• Communications for Statistical Applications and Methods
• /
• v.5 no.2
• /
• pp.287-295
• /
• 1998

A random fuzzy linear regression model is introduced, which includes both randomness and fuzziness. Estimators for the parameters are suggested, which are derived mainly using properties of randomness.

• Geomechanics and Engineering
• /
• v.29 no.3
• /
• pp.219-228
• /
• 2022

The most widely used parameter to represent rock abrasiveness is the Cerchar abrasivity index (CAI). The CAI value can be applied to predict wear in TBM cutters. It has been extensively demonstrated that the CAI is affected significantly by cementation degree, strength, and amount of abrasive minerals, i.e., the quartz content or equivalent quartz content in rocks. The relationship between the properties of rocks and the CAI is investigated in this study. A database comprising 223 observations that includes rock types, uniaxial compressive strengths, Brazilian tensile strengths, equivalent quartz contents, quartz contents, brittleness indices, and CAIs is constructed. A linear model is developed by selecting independent variables while considering multicollinearity after performing multiple regression analyses. Machine learning-based regression methods including support vector regression, regression tree regression, k-nearest neighbors regression, random forest regression, and artificial neural network regression are used in addition to multiple linear regression. The results of the random forest regression model show that it yields the best prediction performance.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• The Journal of Engineering Geology
• /
• v.24 no.1
• /
• pp.101-110
• /
• 2014

This study presents the results of a regression analysis of the point-load strength ($I_{s(50)}$) and the uniaxial compressive strength (UCS) of granites in Korea. The regression was carried out for three cases using the least-squares method, reclassifying the granite samples based on their physical properties. The first regression analysis through the origin according to the weathering grade did not give a result with a sufficient degree of confidence, due to the small number of samples. However, the general trend of the correlation between UCS and $I_{s(50)}$according to weathering grade shows that the slope of the linear regression for weathered granite is steeper than that for fresh granite. The second analysis was a simple linear regression for all the granite samples using the least-squares method as well as a linear regression using the bootstrap resampling method in order to increase the confidence level and the accuracy of the regression results. The third regression considered the average strength of granite groups reclassified according to physical properties. These linear regression analyses yielded linear regression equations with slopes of 14 and small standard deviations being similar to values reported in previous studies on Korean granites, but whose intercept values range from 16 to 43 and have a larger standard deviation than those of the present study. In conclusion, it would be advisable to estimate UCS from $I_{s(50)}$, considering the error range derived from the deviation of the regression equations.

• Journal of Advanced Navigation Technology
• /
• v.24 no.2
• /
• pp.128-133
• /
• 2020

In this study, an 1-dimensional positioning method using iterative linear regression for path loss expression is proposed. In the proposed method, received signal strengths (RSS) measured in several locations and distances between the measuring locat ions obtained by dead reckoning are used to derive a linear regression for the path loss from the transmitting beacon. In the proposed method, for the distance between the transmitting beacon and a target measuring location, several tentative values are assumed. For each tentative value, a linear regression is obtained. Among the linear regression expressions, the one closest to the known reference RSS value is selected and used to derive the distance to the target location. Test results show that the proposed method is more accurate than path loss model.

• International Journal of Highway Engineering
• /
• v.10 no.3
• /
• pp.129-138
• /
• 2008

The finite element method(FEM) was one of tools used to solve problem of previous Concrete Pavement and was applied to Korea Pavement Research Program Study. This study used the ABAQUS and the fortran analysis program to calculate the critical stress on jointed concrete pavement and compared and analyzed the results by using neural networks and linear regression model. In that case, which are not enough analysises by using FEM programs though many input variables, when the results of FEM with NN and linear regression models are compared, there are some differences. The other cases, which are reduced input variables and a lot of analysises each of them, results of Neural Networks(NN) and linear regression models are simulated to them of FEM. But, the result of NN is more exact than them of linear regression at the (0,0), (1,1). On the results of this study, it is suggested that the calculation of stress using NN is more compatible to Korea Pavement Research Program Study.

• Communications for Statistical Applications and Methods
• /
• v.17 no.4
• /
• pp.611-624
• /
• 2010

Several methods were suggested for constructing a fuzzy relationship between fuzzy independent and dependent variables. This paper reviews the use of the method by minimizing the square of the difference between an observed and a predicted fuzzy number in an ${\alpha}$-level linear regression model. We introduce a new distance between fuzzy numbers on the basis of a mode, a core point and a radius of an ${\alpha}$-level set of a fuzzy number an construct the fuzzy regression model using the proposed fuzzy distance. We also investigate sufficient condition for an equivalence in the ${\alpha}$-level regression model.

• Speech Sciences
• /
• v.11 no.4
• /
• pp.75-88
• /
• 2004

In this paper, we propose a new approach to sequential linear regression adaptation of continuous density hidden Markov models (CDHMMs) based on transformation space model (TSM). The proposed TSM which characterizes the a priori knowledge of the training speakers associated with maximum likelihood linear regression (MLLR) matrix parameters is effectively described in terms of the latent variable models. The TSM provides various sources of information such as the correlation information, the prior distribution, and the prior knowledge of the regression parameters that are very useful for rapid adaptation. The quasi-Bayes (QB) estimation algorithm is formulated to incrementally update the hyperparameters of the TSM and regression matrices simultaneously. Experimental results showed that the proposed TSM approach is better than that of the conventional quasi-Bayes linear regression (QBLR) algorithm for a small amount of adaptation data.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.20 no.3
• /
• pp.17-29
• /
• 1995

Recently, neural network models have been employed as an alternative to regression analysis for point estimation or function fitting in various field. Thus far, however, no theoretical or empirical guides seem to exist for selecting the tool which the most suitable one for a specific function-fitting problem. In this paper, we evaluate performance of three major function-fitting techniques, regression analysis and two neural network models, back-propagation and linear-Hebbian-learning neural networks. The functions to be fitted are simple linear ones of a single independent variable. The factors considered are size of noise both in dependent and independent variables, portion of outliers, and size of the data. Based on comutational results performed in this study, some guidelines are suggested to choose the best technique that can be used for a specific problem concerned.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.