Search

Two types of grounding systems are recommended for use in the international standard IEC 62305-3, Part 3: Physical damage to structures and life hazard. One of these is a radial-based grounding system (type-A), which is used in soil resistivities of up to 3000 Ω m and is considered in this paper. It is a well-known fact that during lightning strikes, only a part of the grounding wire contributes to dissipating the lightning current into the surrounding soil. This effective part of the grounding system depends on several features, such as soil resistivity, burial depth, and rise time of the dissipated lightning current. The effect of all of these features on the effective length of the type-A grounding system is explored in this paper. A suitable supervised machine learning regression model is developed, which will enable readers to accurately approximate the effective length of the type-A grounding system for realistic values of input features. The trained model in the paper yielded an R 2 value of 0.99998 on the test set. In addition, two simple mathematical formulas are also provided, which produce similar but less accurate results ( R 2 values of 0.989883 and 0.998557, respectively). [ABSTRACT FROM AUTHOR]

Indoor positioning is a key technology in today's intelligent environments, and it plays a crucial role in many application areas. This paper proposed an unscented Kalman filter (UKF) based on the maximum correntropy criterion (MCC) instead of the minimummean square error criterion (MMSE). This innovative approach is applied to the loose coupling of the Inertial Navigation System (INS) and Ultra-Wideband (UWB). By introducing the maximum correntropy criterion, the MCCUKF algorithm dynamically adjusts the covariance matrices of the system noise and the measurement noise, thus enhancing its adaptability to diverse environmental localization requirements. Particularly in the presence of non-Gaussian noise, especially heavy-tailed noise, the MCCUKF exhibits superior accuracy and robustness compared to the traditional UKF. The method initially generates an estimate of the predicted state and covariance matrix through the unscented transform (UT) and then recharacterizes the measurement information using a nonlinear regression method at the cost of theMCC. Subsequently, the state and covariance matrices of the filter are updated by employing the unscented transformation on the measurement equations. Moreover, to mitigate the influence of non-line-of-sight (NLOS) errors positioning accuracy, this paper proposes a k-medoid clustering algorithm based on bisection k-means (Bikmeans). This algorithm preprocesses the UWB distance measurements to yield a more precise position estimation. Simulation results demonstrate that MCCUKF is robust to the uncertainty of UWB and realizes stable integration of INS and UWB systems. [ABSTRACT FROM AUTHOR]

Using data mining, the purpose of this study is to forecast and analyze the growth of the cotton cultivation industry and the policy financial support demands in the Aksu region. Data mining is a method for maximizing the value of data via the application of numerous algorithms. In contrast to conventional data mining, which adheres to specific algorithms, data mining employs a variety of analysis algorithms to analyze raw data, such as image and panel data, and produce accurate results. In this paper, we propose a data mining method that combines the semantic segmentation algorithm of remote sensing images with various nonlinear regression algorithms to predict the demand for policy-based financial support in a specific region based on a combination of multiple factors, including agricultural crop cultivation area, catastrophe analyses, agricultural price and inflation rates, etc. This paper intends to estimate and analyze actual data pertaining to the cotton cultivation industry in Aksu, and this methodology can further improve the policy-based financial inverse model. The methods presented in this paper can further improve countercyclical regulation of policy finance. [ABSTRACT FROM AUTHOR]

The quality factor (Q) is a parameter reflecting the physical properties of reservoirs. Accurate estimation of the quality factor plays an important role in improving the resolution of seismic data. Spectral-ratio method is a widely used traditional method based on the linear least-squares fitting to extract the quality factor, but is sensitive to noise. This is the main reason preventing this method from being widely used. Some supervised deep-learning methods are proposed to extract Q in which the construction of training labels is a key link. The proposed method is based on the spectral-ratio method to create training labels, avoiding errors in generating them. In contrast to the least-squares method, this paper proposes to use a nonlinear regression algorithm based on a fully connected network to fit the spectral logarithmic ratio and frequency. Meanwhile, the empirical equation is applied to constrain prediction results. The proposed method can effectively overcome the influence of noise and improve the accuracy of prediction results. Tests on the synthesized data of vertical seismic profile and common middle profile show that the proposed method has better generalization ability than the spectral-ratio method. Applying the method to the field vertical seismic profile data successfully extracts the quality factor, which can provide effective information for dividing stratigraphic layers. [ABSTRACT FROM AUTHOR]

