Support Vector Regression For Prediction Research Articles

Prediction of Deformation in Expansive Soil Landslides Utilizing AMPSO-SVR

A non-periodic “step-like” variation in displacement is exhibited owing to the repeated instability of expansive soil landslides. The dynamic prediction of deformation for expansive soil landslides has become a challenge in actual engineering for disaster prevention and mitigation. Therefore, a support vector regression prediction (AMPSO-SVR) model based on adaptive mutation particle swarm optimization is proposed, which is suitable for small samples of data. The shallow displacement is decomposed into a trend component and fluctuating component by complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), and the trend displacement is predicted by cubic polynomial fitting. In this paper, the multiple disaster-inducing factors of expansive landslides and the time hysteresis effect between displacement and its influencing factors are fully considered, and the crucial influencing factors which eliminate the time lag effect and state factors are input into the model to predict the fluctuation displacement. Monitoring data in the Ningming area of China are employed for the model validation. The predicted results are compared with those of the traditional model. The model performance is evaluated through indicators such as the goodness of fit R2 and root mean square error RMSE. The results show that the prediction RMSE of the new model for three monitoring stations can reach 2.6 mm, 6.6 mm, and 2.5 mm, respectively. Compared with the common Grid search support vector regression (GS-SVR), the Particle Swarm Optimization Support Vector Regression (PSO-SVR) and Back Propagation Neural Network (BPNN) models have average improvements of 58.4%, 38.1%, and 25.2% respectively. The goodness of fit R2 is superior to 0.99 in the new method. The proposed model can effectively be deployed for the displacement prediction of non-periodic stepped expansive soil landslides driven by multiple influencing factors, providing a reference idea for the deformation prediction of expansive soil landslides.

Fusion of finite element and machine learning methods to predict rock shear strength parameters

Abstract The trial-and-error method for calibrating rock mechanics parameters has the disadvantages of complexity, being time-consuming, and difficulty in ensuring accuracy. Harnessing the repeatability and scalability intrinsic to numerical simulation calculations and amalgamating them with the data-driven attributes of machine learning methods, this study uses the finite element analysis software RS2 to establish 252 sets of sandstone sample data. The recursive feature elimination and cross-validation method is employed for feature selection. The shear strength parameters of sandstone are predicted using machine learning models optimized by the particle swarm optimization (PSO) algorithm, including the backpropagation neural network, Bayesian ridge regression, support vector regression (SVR), and light gradient boosting machine. The predicted value of cohesion is proposed as the input feature to predict the friction angle. The results indicate that the optimal input characteristics for predicting cohesion are elastic modulus, Poisson's ratio, peak stress, and peak strain, while the optimal input characteristics for predicting friction angle are peak stress and cohesion. The PSO-SVR model demonstrates the best performance. The maximum error between the predicted values of cohesion and friction angle and the calculated results of RSData program are 3.5% and 4.31%, respectively. The finite element calculation is in good agreement with the stress–strain curve obtained in the laboratory. The sensitivity analysis indicates that SVR's prediction performance for cohesion and friction angle tends to be stable when the sample size is >25. These results offer a valuable reference for accurately predicting rock mechanics parameters.

Research on condition operation monitoring of power system based on supervisory control and data acquisition model

In order to better detect and identify the running state of the wind turbine equipment and its generator in the power system wind farm, and then improve the operation reliability of the wind turbine in the power system wind farm, the monitoring method of power system state operation based on Supervisory Control and Data Acquisition (SCADA) model was studied. The SCADA model pre installs different types of sensors on the units of the power system to collect, record and store the power data of the power system. The empirical wavelet transform method is selected to extract the signal characteristics from the state operation signals collected by the SCADA model. ReliefF algorithm is used to select features related to equipment status monitoring from the extracted status operation signal features. Fuzzy C-means clustering algorithm is used to analyze the correlation of feature selection results and identify power system operating conditions. According to the condition identification results of power system, support vector regression prediction algorithm is selected to output the monitoring results of power system state operation. The experimental results show that the monitoring time of the generator and other equipment is less than 100 ms, which provides a strong guarantee for the reliable operation of the power system. This result not only validates the validity of the monitoring and data acquisition model proposed in this paper, but also provides a new idea and method for the intelligent operation and safety management of power system.

