• Journal of Information Technology Services
• /
• v.10 no.2
• /
• pp.203-221
• /
• 2011

The purpose of this study is to investigate the applications of Structural Equation Modeling(SEM) into MIS area in recent years. Two methodologies, Lisrel and PLS, are adopted for the method comparison. A research model, based upon TAM(Technology Acceptance Model) is used for the analysis of the data set of a previous study. The research model includes six research variables that are composed of twenty-eight question items. 272 data are used for data analyses through Lisrel v.8.72 and Visual PLS v.1.04. This study shows the statistical results of Lisrel are the same to those of PLS. The contribution of this study can be suggested as the followings; (1) A theoretical comparison of two methodologies is shown, (2) A statistical analysis is done at a real-situated data set, and (3) Several implications are suggested.

• Journal of Information Technology Applications and Management
• /
• v.14 no.2
• /
• pp.117-127
• /
• 2007

Using an exchange standard, we can design an open architecture for the interchange of decision models and data. XML (eXtensible Markup Language) provides a general framework for creating such a standard. Although XML -based model representation languages such as OOSML were proposed, they are partly limited in expression capability, flexibility, generality, etc. This paper proposes a new method for expressing and sharing decision models and data based on XBRL (eXtensible Business Reporting Language), which is a XML language specialized in business reporting. We have developed a XBRL taxonomy for decision models with the concepts and relationships of a representative modeling framework, SM (Structured Modeling). The method allows for expressing data as well as decision models in a consistent and flexible manner. Diverse dependencies between components of SM models can also be affluently expressed.

• Nuclear Engineering and Technology
• /
• v.34 no.6
• /
• pp.610-618
• /
• 2002

A study of the conceptual data modeling to realize the decommissioning database on the HRR-1&2 was carried out. In this study, the current state of the abroad decommissioning database was investigated to make a reference of the database. A scope of the construction of decommissioning database has been set up based on user requirements. Then, a theory of the database construction was established and a scheme on the decommissioning information was classified . The facility information, work information, radioactive waste information, and radiological information dealing with the decommissioning database were extracted through interviews with an expert group and also decided upon the system configuration of the decommissioning database. A code which is composed of 17 bit was produced considering the construction, scheme and information. The results of the conceptual data modeling and the classification scheme will be used as basic data to create a prototype design of the decommissioning database.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1993.04a
• /
• pp.71-78
• /
• 1993

This study serves as a part for the development of an integrated structural design system. Efficient data management is essential in engineering computer applications where the volume of data is large and the data flow and sharing are required. From a viewpoint of computer application, building structures can be considered to be a mass ofdata. The centralized database(CDB) and database management system frees the application from the details of managing data storage and retrieval while providing a common pool of information. For this, systematic information analysis and modeling have to be preceded. In this paper we described the result of database modeling of building structure.

• ETRI Journal
• /
• v.33 no.6
• /
• pp.914-923
• /
• 2011

This paper concerns robust and reliable speaker model training for text-independent speaker verification. The baseline speaker modeling approach is the Gaussian mixture model (GMM). In text-independent speaker verification, the amount of speech data may be different for speakers. However, we still wish the modeling approach to perform equally well for all speakers. Besides, the modeling technique must be least vulnerable against unseen data. A traditional approach for GMM training is expectation maximization (EM) method, which is known for its overfitting problem and its weakness in handling insufficient training data. To tackle these problems, variational approximation is proposed. Variational approaches are known to be robust against overtraining and data insufficiency. We evaluated the proposed approach on two different databases, namely KING and TFarsdat. The experiments show that the proposed approach improves the performance on TFarsdat and KING databases by 0.56% and 4.81%, respectively. Also, the experiments show that the variationally optimized GMM is more robust against noise and the verification error rate in noisy environments for TFarsdat dataset decreases by 1.52%.

