Abstract: The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.
Abstract: With the development of optical communication, optical performance monitoring (OPM) has received more and more attentions. Since optical signal-to-noise ratio (OSNR) is directly related to bit error rate (BER), it is one of the important parameters in optical networks. Recently, artificial neural network (ANN) has been greatly developed. ANN has strong learning and generalization ability. In this paper, a method of OSNR monitoring based on delay-tap sampling (DTS) and ANN has been proposed. DTS technique is used to extract the eigenvalues of the signal. Then, the eigenvalues are input into the ANN to realize the OSNR monitoring. The experiments of 10 Gb/s non-return-to-zero (NRZ) on–off keying (OOK), 20 Gb/s pulse amplitude modulation (PAM4) and 20 Gb/s return-to-zero (RZ) differential phase-shift keying (DPSK) systems are demonstrated for the OSNR monitoring based on the proposed method. The experimental results show that the range of OSNR monitoring is from 15 to 30 dB and the root-mean-square errors (RMSEs) for 10 Gb/s NRZ-OOK, 20 Gb/s PAM4 and 20 Gb/s RZ-DPSK systems are 0.36 dB, 0.45 dB and 0.48 dB respectively. The impact of chromatic dispersion (CD) on the accuracy of OSNR monitoring is also investigated in the three experimental systems mentioned above.
Abstract: Airborne Laser Scanning (ALS) is one of the main technologies for generating high-resolution digital terrain models (DTMs). DTMs are crucial to several applications, such as topographic mapping, flood zone delineation, geographic information systems (GIS), hydrological modelling, spatial analysis, etc. Laser scanning system generates irregularly spaced three-dimensional cloud of points. Raw ALS data are mainly ground points (that represent the bare earth) and non-ground points (that represent buildings, trees, cars, etc.). Removing all the non-ground points from the raw data is referred to as filtering. Filtering heavily forested areas is considered a difficult and challenging task as the canopy stops laser pulses from reaching the terrain surface. This research presents an approach for removing non-ground points from raw ALS data in densely forested areas. Smoothing splines are exploited to interpolate and fit the noisy ALS data. The presented filter utilizes a weight function to allocate weights for each point of the data. Furthermore, unlike most of the methods, the presented filtering algorithm is designed to be automatic. Three different forested areas in the United Kingdom are used to assess the performance of the algorithm. The results show that the generated DTMs from the filtered data are accurate (when compared against reference terrain data) and the performance of the method is stable for all the heavily forested data samples. The average root mean square error (RMSE) value is 0.35 m.
Abstract: The combination of world population and the third industrial revolution led to high demand for fuels. On the other hand, the decrease of global fossil 8fuels deposits and the environmental air pollution caused by these fuels has compounded the challenges the world faces due to its need for energy. Therefore, new forms of environmentally friendly and renewable fuels such as biodiesel are needed. The primary analytical techniques for methanolysis yield monitoring have been chromatography and spectroscopy, these methods have been proven reliable but are more demanding, costly and do not provide real-time monitoring. In this work, the in situ monitoring of biodiesel from sunflower oil using FTIR (Fourier Transform Infrared) has been studied; the study was performed using EasyMax Mettler Toledo reactor equipped with a DiComp (Diamond) probe. The quantitative monitoring of methanolysis was performed by building a quantitative model with multivariate calibration using iC Quant module from iC IR 7.0 software. 15 samples of known concentrations were used for the modelling which were taken in duplicate for model calibration and cross-validation, data were pre-processed using mean centering and variance scale, spectrum math square root and solvent subtraction. These pre-processing methods improved the performance indexes from 7.98 to 0.0096, 11.2 to 3.41, 6.32 to 2.72, 0.9416 to 0.9999, RMSEC, RMSECV, RMSEP and R2Cum, respectively. The R2 value of 1 (training), 0.9918 (test), 0.9946 (cross-validation) indicated the fitness of the model built. The model was tested against univariate model; small discrepancies were observed at low concentration due to unmodelled intermediates but were quite close at concentrations above 18%. The software eliminated the complexity of the Partial Least Square (PLS) chemometrics. It was concluded that the model obtained could be used to monitor methanol of sunflower oil at industrial and lab scale.