Ocean sound speed is important for underwater acoustic applications, such as communications, navigation and localization, where the assumption of uniformly distributed sound speed profiles (SSPs) is generally used and greatly degrades the performance of underwater acoustic systems. The acquisition of SSPs is necessary for the corrections of the sound ray propagation paths. However, the inversion of SSPs is challenging due to the intricate relations of interrelated physical ocean elements and suffers from the high costs of calculations and hardware deployments. This paper proposes a novel sound speed inversion method based on multi-source ocean remote sensing observations and machine learning, which adapts to large-scale sea regions. Firstly, the datasets of SSPs are generated utilizing the Argo thermohaline profiles and the empirical formulas of the sound speed. Then, the SSPs are analyzed utilizing the empirical orthogonal functions (EOFs) to reduce the dimensions of the feature space as well as the computational load. Considering the nonlinear regression relations of SSPs and the observed datasets, a general framework for sound speed inversion is formulated, which combines the designed machine learning models with the reduced-dimensional feature representations, multi-source ocean remote sensing observations and water temperature data. After being well trained, the proposed machine learning models realize the accurate inversion of the targeted ocean region by inputting the real-time ocean environmental data. The experiments verify the advantages of the proposed method in terms of the accuracy and effectiveness compared with conventional methods. [ABSTRACT FROM AUTHOR]

This paper presents the differential evolution algorithm with adaptive mutation and crossover strategies (DEAMC) for solving nonlinear regression problems. The DEAMC algorithm adaptively uses two mutation strategies and two ranges of crossover rate. We evaluate its performance on the National Institute of Standards and Technology (NIST) nonlinear-regression benchmark containing many models of varying levels of difficulty and compare it with classic differential evolution (DE), enhanced differential evolution algorithm with an adaptation of switching crossover strategy (DEASC), and controlled random search methods (CRS4HC, CRS4HCe). We also apply the proposed method to solve parameter identification applications and compare it with enhanced chaotic grasshopper optimization algorithms (ECGOA), self-adaptive differential evolution with dynamic mutation and pheromone strategy (SDE-FMP), and JAYA and its variant methods. The experimental results show that DEAMC is more reliable and gives more accurate results than the compared methods. [ABSTRACT FROM AUTHOR]

Tensile perpendicular to grain is an important mechanical property in the design of joints in timber structures. However, according to the standards, this strength can be determined using at least two different methods: uniaxial tensile and three-point static bending. In this context, the present paper aims to investigate the influence of these test methods on the determination of tensile strength perpendicular to grain of wood used in civil construction timber. Three wood species from Brazilian planted forests (Pinus spp., Eucalyptus saligna, and Corymbia citriodora) were used in this investigation. Twelve specimens of each species were used for each test method investigated. Moreover, a statistical analysis was performed to propose an adjustment to the equation of the Code of International Organization for Standardization 13910:2014 for the three-point bending test. Tensile strength values perpendicular to grain obtained from the uniaxial tensile test were significantly higher than those determined by the three-point bending test. It is proposed that the tensile strength perpendicular to grain can be determined more precisely with adoption of coefficient 5.233 in the term [(3.75·Fult)/b·Lh] of the equation specified by the Code of International Organization for Standardization 13910:2014 for the three-point bending test. [ABSTRACT FROM AUTHOR]