A horizontal vibration prediction method of high-speed elevator based on transferred-digital twin model

The vibrations of high-speed-elevators (HSEs) significantly impact the comfort of elevator rides, with horizontal vibrations (HV) being the most sensitive to bodies. Customized elevator products are characterized by high-speed capabilities, customization options, and complex operational conditions. These characteristics often lead to challenges such as difficulties in predicting HV, low prediction accuracy, and limited reusability of prediction models and data. In order to mitigate HV in elevators, its crucial to implement HV prediction during the design phase. To address this need, this paper proposes a method for predicting HSEHV based on a Transferred Digital Twin (TLDT) model. The HSE’s design is physically extracted, and an elevator Digital Twin (DT) model with a digital layer is constructed. This model includes product geometry models, dynamics models, and simulation models. A transfer learning (TL) model is developed to integrate simulation data generated by the digital layer with measurement data acquired from the data interface layer, resulting in high-capacity and high-fidelity DT data. Using the support vector regression (SVR) method, a high-dimensional nonlinear HSEHV prediction model is established, and is trained and optimized using DT data to achieve data-driven HSEHV prediction. The validity of this approach is confirmed using measured data from an elevator test tower. Results indicate that the SVR-based TLDT model achieves the highest accuracy and the lowest absolute error values for both peak-to-peak and A95 vibration acceleration when compared to other models such as NN, KNN, decision tree, and lasso models. Furthermore, by incorporating DT data, the model accuracies improve by 16.9%, 14.5%, 8.6%, 14.1%, and 8.6%, and 12.3%, 12.4%, 19.7%, 7.6%, and 8.7%, respectively, for the mentioned models. Finally, the HV of KLK2 elevator car system is predicted. When compared with simulation analysis and the conventional SVR prediction model, obtained results through the proposed method closely align with the measured values.

From NMR to AI: Designing a Novel Chemical Representation to Enhance Machine Learning Predictions of Physicochemical Properties.

A novel approach to the utilization of nuclear magnetic resonance (NMR) spectroscopy data in the prediction of logD through machine learning algorithms is shown. In the analysis, a data set of 754 chemical compounds, organized into 30 clusters, was evaluated using advanced machine learning models, such as Support Vector Regression (SVR), Gradient Boosting, and AdaBoost, and comprehensive validation and testing methods were employed, including 10-fold cross-validation, bootstrapping, and leave-one-out. The study revealed the superior performance of the Bucket Integration method for dimensionality reduction, consistently yielding the lowest root mean square error (RMSE) across all data sets and normalization schemes. The SVR prediction models demonstrated remarkable computational efficiency and low cost, with the best RMSE value reaching 0.66. Our best model outperformed existing tools like JChem Suite's logD Predictor (0.91) and CplogD (1.27), and a comparison with traditional molecular representations yielded a comparable RMSE (0.50), emphasizing the robustness of our NMR data integration. The widespread availability of NMR data in pharmaceutical and industrial research presents an untapped resource for predictive modeling, highlighting the need for accessible methodologies like ours that complement the analytical toolbox beyond conventional 2D approaches. Our approach, designed to leverage the rich spatial data from NMR spectroscopy, provides additional insights and enriches drug discovery and computational chemistry with a freely accessible tool.

