tools. Finally, numerical illustration is provided based on a given set of current status data and some relevant findings are reported. © 2020 Seventh Sense Research Group. All rights reserved.
A Hierarchical Bayes Analysis and Comparison of PH Weibull and PH Exponential Models for One-Shot Device Testing Experiment
(World Scientific, 2021) Reema Sharma; Richa Srivastava; Satyanshu K. Upadhyay
The one-shot devices are highly reliable and, therefore, accelerated life tests are often employed to perform the experiments on such devices. Obviously, in the process, some covariates are introduced. This paper considers the proportional hazards model to observe the effect of covariates on the failure rates under the assumption of two commonly used models, namely the exponential and the Weibull for the lifetimes. The Bayes implementation is proposed using the hybridization of Gibbs and Metropolis algorithms that routinely extend to missing data situations as well. The entertained models are compared using the Bayesian and deviance information criteria and the expected posterior predictive loss criterion. Finally, the results based on two real data examples are given as an illustration. © 2021 World Scientific Publishing Company.
A hierarchical Bayes analysis for one-shot device testing experiment under the assumption of exponentiality
(Taylor and Francis Inc., 2018) Reema Sharma; S.K. Upadhyay
The article considers a two-stage hierarchical Bayes technique to analyze a dataset coming from a “one-shot” device testing experiment. The development is based on the assumption of exponential model for the lifetimes with failure rate regressed according to the Cox proportional hazards model. The Bayes implementation is done through a Gibbs–Metropolis hybridization scheme that easily entertains the missing data cases as well. Lastly, numerical illustration is provided based on a real data example on electro-explosive devices. The results show that the Bayesian method performs considerably well for such type of experiments. © 2018, © 2018 Taylor & Francis Group, LLC.
Arsenic Contamination of Groundwater in Indo-Gangetic Plain
(wiley, 2022) Samikshya Panda; Vinod Kumar Tripathi; Shrinivasa D.j; Reema Sharma
Groundwater contribution is vital among different water resources on the Earth. Recently, groundwater contamination due to the occurrence of arsenic in the deltaic region of India is a major problem that requires appropriate management and efficient treatment measures. Proper identification of sources is necessary to cope up this problem. These sources may be natural or anthropogenic which has been discussed in this chapter. Lower Gangetic plain of India is worst affected by the arsenic contamination due to the hard rock terrain characteristics of the region. A large amount of arsenic is released from geological formations and anthropogenic sources like chemical industries, mining plants, and frequent use of arsenic-rich pesticides and fertilizers. Water containing arsenic used in irrigation sector is also a major reason for soil pollution in agricultural fields. Arsenic contamination is more in the deeper layer of soil profile due to leaching of higher concentration pesticides, mining, and also naturally occurring arsenic from sedimentary and volcanic rocks availability in those layers. The groundwater extracted from deep tube wells fed by deeper aquifers is rich in arsenic content. In the deltaic plain of the Ganga river, the deep tube wells are the major source of irrigation and drinking. Hence, various human diseases and losses in agricultural yield are the biggest issues in this region. The groundwater layer which is closer to the soil surface is having less concentration of arsenic as compared to the deeper zone, as the surface water comes in contact with the arsenic source very less time as compared to deep groundwater. In this chapter, a review of arsenic removal techniques and government initiatives in the arsenic-affected states of India in the Indo-Gangetic plain have been discussed in detail. This chapter reviews various sources, the standard of water quality based on arsenic concentration, and exclusion techniques of arsenic from groundwater along with government initiatives taken for overcoming groundwater arsenic contamination in the Indo-Gangetic plain. © 2023 John Wiley & Sons Ltd. Published 2023 by John Wiley & Sons Ltd. All rights reserved.
Bayes analysis of one-shot device testing data with correlated failure modes using copula models
(Taylor and Francis Ltd., 2023) Ashkamini; Reema Sharma; Satyanshu K. Upadhyay
Copula models are capable of modeling the dependence structure among the random variables, a phenomenon that is often required in the statistical analysis. Such models are the flexible substitutes of multivariate distributions because they model both the marginal distributions and the joint dependence structure distinctly. Because of such important features, the models are recognized as popular tools in a variety of situations including reliability engineering and survival analysis. The present paper studies a Bayesian approach using three Archimedean copulas, namely, the Gumbel Hougaard copula, the Frank copula and the Joe copula for analyzing one-shot device testing data with two correlated failure modes collected from a constant stress accelerated life test. One-shot devices are units that can be used only once and destroyed immediately after the use. Obviously, one obtains either left or right censored data on the failure times instead of actual failure times of the devices. Finally, all the considered copula models are compared using the Bayesian model selection tools. A real dataset is analyzed as an illustration of the proposed Bayesian methodology. © 2023 Taylor & Francis Group, LLC.
