• Journal of Information Technology Services
• /
• v.18 no.2
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.

• Journal of Convergence for Information Technology
• /
• v.11 no.3
• /
• pp.107-124
• /
• 2021

This study is a study on the innovation resistance that may arise in connection with the introduction and use of smart factory-related technologies by SMEs. It is to study the effect of the leading factors of innovation resistance on innovation resistance and the effect of innovation resistance on use intention by using the extended innovation resistance model. A total of 176 survey data were used for the study, and the study was conducted using SPSS 25 and Smart PLS 2.0. Relative advantage, suitability, perceived risk, social impact, and organizational characteristics have a significant effect on innovation resistance, and innovation resistance was tested to have a significant effect on the intention to use. As an implication according to the research, a plan to improve the level of introduction and use of smart factories using the expanded innovative storage model was presented by dividing positive and negative factors, and factors that should be improved and factors that should be reduced are presented. It was specifically presented.

• Wind and Structures
• /
• v.37 no.4
• /
• pp.303-314
• /
• 2023

In this study, two steady RANS turbulence models (SST k-ω and Realizable k-ε) and four unsteady turbulence models (URANS SST k-ω and Realizable k-ε, SST-SAS, and SST-IDDES) are evaluated with respect to their capacity to predict crosswind characteristics on high-speed trains (HSTs). All of the numerical simulations are compared with the wind tunnel values and LES results to ensure the accuracy of each turbulence model. Specifically, the surface pressure distributions, time-averaged aerodynamic coefficients, flow fields, and computational cost are studied to determine the suitability of different models. Results suggest that the predictions of the pressure distributions and aerodynamic forces obtained from the steady and transient RANS models are almost the same. In particular, both SAS and IDDES exhibits similar predictions with wind tunnel test and LES, therefore, the SAS model is considered an attractive alternative for IDDES or LES in the crosswind study of trains. In addition, if the computational cost needs to be significantly reduced, the RANS SST k-ω model is shown to provide relatively reasonable results for the surface pressures and aerodynamic forces. As a result, the RANS SST k-ω model might be the most appropriate option for the expensive aerodynamic optimizations of trains using machine learning (ML) techniques because it balances solution accuracy and resource consumption.

• Journal of Korea Water Resources Association
• /
• v.52 no.4
• /
• pp.301-312
• /
• 2019

The importance of the dual drainage system model has increased as the urban flood damage has increased due to the increase of local storm due to climate change. The dual drainage model is a model for more accurately expressing the phenomena of surface flow and conduit flow. Surface runoff and pipe runoff are analyzed through the respective equations and parameters. And the results are expressed visually in various ways. Therefore, inundation analysis results of dual drainage model are used as important data for urban flood prevention plan. In this study, the applicability of the COBRA model, which can be interpreted by combining the dual drainage system with the natural watershed and the urban watershed, was investigated. And the results were compared with other dual drainage models (XP-SWMM, UFAM) to determine suitability of the results. For the same watershed, the XP-SWMM simulates the flooding characteristics of 3 types of dual drainage system model and the internal flooding characteristics due to the lack of capacity of the conduit. UFAM showed the lowest inundation analysis results compared with the other models according to characteristics of consideration of street inlet. COBRA showed the general result that the flooded area and the maximum flooding depth are proportional to the increase in rainfall. It is considered that the COBRA model is good in terms of the stability of the model considering the characteristics of the model to simulate the effective rainfall according to the soil conditions and the realistic appearance of the flooding due to the surface reservoir.

• Culinary science and hospitality research
• /
• v.22 no.3
• /
• pp.79-91
• /
• 2016

This research was conducted over one month from May 1st to May 30th, 2015. Data were collected after confirming purpose of current study with eating house manager from the restaurant consumers. This study investigated the impact of nostalgia tendency on the propensity to revisit the eating house. Nostalgia impact on the propensity of the perceived emotional food repurchase also had the effect of significantly positive (+) on the road to repurchase B=0.767(p<.001). The coefficient of determination for measuring the adequacy of the model to determine the coefficient that measures the suitability of the model was explaining 58.9% of the variation in the premises 0.589, models with F=431.234(p<.001) to verify the significance of the model is significantly It has been described. Second, nostalgia tendency and social tendencies of the bond part had a strong impact in moderating effects of (-). The lower the social bond was investigated by increasing the propensity nostalgia.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.3
• /
• pp.71-80
• /
• 2016

The component-based modeling framework for agricultural water-resources management (COMFARM) is a user-friendly, highly interoperable, lightweight modeling framework that supports the development of watershed-specific domain components. The objective of this study was to evaluate the suitability of the COMFARM for the design and creation of a component-based modeling system of agricultural reservoir watersheds. A case study that focused on a particular modeling system was conducted on a watershed that includes the Daehwa and Dangwol serial irrigation reservoirs. The hydrologic modeling system for the study area was constructed with linkable components, including the modified Tank, an agricultural water supply and drainage model, and a reservoir water balance model. The model parameters were each calibrated for two years, based on observed reservoir water levels. The simulated results were in good agreement with the observed data. In addition, the applicability of the COMFARM was evaluated for regions where reservoir outflows, including not only spillway release but also return flow by irrigation water supply, substantially affect the downstream river discharge. The COMFARM could help to develop effective water-management measures by allowing the construction of a modeling system and evaluation of multiple operational scenarios customized for a specific watershed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.844-847
• /
• 1997