Analysis of the factors affecting heat transfer performance and prediction of heat transfer coefficient for MVR evaporator: A case study

The heat transfer coefficient of evaporation is one of the key factors affecting the design and management of evaporators. This paper presented an industrial case to investigate the influencing factors on the evaporator's heat transfer coefficient, as well as the interaction between the influencing factors. Besides, a comparison of accuracies was made between the heat transfer coefficients predicted by physical models and the support vector regression (SVR) model. The study results showed that due to the interaction between the influencing factors, changes in the heat transfer coefficient varied greatly from the laboratory results. The impact of other variables must be controlled for in industrial research. There were big errors between the results predicted by the early experimental or numerical models and the observed results. The root mean square error (RMSE) values and mean absolute percentage error (MAPE) values of the physical models were all greater than 150 and 5%, respectively, and their R2 values were all lower than 0.50. The data mining-based SVR predictions were more accurate than the predictions by physical models, with a maximum relative error of 5.38% and a minimum relative error of −5.60%.

The Impact of Financial Statement Integration in Machine Learning for Stock Price Prediction

In the capital market, there are two methods used by investors to make stock price predictions, namely fundamental analysis, and technical analysis. In computer science, it is possible to make prediction, including stock price prediction, use Machine Learning (ML). While there is research result that said both fundamental and technical parameter should give an optimum prediction there is lack of confirmation in Machine Learning to this result. This research conducts experiment using Support Vector Regression (SVR) and Support Vector Machine (SVM) as ML method to predict stock price. Further, the result is compared between 3 groups of parameters, technical only (TEC), financial statement only (FIN) and combination of both (COM). Our experimental results show that integrating financial statements has a neutral impact on SVR predictions but a positive impact on SVM predictions and the accuracy value of the model in this research reached 83%.

Predicting Impact Outcomes and Maximum Spreading of Drop Impact on Heated Nanostructures Using Machine Learning.

Accurate prediction of droplet behavior upon impact on a heated nanostructured surface is vital for various industrial applications. In this study, we leverage multiple data-driven machine learning (ML) techniques to model the impact outcome and droplet spreading, employing existing experimental data. Our approach incorporates a comprehensive range of critical control parameters, such as the impact velocity (V), surface temperature (Ts), nanopillars' packing fraction (ϕ), and surface roughness (r). We obtain optimal results when utilizing the artificial neural network classification (ANNC) to construct a phase diagram that encompasses all of the experimental impact behaviors. Additionally, we utilize the support vector regression (SVR) method to model the maximum spreading factor (βmax) as a function of the Weber number (We), defined as the ratio of droplet kinetic to surface energy, and Ts for each surface combination. Consistent with previous experimental observations, our results illustrate that nanostructures not only introduce distinct impact behaviors, such as central jetting, but also influence the boundaries among the deposition, rebound, and splashing regimes within the phase diagram. An increase in ϕ at a constant r promotes deposition and spreading events, while increasing r at a constant ϕ results in enhanced heat transfer to promote the Leidenfrost effect for the rebound regime and a greater disturbance of the liquid lamella to trigger splashing. The SVR prediction reveals the existence of a We-number threshold governed by the nanostructure parameters. Beyond this threshold, the maximum spreading factor (βmax) of a spreading droplet becomes independent of the surface temperature (Ts) as We increases, suggesting that fluid properties are likely the dominating factors influencing the spreading dynamics in the extreme We range.

Prediction of ash fusion temperatures of municipal solid waste incinerator ash based on support vector regression

The ash fusion temperatures (AFTs) of the municipal solid waste incinerator (MSWI) ash and slags is the main indicator to judge its slagging characteristics. Support vector regression (SVR) algorithm is more appropriate for creating an AFT prediction model than the classic regression method because it can adjust to a wider range of ash sample types in a wider range of areas by avoiding underfitting and overfitting. In this paper, SVR prediction models for the deformation temperature (IDT), softening temperature (ST), hemisphere temperature (HT), and flow temperature (FT) of ash are constructed using the ash chemical composition and AFTs dataset of coal ash and biomass ash and other ash. The AFTs of fly ash, bottom slag, and other ash in the municipal solid waste incinerator are predicted. With average relative errors of 1.98 % and 3.56 % and maximum relative errors of 5.21 % and 5.2 %, respectively, the results demonstrate that ST and FT have greater prediction accuracy. IDT and HT both provide poor predictions, with maximum relative errors of 14.08 % and 9.36 %, respectively, and average relative errors of 10.06 % and 5.95 %, respectively. Additionally, the impact of removing various numbers of outlier samples from training data on prediction accuracy, and the impact of test sample measures, such as ash composition analysis and AFTs determination, on prediction accuracy are analyzed and examined.

