Error Criterion Research Articles

Estimation of probability of large roll angle with envelope peaks over threshold method

The development and application of the Envelope Peak-over-Threshold (EPOT) method is summarized for the roll motion of a ship in irregular waves. The method is based on the conventional Peak-over-Threshold (POT) method, but uses an envelope of the peaks for declustering the data. As suggested by a reduced-order model, a power-law tail should be applicable for the peaks of roll motions, which allows the introduction of physical considerations into the statistical model. A data-driven Generalized Pareto distribution (GPD) is applied to study the behavior of the shape parameter on large-volume samples in order to confirm the theoretical prediction of the tail structure. The physics-informed statistical model approximates data above a suitable threshold with a Pareto distribution, while the threshold is determined with a prediction error criterion. An example is included, where extrapolations with GPD are compared to the physics-informed model.

Restricted Liu estimator under stochastic linear restrictions in generalized linear models: theory and applications

It is a fact that the problem of multicollinearity adversely effects the estimation of parameters not only in normal linear models but also in generalized linear models (GLMs). In this study, we propose a new estimator by imposing the stochastic restrictions on the parameters and combining the Liu estimator in GLMs to address the problem of multicollinearity. The new estimator is referred to as the stochastic restricted Liu estimator. The novel estimator’s first order approximated form (FOA) is presented to compare it to its competitors using the asymptotic mean square error criterion. Furthermore, two empirical applications using a response variable from the Poisson and Gamma distributions are studied to evaluate the performance of estimators. In addition, a simulation study is conducted by considering a response variable from Binomial distribution for comparisons. Based on simulation study and empirical applications, it is found that the performance of the proposed estimator is better than ML, Liu, and mixed estimators for the appropriate selected biasing parameter.

Extended Calibration of Charge Mode Accelerometers to Improve the Accuracy of Energy Systems

This paper presents an extended calibration procedure for mode accelerometers, which makes it possible to compare the accuracy of sensors of this type from different manufacturers. This comparison involves determining the upper bound on dynamic error for a given quality criterion, i.e., the integral square error and absolute error. Therefore, this article extends the standard calibration implemented in engineering practice using tests, providing a value for the upper bound on dynamic error as an additional parameter describing the accelerometer under consideration. This paper presents the theoretical basis for this type of solution, which is partly based on measurement data obtained from a standard calibration process and on the results of parametric identification. The charge mode accelerometer is considered here because this type of sensor is commonly used in the energy industry, as it can operate over a wide range of temperatures. The calculation results presented in this paper were obtained using MathCad 5.0 software, and the tests were carried out using an accelerometer of type 357B21. In the experimental part of this article (Results of Extended Calibration section), values for the upper bound of the dynamic error were determined for two error criteria and constrained simulation signals related to these errors. The impact of interference on the results of accelerometer tests was omitted in this paper.

Multisynchrosqueezing short-time fractional Fourier transform and its application in rolling bearing instantaneous frequency estimation

Multisynchrosqueezing transform (MSST) enhances the time-frequency energy concentration by using iterative reassignment operations in time-frequency analysis (TFA). However, its effectiveness is limited for signals with rapidly changing instantaneous frequency. To address this issue, this paper presents a novel time-frequency representation (TFR) method called multisynchrosqueezing short-time fractional Fourier transform, which offers improved TF concentration for strongly frequency-modulated signals. Firstly, a high-resolution TFR of the signal is obtained by locally optimized short-time fractional Fourier transform (STFrFT). Secondly, iterative synchrosqueezing operations are introduced to further enhance the STFrFT energy concentration, with a termination strategy relying on Rényi entropy proposed to ascertain the optimal number of iterations. Finally, the ideal TFA with high energy concentration is achieved. The proposed method was validated using multi-scene simulated signals and variable-speed bearing signals. The results show that the proposed method exhibits superior time-frequency energy concentration and instantaneous frequency estimation accuracy. The estimation error of the method is consistently at least 40% lower than that of the compared short-time Fourier transform-based methods, as assessed through the evaluation criteria of maximum relative error, mean square error and symmetric mean absolute percentage error.

