An Approach Using Adaptive Weighted Least Squares Support Vector Machines Coupled with Modified Ant Lion Optimizer for Dam Deformation Prediction

Abstract

A dam deformation prediction model based on adaptive weighted least squares support vector machines (AWLSSVM) coupled with modified Ant Lion Optimization (ALO) is proposed, which can be utilized to evaluate the operational states of concrete dams. First, the Ant Lion Optimizer, a novel metaheuristic algorithm, is used to determine the punishment factor and kernel width in the least squares support vector machine (LSSVM) model, which simulates the hunting process of antlions in nature. Second, aiming to solve the premature convergence phenomenon, Levy flight is introduced into the ALO to improve the global optimization ability. Third, according to the statistical characteristics of the datum error, an improved normal distribution weighting rule is applied to update the weighted value of data samples based on the learning result of the LSSVM model. Moreover, taking a concrete arch dam in China as an example, the horizontal displacement recorded by a pendulum is used as a study object. The accuracy and validity of the proposed model are verified and evaluated based on the four evaluating criteria, and the results of the proposed model are compared with those of well-established models. The simulation results demonstrate that the proposed model outperforms other models and effectively overcomes the influence of outliers on the performance of the model. It also has high prediction accuracy, produces excellent generalization performance, and can be a promising alternative technique for the analysis and prediction of dam deformation and other fields, including flood interval prediction, the stock price market, and wind speed forecasting.

A Hybrid Missing Data Imputation Method for Batch Process Monitoring Dataset

“…Machine learning techniques are widely used in various practical application fields, such as air pollution monitoring [27], industrial process monitoring [2], dam safety monitoring [28,29], medical data processing [30], and stock price prediction [31]. To address the challenges posed by missing data, several machine learning-based methods have gained significant popularity [12].…”

A two‐fold optimization framework using hybrid B2 algorithm for resource allocation in long‐term evolution based cognitive radio networks system

“…In the initial time interval k , we can control the predictions . The predictors are mainly computed in this paper using the AWLSSVM technique 50 . With the help of this technique, the evolving changes in both the traffic arrival pattern and traffic bursts can be computed with a higher accuracy value.…”

“…The predictors are mainly computed in this paper using the AWLSSVM technique. 50 With the help of this technique, the evolving changes in both the traffic arrival pattern and traffic bursts can be computed with a higher accuracy value. For this case, an adaptive prediction strategy is used to evaluate the dynamically changing traffic parameters and yield fast convergence with an estimated accuracy level.…”

Gas Outburst Prediction Model Using Improved Entropy Weight Grey Correlation Analysis and IPSO-LSSVM

“…However, the standard SVM algorithm needs to solve the quadratic programming problem, which requires a large amount of calculation. LSSVM uses the least squares algorithm instead of the quadratic optimization algorithm in SVM and transforms the convex quadratic programming problem into a solution of linear equations, which simplifies the calculation process and improves the learning speed [13,21,22]. e principle of LSSVM is to use a nonlinear function to transform the input vector to a high-dimensional feature space and construct a linear function in the high-dimensional feature space to describe the nonlinear relationship between the input vector and the output variable to minimize structural risk.…”