Reliability Estimation Approach Research Articles

Estimating Forest Aboveground Biomass Using a Combination of Geographical Random Forest and Empirical Bayesian Kriging Models

Accurately estimating forest aboveground biomass (AGB) is imperative for comprehending carbon cycling, calculating carbon budgets, and formulating sustainable forest management plans. Currently, random forest (RF) and other machine learning models are widely used to estimate forest AGB, as they can effectively handle nonlinear relationships. However, by constructing a global model using all the samples collected from a study area, these models fail to account for the spatial heterogeneity in the AGB and cannot correct the prediction biases, thereby constraining the estimation accuracy. To overcome these limitations, we proposed a novel approach termed geographical random forest and empirical Bayesian kriging (GRFEBK). This hybrid model combines the localized modeling capability of geographical random forest (GRF) with the bias correction strength of empirical Bayesian kriging (EBK). GRF adapts RF to account for the spatial heterogeneity of the AGB, while EBK utilizes the spatial autocorrelation of residuals to correct the prediction deviations. This study was conducted in Hainan Island, utilizing spectral bands, vegetation indices, tasseled cap components derived from Landsat-8 imagery, backscattering coefficients from ALOS-2 synthetic aperture radar, topographic features, and the forest canopy height as the explanatory variables. A total of 195 forest aboveground biomass (AGB) samples were collected for modeling and assessing the predictive accuracy. The results demonstrate that, among the tested models, including GRFEBK, RF, support vector machine (SVM), k-nearest neighbor (KNN), geographically weighted regression (GWR), GRF, and EBK, GRFEBK attains the highest R2 (0.78) and the lowest RMSE (36.04 Mg/ha) and RRMSE (22.87%), significantly outperforming the conventional models and using GRF or EBK alone. These results demonstrate that by accounting for local non-stationarity in AGB and correcting prediction biases, GRFEBK achieves significantly higher accuracy than conventional RF and other models. While the results are promising, the computational cost of GRFEBK and its performance under varying geographical conditions warrant further investigation at larger scales to assess its broader applicability. Nevertheless, GRFEBK provides an innovative and more reliable approach for accurate forest AGB estimation with great potential to support global forest resource monitoring.

Efficient parameter extraction of photovoltaic models with a novel enhanced prairie dog optimization algorithm

The growing demand for solar energy conversion underscores the need for precise parameter extraction methods in photovoltaic (PV) plants. This study focuses on enhancing accuracy in PV system parameter extraction, essential for optimizing PV models under diverse environmental conditions. Utilizing primary PV models (single diode, double diode, and three diode) and PV module models, the research emphasizes the importance of accurate parameter identification. In response to the limitations of existing metaheuristic algorithms, the study introduces the enhanced prairie dog optimizer (En-PDO). This novel algorithm integrates the strengths of the prairie dog optimizer (PDO) with random learning and logarithmic spiral search mechanisms. Evaluation against the PDO, and a comprehensive comparison with eighteen recent algorithms, spanning diverse optimization techniques, highlight En-PDO’s exceptional performance across different solar cell models and CEC2020 functions. Application of En-PDO to single diode, double diode, three diode, and PV module models, using experimental datasets (R.T.C. France silicon and Photowatt-PWP201 solar cells) and CEC2020 test functions, demonstrates its consistent superiority. En-PDO achieves competitive or superior root mean square error values, showcasing its efficacy in accurately modeling the behavior of diverse solar cells and performing optimally on CEC2020 test functions. These findings position En-PDO as a robust and reliable approach for precise parameter estimation in solar cell models, emphasizing its potential and advancements compared to existing algorithms.

DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation

The intersection of deep learning and photogrammetry unveils a critical need for balancing the power of deep neural networks with interpretability and trustworthiness, especially for safety-critical application like autonomous driving, medical imaging, or machine vision tasks with high demands on reliability. Quantifying the predictive uncertainty is a promising endeavour to open up the use of deep neural networks for such applications. Unfortunately, most current available methods are computationally expensive. In this work, we present a novel approach for efficient and reliable uncertainty estimation for semantic segmentation, which we call Deep Uncertainty Distillation using Ensembles for Segmentation (DUDES). DUDES applies student-teacher distillation with a Deep Ensemble to accurately approximate predictive uncertainties with a single forward pass while maintaining simplicity and adaptability. Experimentally, DUDES accurately captures predictive uncertainties without sacrificing performance on the segmentation task and indicates impressive capabilities of highlighting wrongly classified pixels and out-of-domain samples through high uncertainties on the Cityscapes and Pascal VOC 2012 dataset. With DUDES, we manage to simultaneously simplify and outperform previous work on Deep-Ensemble-based Uncertainty Distillation.

Collaborative modeling-based improved moving Kriging approach for low-cycle fatigue life reliability estimation of mechanical structures

To effectively estimate the reliability level of low-cycle fatigue (LCF) life of mechanical structures, a novel method of collaborative modeling-based improved moving Kriging (IMKCM) approach is proposed by fusing improved moving Kriging method and collaborative modeling strategy. In this method, the improved moving Kriging model is developed by the Kriging model, moving least squares method and artificial hummingbird algorithm, in which the Kriging model is selected as the basis function, the artificial hummingbird algorithm is used to define the optimal radius of compact support region and determine the effective modeling samples, and the moving least squares method is adopted to resolve the unknown coefficients; the collaborative modeling strategy is developed from the decomposition and coordination method, in which the mathematical models of the decomposed sub-objectives are synchronously built by the cell array theory, and the mathematical model between the objective and the sub-objectives is established by the improved moving Kriging model. Furthermore, a numerical example (i.e., nested nonlinear function) and an engineering example (i.e., turbine blisk LCF life reliability estimation) are employed to verify the effectiveness of the IMKCM approach. The results show that the proposed IMKCM method holds excellent abilities in modeling features and simulation performance.

Regression of the Rician Noise Level in 3D Magnetic Resonance Images from the Distribution of the First Significant Digit

This paper investigates the distribution characteristics of Fourier, discrete cosine, and discrete sine transform coefficients in T1 MRI images. This paper reveals their adherence to Benford’s law, characterized by a logarithmic distribution of first digits. The impact of Rician noise on the first digit distribution is examined, which causes deviations from the ideal distribution. A novel methodology is proposed for noise level estimation, employing metrics such as the Bhattacharyya distance, Kullback–Leibler divergence, total variation distance, Hellinger distance, and Jensen–Shannon divergence. Supervised learning techniques utilize these metrics as regressors. Evaluations on MRI scans from several datasets coming from a wide range of different acquisition devices of 1.5 T and 3 T, comprising hundreds of patients, validate the adherence of noiseless T1 MRI frequency domain coefficients to Benford’s law. Through rigorous experimentation, our methodology has demonstrated competitiveness with established noise estimation techniques, even surpassing them in numerous conducted experiments. This research empirically supports the application of Benford’s law in transforms, offering a reliable approach for noise estimation in denoising algorithms and advancing image quality assessment.

A Bayesian approach for reliability estimation for non-homogeneous and interval-censored failure data

Reliability estimation is paramount to predicting costs, planning maintenance actions, and estimating system availability in high-risk industries such as aerospace, aeronautics, and Oil and Gas (O&G). However, a shortage of historical data is very common because of restrictions related to manufacturer rights, costs, or collecting the data. In this context, generic datasets serve as prior information to model failure distributions. A popular approach to dealing with non-homogeneous generic data assumes that the failure rate is constant, which is not true in many cases. In this paper, we propose a Bayesian approach to consider non-constant failure rates using the Weibull distribution. Here, we account for the uncertainty on the Weibull parameters by modeling the population variability via Empirical Bayes. In addition, the challenge is to consider the generic dataset to provide interval-censored failure data. To obtain the posterior distribution after incorporating specific data on the equipment of interest, the Bayesian model also considers the likelihood of complete failure and censored data. As there is no family of conjugate distributions, the posterior estimate is sampled through the Markov Chain Monte Carlo method. The model was tested using simulated data as an application example.

