A New Least Squares Support Vector Machines Ensemble Model for Aero Engine Performance Parameter Chaotic Prediction

Accurate electricity price prediction is key to the orderly operation of the electricity market. However, the uncertain, stochastic and fluctuant characteristics of electricity pricees make prediction difficult. With the aim of solving this issue, this investigation proposed a multi-stage intelligent model integrating the Beveridge–Nelson decomposition (B-N-D) model, the least square support vector machine (LSSVM), and a nature-inspired optimization model named the whale optimization algorithm (WOA). Firstly, the B-N-D model was utilized to decompose the hourly electricity price time series into determinacy component, periodic trend, and stochastic item. Secondly, the WOA–LSSVM model was proposed to forecast the future hourly data of three components respectively, of which the optimal parameters of LSSVM were determined by using WOA. Finally, the future hourly electricity price data were computed by multiplying the forecasted data of those terms. To verify the validity of the proposed electricity price prediction model in this paper, five comparison approaches based on the B-N-D approach were selected, which are auto-regressive integrated moving average (ARIMA), single LSSVM, LSSVM optimized by the fruit-fly optimization algorithm (FOA), LSSVM optimized by particle swarm optimization (PSO) models, and WOA–LSSVM without B-N-D. By comparatively analyzing the error criteria values of the above models through testing on the objective data of the Pennsylvania–New Jersey–Maryland (PJM) electricity market collected from 11 December 2017 to 18 December 2017, from 15 January 2018 to 22 January 2018, and from 1 February 2018 to 25 February 2018, we conclude that the constructed intelligent model in this paper can greatly enhance the prediction precision of electricity prices.

A hybrid wind speed forecasting model based on phase space reconstruction theory and Markov model: A case study of wind farms in northwest China

Accurate forecasting of rainfall has been one of the most important issues in hydrological research. In this paper, a novel nonlinear regression ensemble model is proposed for rainfall forecasting. The model employs Least Square Support Vector Machine (LS-SVM) based on linear regression and nonlinear regression. Firstly, Projection Pursuit (PP) technology and Particle Swarm Optimization (PSO) algorithm are used to obtain the main factors of the rainfall, which optimize projection index from high dimensionality to a lower dimensional subspace. Secondly, using different linear regressions extract linear characteristics of the rainfall system, and using different Neural Network (NN) algorithms and different network architectures extract nonlinear characteristics of the rainfall system. Finally, LS-SVM regression is used for nonlinear ensemble model. This technique is implemented to forecast daily rainfall in Guangxi, China. Empirical results show that the prediction by using the LS-SVM ensemble model is generally better than those obtained using other models presented in this study in terms of the same evaluation measurements. The results suggest that our nonlinear ensemble model can be extended to meteorological applications in achieving greater forecasting accuracy and improving prediction quality.KeywordsProjection PursuitParticle Swarm OptimizationNeural NetworkLeast Square Support Vector Machine Ensemble

According to the current electricity price forecasting studies, it was very difficult to conclude whether support vector machine (SVM) or least squares support vector machine (LSSVM) is more suitable in solving highly non-linear regression problems with very large time horizon such as mid-term electricity market clearing price (MCP) forecasting. In this paper, a detailed evaluation process using price zones analysis technique is applied in evaluating single SVM and single LSSVM based mid-term electricity MCP forecasting models. Based on much more detailed performance evaluation results and consideration of requirements for machine learning techniques utilizing in longer time horizon and highly nonlinear questions, the proposed paper concluded that SVM is more suitable than LSSVM in mid-term electricity MCP forecasting. Numerical examples using PJM interconnection data are utilized to illustrate the conclusion.