Nonlinear regression models are extensively applied across various scientific disciplines. It is vital to accurately fit the optimal nonlinear model while considering the biases of the Bayesian optimal design. We present a Bayesian optimal design by utilising the Dirichlet process as a prior. The Dirichlet process serves as a fundamental tool in the exploration of Nonparametric Bayesian inference, offering multiple representations that are well-suited for application. This research paper introduces a novel one-parameter model, referred to as the 'Unit-Exponential distribution', specifically designed for the unit interval. Additionally, we employ a stick-breaking representation to approximate the D-optimality criterion considering the Dirichlet process as a functional tool. Through this approach, we aim to identify a Nonparametric Bayesian optimal design. [ABSTRACT FROM AUTHOR]

A nonlinear log-Birnbaum–Saunders regression model with additive errors is introduced. It is assumed that the error term follows a flexible sinh-normal distribution, and therefore it can be used to describe a variety of asymmetric, unimodal, and bimodal situations. This is a novelty since there are few papers dealing with nonlinear models with asymmetric errors and, even more, there are few able to fit a bimodal behavior. Influence diagnostics and martingale-type residuals are proposed to assess the effect of minor perturbations on the parameter estimates, check the fitted model, and detect possible outliers. A simulation study for the Michaelis–Menten model is carried out, covering a wide range of situations for the parameters. Two real applications are included, where the use of influence diagnostics and residual analysis is illustrated. [ABSTRACT FROM AUTHOR]

One technique that is widely used in various fields, including nonlinear target tracking, is the extended Kalman filter (EKF). The well-known minimum mean square error (MMSE) criterion, which performs magnificently under the assumption of Gaussian noise, is the optimization criterion that is frequently employed in EKF. Further, if the noises are loud (or heavy-tailed), its performance can drastically suffer. To overcome the problem, this paper suggests a new technique for maximum correntropy EKF with nonlinear regression (MCCEKF-NR) by using the maximum correntropy criterion (MCC) instead of the MMSE criterion to calculate the effectiveness and vitality. The preliminary estimates of the state and covariance matrix in MCKF are provided via the state mean vector and covariance matrix propagation equations, just like in the conventional Kalman filter. In addition, a newly designed fixed-point technique is used to update the posterior estimates of each filter in a regression model. To show the practicality of the proposed strategy, we propose an effective implementation for positioning enhancement in GPS navigation and radar measurement systems. [ABSTRACT FROM AUTHOR]

This paper derives a general Bartlett correction formula to improve the inference based on the likelihood ratio test in a multivariate model under a quite general parameterization, where the mean vector and the variance-covariance matrix can share the same vector of parameters. This approach includes a number of models as special cases such as non-linear regression models, errors-in-variables models, mixed-effects models with non-linear fixed effects, and mixtures of the previous models. We also employ the Skovgaard adjustment to the likelihood ratio statistic in this class of multivariate models and derive a general expression of the correction factor based on Skovgaard approach. Monte Carlo simulation experiments are carried out to verify the performance of the improved tests, and the numerical results confirm that the modified tests are more reliable than the usual likelihood ratio test. Applications to real data are also presented for illustrative purposes. [ABSTRACT FROM AUTHOR]

The paper considers the problem of nonparametric estimation of nonlinear characteristic in the FIR Wiener system. Methods proposed so far have suffered from the so-called 'curse of dimensionality' and their practical applications have been limited to the very short impulse responses of the linear component. In the proposed approach, the class of (stochastically initialised) repeated exponential input excitations is introduced, and a modified kernel-based estimator is presented. It is shown that the rate of convergence to the genuine system characteristic is significantly improved and does not depend on the length of the impulse response of the linear dynamic block. [ABSTRACT FROM AUTHOR]

In this paper, we have introduced a functional approach for approximating nonparametric functions and coefficients in the presence of multivariate and functional predictors. By utilizing the Fisher scoring algorithm and the cross-validation technique, we derived the necessary components that allow us to explain scalar responses, including the functional index, the nonlinear regression operator, the single-index component, and the systematic component. This approach effectively addresses the curse of dimensionality and can be applied to the analysis of multivariate and functional random variables in a separable Hilbert space. We employed an iterative Fisher scoring procedure with normalized B-splines to estimate the parameters, and both the theoretical and practical evaluations demonstrated its favorable performance. The results indicate that the nonparametric functions, the coefficients, and the regression operators can be estimated accurately, and our method exhibits strong predictive capabilities when applied to real or simulated data. [ABSTRACT FROM AUTHOR]

