• 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.

• Journal of Korean Society on Water Environment
• /
• v.23 no.3
• /
• pp.385-390
• /
• 2007

Reliable flow measurement for dry season is very important to set up the in-stream flow exactly and total maximum daily load control program in the basin. Especially, in the points which tidal current effects are dominant because reliability of the low measurement decrease. The reliable measuring methods are needed. In this study, we analysis the water surface elevation difference of water surface elevation. Quantity relationship to consider tidal currents in these regions. It is known that tidal current effects from Nakdong river barrage are dominant in Samrangjin measuring station. We developed multiple regression equation with water surface elevation, quantity, and difference of water surface elevation and compared these results water measured rating curve. All of these regression equation including linear regression equation and log regression equation fits better measured data them existing water surface elevation quantity line and Among three equations, the log regression equation is best to represent the measured the rating curve in Samrangjin point. The log regression equation is useful method to obtain the quantity in the regions which tidal currents are dominant.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.67-72
• /
• 2004

Support vector machine (SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate interval linear and nonlinear regression models combining the possibility and necessity estimation formulation with the principle of SVM. For data sets with crisp inputs and interval outputs, the possibility and necessity models have been recently utilized, which are based on quadratic programming approach giving more diverse spread coefficients than a linear programming one. SVM also uses quadratic programming approach whose another advantage in interval regression analysis is to be able to integrate both the property of central tendency in least squares and the possibilistic property In fuzzy regression. However this is not a computationally expensive way. SVM allows us to perform interval nonlinear regression analysis by constructing an interval linear regression function in a high dimensional feature space. In particular, SVM is a very attractive approach to model nonlinear interval data. The proposed algorithm here is model-free method in the sense that we do not have to assume the underlying model function for interval nonlinear regression model with crisp inputs and interval output. Experimental results are then presented which indicate the performance of this algorithm.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.12 no.4
• /
• pp.87-92
• /
• 2013

In this study, we carried out the turning of plastic mold steel(STAVAX) with whisker reinforced ceramic tool(WA1) and analyzed ANOVA(Analysis of Variance) test. Multi-regression analysis was performed to find influential factors to surface roughness and to derive regression equation. Results are follows: From ANOVA test and confidence interval analysis of surface roughness, We found that influential factors to surface roughness was feed rate, cutting speed and depth of cut in order. From multi-regression analysis, we derived regression equation of STAVAX. it's coefficient of determination($R^2$) was 0.945 and It means that regression equation is significant. From experimental verification, we confirmed that surface roughness was predictable by regression equation. Compared with former research, we confirmed that increase of feed rate is the main cause of the growing of surface roughness and cutting force.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.635-638
• /
• 2006

Regression of conventional prediction techniques in data mining uses the model which is generated from the training step. This model is applied to new input data without any change. If this model is applied directly to time series, the rate of prediction accuracy will be decreased. This paper proposes an incremental regression for time series prediction like typhoon track prediction. This technique considers the characteristic of time series which may be changed over time. It is composed of two steps. The first step executes a fractional process for applying input data to the regression model. The second step updates the model by using its information as new data. Additionally, the model is maintained by only recent data in a queue. This approach has the following two advantages. It maintains the minimum information of the model by using a matrix, so space complexity is reduced. Moreover, it prevents the increment of error rate by updating the model over time. Accuracy rate of the proposed method is measured by RME(Relative Mean Error) and RMSE(Root Mean Square Error). The results of typhoon track prediction experiment are performed by the proposed technique IMLR(Incremental Multiple Linear Regression) is more efficient than those of MLR(Multiple Linear Regression) and SVR(Support Vector Regression).

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.05a
• /
• pp.77-81
• /
• 2008

The local regression rate behavior of solid fuel in swirl injection hybrid rocket were studied. In generally, axial injection regression rate was tending to be decrease with axial distance, beyond which increased with increasing axial distance from the leading edge. On the other hand, swirl injection regression rate was high at the leading edge of the fuel and comparatively uniform regression rate at the downstream. Overall regression rate of swirl injection was increased about 54% for the overall regression rate of axial injection. Through this study, it was found that using swirl injector was useful in applying to the small sounding rocket.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.187-194
• /
• 1996

In this paper, we propose regression neural networks based on regression trees. We map regression trees into three layered feedforward networks. We put multi feature split functions in the first layer so that the networks have a better chance to get optimal partitions of input space. We suggest two supervised learning algorithms for the network training and test both in single feature split and multifeature split functions. In experiments, the proposed regression neural networks is proved to have the better learning performance than those of the single feature split regression trees and the single feature split regression networks. Furthermore, we shows that the proposed learning schemes have an effect to prune an over-grown tree without degrading the learning performance.

• Computers and Concrete
• /
• v.21 no.4
• /
• pp.463-470
• /
• 2018

In the present study, soft computing i.e., machine learning techniques and regression models algorithms have earned much importance for the prediction of the various parameters in different fields of science and engineering. This paper depicts that how regression models can be implemented for the prediction of compressive strength of concrete. Three models are taken into consideration for this; they are Gaussian Process for Regression (GPR), Multi Adaptive Regression Spline (MARS) and Minimax Probability Machine Regression (MPMR). Contents of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and age in days have been taken as inputs and compressive strength as output for GPR, MARS and MPMR models. A comparatively large set of data including 1030 normalized previously published results which were obtained from experiments were utilized. Here, a comparison is made between the results obtained from all the above mentioned models and the model which provides the best fit is established. The experimental results manifest that proposed models are robust for determination of compressive strength of concrete.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2000.11b
• /
• pp.188-195
• /
• 2000

This study was conducted to measure the moisture content of powdered food using RF impedance spectroscopic method. In frequency range of 1.0 to 30㎒, the impedance such as reactance and resistance of parallel plate type sample holder filled with wheat flour and red-pepper powder of which moisture content range were 5.93∼-17.07%w.b. and 10.87 ∼ 27.36%w.b., respectively, was characterized using by Q-meter (HP4342). The reactance was a better parameter than the resistance in estimating the moisture density defined as product of moisture content and bulk density which was used to eliminate the effect of bulk density on RF spectral data in this study. Multivariate data analyses such as principal component regression, partial least square regression and multiple linear regression were performed to develop one calibration model having moisture density and reactance spectral data as parameters for determination of moisture content of both wheat flour and red-pepper powder. The best regression model was one by the multiple linear regression model. Its performance for unknown data of powdered food was showed that the bias, standard error of prediction and determination coefficient are 0.179% moisture content, 1.679% moisture content and 0.8849, respectively.

• Journal of the Korean Society for Precision Engineering
• /
• v.24 no.4 s.193
• /
• pp.93-101
• /
• 2007

Aluminum alloy which is one of the light materials has been tried to apply to light weight vehicle body. In order to do that, welding technology is very important. In case of the aluminum laser welding, the strength of welded part is reduced due to porosity, underfill, and magnesium loss. To overcome these problems, laser welding of aluminum with filler wire was suggested. In this study, experiment about laser welding of AA5182 aluminum alloy with AA5356 filler wire was performed according to process parameters such as laser power, welding speed and wire feed rate. The tensile strength was measured to find the weldability of laser welding with filler wire. The models to estimate tensile strength were suggested using three regression models and one neural network model. For regression models, one was the multiple linear regression model, another was the second order polynomial regression model, and the other was the multiple nonlinear regression model. Neural network model with 2 hidden layers which had 5 and 3 nodes respectively was investigated to find the most suitable model for the system. Estimation performance was evaluated for each model using the average error rate. Among the three regression models, the second order polynomial regression model had the best estimation performance. For all models, neural network model has the best estimation performance.