• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.555-565
• /
• 1999

The optimal identification algorithm of fuzzy systems is presented for rule-based fuzzy modeling of nonlinear complex systems. Nonlinear systems are expressed using the identification of structure such as input variables and fuzzy input subspaces, and parameters of a fuzzy model. In this paper, the rule-based fuzzy modeling implements system structure and parameter identification using the fuzzy inference methods and hybrid structure combined with two types of optimization theories for nonlinear systems. Two types of inference methods of a fuzzy model are the simplified inference and linear inference. The proposed hybrid optimal identification algorithm is carried out using both a genetic algorithm and the improved complex method. Here, a genetic algorithm is utilized for determining initial parameters of membership function of premise fuzzy rules, and the improved complex method which is a powerful auto-tuning algorithm is carried out to obtain fine parameters of membership function. Accordingly, in order to optimize fuzzy model, we use the optimal algorithm with a hybrid type for the identification of premise parameters and standard least square method for the identification of consequence parameters of a fuzzy model. Also, an aggregate performance index with weighting factor is proposed to achieve a balance between performance results of fuzzy model produced for the training and testing data. Two numerical examples are used to evaluate the performance of the proposed model.

• Journal of Intelligence and Information Systems
• /
• v.12 no.4
• /
• pp.1-14
• /
• 2006

This study proposed a customer preference estimation model for production recommendation and a method to enhance the performance of product recommendation using the estimated customer preference information. That is, we suggested customer preference estimation model to estimate exactly customer's product preference with his behavior. This model shows the relationship of customer's behaviors with his preferences. The proposed estimation model is optimized by learning the relative weights of customer's behavior variables to have an effect on his preference and enables to estimate exactly his preference. To validate our proposed models, we collected virtual book store data and then made a comparative analysis of our proposed models and a benchmark model in terms of performance results of collaborative filtering for product recommendation. The benchmark model means a prior preference weighting model. The results of our empirical analysis showed that our proposed model performed better results than the benchmark model.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.5
• /
• pp.177-185
• /
• 2020

The building energy performance indicator, called Energy Performance Index (EPI), has been used for the past decades in South Korea. It has a list of design variables assigned with weighting factors (a, b). Unfortunately, the current EPI method is not performance-based but very close to a prescriptive rating. With this in mind, this study aims to propose a new performance-based EPI method. For this purpose, a global sensitivity analysis method, Sobol, is employed. The Sobol method is suitable for complex nonlinear models and can decompose all the output variance due to every input. The Sobol sensitivity index of each variable is defined as 0 to 1 (0 to 100%), and the sum of all sensitivity indices is equal to 1 (100%). In this study, an office building was modeled using EnergyPlus and then the Latin Hypercube Sampling (LHS) was conducted to generate a surrogate model to EnergyPlus. The sensitivity index was suggested to replace weight (a) in the existing EPI. In addition, the discrete weight (b) in the existing EPI was replaced by a set of continuous regression functions. Due to the introduction of the sensitivity index and the continuous regression functions, the new proposed approach can provide far more accurate outcome than the existing EPI (R²: 0.83 vs. R²: 0.01 for cooling, R²: 0.66 vs. R²: 0.01 for total energy). The new proposed approach proves to be more rational, objective and performance-based than the existing EPI method.

• Atmosphere
• /
• v.31 no.2
• /
• pp.185-198
• /
• 2021

In this study, we examined a spatial downscaling method based on Gradient and Inverse Distance Squared (GIDS) weighting to produce high-resolution grid data from a numerical weather prediction model over Korean Peninsula with complex terrain. The GIDS is a simple and effective geostatistical downscaling method using horizontal distance gradients and an elevation. The predicted meteorological variables (e.g., temperature and 3-hr accumulated rainfall amount) from the Limited-area ENsemble prediction System (LENS; horizontal grid spacing of 3 km) are used for the GIDS to produce a higher horizontal resolution (1.5 km) data set. The obtained results were compared to those from the bilinear interpolation. The GIDS effectively produced high-resolution gridded data for temperature with the continuous spatial distribution and high dependence on topography. The results showed a better agreement with the observation by increasing a searching radius from 10 to 30 km. However, the GIDS showed relatively lower performance for the precipitation variable. Although the GIDS has a significant efficiency in producing a higher resolution gridded temperature data, it requires further study to be applied for rainfall events.

• Atmosphere
• /
• v.33 no.5
• /
• pp.519-530
• /
• 2023

Deep convection can make adverse effects on safe and efficient aviation operations by causing various weather hazards such as convectively-induced turbulence, icing, lightning, and downburst. To prevent such damage, it is necessary to accurately predict spatiotemporal distribution of deep convective area near the airport and airspace. This study developed a new index, the Aviation Convective Index (ACI), for deep convection, using the operational global Unified Model of the Korea Meteorological Administration. The ACI was computed from combination of three different variables: 3-hour maximum of Convective Available Potential Energy, averaged Outgoing Longwave Radiation, and accumulative precipitation using the fuzzy logic algorithm. In this algorithm, the individual membership function was newly developed following the cumulative distribution function for each variable in Korean Peninsula. This index was validated and optimized by using the 1-yr period of radar mosaic data. According to the Receiver Operating Characteristics curve (AUC) and True Skill Score (TSS), the yearly optimized ACI (ACI_YrOpt) based on the optimal weighting coefficients for 1-yr period shows a better skill than the no optimized one (ACI_NoOpt) with the uniform weights. In all forecast time from 6-hour to 48-hour, the AUC and TSS value of ACI_YrOpt were higher than those of ACI_NoOpt, showing the improvement of averaged value of AUC and TSS by 1.67% and 4.20%, respectively.