Performance Evaluation of Artificial Neural Network Modelling to a Ploughing Unit in Various Soil Conditions

Abstract The specific objective of this study is to find a suitable artificial neural network model for estimating the operation indicators (disturbed soil volume, effective field capacity, draft force, and energy requirement) of ploughing units (tractor disc) in various soil conditions. The experiment involved two different factors, i.e., (Ι) soil texture index and (ΙΙ) field work index, and included soil moisture content, tractor engine power, soil bulk density, tillage speed, tillage depth, and tillage width, which were linked to one dimensionless index. We assessed the effectiveness of artificial neural network and multiple linear regression models between the values predicted and the actual values using the mean absolute error criterion to test data points. When the artificial neural network model was applied, the mean absolute error values for disturbed soil volume, effective field capacity, draft force, and energy requirement were 69.41 m3·hr−1, 0.04 ha·hr−1, 1.24 kN, and 1.95 kw·hr·ha−1, respectively. In order to evaluate the behaviour of new models, the coefficient R 2 was used as a criterion, where R 2 values in artificial neural network were 0.9872, 0.9553, 0.9948, and 0.9718, respectively, for the aforementioned testing dataset. Simultaneously, R 2 values in multiple linear regression were 0.7623, 0.696, 0.492, and 0.5572, respectively, for the same testing dataset. Based on these comparisons, it was clear that predictions using the artificial neural network models proposed are very satisfactory.

Predicting default risk bancassurance using GMDH and dce-GMDH neural network models

Purpose This study aims to develop a novel approach for predicting default risk in bancassurance, which plays a crucial role in the relationship between interest rates in banks and premium rates in insurance companies. The proposed method aims to improve default risk predictions and assist with client segmentation in the banking system. Design/methodology/approach This research introduces the group method of data handling (GMDH) technique and a diversified classifier ensemble based on GMDH (dce-GMDH) for predicting default risk. The data set comprises information from 30,000 credit card clients of a large bank in Taiwan, with the output variable being a dummy variable distinguishing between default risk (0) and non-default risk (1), whereas the input variables comprise 23 distinct features characterizing each customer. Findings The results of this study show promising outcomes, highlighting the usefulness of the proposed technique for bancassurance and client segmentation. Remarkably, the dce-GMDH model consistently outperforms the conventional GMDH model, demonstrating its superiority in predicting default risk based on various error criteria. Originality/value This study presents a unique approach to predicting default risk in bancassurance by using the GMDH and dce-GMDH neural network models. The proposed method offers a valuable contribution to the field by showcasing improved accuracy and enhanced applicability within the banking sector, offering valuable insights and potential avenues for further exploration.

Statistical Analysis of Covid-19 Data using the Odd Log Logistic Kumaraswamy Distribution

This paper presents a statistical analysis of Covid-19 data using the Odd log logistic kumaraswamy Kumaraswamy (OLLK) distribution. Some mathematical properties of the proposed OLLK distribution such as the survival and hazard functions, quantile function, ordinary and incomplete moments, moment generating function, probability weighted moment, distribution of order statistic and Renyi entropy were derived. Five estimators are examined for unknown model parameters. The performance of the estimators is compared using an extensive simulation study based on the bias and mean square error criteria. Two Covid-19 data sets representing the percentage of daily recoveries of Covid-19 patients are used to illustrate the applicability of the proposed OLLK distribution. Results revealed that the OLLK distribution is a better alternative to some existing models with bounded support.

A Comprehensive Model for Efficient Design Space Exploration of Imprecise Computational Blocks

After almost a decade of research, development of more efficient imprecise computational blocks is still a major concern in imprecise computing domain. There are many instances of the introduced imprecise components of different types, while their main difference is that they propose different precision-cost-performance trade-offs. In this paper, a novel comprehensive model for the imprecise components is introduced, which can be exploited to cover a wide range of precision-cost-performance trade-offs, for different types of imprecise components. The model helps to find the suitable imprecise component based on any desired error criterion. Therefore, the most significant advantage of the proposed model is that it can be simply exploited for design space exploration of different imprecise components to extract the suitable components, with the desired precision-cost-performance trade-off for any specific application. To demonstrate the efficiency of the proposed model, two novel families of Lowest-cost Imprecise Adders (LIAs) and Lowest-cost Imprecise Multipliers (LIMs) are introduced in the paper, which are systematically extracted based on exploration of the design space provided by the proposed model. A wide range of simulation and synthesis results are also presented in the paper to prove the comparable efficiency of the systematically extracted LIA/LIM structures with respect to the most efficient existing human-made imprecise components both individually and in a Multiply-Accumulate application.