Automated actual evapotranspiration estimation: Hybrid model of a novel attention based U-Net and metaheuristic optimization algorithms

Actual evapotranspiration (ETa) plays a crucial role in the water and energy cycles of the earth. An accurate estimate of the ETa is essential for management of the water resources, agriculture, and irrigation, as well as research on atmospheric variations. Despite the importance of accurate ETa values, estimating and mapping them remains challenging due to the physical and biological complexity of the ET process. As a novel approach for rapid and reliable estimation of ETa, the present study develops automated deep learning (AutoDL) models that incorporate a metaheuristic optimization algorithm for image processing, architectural design, and hyperparameter tuning. The proposed AutoDL models integrate three different spatial and channel attention mechanisms, including a novel activated spatial attention mechanism (ASPAM), with the U-Net architecture. Bypassing the need for meteorological inputs, the proposed framework uses Moderate Resolution Imaging Spectrometer (MODIS) products and Digital Elevation Model (DEM) data as inputs. To evaluate the performance of the models, they are applied to three study areas in the United States with various climatic characteristics. According to the results, during the spring and summer, when the target values have higher certainty, the estimations are highly promising, with R2 as high as 0.91 and MAPE as low as 6.40%. Furthermore, the proposed ASPAM module improves the accuracy of ETa estimations compared to attention gate (AG) and squeeze and excitation (SE) attention modules. The results also indicate that the MODIS raw products and derived vegetation and water indices can predict ETa within a reliable range of accuracy, with the addition of DEM data marginally enhancing the models' performance. The automatic workflow of this model makes it significantly easy to use, contributing to its applicability and generalizability for enhancing atmospheric research.

Affective state estimation based on Russell’s model and physiological measurements

Affective states are psycho-physiological constructs connecting mental and physiological processes. They can be represented in terms of arousal and valence according to the Russel’s model and can be extracted from physiological changes in human body. However, a well-established optimal feature set and a classification method effective in terms of accuracy and estimation time are not present in the literature. This paper aims at defining a reliable and efficient approach for real-time affective state estimation. To obtain this, the optimal physiological feature set and the most effective machine learning algorithm, to cope with binary as well as multi-class classification problems, were identified. ReliefF feature selection algorithm was implemented to define a reduced optimal feature set. Supervised learning algorithms, such as K-Nearest Neighbors (KNN), cubic and gaussian Support Vector Machine, and Linear Discriminant Analysis, were implemented to compare their effectiveness in affective state estimation. The developed approach was tested on physiological signals acquired on 20 healthy volunteers during the administration of images, belonging to the International Affective Picture System, conceived for inducing different affective states. ReliefF algorithm reduced the number of physiological features from 23 to 13. The performances of machine learning algorithms were compared and the experimental results showed that both accuracy and estimation time benefited from the optimal feature set use. Furthermore, the KNN algorithm resulted to be the most suitable for affective state estimation. The results of the assessment of arousal and valence states on 20 participants indicate that KNN classifier, adopted with the 13 identified optimal features, is the most effective approach for real-time affective state estimation.

Thermal imaging-based state estimation of a Stefan problem with application to cell thawing

The Stefan problem describes the evolution of the interface between two phases of a material undergoing phase change. Its formulation has been applied to model and solve a wide range of science and engineering problems across industries. This article describes observer design of a Stefan problem that arises in cell therapy in which frozen cells need to be thawed before injection. The dynamic model is simulated via a finite difference scheme with the method of lines solved over a moving grid. A Luenberger observer is designed based on the continuous-time moving-boundary moving-grid equations and information from real-time thermal imaging. Simulation and experimental results show that the integrated numerical model and observer can precisely predict the spatiotemporal evolution of thawing with errors of 1%–2% throughout the cell thawing process despite sensor noise, offering a reliable approach for state estimation and monitoring of cell thawing.