• Transactions of Materials Processing
• /
• v.33 no.2
• /
• pp.103-111
• /
• 2024

With the increasing global interest in carbon neutrality, the automotive industry is also transitioning to the production of eco-friendly cars, specifically electric vehicles. In order to achieve comparable driving distances to internal combustion engine vehicles, the application of high-capacity battery packs has led to an increase in vehicle weight. To achieve light-weighting and durability requirements of automotive components simultaneously, there is a demand for research on the application of Ultra-High Strength Steel (UHSS). However, when manufacturing chassis components using UHSS, there are challenges related to fracture defects due to lower elongation compared to regular steel sheets, as well as spring-back issues caused by high tensile strength. In this study, a simulated specimen that is not affected by the property changes of four materials was designed to improve formability of the rear cross member, which is the most challenging automotive chassis component. The influence and correlation of material-specific variables were analyzed through finite element analysis (FEA) for each material with tensile strength of 440, 590, 780, and 980 MPa grades, resulting in the development of a predictive equation. To validate the equation, the simulated specimens of 980 MPa grade were produced from the test molds. Then the reliability of the FEA and predictive equation was verified with measured specimen data using a 3D scanner. The results of this study can be proposed to improve the formability of UHSS chassis components in future researches.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.1
• /
• pp.50-60
• /
• 2014

The purpose of this study is to identify characteristics and improvements of the climate change vulnerability analysis methods to build a safe city from disasters. For this, an empirical analysis on sea level rise disasters was performed focusing on Heaundae-gu in Busan. For the analysis, Census output areas and Dongs were set as analysis unit and their disaster vulnerability was analyzed. Improvements were reviewed through the comparison and review of analysis process and results. According to analysis results, Modifiable Areal Unit Problem(MAUP) which gives different results according to aggregate unit occurs. Improvements were induced by analysis process, and it was found that in spatial unit setting stage that becomes the base of analysis, analysis unit adjustment, score computation method adjustment, and clearer analysis method for each disaster type would be needed. In analysis execution stage, it was thought that weighting according to variables, diversification of variables, and exclusion of subjective analysis selection method would be needed. It is expected that accurate the total disaster vulnerability analysis will be the base for the improvement of efficiency in urban resilience responding to future weather changes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.846-851
• /
• 2005

In this paper, we propose Genetic Algorithms(GAs)-based Optimized Polynomial Neural Networks(PNN). The proposed algorithm is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional neural networks and can be generated in a dynamic manner. As each node of PNN structure, we use several types of high-order polynomial such as linear, quadratic and modified quadratic, and it is connected as various kinds of multi-variable inputs. The conventional PNN depends on the experience of a designer that select the number of input variables, input variable and polynomial type. Therefore it is very difficult to organize optimized network. The proposed algorithm leads to identify and select the number of input variables, input variable and polynomial type by using Genetic Algorithms(GAs). The aggregate performance index with weighting factor is proposed as well. The study is illustrated with tile NOx omission process data of gas turbine power plant for application to nonlinear process. In the sequel the proposed model shows not only superb predictability but also high accuracy in comparison to the existing intelligent models.

• Korean Journal of Remote Sensing
• /
• v.11 no.3
• /
• pp.33-47
• /
• 1995

The representation of point-observed environmental variables in Geographic Information Systems(GIS) has often been inadequate to meet the need of regional-scale ecological and environmental applications. To create a map of continuous surface that would represent more reliable spatial variations for these applications, I present three spatial estimation methods. Using a secondary variable of the proximity to coast line together with rainfall acidity data collected at the 63 acid rain monitoring stations in Korea, average rainfall acidity map was cteated using co-kriging. For comparison, two other commonly used interpolation methods (inverse distance weighting and kriging) were also applied to rainfall acidity data without reference to the secondary variable. These estimation methods were evaluated by both visual assessments of the output maps and the quantitative comparison of error measures that were obtained from cross validation. The co-kriging method produced a rainfall acidity map that showed noticeable improvement in repoducing the inherent spatial pattern as well as provided lower statistical error as compared to the methods using only the primary variable.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.20 no.1
• /
• pp.107-123
• /
• 2018

The global impact of climate change on agriculture is now increasing. The purpose of this study was to investigate the effect of climate change on livestock productivity. The variables that have the greatest influence on climate change factors were examined through previous studies and expert surveys. We also used the actual productivity data of livestock farmers to investigate the relationship with climate change. In order to evaluate the climate for changes in livestock productivity, national representative data (such as bullocks, dairy, pigs, laying hens, and broilers) were surveyed in Korea. Also, to select and classify evaluation indexes, we selected climate change factor variables as prior studies and studied the weighting factor of climate variable factors. In this study, the researchers of industry, academia, and farmers in the livestock sector conducted questionnaires on the indicators of vulnerability to climate change using experts, and then weighed the selected indicators using the hierarchical analysis process (AHP). In order to verify the validity of the evaluation index, was examined using domestic climate data (temperature, precipitation, humidity, etc.). Correlation and regression analysis were performed. The empirical relationship between climate change and livestock productivity was examined through this study. As a result, we used data with high reliability of statistical analysis and found that there are significant variables.