Accuracy of the Nova StatStrip® glucometer in patients undergoing major abdominal surgery: an observational study.

While the Nova StatStrip® Glucose Hospital Meter System (Nova Biomedical, Waltham, MA, USA) is approved for point-of-care testing (POCT) in critically ill patients, its use during major abdominal surgery has not been evaluated. The purpose of this study was to assess the accuracy of the Nova StatStrip glucometer in patients undergoing major hepatobiliary procedures using the Parkes error grid (ISO15197:2013) and criteria defined by the Clinical and Laboratory Standards Institute (CLSI) POCT12-A3 guideline. This study was a post hoc exploratory study of patients participating in a prospective randomized controlled trial on the effects of hyperinsulinemic normoglycemia (HNC) on infectious outcomes after hepatobiliary surgery. Arterial blood samples were collected before surgery and one hour, two hours, and three hours after baseline. Blood glucose levels were analyzed by the Nova StatStrip glucometer and the GEM® PremierTM 5000 blood gas analyzer. Accuracy of the StatStrip glucometer was assessed using the Parkes error grid for type 1 diabetes mellitus (when 99% of samples were within zones A and B on the Parkes error grid and clinical accuracy was acceptable) and the CLSI POCT12-A3 criteria. Blood glucose levels were analyzed in 135 patients, 70 of whom received the HNC. In the Parkes error grid plotted, all samples at all time-points were within zones A and B. The Nova StatStrip glucometer also satisfied CLSI POCT12-A3 criteria at all time-points. The Nova StatStrip glucometer was accurate in patients undergoing major upper abdominal surgery, independent of the administration of high-dose insulin therapy. ClinicalTrials.gov (NCT01528189); registered 7 February 2012.

On the performance of two-parameter ridge estimators for handling multicollinearity problem in linear regression: Simulation and application

The inability of ordinary least square estimators against multicollinearity has paved the way for the development of various ridge-type estimators, which are recently classified as one-parameter and two-parameter ridge estimators. In this paper, we offer some efficient two-parameter ridge estimators and evaluate their performance through a simulation study by using the minimum mean square error criterion. Under most of the simulation conditions, our proposed estimators outperformed the existing estimators. Finally, two real-life datasets are used to demonstrate the applications of our proposed estimators.

Machine Learning-based Investigation of the Influencing Factors on the Hardness of Steel Materials

The hardness of steel is often regarded as a crucial indicator of its production and application. The influences of chemical composition and process parameters on the hardness of steel exhibit strong non-linearity, making it challenging to accurately predict hardness through traditional multivariate regression or orthogonal experiments. Although machine learning has achieved distinguished success in diverse applications, its use in studying Metal materials has emerged only recently. Inspired by Sunčana et al.’s work, we select the Jominy distance as an input variable for the chemical composition, and instead of his subtly finding the best artificial neural networks, we simply use Generalized Regression Neural Network (GRNN) and due to the heterogeneity of the data, a second-order clustering method is employed as a data pre-processing step. The predicted hardness values were obtained using leave-one-out cross-validation, and the optimal smoothing factor (spread) was selected based on the Root Mean Square Error (RMSE) criterion. The optimal prediction results showed that in Configuration I, the RMSEs of the two types of data were 62.41 HV and 20.51 HV, respectively, while in Configuration II, they were 66.38 HV and 29.51 HV. Results showed Configuration I was more successful than Configuration II. This research presents a novel approach for predicting the hardness of metal materials using GRNN which is designed to address the need for quick adaptation to changes in design methods and the increasing demand for high-quality manufactured products.

Employ Stress-Strength Reliability Technique in Case the Inverse Chen Distribution

This paper uses classical and shrinkage estimators to estimate the system reliability (R) in the stress-strength model when the stress and strength follow the Inverse Chen distribution (ICD). The comparisons of the proposed estimators have been presented using a simulation that depends on the mean squared error (MSE) criteria.