Support vector regression for prediction of stable isotopes and trace elements using hyperspectral imaging on coffee for origin verification

The potential of using rapid and non-destructive near-infrared – hyperspectral imaging (HSI-NIR) for the prediction of an integrated stable isotope and multi-element dataset was explored for the first time with the help of support vector regression. Speciality green coffee beans sourced from three continents, eight countries, and 22 regions were analysed using a push-broom HSI-NIR (700–1700 nm), together with five isotope ratios (δ13C, δ15N, δ18O, δ2H, and δ34S) and 41 trace elements. Support vector regression with the radial basis function kernel was conducted using X as the HSI-NIR data and Y as the geochemistry markers. Model performance was evaluated using root mean squared error, coefficient of determination, and mean absolute error. Three isotope ratios (δ18O, δ2H, and δ34S) and eight elements (Zn, Mn, Ni, Mo, Cs, Co, Cd, and La) had an R2predicted 0.70 – 0.99 across all origin scales (continent, country, region). All five isotope ratios were well predicted at the country and regional levels. The wavelength regions contributing the most towards each prediction model were highlighted, including a discussion of the correlations across all geochemical parameters. This study demonstrates the feasibility of using HSI-NIR as a rapid and non-destructive method to estimate traditional geochemistry parameters, some of which are origin-discriminating variables related to altitude, temperature, and rainfall differences across origins.

Establishing a Berry Sensory Evaluation Model Based on Machine Learning.

In recent years, people's quality of life has increased, and the requirements for fruits have also become higher; blueberries are particularly popular because of their rich nutrients. In the blueberry industry chain, sensory evaluation is an important link in determining the quality of blueberries. Therefore, to make a more objective scientific evaluation of blueberry quality and reduce the influence of human factors, on the basis of traditional sensory evaluation methods, machine learning is introduced to establish a support vector regression prediction model optimized by the particle swarm algorithm. Ten physical and chemical flavor indices of blueberries (such as catalase, flavonoids, and soluble solids) were used as input data, and sensory evaluation scores were used as output data. Three different predictive models were applied and compared: a particle swarm optimization support vector machine, a convolutional neural network, and a long short-term memory network model. To ensure reliability, the experiments with each of the three models were repeated 20 times, and the mean of each index was calculated. The experimental results showed that the root mean square error and mean absolute error of the particle swarm optimization support vector machine were 0.45 and 0.40, respectively; these values were lower than those of the convolutional neural network (0.96 and 0.78, respectively) and the long short-term memory network (1.22 and 0.97, respectively). Hence, these results highlighted the superiority of the proposed model when sample data are limited.

Selection of Agronomic Parameters and Construction of Prediction Models for Oleic Acid Contents in Rapeseed Using Hyperspectral Data

