• Geomechanics and Engineering
• /
• v.36 no.2
• /
• pp.111-119
• /
• 2024

In the realm of rock excavation projects, precise estimation of the drilling rate index stands as a pivotal factor in strategic planning and cost assessment. This study introduces and evaluates two pioneering computational intelligence models designed for the prognostication of the drilling rate index, a pivotal parameter with direct implications for cost estimation in rock excavation projects. These models, denoted as the Relevance Vector Regression (RVR) optimized with the Invasive Weed Optimization algorithm (IWO) (RVR-IWO model) and the RVR integrated with the Shuffled Frog Leaping algorithm (SFL) (RVR-SFL model), represent a groundbreaking approach to forecasting drilling rate index. The RVR-IWO and RVR-SFL models were meticulously devised to harness the capabilities of computational intelligence and optimization techniques for drilling rate index estimation. This research pioneers the integration of IWO and SFL with RVR, constituting an unprecedented effort in forecasting drilling rate index. The primary objective of this study was to gauge the precision and dependability of these models in forecasting the drilling rate index, revealing significant distinctions between the two. In terms of predictive precision, the RVR-IWO model emerged as the superior choice when compared to the RVR-SFL model, underscoring the remarkable efficacy of the Invasive Weed Optimization algorithm. The RVR-IWO model delivered noteworthy results, boasting a Variance Account for (VAF) of 0.8406, a Mean Squared Error (MSE) of 0.0114, and a Squared Correlation Coefficient (R²) of 0.9315. On the contrary, the RVR-SFL model exhibited slightly lower precision, yielding an MSE of 0.0160, a VAF of 0.8205, and an R2 of 0.9120. These findings serve to highlight the potential of the RVR-IWO model as a formidable instrument for drilling rate index prediction, particularly within the framework of rock excavation projects. This research not only makes a significant contribution to the realm of drilling engineering but also underscores the broader adaptability of the RVR-IWO model in tackling an array of challenges within the domain of rock engineering. Ultimately, this study advances the comprehension of drilling rate index estimation and imparts valuable insights into the practical implementation of computational intelligence methodologies within the realm of engineering projects.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1385-1397
• /
• 2018

There are many factors that affect the wind speed. In addition, the randomness of wind speed also leads to low prediction accuracy for wind speed. According to this situation, this paper constructs the short-time forecasting model based on the least squares support vector machines (LSSVM) to forecast the wind speed. The basis of the model used in this paper is support vector regression (SVR), which is used to calculate the regression relationships between the historical data and forecasting data of wind speed. In order to improve the forecast precision, historical data is clustered by cluster analysis so that the historical data whose changing trend is similar with the forecasting data can be filtered out. The filtered historical data is used as the training samples for SVR and the parameters would be optimized by particle swarm optimization (PSO). The forecasting model is tested by actual data and the forecast precision is more accurate than the industry standards. The results prove the feasibility and reliability of the model.

• Journal of Welding and Joining
• /
• v.24 no.5
• /
• pp.67-73
• /
• 2006

Laser welding is suitable for welding to the aluminum alloy sheet. In order to apply the aluminum laser welding to production line, parameters should be optimized. In this study, the optimal welding condition was searched through the genetic algorithm in laser welding of AA5182 sheet with AA5356 filler wire. Second-order polynomial regression model to estimate the tensile strength model was developed using the laser power, welding speed and wire feed rate. Fitness function for showing the performance index was defined using the tensile strength, wire feed rate and welding speed which represent the weldability, product cost and productivity, respectively. The genetic algorithm searched the optimal welding condition that the wire feed rate was 2.7 m/min, the laser power was 4 kW and the welding speed was 7.95 m/min. At this welding condition, fitness function value was 137.1 and the estimated tensile strength was 282.2 $N/mm^2$.

