LS-SVM Based Software Sensor for Fed-batch Yeast Fermentation and Comparative Studies

This work presents proposing two artificial intelligence methods including Least squares support vector machine (LSSVM) and Adaptive neuro fuzzy inference system (ANFIS) for the prediction of caustic current efficiency (CCE) and cell voltage as a function of pH, current density, brine concentration, electrolyte velocity, operating temperature, and run time. The predictions of LSSVM and ANFIS models were evaluated by the experimental values of this process graphically and statistically. The overall R-squared values of LSSVM and ANFIS for prediction of CCE were 0.999 and 0.972, respectively. On the other hand, these values for cell voltage prediction were 1 and 0.998. According to the CCE and cell voltage predictions results, LSSVM algorithm has great performance in prediction of chlor-alkali membrane cell processes. Furthermore, artificial intelligence methods can have wide use in electrolytic processes to enhance power consumption.

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.

In this paper, we present a new system for the classification of electrocardiogram (ECG) beats by using a fast least square support vector machine (LSSVM). Five feature extraction methods are comparatively examined in the 15-dimensional feature space. The dimension of the each feature set is reduced by using dynamic programming based on divergence analysis. After the preprocessing of ECG data, six types of ECG beats obtained from the MIT-BIH database are classified with an accuracy of 95.2% by the proposed fast LSSVM algorithm together with discrete cosine transform. Experimental results show that not only the fast LSSVM is faster than the standard LSSVM algorithm, but also it gives better classification performance than the standard backpropagation multilayer perceptron network.

This study presents a novel approach for the modelling of transformer core magnetisation characteristics under DC bias condition by using the inverse Jiles–Atherton (J–A) model. An improved shuffled frog leaping algorithm (SFLA) is proposed to identify the five parameters of J–A model, where an adaptive chaotic mutation operation is added in the global searching process to increase the identification accuracy. With the proposed algorithm, the J–A model parameters under different DC components are identified based on the DC‐bias experiment on the real transformer. The conventional SFLA and particle swarm optimisation (PSO) method are also applied to identify the parameters of J–A model. All the identified results are compared with the measured B–H curves to verify their identification accuracy. Moreover, the least square support vector machine (LSSVM) algorithm is used to predict the J–A model parameters of transformer under larger DC component from the previously identified parameters in smaller DC. The calculated results have shown that the improved SFLA has higher identification accuracy than the conventional SFLA and PSO methods. Furthermore, LSSVM algorithm can effectively forecast the transformer magnetisation character under large DC bias condition, which is beneficial for the research of transformer DC bias problem.

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.

This article adopts three soft computing techniques including support vector machine (SVM), least square support vector machine (LSSVM) and relevance vector machine (RVM) for prediction of status of epimetemorphic rock slope. The input variables of SVM, LSSVM and RVM are bulk density, height, inclination, cohesion and internal friction angle. There are 53 datasets which have been used to develop the SVM, LSSVM and RVM models. The developed SVM, LSSVM and RVM give equations for prediction of status of epimetemorphic rock slope. The performance of SVM, LSSVM and RVM is 100%. A comparative study has been presented between the developed SVM, LSSVM and RVM. The results confirm that the developed SVM, LSSVM and RVM are effective tools for prediction of status of epimetemorphic rock slope.

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.

The minimal complexity support vector machine is a fusion of the support vector machine (SVM) and the minimal complexity machine (MCM), and results in maximizing the minimum margin and minimizing the maximum margin. It works to improve the generalization ability of the L1 SVM (standard SVM) and LP (Linear Programming) SVM. In this paper, we discuss whether it also works for the LS (Least Squares) SVM. The minimal complexity LS SVM (MLS SVM) is trained by minimizing the sum of squared margin errors and minimizing the maximum margin. This results in solving a set of linear equations and a quadratic program, alternatingly. According to the computer experiments for two-class and multiclass problems, the MLS SVM does not outperform the LS SVM for the test data although it does for the cross-validation data.

An improved least squares support vector machines (LS-SVM) was proposed to improve the sparse and robust performance of LS-SVM in the small samples prediction. The sparse and robust performance could be improved through adding elements of weighted LS-SVM and robust LS-SVM. We introduced a contrast experiment for ATE parameters prediction control through the three methods of neural network, LS-SVM and improved LS-SVM algorithm. Simulation results show that the improved LS-SVM algorithm has good performance in ATE parameters prediction, which succeeds in stability assessment for an aviation ATE.