High oleic acid oilseed rape is a hot research area in the development of functional oilseed rape. At present, the model of predicting the oleic acid content in rapeseed at the early growth stage based on hyperspectral technology lacks a mechanistic explanation. In this study, based on the data collected at the 5–6 leaf stage of oilseed rape, a one-dimensional linear regression prediction model of the oleic acid content in leaves (x) and the oleic acid content in rapeseed (y) was constructed with the regression equation y = 1.83x + 75.26, and the R2, RMSE, and RPD of the testing set were 0.96, 0.23%, and 4.86, respectively. Then, a support vector regression prediction model of the spectral standard normal transformed feature parameters and the oleic acid content in leaves was constructed, and the R2, RMSE, and RPD of the testing set were 0.74, 0.21%, and 2.01, respectively. Finally, the sensitive parameter transfer model for the prediction of “spectral standard normal transform feature—oleic acid content in leaves—oleic acid content in rapeseed” was validated, and the R2, RMSE, and RPD of the full sample test were 0.71, 0.54%, and 0.54, respectively. The results show that although the accuracy of the prediction model after the introduction of the agronomic parameters was reduced compared with the performance of direct prediction by using spectra, the oleic acid content in oilseed rape leaves, as an important intermediate variable, could better explain the relationship between the reflection spectrum of the leaf and the oleic acid content in rapeseed. This study provides a theoretical basis and technical support for hyperspectral remote sensing technology in the quality prediction of rapeseed.

Temperature Prediction Based on STOA-SVR Rolling Adaptive Optimization Model

In this paper, a support vector regression (SVR) adaptive optimization rolling composite model with a sooty tern optimization algorithm (STOA) has been proposed for temperature prediction. Firstly, aiming at the problem that the algorithm tends to fall into the local optimum, the model introduces an adaptive Gauss–Cauchy mutation operator to effectively increase the population diversity and search space and uses the improved algorithm to optimize the key parameters of the SVR model, so that the SVR model can mine the linear and nonlinear information in the data well. Secondly, the rolling prediction is integrated into the SVR prediction model, and the real-time update and self-regulation principles are used to continuously update the prediction, which greatly improves the prediction accuracy. Finally, the optimized STOA-SVR rolling forecast model is used to predict the final temperature. In this study, the global mean temperature data set from 1880 to 2022 is used for empirical analysis, and a comparative experiment is set up to verify the accuracy of the model. The results show that compared with the seasonal autoregressive integrated moving average (SARIMA), feedforward neural network (FNN) and unoptimized STOA-SVR-LSTM, the prediction performance of the proposed model is better, and the root mean square error is reduced by 6.33–29.62%. The mean relative error is reduced by 2.74–47.27%; the goodness of fit increases by 4.67–19.94%. Finally, the global mean temperature is predicted to increase by about 0.4976 °C in the next 20 years, with an increase rate of 3.43%. The model proposed in this paper not only has a good prediction accuracy, but also can provide an effective reference for the development and formulation of meteorological policies in the future.

Disrupted functional networks within white-matter served as neural features in adolescent patients with conduct disorder

BackgroundConduct disorder (CD) has been conceptualized as a psychiatric disorder associated with white-matter (WM) structural abnormalities. Although diffusion tensor imaging could identify WM structural architecture changes, it cannot characterize functional connectivity (FC) within WM. Few studies have focused on disentangling the WM dysfunctions in CD patients by using functional magnetic resonance imaging (fMRI). MethodsThe resting-state fMRI data were first obtained from both adolescent CD and typically developing (TD) controls. A voxel-based clustering analysis was utilized to identify the large-scale WM FC networks. Then, we examined the disrupted WM network features in CD, and further investigated whether these features could predict the impulsive symptoms in CD using support vector regression prediction model. ResultsWe identified 11 WM functional networks. Compared with TDs, CD patients showed increased FCs between occipital network (ON) and superior temporal network (STN), between orbitofrontal network (OFN) and corona radiate network (CRN), as well as between deep network and CRN. Further, the disrupted FCs between ON and STN and between OFN and CRN were significantly negatively associated with non-planning impulsivity scores in CD. Moreover, the disrupted WM networks could be served as features to predict the motor impulsivity scores in CD. ConclusionsOur results provided further support on the existence of WM functional networks and could extended our knowledge about the WM functional abnormalities related with emotional and perception processing in CD patients from the view of WM dysfunction.