In this paper, scheduling problem is dealt for the minimization of due date penalty for the customer order. Multiproduct batch processes have been dealt with for their suitability for high value added low volume products. Their scheduling problems take minimization of process operation for objective function, which is not enough to meet the customer satisfaction and the process efficiency simultaneously because of increasing requirement of fast adaptation for rapid changing market condition. So new target function has been suggested by other researches to meet two goals. Penalty function minimization is one of them. To present more precisely production scheduling, we develop new scheduling model with penalty function of earliness and tardiness We can find many real cases that penalty parameters are divergent by the difference between the completion time of operation and due date. That is to say, the penalty parameter values for the product change by the customer demand condition. If the order charges different value for due date, we can solve it with the due date period. The period means the time scope where penalty parameter value is 0. If we make use of the due date period, the optimal sequence of our model is not always same with that of fixed due date point. And if every product have due date period, due date of them are overlapped which needs optimization for the maximum profit and minimum penalty. Due date period extension can be enlarged to makespan minimization if every product has the same abundant due date period and same penalty parameter. We solve this new scheduling model by simulated annealing method. We also develop the program, which can calculate the optimal sequence and display the Gantt chart showing the unit progress and time allocation only with processing data.

• Journal of Digital Convergence
• /
• v.11 no.5
• /
• pp.187-199
• /
• 2013

Since the supply of smart phones, a change in mobile environment brought a turning point called a mobile generation. Smart mobile office is a combined form of smart phones' new mobile environment and its social media. A construction of mobile office environment using smart phones brought revitalization of the smart phone market. CRM construction also became new requirements for a customer management. However, based on the current information system audit standard, check fields or check lists are insufficient to apply to audit for CRM construction in a smart mobile office environment. Therefore, this paper proposes a model for auditing CRM system construction in smart mobile office environment. It proposes audit domain and check lists of CRM construction. It also verified whether the proposed model is suitable or not by doing a survey if deduced audit domain and check lists correspond with the purpose of the CRM construction audit during smart mobile office environment. As the result, this study appear to have more than average satisfaction the suitability results were.

• Ocean Science Journal
• /
• v.42 no.4
• /
• pp.211-222
• /
• 2007

We compare insolation results calculated from two well-known empirical formulas (Socket and Beaudry's SB73 formula and the original Smithsonian (SMS) formula) and a radiative transfer model using input data predicted from meteorological weather-forecast models, and review the accuracy of each method. Comparison of annual mean daily irradiance values for clear-sky conditions between the two formulas shows that, relative to the SMS, the SB73 underestimates spring values by 9 W $m^{-2}$ in the northern Adriatic Sea, although overall there is a good agreement between the annual results calculated with the two formulas. We also elucidate the effect on SMS of changing the 'Sun-Earth distance factor (f)', a parameter which is commonly assumed to be constant in the oceanographic context. Results show that the mean daily solar radiation for clear-sky conditions in the northern Adriatic Sea can be reduced as much as 12 W $m^{-2}$ during summer due to a decrease in the f value. Lastly, surface irradiance values calculated from a simple radiative transfer model (GM02) for clear-sky conditions are compared to those from SB73 and SMS. Comparison with iu situ data in the northern Adriatic Sea shows that the GM02 estimate gives more realistic surface irradiance values than SMS, particularly during summer. Additionally, irradiance values calculated by GM02 using the buoy meteorological fields and ECMWF (The European Centre for Medium Range Weather Forecasts) meteorological data show the suitability of the ECMWF data usage. Through tests of GM02 sensitivity to key regional meteorological factors, we explore the main factors contributing significantly to a reduction in summertime solar irradiance in the Adriatic Sea.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.440-447
• /
• 2011

Selecting a suitable place is to determine the attributive conditions and qualified areas for the aim as factors and is to be fulfilled systematically for selecting the area which satisfies all these. This research tries to achieve a rational suitability analysis of residential development using the GIS modeling method and the hierarchical analysis process. A spatial and attributive analysis has been systematized for selecting a suitable place for the study and GIS analysis model has been used for the effective conclusion drawing for different levels. As a next step, a quantitative and qualitative evaluation index was created through complex consideration of the criteria and decision factors of the location selection, and weights were added depending on the relative importance of these factors. In particular, 3D terrain model simulation method has been used in order to reflect the aesthetic factors of the scenery which is an element of the subjective evaluation factors and considered qualitative and subjective evaluation factors which were not considered for the existing AHP technique. After the research, a location that satisfies complex requirements was found rapidly and accurately through the GIS model and hierarchical analysis.