Radial basis function (RBF) networks represent established tools for nonlinear regression modeling with numerous applications in various fields. Because their standard training is vulnerable with respect to the presence of outliers in the data, several robust methods for RBF network training have been proposed recently. This paper is interested in robust regularized RBF networks. A robust inter-quantile version of RBF networks based on trimmed least squares is proposed here. Then, a systematic comparison of robust regularized RBF networks follows, which is evaluated over a set of 405 networks trained using various combinations of robustness and regularization types. The experiments proceed with a particular focus on the effect of variable selection, which is performed by means of a backward procedure, on the optimal number of RBF units. The regularized inter-quantile RBF networks based on trimmed least squares turn out to outperform the competing approaches in the experiments if a highly robust prediction error measure is considered. [ABSTRACT FROM AUTHOR]

In this paper, a novel ensemble learning model named EWT-EnsemLSTM-SSA, which assembles long short-term memory (LSTM), support vector regression (SVR), and sparrow search algorithm (SSA), is a proposed to deal with long term metro passenger flow volume prediction, which is an essential content of traffic flow prediction problems. Firstly, the empirical wavelet transform (EWT) method is introduced to decompose the original dataset into five wavelet time-sequence data for further prediction. Then, a cluster of LSTMs with diverse hidden layers and neuron counts are employed to explore and exploit the implicit information of the EWT-decomposed signals. Next, the output of LSTMs is aggregated into a nonlinear regression method SVR. Lastly, SSA is utilized to optimize the SVR automatically. The proposed EWT-EnsemLSTM-SSA model is applied in three case studies, using the data collected from the passengers' amount in the Minneapolis, America metro, divided into one hour in one day. Experiment results, which compare the proposed EnsemLSTM-SSA model with five conventional time series forecasting models, show that the proposed model can achieve a better performance than the traditional prediction algorithms. [ABSTRACT FROM AUTHOR]

As a common technology product in life, display screen has been deeply embedded in various fields, and the display performance is the key indicator to determine the quality of display products. The evaluation of screen flicker is one of the key control parameters to evaluate the optical performance of the screen. As the paper introduced, commonly there are two methods of testing flicker: FMA method and JEITA method. This paper makes a research about the above two evaluation methods in time and frequency domain. Particularly, by using nonlinear regression of the mathematical statistics, this paper deduces the mathematical relationship of the two methods for the evaluating in the normal data field. Also, this paper gives accurate conversion formula and the precision analysis. By using the empirical formula, the complexity of existing test equipment can be simplified, the cost and test time can be saved greatly. [ABSTRACT FROM AUTHOR]

The incorporation of conformal cooling systems has significantly enhanced the efficiency and quality of injection molding process. While several automated methods have been developed for creating conformal cooling channels in injection molds, the current optimization process for conformal cooling design parameters is hindered by labor-intensive iterative thermal simulation processes and the substantial reliance on empirical human knowledge. This paper presents an innovative machine learning method to assess the thermal performance of conformal cooling systems by employing a combination of a non-linear regression model and a neural network. By employing a logarithmic regression model describing the temperature graph and a neural network predicting the coefficients of the logarithmic regression model, the thermal performance of specified conformal cooling systems can be assessed and predicted precisely. This methodology empowers designers to evaluate the thermal efficiency of conformal cooling systems efficiently and effectively to further optimize the conformal cooling design parameters without relying on tedious manual thermal and fluid simulation processes. [ABSTRACT FROM AUTHOR]