Abstract: Fourier Transform Infrared (FT-IR) spectroscopy coupled with chemometrics was used to distinguish between butter samples and non-butter samples. Further, quantification of the content of margarine in adulterated butter samples was investigated. Fingerprinting region (1400-800 cm–1) was used to develop unsupervised pattern recognition (Principal Component Analysis, PCA), supervised modeling (Soft Independent Modelling by Class Analogy, SIMCA), classification (Partial Least Squares Discriminant Analysis, PLS-DA) and regression (Partial Least Squares Regression, PLS-R) models. PCA of the fingerprinting region shows a clustering of the two sample types. All samples were classified in their rightful class by SIMCA approach; however, nine adulterated samples (between 1% and 30% w/w of margarine) were classified as belonging both at the butter class and at the non-butter one. In the two-class PLS-DA model’s (R2 = 0.73, RMSEP, Root Mean Square Error of Prediction = 0.26% w/w) sensitivity was 71.4% and Positive Predictive Value (PPV) 100%. Its threshold was calculated at 7% w/w of margarine in adulterated butter samples. Finally, PLS-R model (R2 = 0.84, RMSEP = 16.54%) was developed. PLS-DA was a suitable classification tool and PLS-R a proper quantification approach. Results demonstrate that FT-IR spectroscopy combined with PLS-R can be used as a rapid, simple and safe method to identify pure butter samples from adulterated ones and to determine the grade of adulteration of margarine in butter samples.
Abstract: In geophysical exploration surveys, the quality of acquired data holds significant importance before executing the data processing and interpretation phases. In this study, 2D seismic reflection survey data of Fort Abbas area, Cholistan Desert, Pakistan was taken as test case in order to assess its quality on statistical bases by using normalized root mean square error (NRMSE), Cronbach’s alpha test (α) and null hypothesis tests (t-test and F-test). The analysis challenged the quality of the acquired data and highlighted the significant errors in the acquired database. It is proven that the study area is plain, tectonically least affected and rich in oil and gas reserves. However, subsurface 3D modeling and contouring by using acquired database revealed high degrees of structural complexities and intense folding. The NRMSE had highest percentage of residuals between the estimated and predicted cases. The outcomes of hypothesis testing also proved the biasness and erraticness of the acquired database. Low estimated value of alpha (α) in Cronbach’s alpha test confirmed poor reliability of acquired database. A very low quality of acquired database needs excessive static correction or in some cases, reacquisition of data is also suggested which is most of the time not feasible on economic grounds. The outcomes of this study could be used to assess the quality of large databases and to further utilize as a guideline to establish database quality assessment models to make much more informed decisions in hydrocarbon exploration field.
Abstract: Prediction of wall shear stress in a rectangular channel, with non-homogeneous roughness distribution, was studied. Estimation of shear stress is an important subject in hydraulic engineering, since it affects the flow structure directly. In this study, the Genetic Algorithm Artificial (GAA) neural network is introduced as a hybrid methodology of the Artificial Neural Network (ANN) and modified Genetic Algorithm (GA) combination. This GAA method was employed to predict the wall shear stress. Various input combinations and transfer functions were considered to find the most appropriate GAA model. The results show that the proposed GAA method could predict the wall shear stress of open channels with high accuracy, by Root Mean Square Error (RMSE) of 0.064 in the test dataset. Thus, using GAA provides an accurate and practical simple-to-use equation.