In this paper, Artificial Bee Colony (ABC) algorithm which inspired from the behavior of honey bees swarm is presented. ABC is a stochastic population-based evolutionary algorithm for problem solving. ABC algorithm, which is considered one of the most recently swarm intelligent techniques, is proposed to optimize least square support vector machine (LSSVM) to predict the daily stock prices. The proposed model is based on the study of stocks historical data, technical indicators and optimizing LSSVM with ABC algorithm. ABC selects best free parameters combination for LSSVM to avoid over-fitting and local minima problems and improve prediction accuracy. LSSVM optimized by Particle swarm optimization (PSO) algorithm, LSSVM, and ANN techniques are used for comparison with proposed model. Proposed model tested with twenty datasets representing different sectors in S&P 500 stock market. Results presented in this paper show that the proposed model has fast convergence speed, and it also achieves better accuracy than compared techniques in most cases.

Aiming at the difficulty of accurate prediction due to the randomness and nonstationary nature of blood glucose concentration series, a blood glucose concentration prediction model based on complementary ensemble empirical mode decomposition (CEEMD) and least squares support vector machine (LSSVM) is proposed. Firstly, CEEMD is used to convert the blood glucose concentration sequence into a series of intrinsic mode functions (IMFs) to reduce the impact of randomness and nonstationary signals on prediction performance. Then, a LSSVM prediction model is established for each mode IMF. The comprehensive learning particle swarm optimization (CLPSO) algorithm is used to optimize the kernel parameters of LSSVM. Finally, the prediction results of all IMFs are superimposed to yield the final blood glucose concentration prediction value. The experimental results show that the proposed prediction model has higher prediction accuracy in short-term blood glucose concentration values.

In this paper, a novel decoupling control scheme combining least squares support vector machines (LSSVM) inverse models and 2-degree-of-freedom (DOF) internal model controllers (IMC) is employed in the decoupling control system of the bearingless permanent magnet synchronous motor (BPMSM). This scheme can be used to enhance the control properties of high-precision, fast-response, and strong-robustness for the BPMSM system, and effectively eliminate the nonlinear and coupling influence. It introduces LSSVM inverse models into the original BPMSM system to constitute a decoupled pseudo-linear system. In addition, the particle swarm optimization algorithm (PSO) is used to optimize parameters of the LSSVM, which improves its fitting ability and prediction accuracy. What is more, the internal model control scheme is used to design additional closed-loop controllers, thereby improving the robustness of the entire control system. Therefore, this scheme successfully combines the advantages of the LSSVM inverse models and the internal model controller. It can enhance the stability and the static as well as dynamic properties of the whole BPMSM system while independently adjusting the tracking and interference rejection performances. The effectiveness of the proposed scheme has been verified by simulation results at various operations.

In this study, an empirical mode decomposition (EMD) based least square support vector machine (LSSVM) ensemble adaptive learning paradigm is proposed for time series forecasting. For this purpose, the original time series are first decomposed into several intrinsic mode functions (IMFs) and one residual component. Then phase space reconstruction (PSR) is done in each component, where the samples are put into LSSVM for training. Particle swarm optimization algorithm (PSO) is used to achieve the adaptive optimization of forecasting models in different components, which makes LSSVMs better describe the signal characteristics in different scales, thus greatly improves the efficiency and accuracy of the learning and training; Finally, the forecasting values of the original series are obtained through the reconstruction of the forecasting values in each component. For illustration and verification, the spare parts cost series for a vessel is used to test the effectiveness of the proposed EMD-LSSVM-PSO ensemble adaptive learning methodology. Empirical results obtained demonstrate the attractiveness of the proposed method.

The objective of this paper was to determine soluble solids content (SSC) of intact Gannan navel orange by a portable near-infrared (NIR) spectrometer with the optical fiber in the wavelength range of 551~950nm. The effective wavelength regions (EWs) were chosen from the spectra pro-processed by second derivative by interval partial least square (iPLS) and backward interval partial least square (Bipls). Then the partial least square (PLS) and least square support vector machine (LS-SVM) models were developed with EWs. 60 unknown samples were used to evaluate the performance of them. The LS-SVM model was better than others with EWs chosen by Bilps. The correlation coefficient (R) and root mean square error of prediction (RMSEP) for LS-SVM (Bipls) were 0.86 and 0.55°Brix. The results showed that the portable NIR combination with LS-SVM was a feasible method to determine SSC of intact Gannan navel orange nondestructively.