Radioactive Direction of Arrival Estimation Using Neural Networks Approach

In this paper, we present a comprehensive investigation into improving Direction of Arrival (DOA) estimation for gamma-emitting isotopes using deep neural networks. The direction of arrival estimation is most valuable for Home Land Security (HLS) applications or increased safety in Decontamination and Decommissioning (D&D). Traditional methods, such as beamforming (BF), have limitations in accuracy and sensitivity to noise and background variations. In recent years, data-driven approaches utilizing deep neural networks, including Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) models, have shown promise in enhancing DOA estimation. By considering the full energy spectrum and augmenting recorded data, our neural network models outperform traditional BF methods and exhibit greater resilience in diverse background scenarios. The 2-layer CNN model, in particular, achieves up to 40% improvement in estimation accuracy. Our research provides a reliable and data-driven approach for precise DOA estimation with potential applications in nuclear security and safety in D&D.

Using Weibull distribution function to determine the design bounds for carburized 4320 steel shafts subjected to bending dominated fatigue loading

The differential pinion shaft in an axle is often heat-treated to high surface hardness to withstand the extreme bending fatigue loading conditions. The carburized pinion shaft made of 4320 steel material was identified as the primary fracture mode when subjected to various fatigue loading conditions. However, minimal data is available to understand the fatigue behavior of carburized 4320 steel shafts. This research proposes a prediction approach to determine the fatigue life of carburized 4320 steel shafts. Since hardness varies rapidly through the carburized specimen's depth, subsurface crack initiations are likely. The fatigue prediction at the shaft subsurface was made possible by creating a set of hardness-based strain-life curves through the depth of the shaft specimen. Since all the carburized shafts in the experiment had electroless nickel plating, this research could capture the unique fatigue behavior by introducing a surface correction factor. Mean stress correction to the strain-life curves was investigated to account for the shaft failure in the case of tensile-dominated loading conditions. The performance of prominent mean stress correction models was compared by correlating with the experimental data. An analytical model was proposed since the standard models were unable to capture the physics completely. This proposed model showed excellent correlation with test data. Finally, this research implemented a Weibull-statistics-based reliability estimation approach to determine the design bounds for the carburized pinion shaft.

An application of the ensemble Kalman filter in epidemiological modelling.

Since the novel coronavirus (COVID-19) outbreak in China, and due to the open accessibility of COVID-19 data, several researchers and modellers revisited the classical epidemiological models to evaluate their practical applicability. While mathematical compartmental models can predict various contagious viruses’ dynamics, their efficiency depends on the model parameters. Recently, several parameter estimation methods have been proposed for different models. In this study, we evaluated the Ensemble Kalman filter’s performance (EnKF) in the estimation of time-varying model parameters with synthetic data and the real COVID-19 data of Hubei province, China. Contrary to the previous works, in the current study, the effect of damping factors on an augmented EnKF is studied. An augmented EnKF algorithm is provided, and we present how the filter performs in estimating models using uncertain observational (reported) data. Results obtained confirm that the augumented-EnKF approach can provide reliable model parameter estimates. Additionally, there was a good fit of profiles between model simulation and the reported COVID-19 data confirming the possibility of using the augmented-EnKF approach for reliable model parameter estimation.

Human inbreeding has decreased in time through the Holocene

The history of human inbreeding is controversial.1 In particular, how the development of sedentary and/or agricultural societies may have influenced overall inbreeding levels, relative to those of hunter-gatherer communities, is unclear.2-5 Here, we present an approach for reliable estimation of runs of homozygosity (ROHs) in genomes with ≥3× mean sequence coverage across >1 million SNPs and apply this to 411 ancient Eurasian genomes from the last 15,000 years.5-34 We show that the frequency of inbreeding, as measured by ROHs, has decreased over time. The strongest effect is associated with the Neolithic transition, but the trend has since continued, indicating a population size effect on inbreeding prevalence. We further show that most inbreeding in our historical sample can be attributed to small population size instead of consanguinity. Cases of high consanguinity were rare and only observed among members of farming societies in our sample. Despite the lack of evidence for common consanguinity in our ancient sample, consanguineous traditions are today prevalent in various modern-day Eurasian societies,1,35-37 suggesting that such practices may have become widespread within the last few millennia.

