• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.7
• /
• pp.605-618
• /
• 2012

In this study, the possibility of decision error is investigated to identify and improve the reliability of participants in the process of conducting the sound quality analysis for laser printers. So far, there is not a way to identify and express the possibility of individual participant quantitatively. Thus, the decision error model is proposed which is based on the expectation value between the perceived sounds. Through the experimental verification on the laser printers, it was found that the possibility of decision error is affected according to the normalized difference. The possibility of decision error has inversely proportional to the normalized difference between the perceived sounds. When the normalized difference becomes small value, the uncertainly between decisions is inversely increase, and then it is difficult to obtain the proper result in the process of the jury evaluation for laser printers. For this reason, in this study, the proposed decision error model is added in the previous step of the correlation verification. Comparing to the conventional process only using the correlation based method, after the reliability of each participant is verified, the correlation with the mean response of participants is verified. It was found that the participants who were recognized as having unusual preferences are actually identified as having the reliability problem. Based on the results of this study, the proposed decision error model will be helpful to identify and improve the reliability of participants in the following study for the sound quality analysis.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.120-126
• /
• 2019

Recently, accurate prediction of power consumption based on machine learning techniques in Internet of Energy (IoE) has been actively studied using the large amount of electricity data acquired from advanced metering infrastructure (AMI). In this paper, we propose a deep learning model based on Gated Recurrent Unit (GRU) as an artificial intelligence (AI) network that can effectively perform pattern recognition of time series data such as the power consumption, and analyze performance of the prediction based on real household power usage data. In the performance analysis, performance comparison between the proposed GRU-based learning model and the conventional learning model of Long Short Term Memory (LSTM) is described. In the simulation results, mean squared error (MSE), mean absolute error (MAE), forecast skill score, normalized root mean square error (RMSE), and normalized mean bias error (NMBE) are used as performance evaluation indexes, and we confirm that the performance of the prediction of the proposed GRU-based learning model is greatly improved.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.9
• /
• pp.1046-1050
• /
• 1988

A direct adaptive control algorithm for discrete-time SISO systems with arbitrary zeros is presented in a general way by making use of reference model. A linear equation error model is formulated for estimating both the controller parameters and the auxiliary parameters. With this algorithm, asyptotic tracking within an arbitrarily small error can be achieved.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1151-1156
• /
• 2023

In this paper, we propose a deep learning model that utilizes charge/discharge data from initial lithium-ion batteries to predict the remaining useful life of lithium-ion batteries. We build the DMP using the PNP model. To demonstrate the performance of DMP, we organize DML using the LSTM model and compare the remaining useful life prediction performance of lithium-ion batteries between DMP and DML. We utilize the RMSE and RMSPE error measurement methods to evaluate the performance of DMP and DML models using test data. The results reveal that the RMSE difference between DMP and DML is 144.62 [Cycle], and the RMSPE difference is 3.37 [%]. These results indicate that the DMP model has a lower error rate than DML. Based on the results of our analysis, we have showcased the superior performance of DMP over DML. This demonstrates that in the field of lithium-ion batteries, the PNP model outperforms the LSTM model.

• Journal of Electrical Engineering and Technology
• /
• v.8 no.3
• /
• pp.559-564
• /
• 2013

In this paper a new hybrid forecast method composed of wavelet transform and neural network is proposed to forecast the wind speed more accurately. In the field of wind energy research, accurate forecast of wind speed is a challenging task. This will influence the power system scheduling and the dynamic control of wind turbine. The wind data used here is measured at 15 minute time intervals. The performance is evaluated based on the metrics, namely, mean square error, mean absolute error, sum squared error of the proposed model and compared with the back propagation model. Simulation studies are carried out and it is reported that the proposed model outperforms the compared model based on the metrics used and conclusions were drawn appropriately.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.4
• /
• pp.64-71
• /
• 2004

The growing need for higher precision and productivity in manufacturing industry has lead to an increased interest in computer numerical control (CNC) systems. It is well known fact that the cross-coupling controller (CCC) is an effective method for contouring applications. In this paper, a multi-axis contour error controller (CEC) based on a contour error vector using parametric curve interpolator is introduced. The contour error vector is a vector from the actual tool position to the nearest point on the desired path. The contour error vector is the closest error model to the contour error. The simulation results show that the CEC is more accurate than the conventional CCC for a biaxial motion system. In addition, the experimental results on 3-axis motion system show that the CEC is simply applied to 3-axis motions and contouring accuracy is significantly improved.

• Journal of the Korean Statistical Society
• /
• v.28 no.4
• /
• pp.489-501
• /
• 1999

In this paper, we consider the panel data regression model in which the disturbances have nested error component. We derive a Lagrange Multiplier(LM) test which is jointly testing for the presence of random individual effects and nested effects under the normality assumption of the disturbances. This test extends the earlier work of Breusch and Pagan(1980) and Baltagi and Li(1991). Further, it is shown that this LM test has the same asymptotic distribution without normality assumption of the disturbances.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.04a
• /
• pp.451-459
• /
• 2011

In this paper, a software release model is presented to determine the optimum testing time with consideration of software error type. The software errors are classified into two types, major and minor errors. The software testing is continued until the Nth major error is discovered and corrected. The total cost needed before and after testing time is modeled under nonhomogeneous Poisson error correction model. Numerical examples are presented to demonstrate the results.

• Journal of the Korea Institute of Building Construction
• /
• v.22 no.4
• /
• pp.415-423
• /
• 2022

As human factors are the most important cause of construction accidents, it is important to reduce human error in construction work to reduce accidents. However, the error forcing context in organizational situations acts as a factor behind human error. Therefore, fatal construction accidents were analyzed using the m-SHEL model, which can identify the factors behind human errors. Through such analysis, it was found that there are differences in the detailed factors behind human errors according to the type of fatal accidents in construction, This study is meaningful in that it confirmed through accident cases that it is important to understand and respond to organizational situations in order to reduce human error in construction work.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.855-860
• /
• 2007

This paper describes a human driver model developed based on finite preview optimal control method. The human driver steering model is constructed to minimize a performance index which is a quadratic form of lateral position error, yaw angle error and steering input. Simulation studies are conducted using a vehicle simulation software, Carsim. The Carsim vehicle model is validated using vehicle test data. In order to validate the human driving steering model, the human driver steering model is compared to the driving data on a virtual test track(VTT) and the actual vehicle test data. It is shown that human driver steering behaviors can be well represented by the human driver steering model presented in this paper