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 new combination of particle-swarm optimization (PSO) and the least-squares support vector machine (LS-SVM) technique for FDTD time-series forecasting is presented. In this paper, the PSO is extended to optimize the hyperparameter used in the LS-SVM algorithm. The numerical simulations demonstrate that the PSO method can efficiently obtain the optimal value of the hyperparameter used in the LS-SVM algorithm. And the PSO_LS-SVM method can improve the computational efficiency of the FDTD algorithm, as compared to the direct FDTD method. © 2005 Wiley Periodicals, Inc. Microwave Opt Technol Lett 48: 141–144, 2006; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.21288

Fast discrimination of rice varieties plays a key role in the rice processing industry and benefits the management of rice in the supermarket. In order to discriminate rice varieties in a fast and nondestructive way, hyperspectral technology and several classification algorithms were used in this study. The hyperspectral data of 250 rice samples of 5 varieties were obtained using FieldSpec®3 spectrometer. Multiplication Scatter Correction (MSC) was used to preprocess the raw spectra. Principal Component Analysis (PCA) was used to reduce the dimension of raw spectra. To investigate the influence of different linear and non-linear classification algorithms on the discrimination results, K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Least Square Support Vector Machine (LS-SVM) were used to develop the discrimination models respectively. Then the performances of these three multivariate classification methods were compared according to the discrimination accuracy. The number of Principal Components (PCs) and K parameter of KNN, kernel function of SVM or LS-SVM, were optimized by cross-validation in corresponding models. One hundred and twenty five rice samples (25 of each variety) were chosen as calibration set and the remaining 125 rice samples were prediction set. The experiment results showed that, the optimal PCs was 8 and the cross-validation accuracy of KNN (K = 2), SVM, LS-SVM were 94.4, 96.8 and 100%, respectively, while the prediction accuracy of KNN (K = 2), SVM, LS-SVM were 89.6, 93.6 and 100%, respectively. The results indicated that LS-SVM performed the best in the discrimination of rice varieties.

Short-term electricity load forecasting is a difficult work because the accuracy of forecasting is influenced by many unpredicted factors whose relationships are commonly complex, implicit and nonlinear. By studying the methods proposed by other scholars, a mew method, ICA (independent component analysis) -LSSVM (least squares support vector machine) is proposed by this paper. The first step of this method is to apply ICA to LSSVM for feature extraction. By using ICA, the original higher dimensional inputs will be transformed into other lower dimensional features. These new features are then used as the inputs of LSSVM to solve the load forecasting problem. By learning and training, we use the data of this subset to get the solution and find interrelationship of input and output by the LSSVM. This method has the advantage of self adaptability to weaken the human factors in fixing weight index and better extensive capability than traditional methods. It also has better convergence ability and strong global search ability, which consumes less time than other methods. Practical examples are cited in this paper to illustrate the process. The ICA-LSSVM method can also be used in other forecasting problem.

Improving the accuracy and speed has become a main concern of time-series prediction. Aiming at these problems existing in time-series prediction, three kinds of researches and improvements are made as follows. This paper proposes a prediction method of combining Empirical Mode Decomposition (EMD) with least squares support vector machines (LS-SVM), the experimental results show that under the same conditions, the testing error of EMD combining with LS-SVM method is 0.1943 which significantly better than any single method of LS-SVM or SVM or BP neural network (BPNN), thus it is better for non-stationary time series. The immune clonal memetic algorithm (ICMA) is employed for resolving the parameter optimization problem in LS-SVM model, by combining global optimization with local optimization, the experiments show that the testing error of this method is 0.0865, which is faster than the optimization with the genetic algorithm (GA) or grid search algorithm. To raise the prediction speed, an improved LS-SVM online prediction method is proposed, which combine selective pruning algorithm with fast incremental learning, the results of experiment show that the speed of this method is improved nearly double compared with the direct inverse LS-SVM's, and a quarter is raised than the recursive inversion LS-SVM, with higher real-time performance while ensuring the reasonable prediction accuracy.