• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2007.12a
• /
• pp.129-130
• /
• 2007

A great variety of models including marine ecology model, water quality model, marine fluid model have been used in the marine research. The results of marine model is presented as a numerical value that is difficult for researcher to understand. In this paper, we developed a method for conversing and presenting results of marine models to visual form to improve the visualization of modelling results that is difficult to analyze and applied the method in actual practice.

• Journal of Korea Multimedia Society
• /
• v.25 no.10
• /
• pp.1448-1456
• /
• 2022

This paper studies a model to diagnose efficiency reduction of inverter using Multilayer Perceptron(MLP). In this study, two inverter data which started operation at different day was used. A Multilayer Perceptron model was made to predict photovoltaic power data of the latest inverter. As a result of the model's performance test, the Mean Absolute Percentage Error(MAPE) was 4.1034. The verified model was applied to one-year-old and two-year-old data after old inverter starting operation. The predictive power of one-year-old inverter was larger than the observed power by 724.9243 on average. And two-year-old inverter's predictive value was larger than the observed power by 836.4616 on average. The prediction error of two-year-old inverter rose 111.5572 on a year. This error is 0.4% of the total capacity. It was proved that the error is meaningful difference by t-test. The error is predicted value minus actual value. Which means that PV system actually generated less than prediction. Therefore, increasing error is decreasing conversion efficiency of inverter. Finally, conversion efficiency of the inverter decreased by 0.4% over a year using this model.

• Korean Journal of Agricultural Science
• /
• v.38 no.4
• /
• pp.769-774
• /
• 2011

This study aimed at finding the factors impacting customer satisfaction (CS) for conversion farm with $2^{nd}$ and $3^{rd}$ industry, because the most important thing in the conversion farm is enhancing customer satisfaction. The data on CS from 173 pumpkin farm's customers by on-line survey were gathered. The analysis using structural equation model with Amos was carried out. Product, service and purchasing were determined as 3 factors impacting to CS. The result showed that purchasing is the biggiest contributor to CS. It means the customers using on-ine market are very sensitive to farm's brand and logistics. It is also found that conversion with processing and farm experience activity is definitely affecting to building customer's trust. In conclusion, making efforts on enhancing CS in conversion farm is the key to success.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.57-64
• /
• 2016

In this paper, we propose the design of railway safety common data model to provide common transformation method for collecting data from railway facility fields to Real-time railway safety monitoring and control system. This common data model is divided into five abstract sub-models according to the characteristics of data such as 'StateInfoMessage', 'ControlMessage', 'RequestMessage', 'ResponseMessage' and 'ExtendedXXXMessage'. This kind of model structure allows diverse heterogeneous data acquisitions and its common conversion method to DDS (Data Distribution Service) format to share data to the sub-systems of Real-time railway safety monitoring and control system. This paper contains the design of common data model and its DDS Topic expression for DDS communication, and presents two kinds of data transformation case studied for verification of the model design.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.1-6
• /
• 2019

The proposed model is developed to minimize the loss of information in incomplete data including missing data. The first step is to transform the learning data to compensate for the loss information using the data extension technique. In this conversion process, the attribute values of the data are filled with binary or probability values in one-hot encoding. Next, this conversion data is input to the deep learning model, where the number of entries is not constant depending on the cardinality of each attribute. Then, the entry values of each attribute are assigned to the respective input nodes, and learning proceeds. This is different from existing learning models, and has an unusual structure in which arbitrary attribute values are distributedly input to multiple nodes in the input layer. In order to evaluate the learning performance of the proposed model, various experiments are performed on the missing data and it shows that it is superior in terms of performance. The proposed model will be useful as an algorithm to minimize the loss in the ubiquitous environment.