• Geomechanics and Engineering
• /
• v.1 no.4
• /
• pp.307-321
• /
• 2009

The paper employs a feed forward neural network with back-propagation algorithm for modeling time dependent swell in clays containing carbonate in the presence of sulfuric acid. The oedometer swell percent is estimated at a nominal surcharge pressure of 6.25 kPa to develop 612 data sets for modeling. The input parameters used in the network include time, sulfuric acid concentration, carbonate percentage, and liquid limit. Among the total data sets, 280 (46%) were assigned to training, 175 (29%) for testing and the remaining 157 data sets (25%) were relegated to cross validation. The network was programmed to process this information and predict the percent swell at any time, knowing the variable involved. The study demonstrates that it is possible to develop a general BPNN model that can predict time dependent swell with relatively high accuracy with observed data ($R^2$=0.9986). The obtained results are also compared with generated non-linear regression model.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.239-250
• /
• 2022

In many applications, we frequently encounter correlated multiple outcomes measured on the same subject. Joint modeling of such multiple outcomes can improve efficiency of inference compared to independent modeling. For instance, in developmental toxicity studies, fetal weight and number of malformed pups are measured on the pregnant dams exposed to different levels of a toxic substance, in which the association between such outcomes should be taken into account in the model. The number of malformations may possibly have many zeros, which should be analyzed via zero-inflated count models. Motivated by applications in developmental toxicity studies, we propose a Bayesian joint modeling framework for continuous and count outcomes with excess zeros. In our model, zero-inflated Poisson (ZIP) regression model would be used to describe count data, and a subject-specific random effects would account for the correlation across the two outcomes. We implement a Bayesian approach using MCMC procedure with data augmentation method and adaptive rejection sampling. We apply our proposed model to dose-response analysis in a developmental toxicity study to estimate the benchmark dose in a risk assessment.

• ETRI Journal
• /
• v.45 no.4
• /
• pp.557-569
• /
• 2023

Traditional deterministic channel modeling is accurate in prediction, but due to its complexity, improving computational efficiency remains a challenge. In an alternative approach, we investigated a multilayer artificial neural network (ANN) to predict large-scale and small-scale channel characteristics in metro tunnels. Simulated high-precision training datasets were obtained by combining measurement campaign with a ray tracing (RT) method in a metro tunnel. Performance on the training data was used to determine the number of hidden layers and neurons of the multilayer ANN. The proposed multilayer ANN performed efficiently (10 s for training; 0.19 ms for prediction), and accurately, with better approximation of the RT data than the single-layer ANN. The root mean square errors (RMSE) of path loss (2.82 dB), root mean square delay spread (0.61 ns), azimuth angle spread (3.06°), and elevation angle spread (1.22°) were impressive. These results demonstrate the superior computing efficiency and model complexity of ANNs.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.14 no.6
• /
• pp.79-88
• /
• 2010

This paper dealt with the performance modeling of a low bypass turbofan engine for supersonic aircraft. The Pratt and Whitney F100-PW-229 engine has been employed for low bypass turbofan engine performance modeling. Generally, the complete commercially-classified informations concerning the engine are unknown. The components' generic characteristics and assumptions made in order to build the F100-PW-229 engine performance model using by the published data from the open literature as basic data are described. Through the comparison of engine performance model's analysis data using Gasturb11 with engine deck data showed that the engine performance model was evaluated to be properly constructed.

• Journal of information and communication convergence engineering
• /
• v.5 no.4
• /
• pp.295-299
• /
• 2007

This paper presents the ASF(Additional Secondary Factor) modeling of DGPS beacon signal. In addition to DGPS's original purpose, the feasibility to utilize DGPS system for timing and navigation has been studied. For timing and navigation, the positioning system must know the accurate time delay of signal traveling from the transmitter to receiver. Then the delay can be used to compute the user position. The DGPS beacon signal transmits the data using medium frequency, which travels through the surface and cause the additional delay rather than the speed of light according to conductivities and elevations of the irregular terrain. We introduce the modeling of additional delay(ASF) and present the results of implementation. The similar approach is Locan-C. Loran-C has been widely used as the maritime location system and was enhanced to E-Loran(Enhanced Loran). E-Loran system uses the ASF estimation method and is able to provide the more precise location service. However there was rarely research on this area in Korea. Hence, we introduce the ASF and its estimation model. With the comparison of the same condition and data from the original Monteath model and ASF estimation data of Loran system respectively, we guarantee that the implementation is absolutely perfect. For further works, we're going to apply the ASF estimation model to Korean DGPS beacon system with the Korean terrain data.