• Computers and Concrete
• /
• v.30 no.5
• /
• pp.301-310
• /
• 2022

Cement-based sensors have been widely used as structural health monitoring systems, however, their long-term sensing performance have not actively investigated. In this study, a deep learning-based methodology is adopted to predict the long-term piezoresistive properties of cement-based sensors. Samples with different multi-walled carbon nanotube contents (0.1, 0.3, and 0.5 wt.%) are fabricated, and piezoresistive tests are conducted over 10,000 loading cycles to obtain the training data. Time-dependent degradation is predicted using a modified long short-term memory (LSTM) model. The effects of different model variables including the amount of training data, number of epochs, and dropout ratio on the accuracy of predictions are analyzed. Finally, the effectiveness of the proposed approach is evaluated by comparing the predictions for long-term piezoresistive sensing performance with untrained experimental data. A sensitivity of 6% is experimentally examined in the sample containing 0.1 wt.% of MWCNTs, and predictions with accuracy up to 98% are found using the proposed LSTM model. Based on the experimental results, the proposed model is expected to be applied in the structural health monitoring systems to predict their long-term piezoresistice sensing performances during their service life.

• Journal of Korean Society on Water Environment
• /
• v.36 no.6
• /
• pp.611-620
• /
• 2020

Although process-based models have been a preferred approach for modeling freshwater aquatic systems over extended time intervals, the increasing utility of data-driven models in a big data environment has made the data-driven models increasingly popular in recent decades. In this study, international peer-reviewed journals for the relevant fields were searched in the Web of Science Core Collection, and an extensive literature review, which included total 2,984 articles published during the last two decades (2000-2020), was performed. The review results indicated that the rate of increase in the number of published studies using data-driven models exceeded those using process-based models since 2010. The increase in the use of data-driven models was partly attributable to the increasing availability of data from new data sources, e.g., remotely sensed hyperspectral or multispectral data. Consistently throughout the past two decades, South Korea has been one of the top ten countries in which the greatest number of studies using the data-driven models were published. Among the major data-driven approaches, i.e., artificial neural network, decision tree, and Bayesian model, were illustrated with case studies. Based on the review, this study aimed to inform the current state of knowledge regarding the biogeochemical water quality and ecological models using data-driven approaches, and provide the remaining challenges and future prospects.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.97-107
• /
• 2022

Recently, interest in smart factories is increasing. Investments to improve intelligence/automation are also being made continuously in manufacturing plants. Facility automation based on sensor data collection is now essential. In addition, we are operating our factories based on data generated in all areas of production, including production management, facility operation, and quality management, and an integrated standard information system. When producing LCD polarizer products, it is most important to link trace information between data generated by individual production processes. All systems involved in production must ensure that there is no data loss and data integrity is ensured. The large-capacity data collected from individual systems is composed of key values linked to each other. A real-time quality analysis processing system based on connected integrated system data is required. In this study, large-capacity data collection, storage, integration and loss prevention methods were presented for optimization of LCD polarizer production. The identification Risk model of inspection products can be added, and the applicable product model is designed to be continuously expanded. A quality inspection and analysis system that maximizes the yield rate was designed by using the final inspection image of the product using big data technology. In the case of products that are predefined as analysable products, it is designed to be verified with the big data knn analysis model, and individual analysis results are continuously applied to the actual production site to operate in a virtuous cycle structure. Production Optimization was performed by applying it to the currently produced LCD polarizer production line.