• Journal of the Korean Statistical Society
• /
• v.33 no.1
• /
• pp.25-34
• /
• 2004

In this paper we propose a prediction method on the regression model with randomly censored observations of the training data set. The least squares support vector machine regression is applied for the regression function prediction by incorporating the weights assessed upon each observation in the optimization problem. Numerical examples are given to show the performance of the proposed prediction method.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.351-356
• /
• 2022

In this paper, we present the regression analysis and design optimization for improving the permeability of 3D woven materials based on numerical analysis data. First, the parametric analysis model is generated with variables that define the gap sizes between each directional wire of the woven material. Then, material properties such as bulk modulus, thermal conductivity coefficient, and permeability are calculated using numerical analysis, and these material data are used in the polynomial-based regression analysis. The Pareto optimal solution is obtained between bulk modulus and permeability by using multi-objective optimization and shows their trade-off relation. In addition, gradient-based design optimization is applied to maximize the fluid permeability for 3D woven materials, and the optimal designs are obtained according to the various minimum bulk modulus constraints. Finally, the optimal solutions from regression equations are verified to demonstrate the accuracy of the proposed method.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.4 s.175
• /
• pp.894-900
• /
• 2000

Optimization of chassis frame is performed according to the minimization of eleven responses representing one total frame weight, three natural frequencies and seven strength limits of chassis frame that are analyzed by using each response surface model from D-optimal design of experiments. After each response surface model is constructed form D-optimal design and random orthogonal array, the main effect and sensitivity analyses are successfully carried out by using this approximated regression model and the optimal solutions are obtained by using a nonlinear programming method. The response surface models and the optimization algorithms are used together to obtain the optimal design of chassis frame. The eleven-polynomial response surface models of the thirteen frame members (design factors) are constructed by using D-optimal Design and the multi-disciplinary design optimization is also performed by applying dual response analysis.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.719-728
• /
• 2022

The prediction of short-term traffic flow is the theoretical basis of intelligent transportation as well as the key technology in traffic flow induction systems. The research on short-term traffic flow prediction has showed the considerable social value. At present, the support vector regression (SVR) intelligent prediction model that is suitable for small samples has been applied in this domain. Aiming at parameter selection difficulty and prediction accuracy improvement, the artificial bee colony (ABC) is adopted in optimizing SVR parameters, which is referred to as the ABC-SVR algorithm in the paper. The simulation experiments are carried out by comparing the ABC-SVR algorithm with SVR algorithm, and the feasibility of the proposed ABC-SVR algorithm is verified by result analysis. Continuously, the simulation experiments are carried out by comparing the ABC-SVR algorithm with particle swarm optimization SVR (PSO-SVR) algorithm and genetic optimization SVR (GA-SVR) algorithm, and a better optimization effect has been attained by simulation experiments and verified by statistical test. Simultaneously, the simulation experiments are carried out by comparing the ABC-SVR algorithm and wavelet neural network time series (WNN-TS) algorithm, and the prediction accuracy of the proposed ABC-SVR algorithm is improved and satisfactory prediction effects have been obtained.

• International Journal of Automotive Technology
• /
• v.8 no.1
• /
• pp.93-102
• /
• 2007

The frontal crash optimization of an engine room member using the response surface method was studied. The engine room member is composed of the front side member and the sub-frame. The thicknesses of the panels on the front side member and the sub-frame were selected as the design variables. The purpose of the optimization was to reduce the weight of the structure, under the constraint that the objective quantity of crash energy is absorbed. The response surface method was used to approximate the crash behavior in mathematical form for optimization procedure. To research the effect of the regression method, two different methodologies were used in constructing the response surface model, the least square method and the moving least square method. The optimum with the two methods was verified by the simulation result. The precision of the surrogate model affected the optimal design. The moving least square method showed better approximation than the least square method. In addition to the deterministic optimization, the reliability-based design optimization using the response surface method was executed to examine the effect of uncertainties in design variables. The requirement for reliability made the optimal structure be heavier than the result of the deterministic optimization. Compared with the deterministic optimum, the optimal design using the reliability-based design optimization showed higher crash energy absorption and little probability of failure in achieving the objective.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.