A novel neural-evolutionary framework for predicting weight on the bit in drilling operations

This study compares the performance of artificial neural networks (ANN) trained by grey wolf optimization (GWO), biogeography-based optimization (BBO), and Levenberg–Marquardt (LM) to estimate the weight on bit (WOB). To this end, a dataset consisting of drilling depth, drill string rotational speed, rate of penetration, and volumetric flow rate as input variables and the WOB as a response is used to develop and validate the intelligent tools. The relevance test is applied to sort the strength of WOB dependency on the considered features. It was observed that the WOB has the highest linear correlation with the drilling depth and drill string rotational speed. After dividing the databank into the training and testing (4:1) parts, the proposed LM-ANN, GWO-ANN, and BBO-ANN ensembles are constructed. A sensitivity analysis is then carried out to find the most powerful structure of the models. Each model performs to reveal the relationship between the WOB and the mentioned independent factors. The performance of the models is finally evaluated by mean square error (MSE) and mean absolute error criteria. The results showed that both GWO and BBO algorithms effectively help the ANN to achieve a more accurate prediction of the WOB. Accordingly, the training MSEs decreased by 14.62% and 24.90%, respectively, by applying the GWO and BBO evolutionary algorithms. Meanwhile, these values were obtained as around 9.86% and 9.41% for the prediction error of the ANN in the testing phase. It was also deduced that the BBO performs more efficiently than the other technique. The effect of input variables dimension on the accuracy and training time of the BBO-ANN clarified that the most accurate WOB predictions are achieved when the model constructs with all four input variables instead of utilizing either three or two of them with the highest linear correlation. It was also observed that the training stage of the BBO-ANN model with four input variables needs a little more computational time than its training with either two or three variables. Finally, the accuracy of the BBO-ANN model for the WOB prediction has been compared with the multiple linear regression, support vector regression, adaptive neuro-fuzzy inference systems, and group method of data handling. The statistical accuracy analysis confirmed that the BBO-ANN is more accurate than the other checked techniques.

К ВОПРОСУ О ПЕРЕВОДЧЕСКИХ ОШИБКАХ В ПЕРЕДАЧЕ АУДИОВИЗУАЛЬНОГО ПЕСЕННОГО ТЕКСТА

Assessment of the audiovisual translation quality is an important matter of modern language studies since the amount of video materials has become unprecedented these days, and the popularity and spread of unedited amateur and automated translations keep growing. The concept and defining criteria of a translation error have been developed by many linguists, but these criteria are hardly universally applicable, and their practical value frequently depends on the type of a text and the format of its presentation to the audience. This paper reviews various approaches to the concept of translation error in general and in audiovisual translation in particular. Special attention is paid to the controversial nature of audiovisual translation of songs when they are an integral element of the storyline. The analysis of translation errors in Russian and Spanish versions of the animated movie Moana was used to develop specific criteria of distinguishing translation errors, based on intertextuality, technical compliance, and language norm.

EFFECT OF LINEAR DATA PROCESSING PROCESSES ON THE PREDICTION PERFORMANCE OF THE NEURAL NETWORK: AN APPLICATION WITH EXCHANGE RATE DATA

This study investigated the effect of traditional data preprocessing processes on the prediction performance of predictions made with artificial neural network models. For this purpose, two different models were created and time series estimation was made. The original data was used in the first model, and in the second model, the data obtained by the traditional data preprocessing method in the time series were used. The data set consists of monthly real US Dollar/Turkish Lira rates between 2000M1 and 2022M2 for Turkey. Jordan model with feedback artificial neural network architecture is used for time series estimation. Estimation errors were calculated according to the Root Squared Value of Mean Squared Error (RMSE) criteria and the results were discussed according to this statistic. In the study, it was concluded that data processing reduces the estimation error of the nonlinear method.

A novel cascade-loop controller for load frequency control of isolated microgrid via dandelion optimizer

In fast-growing isolated microgrids (IMGs), load frequency control (LFC) ensures optimal power quality for end users. Stochastic grids, notably with renewable energy resources (RESs), require robust and intelligently designed LFC schemes. Thus, this research presents a novel cascade-loop controller combining a fractional order-proportional derivative with a filter and a fractional order-proportional tilt integral derivative (FPDN-FPTID) to improve LFC for single and multi-area IMGs. Recent dandelion optimization adjusts FPDN-FPTID controller settings. Anti-windup keeps the controller out of the non-linear zone for low inertia IMGs. It concerns various sources' maximum generating rates. The two-area IMG model shows its potential and scalability. Extensive MATLAB/Simulink simulations show that the FPDN-FPTID controller outperforms numerous published controllers, either single or cascade-loop, in minimum error criteria, undershoots/ overshoots/settling times, frequency, and tie-line power deviation following load and RES variations. Finally, the sensitivity study indicates the suggested controller stabilizes the system despite ±25 % parameter changes.