• Atmosphere
• /
• v.29 no.4
• /
• pp.355-365
• /
• 2019

Based on in-situ monitoring data produced by National Institute of Meteorological Sciences, we evaluated the performance of Joint UK Land Environment Simulator (JULES) on the surface energy balance for rice-paddy and cropland in Korea with the operational ancillary data used for Unified Model (UM) Local Data Assimilation and Prediction System (LDAPS) (CTL) and the high-resolution ancillary data from external sources (EXP). For these experiments, we employed the one-year (March 2015~February 2016) observations of eddy-covariance fluxes and soil moisture contents from a double-cropping rice-paddy in BoSeong and a cropland in AnDong. On the rice-paddy site the model performed better in the CTL experiment except for the sensible heat flux, and the latent heat flux was underestimated in both of experiments which can be inferred that the model represents flood-irrigated surface poorly. On the cropland site the model performance of the EXP experiment was worse than that of CTL experiment related to unrealistic surface type fractions. The pattern of the modeled soil moisture was similar to the observation but more variable in time. Our results shed a light on that 1) the improvement of land scheme for the flood-irrigated rice-paddy and 2) the construction of appropriate high-resolution ancillary data should be considered in the future research.

• Journal of Korean Society for Quality Management
• /
• v.41 no.4
• /
• pp.623-635
• /
• 2013

Purpose: The recent major recalls of hazardous products caused consumer product safety acts to be strengthen worldwide. Although the recall system of hazardous products in Korea has been operating based on Framework Act on Product Safety since 2011, the evaluation of product risk has been relied on not the results of objective incident data but the results of illegal product investigations. The purpose of this paper is to propose a product risk assessment model for Korea using injury data. Methods: The authors derived Korea's risk assessment method by analysing the advantages and disadvantages of the most widely used models in advanced countries such as EU's RAPEX RAG and Janpan's R-MAP. In this study, the level of relative frequency and severity of injury are determined based on the objective incident data and the length of hospitalization respectively. In addition, the injury data occurred during 2011 is applied to the proposed risk assessment model for case study. Results: The data analysed in this paper can be classified as high risk, medium risk, low risk, acceptable risk, and safe products through the matrix f rom the combination of the relative frequency and the severity derived. Conclusion: The proposed risk assessment model in this study has advantage obtaining reliable objective results because it uses actual injury data and redeems the drawbacks of the existing models used in advanced countries. Furthermore, because the proposed model shows the high risk products among many, it is expected to be useful especially for customs whose main job is inspecting the imported goods and the government when selecting the target product groups for safety investigation.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.1
• /
• pp.11-18
• /
• 2022

In order to improve the accuracy of particle tracking prediction techniques near the Korean Strait, this study compared and analyzed a particle tracking model based on a seawater flow numerical model and a machine learning based on a particle tracking model using field observation data. The data used in the study were the surface drifter buoy movement trajectory data observed in the Korea Strait, prediction data by machine learning (linear regression, decision tree) using the tide and wind data from three observation stations (Gageo Island, Geoje Island, Gyoboncho), and prediciton data by numerical models (ROMS, MOHID). The above three data were compared through three error evaluation methods (Correlation Coefficient (CC), Root Mean Square Errors (RMSE), and Normalized Cumulative Lagrangian Separation (NCLS)). As a final result, the decision tree model had the best prediction accuracy in CC and RMSE, and the MOHID model had the best prediction results in NCLS.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.119-133
• /
• 2023

With the rapid growth of the economy and fossil fuel consumption, the concentration of air pollutants has increased significantly and the air pollution problem is no longer limited to small areas. We conduct statistical analysis with the actual data related to air quality that covers the entire of South Korea using R and Python. Some factors such as SO₂, CO, O₃, NO₂, PM₁₀, precipitation, wind speed, wind direction, vapor pressure, local pressure, sea level pressure, temperature, humidity, and others are used as covariates. The main goal of this paper is to predict air quality index (AQI) spatio-temporal data. The observations of spatio-temporal big datasets like AQI data are correlated both spatially and temporally, and computation of the prediction or forecasting with dependence structure is often infeasible. As such, the likelihood function based on the spatio-temporal model may be complicated and some special modelings are useful for statistically reliable predictions. In this paper, we propose several methods for this big spatio-temporal AQI data. First, random effects with spatio-temporal basis functions model, a classical statistical analysis, is proposed. Next, neural networks model, a deep learning method based on artificial neural networks, is applied. Finally, random forest model, a machine learning method that is closer to computational science, will be introduced. Then we compare the forecasting performance of each other in terms of predictive diagnostics. As a result of the analysis, all three methods predicted the normal level of PM_2.5 well, but the performance seems to be poor at the extreme value.