This paper established a novel approach for developing simplified yet accurate models using artificial neural networks (ANNs) in industrial environments. It demonstrates that combining nonlinear regression with neural network modeling enhances predictive accuracy while maintaining the inherent simplicity of ANNs. Industrial sectors are increasingly adopting environmentally friendly practices, driven by the recognition that sustainable initiatives can lead to significant and lasting financial benefits rather than merely a sense of ecological duty. Integrating energy efficiency practices offers potential advantages in waste reduction and resource conservation, which can decrease operating expenses over time. This contributes significantly to pollution mitigation by reducing overall energy consumption cost‐effectively. Numerical simulations based on experimental results validate the proposed method, addressing the complexity and accuracy challenges in business models within the energy sector. [ABSTRACT FROM AUTHOR]

This paper proposes methods for Machine Learning (ML)-based Beam Alignment (BA), using low-complexity ML models, and achieves a small pilot overhead. We assume a single-user massive mmWave MIMO, Uplink, using a fully analog architecture. Assuming large-dimension codebooks of possible beam patterns at  U E  and  B S , this data-driven and model-based approach aims to partially and blindly sound a small subset of beams from these codebooks. The proposed BA is blind (no CSI), based on Received Signal Energies (RSEs), and circumvents the need for exhaustively sounding all possible beams. A sub-sampled subset of beams is then used to train several ML models such as low-rank Matrix Factorization (MF), non-negative MF (NMF), and shallow Multi-Layer Perceptron (MLP). We provide an extensive mathematical description of these models and the algorithms for each of them. Our extensive numerical results show that, by sounding only  10 %  of the beams from the  U E  and  B S  codebooks, the proposed ML tools are able to accurately predict the non-sounded beams through multiple transmitted power regimes. This observation holds as the codebook sizes at  U E  and  B S  vary from  128 × 128  to  1024 × 1024 . [ABSTRACT FROM AUTHOR]

Accurate assessment and prediction of mandible shape are fundamental prerequisites for successful orthognathic surgery. Previous studies have predominantly used linear models to predict lower facial structures from facial landmarks or measurements; the prediction errors for this did not meet clinical tolerances. This paper compared non-linear models, namely a Multilayer Perceptron (MLP), a Mixture Density Network (MDN), and a Random Forest (RF) model, with a Linear Regression (LR) model in an attempt to improve prediction accuracy. The models were fitted to a dataset of measurements from 155 subjects. The test-set mean absolute errors (MAEs) for distance-based target features for the MLP, MDN, RF, and LR models were respectively 2.77 mm, 2.79 mm, 2.95 mm, and 2.91 mm. Similarly, the MAEs for angle-based features were 3.09°, 3.11°, 3.07°, and 3.12° for each model, respectively. All models had comparable performance, with neural network-based methods having marginally fewer errors outside of clinical specifications. Therefore, while non-linear methods have the potential to outperform linear models in the prediction of lower facial measurements from upper facial measurements, current results suggest that further refinement is necessary prior to clinical use. [ABSTRACT FROM AUTHOR]

Solar photovoltaic energy is a vital renewable resource because it is clean, endless, and pollution‐free. Due to the fast growth of the semiconductor and power electronics sectors, photovoltaic (PV) technologies are climbing significant attention in modern electrical power applications. Operating PV energy conversion systems at the maximum power point is essential for getting the maximum power output and raising efficiency. This paper proposes a regression‐based Perturb and Observe method to quickly find a global maximum power point, avoiding being stuck in local maxima, likewise analytical and metaheuristic methods. The improved control focuses on the narrowed search areas by linear and non‐linear regression analyses using the generated PV model on a flexible Python environment. Furthermore, the method's accuracy is validated in real time under variable temperatures, irradiations, and loads. This method was proven with a hardware implementation. The proposed method is more than 98% accurate and can withstand long‐term modelling. The suggested regression‐based perturbation and observation method provided a short learning time and easy implementation. Additionally, the dynamic recorded results can be visualized for researchers to utilize efficiently. [ABSTRACT FROM AUTHOR]