Conjoint influence of environment and load on fatigue life of a bolted aluminum alloy structure

In this paper, an attempt is made to describe the decline in fatigue life of an aluminum alloy structure containing bolted joints under the conjoint influence of an aggressive aqueous environment and loading that is essentially cyclic in nature. In an attempt to project the real situation experienced by an aluminum alloy structure containing bolted joints while in service, an alternate cycle test method was used to essentially include the damage caused by the environment and cyclic loading. A chloride-containing solution was used to simulate the damage caused to the bolted structure upon exposure of the aluminum alloy structure containing a joint to the environment. The nature of fatigue loading was essentially cyclic tension. It was found that following an observable amount of environment-induced damage caused by exposure to a wet–dry environment followed by cyclic loading, the fracture position revealed a noticeable shift from the centerline of the bolt hole to the loading end. This can be attributed to the occurrence of fretting-related damage at the fine microscopic level. Based on an assumption of an average fracture line, a life prediction model was established. Compared with experimental results, the prediction method considering the fracture position to shift from the centerline of the bolt hole does provide results with a reasonably high degree of accuracy. The method proposed in this study does provide a convincing approach for reliable estimation of life, or endurance, of an aluminum alloy structure containing joints.

Firm, Industry and Macroeconomics Dynamics of Stock Returns: A Case of Pakistan Non-Financial Sector

The available research literature on stock performance has primarily stressed the importance of asset price theories, macroeconomic and microeconomic, and institutional differences. However, there is still an open question: Are there any other factors those influence stock performance? This research aims to answer this question by providing new insights into industry factors along with country-level and firm-specific factors in conjunction with the stock performance of the non-financial sector firms listed at the Pakistan Stock Exchange. The study provides new insights into the prevailing research literature by considering an emerging economy, Pakistan. We find that non-financial sector firms are heterogeneous, suggesting applying a fixed effect approach for reliable estimation. To investigate the issue, data from 80 companies spanning 17 years (2004–2020) were analyzed with a fixed-effect model. Our study results revealed that firm tangibility, munificence, gross domestic product, inflation and money supply have negative, while size, growth, dynamism, Herfindahl–Hirschman index, exchange rate and oil prices have a positive relationship with financial performance. The results are robust under alternative estimation approaches and offer useful policy implications.

Estimation and Control for Industrial Products Reliability under Failure Trials

In practices, most industrial products are subject to sudden failure and only failure information can be collected, which presents a great challenge for reliability prediction of modern devices. To address this issue, our paper proposes a dynamic reliability estimation and control for industrial products under regular failure trials. The failure trial is performed at different operational time points of the products, which provides sole data source for evaluating the status of industrial products. We use Bayesian approach to dynamically estimate the industrial products when the failure trial is available. The estimated reliability is updated using a point estimate with new available data. To maintain the reliability of products at a desirable status, a reliability control method is presented to monitor the confidence interval of reliability distribution. The lower limit of confidence interval is maintained above a control limit, which indicates that a corresponding quality-assurance action is preferable. The proposed reliability estimation and control approach is demonstrated using a case of light-emitting diodes under failure trials at production process. The obtained results indicate the effectiveness of our estimation and control model.