Abstract: Rubberwood is a crucial commercial timber in Southern Thailand. All processes in a rubberwood production depend on the knowledge and expertise of the technicians, especially the drying process. This research aims to develop an empirical model for drying kinetics in rubberwood. During the experiment, the temperature of the hot air and the average air flow velocity were kept at 80-100 °C and 1.75 m/s, respectively. The moisture content in the samples was determined less than 12% in the achievement of drying basis. The drying kinetic was simulated using an empirical solver. The experimental results illustrated that the moisture content was reduced whereas the drying temperature and time were increased. The coefficient of the moisture ratio between the empirical and the experimental model was tested with three statistical parameters, R-square (R²), Root Mean Square Error (RMSE) and Chi-square (χ²) to predict the accuracy of the parameters. The experimental moisture ratio had a good fit with the empirical model. Additionally, the results indicated that the drying of rubberwood using the Henderson and Pabis model revealed the suitable level of agreement. The result presented an excellent estimation (R² = 0.9963) for the moisture movement compared to the other models. Therefore, the empirical results were valid and can be implemented in the future experiments.
Abstract: This research attempts to investigate the effects of heteroscedasticity and periodicity in a Panel Data Regression Model (PDRM) by extending previous works on balanced panel data estimation within the context of fitting PDRM for Banks audit fee. The estimation of such model was achieved through the derivation of Joint Lagrange Multiplier (LM) test for homoscedasticity and zero-serial correlation, a conditional LM test for zero serial correlation given heteroscedasticity of varying degrees as well as conditional LM test for homoscedasticity given first order positive serial correlation via a two-way error component model. Monte Carlo simulations were carried out for 81 different variations, of which its design assumed a uniform distribution under a linear heteroscedasticity function. Each of the variation was iterated 1000 times and the assessment of the three estimators considered are based on Variance, Absolute bias (ABIAS), Mean square error (MSE) and the Root Mean Square (RMSE) of parameters estimates. Eighteen different models at different specified conditions were fitted, and the best-fitted model is that of within estimator when heteroscedasticity is severe at either zero or positive serial correlation value. LM test results showed that the tests have good size and power as all the three tests are significant at 5% for the specified linear form of heteroscedasticity function which established the facts that Banks operations are severely heteroscedastic in nature with little or no periodicity effects.
Abstract: The Earth system generates different phenomena that are observable at the surface of the Earth such as mass deformations and displacements leading to plate tectonics, earthquakes, and volcanism. The dynamic processes associated with the interior, surface, and atmosphere of the Earth affect the three pillars of geodesy: shape of the Earth, its gravity field, and its rotation. Geodesy establishes a characteristic structure in order to define, monitor, and predict of the whole Earth system. The traditional and new instruments, observables, and techniques in geodesy are related to the gravity field. Therefore, the geodesy monitors the gravity field and its temporal variability in order to transform the geodetic observations made on the physical surface of the Earth into the geometrical surface in which positions are mathematically defined. In this paper, the main components of the gravity field modeling, (Free-air and Bouguer) gravity anomalies are calculated via recent global models (EGM2008, EIGEN6C4, and GECO) over a selected study area. The model-based gravity anomalies are compared with the corresponding terrestrial gravity data in terms of standard deviation (SD) and root mean square error (RMSE) for determining the best fit global model in the study area at a regional scale in Turkey. The least SD (13.63 mGal) and RMSE (15.71 mGal) were obtained by EGM2008 for the Free-air gravity anomaly residuals. For the Bouguer gravity anomaly residuals, EIGEN6C4 provides the least SD (8.05 mGal) and RMSE (8.12 mGal). The results indicated that EIGEN6C4 can be a useful tool for modeling the gravity field of the Earth over the study area.