A Novel Flight Dynamics Modeling Using Robust Support Vector Regression against Adversarial Attacks

<div>An accurate Unmanned Aerial System (UAS) Flight Dynamics Model (FDM) allows us to design its efficient controller in early development phases and to increase safety while reducing costs. Flight tests are normally conducted for a pre-established number of flight conditions, and then mathematical methods are used to obtain the FDM for the entire flight envelope. For our UAS-S4 Ehecatl, 216 local FDMs corresponding to different flight conditions were utilized to create its Local Linear Scheduled Flight Dynamics Model (LLS-FDM). The initial flight envelope data containing 216 local FDMs was further augmented using interpolation and extrapolation methodologies, thus increasing the number of trimmed local FDMs of up to 3,642. Relying on this augmented dataset, the Support Vector Machine (SVM) methodology was used as a benchmarking regression algorithm due to its excellent performance when training samples could not be separated linearly. The trained Support Vector Regression (SVR) predicted the FDM for the entire flight envelope. Although the SVR-FDM showed excellent performance, it remained vulnerable to adversarial attacks. Hence, we modified it using an adversarial retraining defense algorithm by transforming it into a Robust SVR-FDM. For validation studies, the quality of predicted UAS-S4 FDM was evaluated based on the Root Locus diagram. The closeness of predicted eigenvalues to the original eigenvalues confirmed the high accuracy of the UAS-S4 SVR-FDM. The SVR prediction accuracy was evaluated at 216 flight conditions, for different numbers of neighbors, and a variety of kernel functions were also considered. In addition, the regression performance was analyzed based on the step response of state variables in the closed-loop control architecture. The SVR-FDM provided the shortest rise time and settling time, but it failed when adversarial attacks were imposed on the SVR. The Robust-SVR-FDM step response properties showed that it could provide more accurate results than the LLS-FDM approach while protecting the controller from adversarial attacks.</div>

A GAN–SVR Prediction Method of the Metal Tube‐Bending Rebound with Small Samples

This paper investigates a predictive algorithm for the angle of the metal tube‐bending rebound with small samples. First, the generative adversarial network (GAN) approach is introduced to address the issues of insufficient sample data. The proposed method can realize data augmentation through a generator, enhancing training effectiveness compared to conventional model‐based and experimental prediction methods. To further reduce the problems caused by the small samples, the Wasserstein distance is utilized as the optimization objective for the GAN approach. Second, after obtaining the augmented dataset, Support Vector Regression (SVR) is employed to predict the rebound model of the metal tube‐bending. A novel predictive algorithm for the angle of the metal tube‐bending rebound based on GAN–SVR is proposed. It exhibits that the GAN–SVR owns more positive prediction ability and error when dealing with small samples than conventional GAN‐radial basis function methd (GAN–BP) and GAN–convolutional neural networks. Finally, the effectiveness of the proposed method is validated through experimental results.

A Free-Space-Based Model for Predicting Peanut Moisture Content during Natural Drying

This study aimed to investigate the water dissipation pattern from peanut pods under natural drying conditions after harvest. The Shandong peanut Luhua 22 was used to examine the effects of varying moisture content, bulk density, and porosity on the relative permittivity of the peanut at a signal frequency of 5.8 GHz. The peanut dielectric constant, porosity, and bulk density were used as inputs and peanut kernel moisture as outputs. Support vector regression (SVR), extreme learning machine (ELM), sparrow search algorithm-support vector regression (SSA-SVR), and sparrow search algorithm-extreme learning machine (SSA-ELM) were used to create a prediction model of peanut kernel moisture content. The results show that the water content of peanut kernels decreased in a fast and then slow manner throughout the drying process and that the water content of kernels was stable at 5–8% at the end of drying. The relative permittivity of peanut kernels increased with an increase in the water content and bulk density but decreased with an increase in porosity. The developed SVR, ELM, SSA-SVR, and SSA-ELM water-content prediction models were validated and analyzed in this study, with the model test set coefficients of determination of 0.936, 0.949,0.984, and 0.994, respectively. In comparison to SVR, ELM, and SSA-SVR, the SSA-ELM root mean square error was reduced by 0.0080, 0.0060, and 0.0012, respectively. According to the findings, the ELM neural network model, which is based on the optimization of the SSA, has an improved prediction accuracy. This prediction model provides a theoretical foundation for the variations in peanut seed moisture content during the natural drying process after harvesting peanuts in Shandong, which will be useful for future peanut storage and transportation.

