• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Journal of the Korea Society for Simulation
• /
• v.19 no.3
• /
• pp.71-79
• /
• 2010

The simulator models for 500MW fossil power plant have been developed, and interconnected with the turbine control system to test and validate the digital instrumentation & control (I&C) systems before they are implemented in operating power plants. When the performance of a selected digital I&C system is tested, the corresponding simulator model is replaced by the plant digital I&C systems which is considered as a non-tunable system. The input/out variables of simulator models and control systems were mapped using the LabView in interface systems. This paper describes the interconnection method between the simulator model and the digital I&C system, and summarizes the validation test results performed at the condition of steady-state operation, normal evolution, and malfunction. The integrated validation method of digital I&C systems using the simulator models showed that the simulator can be used as a test bed for the implementation of digital I&C systems in power plants.

• Communications for Statistical Applications and Methods
• /
• v.15 no.6
• /
• pp.1013-1026
• /
• 2008

Kolmogorov-Smirnov(K-S) statistic has been widely used for the model validation of credit rating models. Validation criteria for the K-S statistic is empirically used at the levels of 0.3 or 0.4 which are much larger than the critical values of K-S test statistic. We examine whether these criteria are reasonable and appropriate through the simulations according to various sample sizes, type II error rates, and the ratio of bads among data. The simulation results say that the currently used validation criteria are too lower than values of K-S statistics obtained from any credit rating models in Korea, so that any credit rating models have good discriminatory power. In this work, alternative criteria of K-S statistic are proposed as critical levels under realistic situations of credit rating models.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.1
• /
• pp.1-13
• /
• 2024

This study assessed the efficacy of improving the accuracy of reservoir water level prediction models by employing automated machine learning models and efficient cross-validation methods for time-series data. Considering the inherent complexity and non-linearity of time-series data related to reservoir water levels, we proposed an optimized approach for model selection and training. The performance of twelve models was evaluated for the Obong Reservoir in Gangneung, Gangwon Province, using the TPOT (Tree-based Pipeline Optimization Tool) and four cross-validation methods, which led to the determination of the optimal pipeline model. The pipeline model consisting of Extra Tree, Stacking Ridge Regression, and Simple Ridge Regression showed outstanding predictive performance for both training and test data, with an R² (Coefficient of determination) and NSE (Nash-Sutcliffe Efficiency) exceeding 0.93. On the other hand, for predictions of water levels 12 hours later, the pipeline model selected through time-series split cross-validation accurately captured the change pattern of time-series water level data during the test period, with an NSE exceeding 0.99. The methodology proposed in this study is expected to greatly contribute to the efficient generation of reservoir water level predictions in regions with high rainfall variability.

• Journal of the Korean Applied Science and Technology
• /
• v.41 no.2
• /
• pp.172-187
• /
• 2024

In good laboratory practice (GLP), analytical method validation prior to toxicity testing is important in terms of concentration setting and sample preparation. The testing agency performed validation of the two requested test substances using high-performance liquid chromatography (HPLC), and as a result, the analysis satisfied the criteria for specificity, system suitability, linearity, intra-day reproducibility, homogeneity, stability, concentration analysis, and quality control. The method was established and validated. However, the content of standard substances in the test report of the requesting institution was found to be 1.34 and 1.17 times higher than the results of the testing institution, confirming that deriving results through validation of analysis methods suitable for GLP is important in terms of securing reliability and stability.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.4
• /
• pp.242-250
• /
• 2014

Conventional researches of standard tool validating cryptographic algorithm have been studied for the internet environment, for the mobile internet. It is important to develop the validation tool for establishment of interoperability and convenience of users in the information systems. Therefore, this paper presents the validation tool of Elliptic Curve Cryptography algorithm that can test if following X9.62 technology standard specification. The validation tool can be applied all information securities using DES, SEED, AES, SHA-1/256/384/512, RSA-OAEP V2.0, V2.1, ECDSA, ECKCDSA, ECDH, etc. Moreover, we can enhance the precision of validation through several experiments and perform the validation tool in the online environment.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.153-160
• /
• 2010

Most part of errors in software development process are included during the stage of requirements definition and design. And correction or elimination of errors from those stages requires much more efforts and costs than those from the later part of software development process. However, despite of the importance of the validation of requirement definition and design stages, several kinds of problem have made it hard to be done successfully. Therefore, in this paper, we introduce a novel validation process for the preliminary design stage. The validation process is based on simulations of model and it can be used to validate requirements and model simultaneously. Models in the validation process will take only the behavior of software and be built on Ptolemy framework. The usability of our validation process is confirmed with a case study over DNS system environment. And the result of simulation shows well-known errors or vulnerabilities can be found with simulations of model which has the behavior of software. This means our validation process can be used as a process to validate requirements and models during the early stage of software development process.

• Korean Journal of Child Studies
• /
• v.20 no.2
• /
• pp.3-19
• /
• 1999

The Revised Classroom Play(RCP) scale was validated for Korean 4th grade students. 104 boys and 80 girls took the translated RCP. Test-retest reliability was established with 41 children after 2 months, and test of criterion-related validation was established by the Social Behavior Scale administered to 71 children. All raw scores were standardized by classroom and sex to adjust for differences in the number of nominators and nominatees. The structure of the RCP resulted in 3 factors, 'sociability-disruptive' and 'shy-isolated', with 28 items similar to the original RCP 3 factors. For criterion-related validity, the correlations between the 3 factors of the RCP and the 3 factors of the Social Behavior Scale were positive. For internal consistencies, Cronbach's ${\alpha}$ of the RCP factors ranged from .77 to .94. Test-retest reliability coefficients ranged from .33 to .51. Analyses of variance revealed good item discrepancies for all 28 items. These results confirm the RCP as a valid and reliable measure of the quality of peer relations.

• Nuclear Engineering and Technology
• /
• v.55 no.5
• /
• pp.1616-1629
• /
• 2023

To quantify the conservatism of existing ASME strain-based evaluation methods for seismic loading, this paper presents very low cycle fatigue test data of elbows under various cyclic loading conditions and comparison of evaluation results with experimental failure cycles. For strain-based evaluation methods, the method presented in ASME BPVC CC N-900 and Sec. VIII are used. Predicted failure cycles are compared with experimental failure cycle to quantify the conservatism of evaluation methods. All methods give very conservative failure cycles. The CC N-900 method is the most conservative and prediction results are only ~0.5% of experimental data. For Sec. VIII method, the use of the option using code tensile properties gives ~3% of experimental data, and the use of the material-specific reduction of area can reduce conservatism but still gives ~15% of experimental data.

• International Journal of Aeronautical and Space Sciences
• /
• v.5 no.1
• /
• pp.46-56
• /
• 2004

The verification and improvement of the measurement uncertainty have beenperformed in the altitude test facility for small gas turbine engines, which was built atthe Korea Aerospace Research Institute (KARI) in October 1999. This test is performedwith a single spool turbojet engine at several flight conditions. This paper discussesthe evaluation and validation process for the measurement uncertainty improvements usedin the altitude test facility. The evaluation process, defined as tests before the facilitymodification, shows that the major contnbutors to the measurement uncertainty are theflow meter discharge coefficient, the inlet static and total pressures, the cell pressureand the fuel flow rate. The measurement uncertainty is focused on the primary parametersof the engine performance such as airflow rate, thrust and specific fuel consumption (SFC).The validation process, defined as tests after the facility modification, shows that themeasurement uncertainty, in seal level condition, is tmproved to the acceptable level throughthe facility modification. In altitude test conditions, the measurement uncertainties arenot improved as much as the uncertainty in sea level condition.