Forecasting of National Expressway Network Scale Based on Support Vector Regression with Adaptive Genetic Algorithm

The Support Vector Regression (SVR) parameters selection problem is considered in this report. The purpose of work is to create an intelligent algorithm for SVR parameters optimization and, thus, to improve the accuracy of modeling in soft measurements (on example of the rice leaves modeling and data processing). Initially, the program collects the statistical data of learning assemblies analysis results and evaluates the values of SVR parameters, after then it uses developed by the authors improved fruit fly optimization algorithm to get more accurate values of SVR parameters. During the experiments, the obtained results were compared with the results of work of classical Fruit Fly Optimization Algorithm (FOA). It was found, that the authors' algorithm works more effective in convergence speed and accuracy. Thus, it provides the better solution of SVR optimal parameters selection problem.

Support vector regression with genetic algorithms in forecasting tourism demand

Forecasting systems reliability based on support vector regression with genetic algorithms

A dynamic particle filter-support vector regression method for reliability prediction

Traditional time series forecasting models are difficult to capture the nonlinear patterns. Support vector regression (SVR) is a powerful tool for modeling the inputs and output(s) of complex and nonlinear systems. However, parameters determination for a SVR model is competent to the forecasting accuracy. Several evolutionary algorithms, such as genetic algorithms and simulated annealing algorithms have been used to the parameters selection, however, these algorithms often suffer the problem of being trapped in local optimum. In this paper, a novel building cooling load forecasting approach combining support vector regression (SVR) and Ant colony algorithm (ACO) is proposed. ant colony (ACO) optimization was developed to optimize three parameters of SVR, including penalty parameter C, insensitive loss function ε and kernel function σ. SVR constructs hyperplane in high dimension space and fits the data in non-linear form. Normalized Mean square error (NMSE) of fitting result is used as target of ant colony optimization. ACO finds the best parameters which correspond to the NMSE. The results showed that the proposed approach, by comparing with back-propagation neural network model, was an efficient way to model building cooling load with good predictive accuracy. ACO and SVR provide a useful tool for maximizing the combustion efficiency of cooling load. Also, the method can be easily extended to other applications.

A novel support vector regression(SVR) was proposed for complex grouting process, which has the feature of invisible stratum and varied rock facture width. The features of SVR were selected through analyzing the major mechanism sub-models. In order to improve regression model performance, a fast embedded uniform algorithm of optimizing parameters of SVR was introduced. Two steps of optimization are adopted in the embedded uniform algorithm. Firstly rough parameters of SVR are found by throwing uniform point in rectangle area of parameters, seccondly the precise parameters of SVR are found in new subsection of grid. At last, 600 sets data have be selected to test in HENGYANG dam project of Hunan province in China. The results of simulation show that the embedded uniform method is superior to grid algorithm in arithmetic speed and precision in grouting model.

The particleboard (PB) production is an extremely complex process, many operating parameters affecting panel quality. It is a big challenge to optimize the PB production parameters. The production parameters of particle gluing have an important influence on the internal bond (IB) strength of PB. In this study, using grey relation analysis (GRA) and support vector regression (SVR) algorithm, a prediction model was developed to accurately predict IB of PB through particle gluing processing parameters in a PB production line. GRA was used to analyze the grey relational grade between the particle gluing processing parameters and IB of PB, and the variables were screened. The SVR algorithm was used to train 724 groups of particle gluing sample data between six particle gluing processing parameters and IB. The SVR model was tested with 181 sets of experimental data. The SVR model was verified by 181 sets of experimental data, and the values of mean absolute error (MAE), mean relative error (MRE), root mean square error (RMSE), and Theil’s inequality coefficient (TIC) of the model were 0.008, 0.017, 0.013, and 0.014, respectively. The results showed that the prediction performance of the nonlinear regression prediction model based on GRA–SVR is superior, and the GRA–SVR prediction model can be used to real-time predict the IB in the PB production line.

In order to make an exact prediction for the density of the lead-acid battery electrolyte, this paper proposes a method by using a genetic algorithm to optimise the support vector regression. In this AGA-SVR model, a kind of adaptive genetic algorithm is exploited to choose the model parameters of support vector regression for obtaining better prediction performance. The proposed predicting model is applied to the density predicting for lead-acid battery. The experimental results indicate that both GA and AGA have good efficiency on parameter optimisation. Furthermore, the AGA-SVR model provides a superior prediction performance than the other three models including SPSO-SVR model, IPSO-SVR model and GA-SVR model. Therefore, the AGA method could be considered as an effective alternative method for predicting electrolyte density.