• Information Systems Review
• /
• v.10 no.2
• /
• pp.123-135
• /
• 2008

The online advertising industry's business model undertakes the change from CPM (cost-per-mille)-based to CPC(cost-per-click)-based. However, due to the problem of 'Click Fraud', CPA (cost-per-action) has been regarded as a new step. For CPA, publishers need to get information after a user clicks an advertisement. Therefore, in CPA, the key is to get Conversion Action Data (CAD). This paper introduces two existing mechanisms for getting CAD, compare their characteristics, and analyze their limitations. Then the two new mechanisms are introduced and their requirements and feasibility are analyzed. Lastly, we compare the existing two and the new two mechanisms, and point out each mechanism's business possibility, value and Application Area. This paper will help publishers choose the most appropriate mechanism on the basis of their situation.

• Plant Journal
• /
• v.16 no.4
• /
• pp.26-32
• /
• 2020

The performance monitoring system in the power plant should have the capability to estimate power generation efficiency accurately. Several power generation efficiency models have been proposed for the combined heat and power (CHP) plant which produces both electricity and process steam(or heating energy, hereinafter expressed by process steam only). However, most of the models are not sufficiently accurate due to the wrong evaluation of the process steam value. The study suggests Electricity Conversion Efficiency (ECE) model with determination of the heat rate of process steam using operational data. The suggested method is applied to the design data and the resulted trajectory curve of power generation efficiency meets the data closely with R2 99.91%. This result confirms that ECE model with determination of the model coefficient using the operational data estimate the efficiency so accurately that can be used for performance monitoring of CHP plant.

• Phonetics and Speech Sciences
• /
• v.12 no.3
• /
• pp.55-63
• /
• 2020

Voice conversion can be applied to various voice processing applications. It can also play an important role in data augmentation for speech recognition. The conventional method uses the architecture of voice conversion with speech synthesis, with Mel filter bank as the main parameter. Mel filter bank is well-suited for quick computation of neural networks but cannot be converted into a high-quality waveform without the aid of a vocoder. Further, it is not effective in terms of obtaining data for speech recognition. In this paper, we focus on performing voice-to-voice conversion using only the raw spectrum. We propose a deep learning model based on the transformer network, which quickly learns the voice conversion properties using an attention mechanism between source and target spectral components. The experiments were performed on TIDIGITS data, a series of numbers spoken by an English speaker. The conversion voices were evaluated for naturalness and similarity using mean opinion score (MOS) obtained from 30 participants. Our final results yielded 3.52±0.22 for naturalness and 3.89±0.19 for similarity.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.16 no.4
• /
• pp.411-420
• /
• 2018

This study presents a revised crackling core model for the description of $UO_2$ sphere oxidation in air atmosphere. For close reproduction of the sigmoid behavior exhibited in $UO_2$ to $U_3O_8$ conversion, the fragmentation effect contributing to the increased reactive surface area and the concept of variable grain conversion time were considered in the model development. Under the assumptions of two-step successive reaction of $UO_2{\rightarrow}U_3O_7{\rightarrow}U_3O_8$ and final grain conversion time equivalent to ten times the initial grain conversion time, the revised model showed good agreement with the experimental data measured at 599 - 674 K and a lowest deviation when compared with Nucleation and Growth model and AutoCatalytic Reaction model. The evaluated activation energy at 100% conversion to $U_3O_8$, $57.6kJ{\cdot}mol^{-1}$, was found to be closer to the experimentally extrapolated value than to the value determined in AutoCatalytic Reaction model, $48.6kJ{\cdot}mol^{-1}$.

• Spatial Information Research
• /
• v.2 no.2
• /
• pp.147-163
• /
• 1994

This paper presents three methods of generating the transportation network data out of the topological geographic database in the hope that the conversion of the geographic database file containing the topology to the conventional node-link type trans¬portation network file may facilitate the integration between transportation planning mod¬els and GIS by alleviating the inherent problems of both computing environments. One way of the proposed conversion method is to use the conversion software that allows the bi-directional conversion between the UTPS (Urban Transportation Planning System) type transportation planning model and GIS. The other two methods of data structure conversion approach directly transform the GIS's user-level topology into the transportation network data topology, and have been introduced with codes programmed with FORTRAN and AML (Arc Macro Language) of ARC/INFO. If used successfully, any approach would not only improve the efficiency of transportation planning process and the associated decision-making activities in it, but enhance the productivity of trans¬portation planning agencies.