Abstract: Poor air quality is one of the main environmental causes of premature deaths worldwide, and mainly in cities, where the majority of the population lives. It is a consequence of successive land cover (LC) and use changes, as a result of the intensification of human activities. Knowing these landscape modifications in a comprehensive spatiotemporal dimension is, therefore, essential for understanding variations in air pollutant concentrations. In this sense, the use of air quality models is very useful to simulate the physical and chemical processes that affect the dispersion and reaction of chemical species into the atmosphere. However, the modelling performance should always be evaluated since the resolution of the input datasets largely dictates the reliability of the air quality outcomes. Among these data, the updated LC is an important parameter to be considered in atmospheric models, since it takes into account the Earth’s surface changes due to natural and anthropic actions, and regulates the exchanges of fluxes (emissions, heat, moisture, etc.) between the soil and the air. This work aims to evaluate the performance of the Weather Research and Forecasting model coupled with Chemistry (WRF-Chem), when different LC classifications are used as an input. The influence of two LC classifications was tested: i) the 24-classes USGS (United States Geological Survey) LC database included by default in the model, and the ii) CLC (Corine Land Cover) and specific high-resolution LC data for Portugal, reclassified according to the new USGS nomenclature (33-classes). Two distinct WRF-Chem simulations were carried out to assess the influence of the LC on air quality over Europe and Portugal, as a case study, for the year 2015, using the nesting technique over three simulation domains (25 km2, 5 km2 and 1 km2 horizontal resolution). Based on the 33-classes LC approach, particular emphasis was attributed to Portugal, given the detail and higher LC spatial resolution (100 m x 100 m) than the CLC data (5000 m x 5000 m). As regards to the air quality, only the LC impacts on tropospheric ozone concentrations were evaluated, because ozone pollution episodes typically occur in Portugal, in particular during the spring/summer, and there are few research works relating to this pollutant with LC changes. The WRF-Chem results were validated by season and station typology using background measurements from the Portuguese air quality monitoring network. As expected, a better model performance was achieved in rural stations: moderate correlation (0.4 – 0.7), BIAS (10 – 21µg.m-3) and RMSE (20 – 30 µg.m-3), and where higher average ozone concentrations were estimated. Comparing both simulations, small differences grounded on the Leaf Area Index and air temperature values were found, although the high-resolution LC approach shows a slight enhancement in the model evaluation. This highlights the role of the LC on the exchange of atmospheric fluxes, and stresses the need to consider a high-resolution LC characterization combined with other detailed model inputs, such as the emission inventory, to improve air quality assessment.
Abstract: Employee turnover leads to lowered productivity, decreased morale and work quality, and psychological effects associated with employee separation and replacement. Yet, it remains unknown why talented employees willingly withdraw from organizations. This uncertainty is worsened as studies; a) priorities organizational over individual predictors resulting in restriction in range in turnover measurement; b) focus on actual rather than intended turnover thereby limiting conceptual understanding of the turnover construct and its relationship with other variables and; c) produce inconsistent findings across cultures, contexts and industries despite a clear need for a unified perspective. The current study addressed these gaps by adopting the theory of planned behavior (TPB) framework to examine socio-cognitive factors in organizational trust and individual turnover intentions among bankers and energy employees in Jamaica. In a comparative study of n=369 [nbank= 264; male=57 (22.73%); nenergy =105; male =45 (42.86)], it was hypothesized that organizational trust was a predictor of employee turnover intention, and the effect of individual, group, cognitive and socio-affective variables varied across industry. Findings from structural equation modelling confirmed the hypothesis, with a model of both cognitive and socio-affective variables being a better fit [CMIN (χ2) = 800.067, df = 364, p ≤ .000; CFI = 0.950; RMSEA = 0.057 with 90% C.I. (0.052 - 0.062); PCLOSE = 0.016; PNFI = 0.818 in predicting turnover intention. The findings are discussed in relation to socio-cognitive components of trust models and predicting negative employee behaviors across cultures and industries.
Abstract: Crop yield prediction is a paramount issue in
agriculture. The main idea of this paper is to find out efficient
way to predict the yield of corn based meteorological records.
The prediction models used in this paper can be classified into
model-driven approaches and data-driven approaches, according to
the different modeling methodologies. The model-driven approaches are based on crop mechanistic
modeling. They describe crop growth in interaction with their
environment as dynamical systems. But the calibration process of
the dynamic system comes up with much difficulty, because it
turns out to be a multidimensional non-convex optimization problem.