The error test station is an important part in the automatic verification assembly line of current transformer, and its accuracy and stability of working state are related to the evaluation of the accuracy level of the current transformer being verified. This paper aims to study the short-term prediction method of transformer error based on intelligent algorithm. In this paper, the risk early-warning method based on error verification test data is used for period verification. Aiming at the characteristics of limited, nonlinear and uncertain samples in risk early-warning problems, fuzzy support vector regression based on correlation analysis and other intelligent algorithms are used for analysis. The error test data are sampled according to time. In the prediction of this kind of data, the correlation between the prediction results and the recent data is strong, but the correlation between the prediction results and the early data is weak. Therefore, the weights from small to large are assigned to the sample data according to the distance of sampling time, which is used to determine the penalty factor of fuzzy support vector regression. According to the interaction of multi-dimensional features of samples, the correlation between each feature is analyzed, and the factors with strong correlation with the parameters to be predicted are screened out. On this basis, a prediction model is established by using fuzzy support vector regression, and the parameters of support vector regression are optimized by adaptive genetic algorithm to achieve the best prediction effect. The example analysis shows that this prediction model has better performance than other prediction models in this paper. Finally, the prediction results are combined with the risk assessment strategy to realize the risk warning of current transformer error test station. Based on the research of intelligent algorithm, the risk early warning system is implemented in this paper. The trial operation results show that the system can give the changing trend of the equipment state on the basis of the period check, which provides technical support for the early maintenance of the error test station of current transformer.

This paper proposes an optimal design scheme to reduce the noise of the intake system by using support vector regression techniques. For this, as a measuring tool for the performance of the intake system, the performance prediction software was used. Then, the length and radius of each component of the current intake system were selected as input variables and the L18 table of orthogonal arrays was adapted as a space-filling design. The simulation of parameter design utilized an orthogonal array design, L 18(21 × 37). In order to evaluate the above design and levels, the experiments satisfying the condition were done. With these simulated data, we can estimate parameters in support vector regression by solving a nonlinear problem and finding an optimal level for the intake system by using support vector regression.

Aiming at the nonlinear and non- stationary characteristics of vibration signal sequence of mechanical equipment, a condition trend prediction method for mechanical equipment is proposed based on phase space reconstruction and genetic optimization support vector regression (SVR). First of all, a one- dimensional time series of vibration signals are transformed into a matrix by use of phase space reconstruction technique, and its features are selected adaptively. The phase points are imported to SVR model as input features and the SVR predictor is trained. Then, adaptive genetic algorithm is applied to optimize the penalty factor C, non- sensitive factor and Gaussian kernel width synchronously. The best model parameters are obtained automatically. Finally, the SVR prediction model is constructed and is applied to vibration signal prediction of a machine unit. The experimental results show that whether for single-step or 24-step prediction, the prediction accuracy of the proposed genetic optimization SVR is higher than that of the conventional SVR, indicating that the proposed method has a good ability for prediction of the condition trend of the mechanical equipment.

Prediction of TVB-N content in eggs based on electronic nose

This paper proposes an algorithm for estimating the true boundary values of non-isothermal control heat equations based on binary sampling information from the boundary values, utilizing the Sparrow Search Algorithm (SSA) and Support Vector Regression (SVR) parameter optimization algorithm (hereinafter referred to as SSA-SVR). The performance of the proposed SSA-SVR algorithm was compared with the standalone SVR algorithm and the traditional Particle Swarm Optimization (PSO) algorithm combined with SVR parameter optimization (referred to as PSO-SVR) in estimating boundary values. The results indicate that the proposed SSA-SVR algorithm possesses advantages in estimating boundary values, with faster speed, lower error, and greater stability. This enables more accurate reconstruction of the boundary values, allowing the reconstructed signals to be utilized for other related synchronization controls.

In the analysis of electronic circuit fault diagnosis based on support vector regression (SVR), irrelevant or correlated features in the samples could spoil the performance of the SVR classifier, leading to decrease of prediction accuracy. In order to solve the problems mentioned above, this paper used rough sets as a preprocessor of SVR to select a subset of input variables and employed the particle swarm optimization algorithm (PSOA) to optimize the parameters of SVR. Additionally, the proposed PSOA-SVR model that can automatically determine the optimal parameters was tested on the prediction of electronic circuit fault. Then, we compared the proposed PSOA-SVR model with other artificial intelligence models of (BPN and fix-SVR). The experiment indicates that the proposed method is quite effective and ubiquitous.

The thermal data of the hypersonic wind tunnel field accurately reflect the aerodynamic performance and key parameters of the aircraft model. However, the prediction of the temperature in hypersonic wind tunnels has problems such as a large delay, nonlinearity and multivariable coupling. In order to reduce the influence brought by temperature changes and improve the accuracy of temperature prediction in the field control of hypersonic wind tunnels, this paper first combines kernel principal component analysis (KPCA) with phase space reconstruction to preprocess the temperature data set of wind tunnel tests, and the processed data set is used as the input of the temperature-prediction model. Secondly, support vector regression is applied to the construction of the temperature prediction model for the hypersonic wind-tunnel temperature field. Meanwhile, aiming at the problem of difficult parameter-combination selection in support vector regression machines, an Improved African Vulture Optimization Algorithm (IAVOA) based on adaptive chaotic mapping and local search enhancement is proposed to conduct combination optimization of parameters in support vector regression. The improved African Vulture Optimization Algorithm (AVOA) proposed in this paper was compared and analyzed with the traditional AVOA, PSO (Particle Swarm Optimization Algorithm) and GWO (Grey Wolf Optimizer) algorithms through 10 basic test functions, and the superiority of the improved AVOA algorithm proposed in this paper in optimizing the parameters of the support vector regression machine was verified in the actual temperature data in wind-tunnel field control.