Least Squares Support Vector Regression Algorithm Research Articles

Revealing accuracy in climate dynamics: enhancing evapotranspiration estimation using advanced quantile regression and machine learning models

This study examines the effectiveness of various quantile regression (QR) and machine learning (ML) methodologies developed for analyzing the relationship between meteorological parameters and daily reference evapotranspiration (ETref) across diverse climates in Iran spanning from 1987 to 2022. The analyzed models include D-vine copula-based quantile regression (DVQR), multivariate linear quantile regression (MLQR), Bayesian model averaging quantile regression (BMAQR), as well as machine learning algorithms such as extreme learning machine (ELM), random forest (RF), M5 model Tree (M5Tree), least squares support vector regression algorithm (LSSVR), and extreme gradient boosting (XGBoost). Additionally, empirical equations (EEs) such as Baier and Robertson (BARO), Jensen and Haise (JEHA), and Penman (PENM) models were considered. While the EEs demonstrated acceptable performance, the QR and ML models exhibited superior accuracy. Among these, the MLQR model displayed the highest accuracy compared to DVQR and BMAQR models. Moreover, LSSVR, XGBoost, and M5Tree models outperformed ELM and RF models. Notably, LSSVR, XGBoost, and MLQR models exhibited comparable performance (R2 and NSE > 0.92, MBE and RMSE < 0.5, and SI > 0.05) to M5Tree and BMAQR models across all climates. Importantly, these models significantly outperformed EEs, DVQR, ELM, and RF models in all climates. In conclusion, high-dimensional QR and ML models are recommended as promising alternatives for accurately estimating daily ETref in diverse global climate conditions.

Parametric modeling and analysis of transonic aeroelastic systems based on incremental learning

The aerodynamic reduced order model (ROM) is an effective tool for predicting unsteady aerodynamics and aeroelastic responses with high accuracy and low computational costs. However, traditional aerodynamic ROMs with respect to different flow conditions are lack of robustness. How to enhance dramatically the generalization capability of aerodynamic ROMs should be further studied. This paper presents three parametric ROMs based on the least squares support vector regression algorithm (LS-SVR) and two incremental learning algorithms. LS-SVR is used to establish the relationship between aerodynamic inputs and outputs based on training data from high-fidelity flow simulations. And the Mach number is considered as an additional system input to account for varying flow conditions. The main contribution of incremental learning algorithms based on LS-SVR is that it does not need to reconstruct the ROM when adding sample data. For incremental learning algorithm with forgetting mechanism, training samples are added in the manner of a time-window to improve training efficiency. To illustrate the performance of these ROMs, the aerodynamic and aeroelastic responses of a NACA 0012 airfoil with two degrees of freedom are investigated. The simulation results show that both unsteady aerodynamic results and aeroelastic responses computed by using the three ROM-based models agree well with the results of the high-fidelity simulation. The three proposed ROMs have better generalization capacity and modeling efficiency.

An Intelligent Clinical Psychological Assessment Method Based on AHP-LSSVR Model.

Clinical psychology is a branch of applied psychology. Clinical psychology has a clear understanding of individual behavior ability and behavior characteristics through psychological measurement analysis, observation, and other methods and combines the situation learned from individual psychosomatic diagnosis and life history with the observation and analysis of individual living conditions. Psychological quality and its evaluation methods have been widely used in many fields, which has greatly promoted the development of this field. However, the current assessment methods are mainly based on a simple statistical analysis, and the results are not accurate. To this end, this article proposes the analytic hierarchy process (AHP) and least-squares support vector regression algorithm (LSSVR). Specifically, through the construction of the specific object's psychological quality evaluation index system, the design and implementation of the psychological quality evaluation model based on AHP-LSSVR and the proposed method were discussed in the experiment.

Illumination correction model with sine‐cosine algorithm to optimize gray wolf population for least‐squares support vector regression

AbstractThe color of an object appears different from its true color when illuminated with light sources of different hues. To solve this problem, this article proposes a combination algorithm (SCA‐GWO‐LSSVR) based on the sine‐cosine algorithm (SCA) and the gray wolf optimization (GWO) algorithm to optimize the regression prediction model of the least‐squares support vector regression (LSSVR) algorithm. The performance of the traditional LSSVR is significantly affected by the penalty parameter (gamma) and the sig2 kernel function parameter. The proposed method uses the improved GWO algorithm to search the population to find the best LSSVR parameter solution. The proposed algorithm uses the SCA to create multiple random candidate solutions in population initialization to avoid blind initialization of the GWO algorithm. In the process of iterative optimization, the SCA is infiltrated, and its sine‐cosine wave mathematical model is used to quickly identify the best outward or inward position of the gray wolf. Finally, the LSSVR combines the optimal sig2 kernel function parameters and penalty parameters (gamma) to obtain a highly versatile illumination correction model. The experimental results show that the fitting accuracy of the proposed method reaches 86.8%, which is 5% higher than that of the LSSVR algorithm alone.