An original contribution of this paper is to propose a statistical
methodology, Multi-Scenarios Parameters Estimation (MSPE), for the
parametrization of potentially complex mechanistic models from a
new type of datasets (climatic data, final yield in many situations).
It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction
is free of the complex biophysical process. But it has some strict
requirements about the dataset.
A second contribution of the paper is the comparison of these
model-driven methods with classical data-driven methods. For this
purpose, we consider two classes of regression methods, methods
derived from linear regression (Ridge and Lasso Regression, Principal
Components Regression or Partial Least Squares Regression) and
machine learning methods (Random Forest, k-Nearest Neighbor,
Artificial Neural Network and SVM regression).
The dataset consists of 720 records of corn yield at county scale
provided by the United States Department of Agriculture (USDA) and
the associated climatic data. A 5-folds cross-validation process and
two accuracy metrics: root mean square error of prediction(RMSEP),
mean absolute error of prediction(MAEP) were used to evaluate the
crop prediction capacity.
The results show that among the data-driven approaches, Random
Forest is the most robust and generally achieves the best prediction
error (MAEP 4.27%). It also outperforms our model-driven approach
(MAEP 6.11%). However, the method to calibrate the mechanistic
model from dataset easy to access offers several side-perspectives.
The mechanistic model can potentially help to underline the stresses
suffered by the crop or to identify the biological parameters of interest
for breeding purposes. For this reason, an interesting perspective is
to combine these two types of approaches.
Abstract: The experiment was carried out to study the performance of solar crop dryer coupled with reversed absorber type solar air heater (SD2). Excel software is used to analyse the raw data obtained from the drying experiment to develop a model. An attempt is made in this paper to correlate the collector efficiency, dryer efficiency and pick-up efficiency. All these efficiencies are dependent on the parameters such as solar flux, ambient temperature, collector outlet temperature and moisture content. The simulation equation was developed to predict the values of collector efficiency. The parameters a, n and drying constant k were determined from a plot of curve using a drying models. Experimental data of drying red chili in conventional solar dryer and solar dryer coupled with reversed absorber solar air heater was compared by fitting with three drying models. The moisture content will be rapidly reduced in solar dryer with reversed absorber due to higher drying temperatures. The best fit model was selected to describe the drying behavior of red chili. For SD2 the values of the coefficient of determination (R2=0.997), mean bias error (MBE=0.00026) and root mean square error (RMSE=0.016) were used to determine the goodness or the quality of the fit. Pages model showed a better fit to drying red chili among Newton model and Henderson & Pabis model.
Abstract: The Numerical weather prediction (NWP) models are
considered powerful tools for guiding quantitative rainfall prediction.
A couple of NWP models exist and are used at many operational
weather prediction centers. This study considers two models namely
the Consortium for Small–scale Modeling (COSMO) model and the
Weather Research and Forecasting (WRF) model. It compares the
models’ ability to predict rainfall over Uganda for the period 21st
April 2013 to 10th May 2013 using the root mean square (RMSE)
and the mean error (ME). In comparing the performance of the
models, this study assesses their ability to predict light rainfall events
and extreme rainfall events. All the experiments used the default
parameterization configurations and with same horizontal resolution
(7 Km). The results show that COSMO model had a tendency of
largely predicting no rain which explained its under–prediction. The
COSMO model (RMSE: 14.16; ME: -5.91) presented a significantly
(p = 0.014) higher magnitude of error compared to the WRF
model (RMSE: 11.86; ME: -1.09). However the COSMO model
(RMSE: 3.85; ME: 1.39) performed significantly (p = 0.003) better
than the WRF model (RMSE: 8.14; ME: 5.30) in simulating light
rainfall events. All the models under–predicted extreme rainfall events
with the COSMO model (RMSE: 43.63; ME: -39.58) presenting
significantly higher error magnitudes than the WRF model (RMSE:
35.14; ME: -26.95). This study recommends additional diagnosis of
the models’ treatment of deep convection over the tropics.