An efficient equalizer for the impulsive noise environment

In some communication systems, the transmitted signal is contaminated by impulsive noise with a non-Gaussian distribution, which usually causes significant performance degradation to communication receivers. To deal with the impulsive noise, this paper proposes an efficient equalizer based on new fractional lower-order statistic (FLOS). Firstly, a nonlinear function-based new FLOS associated with the linear equalizer is designed to decrease the influence of impulsive noise. Secondly, referring to minimum mean square error (MMSE) criterion, an unconstrained optimization problem is formulated, and it is solved by the gradient descent method. Thirdly, to further improve the robustness of the proposed algorithm, the gradient is normalized by the l∞-norm of the equalizer input vector. Finally, simulation results demonstrate that the proposed algorithm achieves superior performance under Gaussian noise, even in the case of strong impulsive noise. Also, the simulation results prove the rationality of the new statistics under impulsive noise environments.

FrFT equalization for underwater sweep-spread communication system

In underwater acoustic channels, multipath propagation and Doppler frequency can distort the received signal and reduce system reliability. In order to effectively combat multipath interference, the Sweep-Spread Carrier (SSC) system using frequency swept signal is proposed, however, the SSC receiver performs well only when the maximum delay spread of path arrivals and the Doppler spread are moderate. In this paper, fractional Fourier transform (FrFT) is applied to channel equalization of the SSC system, which improves the ability to resist the Doppler effect and intersymbol interference (ISI). FrFT can simplify the channel characteristics by selecting an appropriate transform order. We analyze the FrFT equalizer in the SSC system under the zero forcing (ZF) criterion and minimum mean squared error (MMSE) criterion. Compared with typical nonlinear Turbo equalization, FrFT equalizer only requires lower complexity to achieve good performance. The numerical simulation results in bellhop and ray tracing channels and the results of the Wu-yuan Bay test channel show the high robustness of the proposed method in doubly dispersive channels.

Maximum Likelihood Estimation for the Log-Logistic Distribution Using Whale Optimization Algorithm with Applications

The log-logistic distribution has been widely used in several fields, including engineering, survival analysis, and economics. The method of maximum likelihood estimation is used in this study for estimating the shape and scale parameters for the log-logistic distribution, whereas in the case of the log-logistic distribution, likelihood equations lack explicit solutions. Therefore, problems with solving likelihood equations can be solved by using two highly efficient algorithms, which are the whale optimization algorithm and the Nelder-Mead algorithm, as well as by showing the applicability of this distribution by comparing it with other well-known classical distributions. To demonstrate the performance of each algorithm implemented, an extensive Monte Carlo simulation study has been conducted. The performance of maximum likelihood estimators for each algorithm has been evaluated in terms of mean square error and deficiency criteria. It has been seen that the whale optimization algorithm provides the best estimates for the log-logistic distribution parameters according to the simulation data.

Multiple similarity measure-based maximum correntropy criterion Kalman filter with adaptive kernel width for GPS/INS integration navigation

The filter based on the maximum correntropy criterion (MCC) has low sensitivity to non-Gaussian noise, which can effectively improve the robustness of the filter. However, the uncertainty of kernel width restricted the application of the maximum correntropy criterion Kalman filter (MCCKF) in the integrated navigation system. In order to overcome the above difficulty, this paper proposes a multiple similarity measure-based maximum correntropy criterion Kalman filter with adaptive kernel width (ABMCCKF). ABMCCKF uses the MORKF framework and distinguishes the noise polluted by outliers through a designed protecting window, which also ensures that the kernel width is compatible with the noise pollution level. Through the window, ABMCCKF utilizes the optimality of both MCC and the minimum mean square error criterion (MMSE). Simulations and vehicular experiments are used to verify the effectiveness of the method. The results show that the ABMCCKF have a good performance when the optimal kernel width is uncertain.