Buried pipelines, as the most common method of natural gas transportation, are prone to pipeline leakage accidents and are difficult to detect due to their harsh and concealed environment. This paper focused on the problem regarding the free dissipation of residual gas in buried gas pipelines and soil after closing the gas supply end valve after a period of leakage by numerical simulation. A multiple non-linear regression model was established based on the least squares method and multiple regression theory, and MATLAB 2016b mathematical calculation software was used to solve the problem. The research results indicated that compared to the gas leakage diffusion stage, the pressure and velocity distribution during the free dissipation stage were significantly reduced. The increase in leakage time, pipeline pressure, leakage size, and pipeline burial depth led to a large accumulation of natural gas, which increased the concentration and distribution range of gas on the same free dissipation stage monitoring line. A prediction model for natural gas concentration in the free dissipation stage was established with an average error of 7.88%. A calculation model for the safety repair time of buried gas pipeline leakage accidents was further derived to determine the safety repair time of leakage accidents. [ABSTRACT FROM AUTHOR]

Sparse recovery space–time adaptive processing (SR-STAP) technology improves the moving target detection performance of airborne radar. However, the sparse recovery method with a fixed dictionary usually leads to an off-grid effect. This paper proposes a STAP algorithm for airborne radar based on dictionary and clutter power spectrum joint correction (DCPSJC-STAP). The algorithm first performs nonlinear regression in a non-stationary clutter environment with unknown yaw angles, and it corrects the corresponding dictionary for each snapshot by updating the clutter ridge parameters. Then, the corrected dictionary is combined with the sparse Bayesian learning algorithm to iteratively update the required hyperparameters, which are used to correct the clutter power spectrum and estimate the clutter covariance matrix. The proposed algorithm can effectively overcome the off-grid effect and improve the moving target detection performance of airborne radar in actual complex clutter environments. Simulation experiments verified the effectiveness of this algorithm in improving clutter estimation accuracy and moving target detection performance. [ABSTRACT FROM AUTHOR]

Land price plays a crucial role in the development of a region, which serves as an indicator of the features of a property. The primary goal of this paper is to explore the relationship between land price and various geographical and accessibility parameters and thereby arrive at a model to predict the land price. Based on literature surveys, the parameters that influence land price are identified further through which data collection from primary surveys, the creation of a road network map, a geographic information system (GIS) analysis to determine the distance to the central business district (CBD), measurement of road density and access road width, assessment of employment opportunities through establishment surveys, and identification of various land use parcels in the study region are accomplished. The land prices are collected from recently sold parcels in each of the zones in the study region. A negative and significant correlation is observed between land price and distance to the CBD. Positive correlations are observed between land price and other factors considered, such as road density, availability of educational facilities, employment opportunities, and the extent of commercial and residential land use areas. A non-linear regression model is developed that can predict land price depending on the significant parameters. [ABSTRACT FROM AUTHOR]

The objective this paper is determine the highest performance of fresh mass and number of fruits in tomato crops using different nutrient solution. An absolute hybrid with a semi-determined growth was used. It was grown in a protected environment using a fertigated substrate inside plastic bags containing ten liters of solution. The experiment was completely randomized with four levels of fertilization and five replications. Two experiments were carried out in two cultivation cycles (spring 2018 and autumn 2019) by performing an analysis of variance and Scott & Knott test and estimating the parameters of nonlinear logistic model and its critical points for both variables in each treatment. The mean fruit mass per plant was 3.70 kg for the spring experiment and 3.80 kg for the autumn experiment. The mean number of fruits per plant was 10.50 and 10.70 fruits for spring and autumn, respectively. There are significant differences between the treatments KO46, KO45 and KO56 compared to KO69 for fruit mass in the autumn experiment. For the other variables and cultivation cycles, the treatments did not show statistical differences. The logistic growth model fitted the weight and number of tomato fruits according to days after transplanting the seedlings and evidenced production cycle data, highlighting the main differences between the nutrient solutions. The nutritional solutions KO46, KO45 and KO56 are recommended for growing Gaúcho tomatoes in substrate. The nutrient solution KO56 has the best performance because it has a higher K availability, meets the balance of loads and antagonism between nutrients, provides equal response of means mass and number of fruits, and has a lower N:K ratio and balance of K over Ca and Mg, thus favoring fruit production, precocity, and development. [ABSTRACT FROM AUTHOR]