• Proceedings of the Safety Management and Science Conference
• /
• 2004.11a
• /
• pp.415-438
• /
• 2004

This dissertation is assumed to continuously occur adjustment cost on present investment. So, I derived from time-nonseparable production-based CAPM and tested the performance of model through data. I also compared time-nonseparable production-based CAPM with time-separable production-based CAPM and CCAPM, CAPM through testifying the performance of model. At the part of applied application, I estimated time-nonseparable PCAPM-betas. The data of Korea consists of 320 listed companies on Korea Stock Exchange (KOSPI) from first quarter 1987 to first quarter 2002. This data also is categorized by scale and industries. Additionally, I estimated time-nonseparable PCAPM-betas through 500 listed companies of New York Stock Exchange (NYSE) from first quarter 1973 to first quarter 2002. I observed the statistical significance of 230 firms by 320 companies in Korea. After that, I compared time-nonseparable PCAPM-betas by firms with time-separable production-based CAPM-betas and CCAPM-betas, CAPM-betas through individual firms. At empirical test, I found that estimated parameter of adjustment cost on time-nonseparable production-based CAPM by scale and industries in Korea had positive value and statistical significance, Moreover, this approach proved to resolve the underestimation of adjustment cost on time-separable production-based CAPM by scale and industries. I also found that the time-nonseparable PCAPM performed better than time-separable production-based CAPM and CCAPM, CAPM. The result from U.S data proved to have similarity to that of Korea. Specifically, I found that time-nonseparable PCAPM-betas by firms performed better than CAPM-betas on individual firms in Korea.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.4
• /
• pp.1759-1768
• /
• 2018

The energy density, power density and ohm resistance of battery change significantly as results of battery aging, which lead to decrease in the accuracy of the equivalent model. A parameter identification method of the equivale6nt circuit model with 3 R-C branches based on the test database of battery life cycle is proposed in this paper. This database is built on the basis of experiments such as updating of available capacity, charging and discharging tests at different rates and relaxation characteristics tests. It can realize regular update and calibration of key parameters like SOH, so as to ensure the reliability of parameters identified. Taking SOH, SOC and T as independent variables, lookup table method is adopted to set initial value for the parameter matrix. Meanwhile, in order to ensure the validity of the model, the least square method based on variable forgetting factor is adopted for optimizing to complete the identification of equivalent model parameters. By comparing the simulation data with measured data for charging and discharging experiments of Li-ion battery, the effectiveness of the full life cycle database and the model are verified.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.1
• /
• pp.95-105
• /
• 2019

Evapotranpiration (ET) is one of the important factor in Hydrological cycle and irrigation planning. In this study, temperature-based artificial neural network (ANN) model for daily reference crop ET estimation was developed and compared with reference crop evapotranpiration ($ET_0$) from FAO-56 Penman-Monteith method (FAO-56 PM) and parameter regionalized Hargreaves method. The ANN model was trained and tested for 10 weather stations (5 inland stations and 5 costal stations) and two input climate factors, maximum temperature ($T_{max}$), minimum temperature ($T_{min}$), and extraterrestrial radiation (RA) were used for training and validation of temperature-based ANN model. Monthly reference ET by the ANN model also compared with parameter regionalized Hargreaves method for ANN model applicability evaluation. The ANN model evapotranspiration demonstrated more accordance to FAO-56 PM evapotranspiration than the $ET_0$ from parameter regionalized Hargreaves method(R-Hargreaves). The results of this study proposed that daily reference crop ET estimated by the ANN model could be used in the condition of no sufficient climate data.