On-line monitoring of multiple component parameters during ethanol fermentation by near-infrared spectroscopy

The quantity of biomass, glucose concentration and ethanol concentration are important parameters in ethanol fermentation. Traditional methods are usually based on samples for off-line measurement, which not only requires multiple instruments for test and analysis but also consumes notable time and effort, and therefore is inconvenient for real-time process control and optimization. In this study, an in-situ detection method based on the near-infrared (NIR) spectroscopy is proposed for measuring the above process parameters in real time. The in-situ measurement is carried out by using an immersion type NIR spectroscopy. A multi-output prediction model for simultaneously estimating the quantity of glucose, biomass and ethanol is established based on a multi-output least-squares support vector regression algorithm. The experimental results show that the proposed method can precisely measure the quantity of glucose, biomass and ethanol during the ethanol fermentation process. Compared to the existing partial-least-squares method for modeling and prediction of individual components, the proposed method could evidently improve the measurement accuracy and reliability.

Self-adjusted adsorption strategy for an aircraft skin inspection robot

A self-adjusted adsorption strategy is developed for an aircraft skin inspection robot with double frames to improve adsorption safety and movement stability. The principal aim is to determine the optimal value of adsorption force when the robot slips or overturns on the fuselage. A pneumatic system that consists of suction cup and cylinder control is designed. Static force analysis shows that the adsorption force of the aircraft skin inspection robot is related to the curvature of the fuselage. The relationship between the minimum value of adsorption force and offset angle of the robot barycenter is established with the least-squares support vector regression algorithm. Pulsewidth modulation is then applied to control the pressure difference in the suction cup. Experimental results prove the feasibility of suction cup control with the self-adjusted adsorption strategy.

Mobile node localization method based on KF-LSSVR algorithm

As the mobile node localization algorithm in three-dimensional environment cannot meet the demand of actual application, a hybrid mobile node localization algorithm for a wireless sensor network (WSN) in three-dimensional environment is proposed in this paper, which is based on the least squares support vector regression (LSSVR) and Kalman filter (KF). The proposed algorithm firstly constructs the LSSVR localization model by sampling measurement area and training sample sets. Then, the KF model is used to iterate and correct the measured distance in order to obtain the distance between the unknown node and each anchor node. Finally, the LSSVR localization model is employed to obtain the estimated location of the unknown node. The experiments were conducted and the experimental results were analyzed according to ranging errors, anchor node density, communication radius, moving speed, and node localization errors. Simulation results show that the proposed algorithm using a joint KF and LSSVR algorithm is superior to the KF algorithm and the LSSVR algorithm, and it can reduce the localization errors and improve the localization accuracy.

Illumination compensation in textile colour constancy, based on an improved least‐squares support vector regression and an improved GM(1,1) model of grey theory

In many colour‐related fields, such as textile colour measurement systems based on computer vision as well as dyestuff synthesis, colour constancy with illumination variation is a key problem to be solved. A new algorithm of illumination compensation for colour constancy for textured textiles is proposed in this paper, combining an improved least‐squares support vector regression (LSSVR) and an improved GM(1,1) model of grey theory. The LSSVR algorithm was improved by determining the error limitation according to the distance between a standard sample and a test sample, while the improved GM(1,1) model used the average value of the sequence as the initial iteration value. The disadvantage of LSSVR, that it easily falls into global optimisation, can be compensated for by the local optimisation capacity of the GM(1,1) model. Experimental results show that the algorithm of this paper is very stable and provides good illumination compensation, whereby the time complexity of compensation is reduced by repeatedly processing fractional data with the LSSVR algorithm, and the prediction accuracy is improved by combining the improved GM(1,1) model and the LSSVR algorithm.