In the current version of the Highway Capacity Manual (HCM-6), the equal capacity passenger car equivalency (EC-PCE) method is used to account for the effect of trucks for capacity analyses. The EC-PCEs for freeway segments were estimated using a microsimulationbased methodology where a nonlinear regression model (NLRM) with 15 model parameters was used to develop capacity adjustment factor (CAF) models using the microsimulation data as input. The objective of this paper is to introduce a simpler nonlinear regression model with 6 model parameters that can be used for the estimation of CAF values and EC-PCE values for freeway and multilane highway segments. It was found that the proposed model can readily substitute the original model with little loss in fidelity. The CAF formulae developed in this paper can be used to calculate EC-PCE values directly, obviating the need for the HCM-6 EC-PCE tables. Equally important, the simpler models provide the user with a better understanding of the trade-offs between capacity, CAF, and EC-PCE values and the parameters that affect them. [ABSTRACT FROM AUTHOR]

In this paper, we propose and assess the accuracy of new fuel consumption estimation models for vehicle routing. Based on real-world data consisting of instantaneous fuel consumption, time-varying speeds observations, and high-frequency traffic, we propose effective methods to estimate fuel consumption. By carrying out nonlinear regression analysis using supervised learning methods, namely Neural Networks, Support Vector Machines, Conditional Inference Trees, and Gradient Boosting Machines, we develop new models that provide better prediction accuracy than classical models. We correctly estimate consumption for time-dependent point-to-point routing under realistic conditions. Our methods provide a more precise alternative to classical regression methods used in the literature, as they are developed for a specific situation. Extensive computational experiments under realistic conditions show the effectiveness of the proposed machine learning consumption models, clearly outperforming macroscopic and microscopic consumption models such as the Comprehensive Modal Emissions Model (CMEM) and the Methodology for Estimating air pollutant Emissions from Transport (MEET). Based on sensitivity analyses we show that MEET underestimates real-world consumption by 24.94% and CMEM leads to an overestimation of consumption by 7.57% with optimised parameters. Our best machine learning model (Gradient Boosting Machines) exhibited superior estimation accuracy with a gap of only 1.70%. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to employ a multivariate nonlinear regression analysis to establish a predictive model for the final fracture area, while accounting for the impact of individual parameters. Design/methodology/approach: This analysis is based on the numerical simulation data obtained, using the hybrid finite element–discrete element (FE–DE) method. The forecasting model was compared with the numerical results and the accuracy of the model was evaluated by the root mean square (RMS) and the RMS error, the mean absolute error and the mean absolute percentage error. Findings: The multivariate nonlinear regression model can accurately predict the nonlinear relationships between injection rate, leakoff coefficient, elastic modulus, permeability, Poisson's ratio, pore pressure and final fracture area. The regression equations obtained from the Newton iteration of the least squares method are strong in terms of the fit to the six sensitive parameters, and the model follow essentially the same trend with the numerical simulation data, with no systematic divergence detected. Least absolutely deviation has a significantly weaker performance than the least squares method. The percentage contribution of sensitive parameters to the final fracture area is available from the simulation results and forecast model. Injection rate, leakoff coefficient, permeability, elastic modulus, pore pressure and Poisson's ratio contribute 43.4%, −19.4%, 24.8%, −19.2%, −21.3% and 10.1% to the final fracture area, respectively, as they increased gradually. In summary, (1) the fluid injection rate has the greatest influence on the final fracture area. (2)The multivariate nonlinear regression equation was optimally obtained after 59 iterations of the least squares-based Newton method and 27 derivative evaluations, with a decidability coefficient R2 = 0.711 representing the model reliability and the regression equations fit the four parameters of leakoff coefficient, permeability, elastic modulus and pore pressure very satisfactorily. The models follow essentially the identical trend with the numerical simulation data and there is no systematic divergence. The least absolute deviation has a significantly weaker fit than the least squares method. (3)The nonlinear forecasting model of physical parameters of hydraulic fracturing established in this paper can be applied as a standard for optimizing the fracturing strategy and predicting the fracturing efficiency in situ field and numerical simulation. Its effectiveness can be trained and optimized by experimental and simulation data, and taking into account more basic data and establishing regression equations, containing more fracturing parameters will be the further research interests. Originality/value: The nonlinear forecasting model of physical parameters of hydraulic fracturing established in this paper can be applied as a standard for optimizing the fracturing strategy and predicting the fracturing efficiency in situ field and numerical simulation. Its effectiveness can be trained and optimized by experimental and simulation data, and taking into account more basic data and establishing regression equations, containing more fracturing parameters will be the further research interests. [ABSTRACT FROM AUTHOR]