A combined approach for estimating horizontal principal stress magnitudes from borehole breakout data via artificial neural network and rock failure criterion

In this paper, a newly proposed approach on horizontal stress estimation from borehole breakout data is presented. In a previous study, a machine learning model was developed, capable of estimating maximum horizontal stress (σH) from breakout data accurately. However, due to the limitation in experimental data, it was difficult to obtain the minimum horizontal stress (σh) reliably. In this study, a series of breakout tests on Hydrostone-TB specimens was carried out to investigate the influence of σh and vertical stress (σv) on breakout geometries, as these two parameters were rarely studied previously. Results revealed that both breakout angular span and depth decrease with increasing σh or σv, although the influence of σh is more significant. Based on experimental results from this paper as well as the literature, nine failure criteria were examined on the prediction accuracy of σh providing the magnitude of σH. Except for one model, all the other eight failure criteria consider the influence of σv, as indicated in experimental findings. However, none of the failure criteria yielded reasonable σh estimations. To overcome this problem, an Artificial Neural Network (ANN) model was developed from the experimental dataset. Once the model was constructed, it was examined against twenty-three field data, and yielded an acceptable average error rate of 15.88% on σh considering the easily accessible breakout data. Then a comparative analysis on σH estimation was performed via a number of approaches, namely, Kriging, ANN, and constitutive modeling. Results revealed that the use of the Mogi-Coulomb failure criterion is the most reliable approach for σH estimation, with an average error rate of 6.82%. Overall, this newly presented ‘ANN’-‘Mogi-Coulomb’ approach to horizontal stress estimation shows reasonable prediction results, which is expected to be improved in future studies by including additional data.

Visibility Parameter in Sand/Dust Storms’ Radio Wave Attenuation Equations: An Approach for Reliable Visibility Estimation Based on Existing Empirical Equations to Minimize Potential Biases in Calculations

In efforts to structure an expression for wave attenuation under a sand/dust storm, most established calculations pronounce optical visibility as an essential parameter. Although visibility information can be retrieved from weather stations, other commonly encountered sources may present it differently, i.e., as total suspended particles (TSP). Consequently, several empirical equations linking visibility to TSP concentrations were evaluated to address offset tendencies in estimations. In addition to substantiating specific equations, the results revealed that averaging a pair of equations has a 46.09% chance of estimating visibilities with a probability of 37.27%, a relatively low error compared to that achieved by employing single equations, which were found to have a probability of 28.93% with a lesser chance (29.58%) of a low estimation error for the same set of data. The resulting enhancement was evaluated by considering a study on a wireless sensor network’s (WSN’s) signal performance under vaguely labelled meteorological conditions. The meteorological conditions were converted to visibility using the results’ suggestions and were found to be in good agreement with an observation standard set by the China Meteorological Administration (CMA) for sand/dust storm outbreak classifications.

An Approach for Estimating the Reliability of IGBT Power Modules in Electrified Vehicle Traction Inverters

The reliability analysis of traction inverters is of great interest due to the use of new semi-conductor devices and inverter topologies in electric vehicles (EVs). Switching devices in the inverter are the most vulnerable component due to the electrical, thermal and mechanical stresses based on various driving conditions. Accurate stress analysis of power module is imperative for development of compact high-performance inverter designs with enhanced reliability. Therefore, this paper presents an inverter reliability estimation approach using an enhanced power loss model developed considering dynamic and transient influence of power semi-conductors. The temperature variation tracking has been improved by incorporating power module component parameters in an LPTN model of the inverter. A 100 kW EV grade traction inverter is used to validate the developed mathematical models towards estimating the inverter performance and subsequently, predicting the remaining useful lifetime of the inverter against two commonly used drive cycles.

Kernel-based estimation of P(X < Y) when X and Y are dependent random variables based on progressive type II censoring

The most widely used approach for reliability estimation is the well-known stress-strength model, θ = P(X < Y), where X and Y are random variables. In this model, the reliability, θ, of the system is the probability that the system is strong enough to overcome the stress imposed on it. In most cases, X and Y are assumed to be independent. Nevertheless, in reality, the strength variable Y could be highly dependent on the stress variable X. In this paper, we discuss the kernel-based estimation of θ when X and Y are dependent random variables under progressive type II censored sample. The asymptotic properties of the kernel-based estimators of θ based on progressive type II censoring are proposed. An extensive computer simulation is conducted to gain insight into the performance of the proposed estimators. A real data example is provided to illustrate the process.