• 한국데이터정보과학회:학술대회논문집
• /
• 2006.04a
• /
• pp.1-6
• /
• 2006

We consider the issue of Bayesian prediction of the unobservable random effects, And we characterize priors that ensure approximate frequentist validity of posterior quantiles of unobservable random effects. Finally we show that the probability matching criteria for prediction of unobservable random effects in one-way random ANOVA model.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2010.05a
• /
• pp.477-478
• /
• 2010

It was in the mid-1980s when the shipboard noise analysis was introduced to the Korean shipbuilding industry. Since then through the continued efforts of the industries in the last decades, native computational codes dedicated to the shipboard noise prediction have been developed based on empirical formula and/or sophisticated theories such as SEA and PFM. This paper addresses some problems in dealing with predicting shipboard noise and the way how to overcome the uncertainties in the prediction.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2019

An accurate trajectory prediction is a key to the safe and efficient operations of aircraft. One way to improve trajectory prediction accuracy is to develop a model for aircraft ground speed prediction. This paper proposes a generative model for posterior aircraft ground speed prediction. The proposed method fits the Gaussian Mixture Model(GMM) to historical data of aircraft speed, and then the model is used to generates probabilistic speed profile of the aircraft. The performances of the proposed method are demonstrated with real traffic data in Incheon Flight Information Region(FIR).

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.809-819
• /
• 2020

Gender prediction accuracy increases as convolutional neural network (CNN) architecture evolves. This paper compares voting and ensemble schemes to utilize the already trained five CNN models to further improve gender prediction accuracy. The majority voting usually requires odd-numbered models while the proposed softmax-based voting can utilize any number of models to improve accuracy. The ensemble of CNN models combined with one more fully-connected layer requires further tuning or training of the models combined. With experiments, it is observed that the voting or ensemble of CNN models leads to further improvement of gender prediction accuracy and that especially softmax-based voters always show better gender prediction accuracy than majority voters. Also, compared with softmax-based voters, ensemble models show a slightly better or similar accuracy with added training of the combined CNN models. Softmax-based voting can be a fast and efficient way to get better accuracy without further training since the selection of the top accuracy models among available CNN pre-trained models usually leads to similar accuracy to that of the corresponding ensemble models.

• Communications for Statistical Applications and Methods
• /
• v.15 no.2
• /
• pp.255-264
• /
• 2008

It is common in practice to use mean squared error(MSE) for prediction. Recently, Park and Shin (2005) and Jones et al. (2007) studied prediction based on mean squared relative error(MSRE). We proposed a new nonparametric way of prediction based on MSRE substituting Jones et al. (2007) and provided a small simulation study which highly supports the proposed method.

• Advances in Computational Design
• /
• v.2 no.2
• /
• pp.121-131
• /
• 2017

Collapse was one of the typical common geological hazards during the construction of tunnels. The risk assessment of collapse was an effective way to ensure the safety of tunnels. We established a prediction model of collapse based on Bayesian Network. 76 large or medium collapses in China were analyzed. The variable set and range of the model were determined according to the statistics. A collapse prediction software was developed and its veracity was also evaluated. At last the software was used to predict tunnel collapses. It effectively evaded the disaster. Establishing the platform can be subsequent perfect. The platform can also be applied to the risk assessment of other tunnel engineering.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.81-86
• /
• 2018

Software defect severity is very important in projects with limited historical data or new projects. But general software defect prediction is very difficult to collect the label information of the training set and cross-project defect prediction must have a lot of data. In this paper, an unclassified data set with defect severity is clustered according to the distribution ratio. And defect severity-based prediction model is proposed by way of labeling. Proposed model is applied CLAMI in JM1, PC4 with the least ambiguity of defect severity-based NASA dataset. And it is evaluated the value of ACC compared to original data. In this study experiment result, proposed model is improved JM1 0.15 (15%), PC4 0.12(12%) than existing defect severity-based prediction models.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.5
• /
• pp.768-773
• /
• 2011

The prediction method of future events using the time histories of velocity or pressure, etc., is a useful way for controlling various air vehicles. For example, the sensors of velocity or pressure can be used to extract the time mode coefficients of eigenmode of flow field, and then the result is applied to suppress wake or drag. The velocity information is mapped to the entire flow field, so this mapping function can be used to predict the future events based on the current information. The mapping function is composed of the huge amount of weight parameters, so the efficient way of finding these parameters is needed. Here, the neural network algorithm is studied to draw a mapping function using the number and location of velocity sensors.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.4
• /
• pp.114-125
• /
• 1994

Fatigue behavior and life prediction method were presented for themal-mechanical and isothermal low cycle fatigue of 12 Cr forged steel used for high temperature applications. In-phase and out-of-phase thermal-mechanical fatigue test from 350 .deg. C to 600 .deg. C and isothermal low cycle fatigue test at 600 .deg. C, 475 .deg. C, 350 .deg. C were conducted using smooth cylindrical hollow specimen under strain-control with total strain ranges from 0.006 to 0.015. The phase difference between temperature and strain in thermal-mechanical fatigue resulted in significantly shorter fatigue life for out-of-phase than for in-phase. Thermal-mechanical fatigue life predication was made by partitioning the strain ranges of the hysteresis loops and the results of isothermal low cycle fatigue tests which were performed under the combination of slow and fast strain rates. Predicted fatigue lives for out-of-phase using the strain range partitioning method showed an excellent agreement with the actual out-of-phase thermal-mechanical fatigue lives within a factor of 1.5. Conventional strain range partitioning method exhibited a poor accuracy in the prediction of in-phase range partitioning method in a conservative way. By the way life prediction of thermal-mechanical fatigue by Taira's equivalent temperature method and spanning fartor method showed good agreement within out-of-phase thermal-mechanical fatigue.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2005.05a
• /
• pp.119-124
• /
• 2005

It is necessary for prediction of recycled aggregate concrete(RAC) strength at the early stage that facilitate concrete form removal and scheduling for construction. However, to predict RAC strength is difficult because of being influenced by complicated many factors. Therefore, this research suggest optimized estimation method that can reflect many factors. One way is Case-Based Reasoning(CBR) that solved new problems by adapting solutions to similar problems solved in the past, which are solved in the case library. Other way is Artificial Neural Networks(ANN) that solved new problems by training using a set of data, which is representative of problem domain. This study is to propose comparing accuracy of the estimating the compressive strength of recycled aggregate concrete using Case-Based Reasoning(CBR) and Artificial Neural Networks(ANN).