Text regression is an important task in natural language processing (NLP), which aims to predict continuous numerical values associated with text. Previous work focused on linear text regression requiring manual feature selection for financial prediction. Recently, non‐linear text regression through neural network models has become a trend. However, most models rely only on convolutional neural networks (CNN) and suffer from insufficient interpretability. In this paper, we propose a deep neural network model named EM‐CBA for text regression and further interpret the model. The proposed model is powered by word EMbedding, CNN, Bidirectional long short‐term memory (Bi‐LSTM) and Attention mechanism. The proposed EM‐CBA takes financial report texts as input and predicts a financial metric named return on assets (ROA). We conduct comprehensive experiments on a dataset about the reports of enterprises. Experimental results show that the proposed model provides more accurate predictions of enterprises' metrics than previous convolutional neural network models and other classical models. The validity of each module of the model is also verified. Finally, we demonstrate a way of performing analysis in words change and results errors to intuitively interpret the effect of different text inputs on the model. The analysis demonstrates that the model is able to use information about sentiment words to analyse their associated contexts to revise the predictions. [ABSTRACT FROM AUTHOR]

In microseismic monitoring, the reconstruction of a reliable velocity model is essential for precise seismic source localization and subsurface imaging. However, traditional methods for microseismic velocity inversion face challenges in terms of precision and computational efficiency. In this paper, we use deep learning (DL) algorithms to achieve precise and efficient real-time microseismic velocity modeling, which holds significant importance for ensuring engineering safety and preventing geological disasters in microseismic monitoring. Given that this task was approached as a non-linear regression problem, we adopted and modified the Attention U-Net network for inversion. Depending on the degree of coupling among microseismic events, we trained the network using both single-event and multi-event simulation records as feature datasets. This approach can achieve velocity modeling when dealing with inseparable microseismic records. Numerical tests demonstrate that the Attention U-Net can automatically uncover latent features and patterns between microseismic records and velocity models. It performs effectively in real time and achieves high precision in velocity modeling for Tilted Transverse Isotropy (TTI) velocity structures such as anticlines, synclines, and anomalous velocity models. Furthermore, it can provide reliable initial models for traditional methods. [ABSTRACT FROM AUTHOR]

The paper is devoted to the formal description of the running time of the user task on some virtual nodes in the computing network. Based on the probability theory framework, this time represents a random value with a finite mean and variance. For any class of user task, these moments are the functions of the node resources, task numerical characteristics, and the parameters of the current node state. These functions of the vector arguments can be treated as some surfaces in the multidimensional Euclidean spaces, so the proposed models are called the stochastic time complexity surfaces. The paper also presents a class of functions suitable for the description of both the mean and variance. They contain unknown parameters which should be estimated. The article includes the statement of the parameter identification problem given the statistical results of the node stress testing, recommendations concerning the test planning, and preprocessing of the raw experiment data. To illustrate the performance of the proposed model, the authors design it for an actual database application—the prototype of the passengers' personal data anonymization system. Its application functions are classified into two user task classes: the data anonymization procedures and fulfillment of the statistical queries. The authors identify the stochastic time complexity surfaces for both task types. The additional testing experiments confirm the high performance of the suggested model and its applicability to the solution of the practical providers' problems. [ABSTRACT FROM AUTHOR]