Bayes analysis of one-shot device testing data with correlated failure modes using copula models
(Taylor and Francis Ltd., 2025) Ashkamini; Reema Sharma; Satyanshu Kumar Upadhyay
Copula models are capable of modeling the dependence structure among the random variables, a phenomenon that is often required in the statistical analysis. Such models are the flexible substitutes of multivariate distributions because they model both the marginal distributions and the joint dependence structure distinctly. Because of such important features, the models are recognized as popular tools in a variety of situations including reliability engineering and survival analysis. The present paper studies a Bayesian approach using three Archimedean copulas, namely, the Gumbel Hougaard copula, the Frank copula and the Joe copula for analyzing one-shot device testing data with two correlated failure modes collected from a constant stress accelerated life test. One-shot devices are units that can be used only once and destroyed immediately after the use. Obviously, one obtains either left or right censored data on the failure times instead of actual failure times of the devices. Finally, all the considered copula models are compared using the Bayesian model selection tools. A real dataset is analyzed as an illustration of the proposed Bayesian methodology. © 2023 Taylor & Francis Group, LLC.
Capability assessment of machine learning classifiers for spatial landslide susceptibility mapping in Malappuram district, Kerala, India
(Taylor and Francis Ltd., 2025) Shuchismita Giri; Vinod Kumar Tripathi; Thenmozhi M; Kanhu Charan Panda; Reema Sharma; Amitava Rakshit; Samikshya Panda
The landslide has been identified as a ruinous natural hazard. It causes tremendous loss to human lives, infrastructure, and the economic structure of a region. It is vital to recognize the landslide susceptible zones as a means to design preventive measures and mitigating plans. The accuracy of landslide susceptibility mapping has been progressing from expert opinion-dominated techniques to data-driven machine learning algorithms. The present study aims to determine the accuracy rate of the Artificial Neural Network (ANN), Random Forest (RF), k-Nearest Neighbour (kNN), and Support Vector Machine (SVM) models and compare their performances for landslide susceptibility mapping in Malappuram, Kerala. The multicollinearity test identified the effective causative factors: slope, elevation, drainage density, land use and land cover (LULC), rainfall pattern, geomorphology, geology, soil texture and the Boruta algorithm. Statistical indices and area under the receiver operating characteristic (AUROC) value were employed to compare the performance of the models in generating the maps of landslide susceptibility. The result revealed that both the success rate (AUROC = 0.9989) and the prediction rate (AUROC = 0.99) of the RF model exceeded the ANN model (0.9713, 0.92), the SVM model (0.9965, 0.97), and the kNN model (0.9956, 0.96). The RF model can predict spatial landslide susceptibility mapping. © 2025 Informa UK Limited, trading as Taylor & Francis Group.
Future projections of crop water and irrigation water requirements using a bias-corrected regional climate model coupled with CROPWAT
(IWA Publishing, 2023) Abhishek Agrawal; Prashant Kumar Srivastava; Vinod Kumar Tripathi; D.J. Shrinivasa; Swati Maurya; Reema Sharma
The study is conducted to examine the climate change impact on rice Crop Water Requirement (CWR) and Net Irrigation Requirement (NIR) using the NASA Earth Exchange Global Daily Downscaled Projection (NEX-GDDP) coupled with the CROPWAT 8.0 model. The maximum temperature (Tmax ), minimum temperature (Tmin), and rainfall projections for the baseline (years 1981–2015) and future (years 2030 and 2040) under Representative Concentration Pathway (RCP) 4.5 were derived from NEX-GDDP. To reduce the bias, linear scaling (LS) and the modified difference approach (MDA) were employed. Results show that LS performed better than the MDA along with improved statistical measures such as mean (μ), standard deviation (σ), and percent bias (Pbias), in the case of Tmax and Tmin (μ ¼ 31.14 and 19.63 °C, σ ¼ 5.75 and 6.78 °C, Pbias ¼ 1.43 and 0.33%), followed by rainfall (μ ¼ 2.67 mm, σ ¼ 4.94 mm, and Pbias ¼ 2.4%). The future climatic projections showed an increasing trend in both Tmax and Tmin, which are expected to increase by 1.7 °C by 2040. This would cause an increased range of 1.2 and 2% in 2030 and 2040, respectively. Due to a wide variation in effective rainfall (Peff ), NIR could increase by 4 and 9% in 2030 and 2040, respectively. The above results may help formulate adaptation measures to alleviate the impacts of climate change on rice production. © 2023 The Authors.
Metropolis Algorithm Based Bayesian Analysis of a Competing Risk Data Using Copula-Frailty Model
(Pleiades Publishing, 2024) Ashkamini; Reema Sharma; Satyanshu K. Upadhyay
Abstract: Competing risks can play a significant role in the design and analysis of critical intelligent systems which experience several risks of failure but actually fail due to a single cause that occurs first. The failure time of various components of these systems may be correlated as one failure may lead to another. In order to model such a dependence structure, copula models and frailty models have been developed for such competing risk data. The frailty term is used to describe the underlying heterogeneity among the units and the copula function is utilized to represent the dependence between the failure times. A Bayesian analysis using the Weibull distribution as the underlying failure time distribution to describe the competing risk data is carried out. The paper also considers some other models and compares them using a few standard Bayesian model comparison tools. Lastly, a real data set is studied to illustrate the proposed Bayesian approach. © Allerton Press, Inc. 2024.