Abstract: Background: Persons with schizophrenia patient and misusing methamphetamines suffering from social dysfunction that impact on their quality of life. Knowledge of factors related to social dysfunction will guide the effective intervention. Objectives: To determine the direct effect, indirect effect and total effect of an acerbate Psychotics’ Symptoms, Social Support, Stressful life events, Medication use self-efficacy impact on social dysfunction in Thai schizophrenic patient and methamphetamine misuse. Methods: Data were collected from schizophrenic and methamphetamine misuse patient by self report. A linear structural relationship was used to test the hypothesized path model. Results: The hypothesized model was found to fit the empirical data and explained 54% of the variance of the psychotic symptoms (X2 = 114.35, df = 92, p-value = 0.05, X2 /df = 1.24, GFI = 0.96, AGFI = 0.92, CFI = 1.00, NFI = 0.99, NNFI = 0.99, RMSEA = 0.02). The highest total effect on social dysfunction was psychotic symptoms (0.67, p
Abstract: Crop coefficient (Kc) is an important factor contributing to estimation of evapotranspiration, and is also used to determine the irrigation schedule. This study investigated and determined the monthly Kc of winter wheat (Triticum aestivum L.) using five vegetation indices (VIs): Normalized Difference Vegetation Index (NDVI), Difference Vegetation Index (DVI), Soil Adjusted Vegetation Index (SAVI), Infrared Percentage Vegetation Index (IPVI), and Ratio Vegetation Index (RVI) of four basins in Golestan province, Iran. 14 Landsat-8 images according to crop growth stage were used to estimate monthly Kc of wheat. VIs were calculated based on infrared and near infrared bands of Landsat 8 images using Geographical Information System (GIS) software. The best VIs were chosen after establishing a regression relationship among these VIs with FAO Kc and Kc that was modified for the study area by the previous research based on R² and Root Mean Square Error (RMSE). The result showed that local modified SAVI with R²= 0.767 and RMSE= 0.174 was the best index to produce monthly wheat Kc maps.
Abstract: This paper aimed to establish econometrical equation models for the Nile delta region in Egypt, which will represent a basement for future predictions of Lumpy skin disease outbreaks and its pathway in relation to climate change. Data of lumpy skin disease (LSD) outbreaks were collected from the cattle farms located in the provinces representing the Nile delta region during 1 January, 2015 to December, 2015. The obtained results indicated that there was a significant association between the degree of the LSD outbreaks and the investigated climate factors (temperature, wind speed, and humidity) and the outbreaks peaked during the months of June, July, and August and gradually decreased to the lowest rate in January, February, and December. The model obtained depicted that the increment of these climate factors were associated with evidently increment on LSD outbreaks on the Nile Delta of Egypt. The model validation process was done by the root mean square error (RMSE) and means bias (MB) which compared the number of LSD outbreaks expected with the number of observed outbreaks and estimated the confidence level of the model. The value of RMSE was 1.38% and MB was 99.50% confirming that this established model described the current association between the LSD outbreaks and the change on climate factors and also can be used as a base for predicting the of LSD outbreaks depending on the climatic change on the future.
Abstract: To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.
Abstract: Accurate software reliability prediction not only enables developers to improve the quality of software but also provides useful information to help them for planning valuable resources. This paper examines the performance of three well-known data mining techniques (CART, TreeNet and Random Forest) for predicting software reliability. We evaluate and compare the performance of proposed models with Cascade Correlation Neural Network (CCNN) using sixteen empirical databases from the Data and Analysis Center for Software. The goal of our study is to help project managers to concentrate their testing efforts to minimize the software failures in order to improve the reliability of the software systems. Two performance measures, Normalized Root Mean Squared Error (NRMSE) and Mean Absolute Errors (MAE), illustrate that CART model is accurate than the models predicted using Random Forest, TreeNet and CCNN in all datasets used in our study. Finally, we conclude that such methods can help in reliability prediction using real-life failure datasets.