Robust data-driven soft sensor based on iteratively weighted least squares support vector regression optimized by the cuckoo optimization algorithm

In process industries, use of the data-driven soft sensors for the purpose of process control and monitoring has gained much popularity. Data-driven soft sensors infer the process quality variables from the available historical process data. A considerable amount of process data such as pressures, temperatures, etc., are measured routinely and stored permanently. However, the quality of these data often varies. Measurement noises and data outliers are the most common effects which lead to poor quality of process data. Application of standard statistical techniques to operate data may lead to model deterioration due to contaminating observations. Therefore, the objective of this paper is to present a robust approach for the development of data-driven soft sensors. In this paper, the modeling method that is used to develop soft sensor is a combination of Nonlinear Auto Regressive with eXogenous inputs (NARX) structure with Least Squares Support Vector Regression (LSSVR). The LSSVRs' parameters are optimized by a new evolutionary optimization technique known as the Cuckoo Optimization Algorithm (COA). Then in order to make the soft sensor robust against the data outliers and noises especially the long tail noises, a new approach is proposed. The proposed method is based on the Iteratively Weighted LSSVR (IWLSSVR) which uses the Myriad weighting function. The proposed approach was applied to the prediction of the n-butane (C4) concentration in a debutanizer column unit. The technique was consequently compared against the conventional LSSVR algorithm which is based on the quadratic loss function. It turns out that reweighting the LSSVR estimate using the Myriad weight function improves the performance of the LSSVR-based soft sensor when noises and outliers exist in the measured data. The designed robust soft sensor is also compared with another robust soft sensor which is recently developed based on the Adaptive Neuro-Fuzzy Inference System (ANFIS) optimized by the Particle Swarm Optimization (PSO). The simulation results show that the designed IWLSSVR-based soft sensor is more robust when the measured data have some impurities.

Fault Prediction for Nonlinear System Using Sliding ARMA Combined with Online LS-SVR

A robust online fault prediction method which combines sliding autoregressive moving average (ARMA) modeling with online least squares support vector regression (LS-SVR) compensation is presented for unknown nonlinear system. At first, we design an online LS-SVR algorithm for nonlinear time series prediction. Based on this, a combined time series prediction method is developed for nonlinear system prediction. The sliding ARMA model is used to approximate the nonlinear time series; meanwhile, the online LS-SVR is added to compensate for the nonlinear modeling error with external disturbance. As a result, the one-step-ahead prediction of the nonlinear time series is achieved and it can be extended ton-step-ahead prediction. The result of then-step-ahead prediction is then used to judge the fault based on an abnormity estimation algorithm only using normal data of system. Accordingly, the online fault prediction is implemented with less amount of calculation. Finally, the proposed method is applied to fault prediction of model-unknown fighter F-16. The experimental results show that the method can predict the fault of nonlinear system not only accurately but also quickly.

A Hybrid LSSVR/HMM-Based Prognostic Approach

In a health management system, prognostics, which is an engineering discipline that predicts a system's future health, is an important aspect yet there is currently limited research in this field. In this paper, a hybrid approach for prognostics is proposed. The approach combines the least squares support vector regression (LSSVR) with the hidden Markov model (HMM). Features extracted from sensor signals are used to train HMMs, which represent different health levels. A LSSVR algorithm is used to predict the feature trends. The LSSVR training and prediction algorithms are modified by adding new data and deleting old data and the probabilities of the predicted features for each HMM are calculated based on forward or backward algorithms. Based on these probabilities, one can determine a system's future health state and estimate the remaining useful life (RUL). To evaluate the proposed approach, a test was carried out using bearing vibration signals. Simulation results show that the LSSVR/HMM approach can forecast faults long before they occur and can predict the RUL. Therefore, the LSSVR/HMM approach is very promising in the field of prognostics.

Flatness intelligent control via improved least squares support vector regression algorithm

To overcome the disadvantage that the standard least squares support vector regression (LS-SVR) algorithm is not suitable to multiple-input multiple-output (MIMO) system modelling directly, an improved LS-SVR algorithm which was defined as multi-output least squares support vector regression (MLSSVR) was put forward by adding samples’ absolute errors in objective function and applied to flatness intelligent control. To solve the poor-precision problem of the control scheme based on effective matrix in flatness control, the predictive control was introduced into the control system and the effective matrix-predictive flatness control method was proposed by combining the merits of the two methods. Simulation experiment was conducted on 900HC reversible cold roll. The performance of effective matrix method and the effective matrix-predictive control method were compared, and the results demonstrate the validity of the effective matrix-predictive control method.