Error analysis of multi-step day-ahead PV production forecasting with chained regressors

This paper presents a comprehensive error analysis of the day-ahead photovoltaic (PV) production multi-step forecasting model that uses a chained support vector regression (SVR). A principal component analysis (PCA) is also implemented to investigate possible improvements of the SVR prediction accuracy. Special attention was given to the hyper-parameter tuning of the chained SVR and PCA+SVR models; specifically, the dispersion of the prediction errors when fine-tuning the model with an experimental halving random search algorithm implemented within scikit-learn, i.e. the HalvingRandomSearchCV (HRSCV). The obtained results were compared with the traditional randomized search technique, i.e. the RandomizedSearchCV (RSCV). The chained SVR model prediction errors were analysed for several different parameter distribution settings. After doing repetitive fine-tuning and predictions, it was observed that the HRSCV tends to choose sub-optimal hyper-parameters for certain scenarios, as will be elaborated in the paper. Moreover, when analysing prediction errors of the same model fine-tuned repetitively with the HRSCV and RSCV, it was found that HRSCV creates larger errors and more inconsistency (variability) in the prediction results. The introduction of the PCA to the chained SVR model, at the same time, reduces the influence of exogenous variables and, on average, increases its performance and decreases prediction errors regardless of the optimization technique used.

Predicting coagulation-flocculation process for turbidity removal from water using graphene oxide: a comparative study on ANN, SVR, ANFIS, and RSM models.

Three artificial intelligence (AI) data-driven techniques, including artificial neural network (ANN), support vector regression (SVR), and adaptive neuro-fuzzy inference system (ANFIS), were applied for modeling and predicting turbidity removal from water using graphene oxide (GO). Based on partial mutual information (PIM) algorithm, pH, GO dosage, and initial turbidity were selected as the input variables for developing the models. The prediction performance of the AI-based models was compared with each other and with the response surface methodology (RSM) model, previously reported by the authors, as well. The models' estimation accuracy was assessed through statistical measures, including mean-squared error (MSE), root-mean-square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Among the evaluated models, ANN had the highest estimation accuracy as it showed the highest R2 for the validation data (0.949) and the lowest MSE, RMSE, and MAE values. Furthermore, ANN predicted 76.1% of data points with relative errors (RE) less than 10%. In contrast, the weakest prediction performance belonged to the SVR model with the lowest R2 for both calibration (0.712) and validation (0.864) data. Besides, only 57.1% of the SVR's predictions were characterized by RE < 10%. The ANFIS and RSM models exhibited a more or less similar performance in terms of R2 for the validation data (0.877 and 0.871, respectively) and other statistical parameters. According to the results, the ANN technique is proposed as the best option for modeling the process. Nevertheless, as the RSM technique provides valuable information about the contribution of the independent operational parameters and their complex interaction effects using the least number of experiments, simulating the process by this technique before modeling by ANN is inevitable.

A traffic flow forecasting method based on the GA-SVR

This paper uses support vector regression (SVR) to predict short-term traffic flow, and studies the feasibility of SVR in short-term traffic flow prediction. The short-time traffic flow has many influencing factors, which are characterized by nonlinearity, randomness and periodicity. Therefore, SVR algorithm has advantages in dealing with such problems. In order to improve the prediction accuracy of the SVR, this paper uses genetic algorithm (GA) to optimize the SVR and other parameters to obtain the global optimal solution. The optimal parameters are used to construct the SVR prediction model. This paper selects the traffic flow data of the Jiangxi Provincial Transportation Department database to verify the feasibility and effectiveness of the proposed model.