Regularization parameter and kernel parameters play a crucial role on the accuracy and rapidity of the least squares support vector machine (LS-SVM) algorithm. Existing methods of tuning the parameters for LS-SVM have some disadvantages, such as difficulty of getting global optimum and poor convergent speed. In this work, we develop the parameter design of LS-SVM using quantum particle swarm optimization (QPSO) and apply the designed LS-SVM into node localization. According to the initial values, the optimal parameter values are obtained using the leave-10-out cross validation method. Simulation results show that the proposed method is compared to the coupling simulated annealing (CSA) LS-SVM and the improved particle swarm optimization (IPSO) LS-SVM.

In order to relieve the pressure of airspace and optimize the allocation of airspace resources, the traffic prediction method is studied. This paper proposes a least squares support vector machine (LSSVM) prediction method based on the particle swarm optimization (PSO) algorithm, which optimizes the relevant parameters in the least squares support vector machine by the particle swarm algorithm to construct a PSO-LSSVM waypoint traffic prediction model. The ADS-B data of Dawangzhuang waypoint was used as the base statistical traffic for the simulation test, and the root mean square error of the prediction results were 1.3236 and 1.2898, and the average relative errors were 0.1201 and 0.2703, which verified the correctness and applicability of the method.

Stock return forecast has been an important issue and difficult task for both shareholders and financial professionals. To tackle this problem, we introduce Least Square Support Vector Machine (LS-SVM), an improved algorithm that regresses faster than standard SVM, and Dynamic Inertia Weight Particle Swarm Optimization (W-PSO), that outperform standard PSO in parameter selection. The work of this paper is as following: First, forecast daily stock Return of Shanghai Security Exchanges of China using Back Propagation Neural Network (BPNN) and LS-SVM. Secondly, forecast the stock return using LS-SVM optimized by W- PSO. Finally, make a comparative analysis of the three algorithms. We reached conclusion that, in terms of forecast accuracy, LS-SVM outperforms BPNN, and when LS-SVM is optimized by W-PSO, the best result is achieved.

In nuclear power plant's peripheral environmental radiation monitoring wireless sensor network, the γ dose rate data collected in sensor node may be missed due to various factors, which will influence the validity of environmental radiation monitoring. To solve the problem, a missing data imputation algorithm based on least squares support vector machine(LSSVM) is proposed and particle swarm optimization is adopted to search the optimal set of the LSSVM model parameters. This LSSVM model imputes missing data utilizing node's previous monitoring data and neighbor node's current monitoring data jointly. The experimental results using the real radiation monitoring data around a nuclear power plant demonstrate that the proposed algorithm can achieve higher imputation accuracy than neural network model as well as direct LSSVM model, which has the non-optimized parameters.

Utilization of SVM, LSSVM and GP for Predicting the Medical Waste Generation

The prediction of wastes generated in the hospital will help their management for several activities like storage, transport and disposing. This chapter adopts Support Vector Machine (SVM), Least Square Support Vector Machine (LSSVM) and Genetic Programming (GP) in order to estimate the rate of medical waste generation. In the event of predicting the rate, type of hospital, capacity and bed occupancy has been used as inputs of SVM, LSSVM and GP. SVM is based on statistical learning theory, which provides an elegant tool for nonlinear system modeling. LSSVM is the re-formulation to the general SVM. GP, a best part of evolutionary algorithm and also the specification of Genetic Algorithm (GA). These SVM, LSSVM and GP have been used as the regression techniques. The results show the performance of the developed SVM, LSSVM and GP models were elegant and outstanding.