• The Journal of the Korea Contents Association
• /
• v.21 no.6
• /
• pp.35-43
• /
• 2021

Citrus quality is generally determined by its sugar content and acidity. In particular, sugar content is a very important factor because it determines the taste of citrus. Currently, the most commonly used method of measuring citrus sugar content in farms is a portable juiced sugar meter and a non-destructive sugar meter. This method can be easily measured by individuals, but the accuracy of the sugar content is inferior to that of the citrus NongHyup official machine. In particular, there is an error difference of 0.5 Brix or more, which is still insufficient for use in the field. Therefore, in this paper, we propose an AI model that predicts the citrus sugar content of unmeasured days within the error range of 0.5 Brix or less based on the previously collected citrus sugar content and meteorological data (average temperature, humidity, rainfall, solar radiation, and average wind speed). In addition, it was confirmed that the prediction model proposed through performance evaluation had an mean absolute error of 0.1154 for Seongsan area and 0.1983 for the Hawon area in Jeju Island. Lastly, the proposed model supports an error difference of less than 0.5 Brix and is a technology that supports predictive measurement, so it is expected that its usability will be highly progressive.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.2 s.20
• /
• pp.57-66
• /
• 2002

This paper establised GPS network consist of 75km average baseline lengths over Jeollanamdo and Jeollabukdo nine point station and fixed Gwangju point station. We quantitavely analyzed how much precision of the baseline determination is improved for GPS survey when using the precise eqhemeris instead of tile broadcast ephemeris of GPS satellites. The observed data for each baseline were processed two times with the same conditions alternately changing the broadcast and the precise ephemeris. The standard deviations from the repeated measurments for each baseline ara compared between the results of using the broadcast ephemeris and the precise ephemeris. As the results, the precision, stability and reliability of the baseline determination using the precise ephemeris is better than those of using the broadcast ephemeris for all baselines.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.1609-1613
• /
• 2008

국내에서 하천 정비 사업을 수행할 경우에 HEC-RAS와 같은 1차원 수치모형을 이용하여 개략적으로 홍수위 및 단면평균 유속 분석을 통한 치수안전성을 검토하고 있다. 그러나 1차원 모형은 교량이나 보 등의 하천 횡단구조물에 의한 수위 상승 구간을 정확히 산정하기 어려우며 지류가 유입하는 합류지점이나 하도형상이 급변하는 지점에서의 국부적인 흐름의 변화양상을 계산하기에는 많은 한계가 있다. 따라서 본 연구에서는 감천과 직지사천이 합류하는 구간을 대상으로, 1차원 수치모형인 HEC-RAS와 2차원 모형인 FLUMEN을 이용하여 수위 및 유속분포 등 수리특성을 비교 분석하여 그 특성을 파악하였다. 모형의 적용 결과, 두 모형 모두 김천교 수위국의 실측치에 대해 절대오차율평균이 5% 이내이며 상관계수 및 결정계수가 1에 가까운 값을 보여 비교적 정확한 모의 결과를 보여주었다. 또한 두 모형 모두 교량 직상류부의 수위상승과 직하류부의 수위하강의 양상은 비교적 동일하게 나타났다. 그러나 수리구조물에 대한 영향을 1차원 모형이 잘 반영하지 못하기 때문에 합류부 상류구간의 교량 단면에서 수위 및 유속분포의 차이는 비교적 크게 나타났으며, 특히 합류부 직상류부의 교량단면에서의 수위분포는 $15{\sim}20%$ 정도의 차이가 나타났다.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.923-932
• /
• 2013

This paper proposes a method to predict the number of foodborne disease outbreaks by microbes. The weekly data of food poisoning occurrences by microbes in Korea contain many zero-valued observations and have dependency between outbreaks. In order to model both phenomena, the number of food poisonings is predicted by an autoregressive model and the probabilities of food poisoning occurrences by microbes (given the total of food poisonings) are estimated by the baseline category logit model. The predicted number of foodborne disease outbreaks by a microbe is obtained by multiplying the predicted number of foodborne disease outbreaks and the estimated probability of the food poisoning by the corresponding microbe. The mean squared error and the mean absolute value error are evaluated to compare the performances of the proposed method and the zero-inflated model.

• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1193-1201
• /
• 2020

This study aims to develop a regression model that estimates a low-flow index that can be applied to ungauged basins. A total of 30 midsized basins in South Korea use long-term runoff data provided by the National Integrated Water Management System (NIWMS) to calculate average low-flow, average minimum streamflow, and low-flow index duration and frequency. This information is used in the correlation analysis with 18 basin factors and 3 climate change factors to identify the basin area, average basin altitude, average basin slope, water system density, runoff curve number, annual evapotranspiration, and annual precipitation in the low-flow index regression model. This study evaluates the model's accuracy by using the root-mean-square error (RMSE) and the mean absolute error (MAE) for 10 ungauged, verified basins and compares them with the previous model's low-flow calculations to determine the effectiveness of the newly developed model. Comparative analysis indicates that the new regression model produces average low-flow, attributed to the consideration of varied basin and hydrologic factors during the new model's development.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.33-47
• /
• 2018

City gas pipelines are buried underground. Because of this, pipeline is hard to manage, and can be easily damaged. This research proposes a real time prediction system that helps experts can make decision about pressure anomalies. The gas pipline pressure data of Jungbu City Gas Company, which is one of the domestic city gas suppliers, time variables and environment variables are analysed. In this research, regression models that predicts pipeline pressure in minutes are proposed. Random forest, support vector regression (SVR), long-short term memory (LSTM) algorithms are used to build pressure prediction models. A comparison of pressure prediction models' preformances shows that the LSTM model was the best. LSTM model for Asan-si have root mean square error (RMSE) 0.011, mean absolute percentage error (MAPE) 0.494. LSTM model for Cheonan-si have RMSE 0.015, MAPE 0.668.

• Korean Chemical Engineering Research
• /
• v.58 no.2
• /
• pp.248-256
• /
• 2020

In this study, predictive models based on machine learning for evaluating the extent of hazardous zone of explosive gases are developed. They are able to provide important guidelines for installing the explosion proof apparatus. 1,200 research data sets including 12 combustible gases and their extents of hazardous zone are generated to train predictive models. The extent of hazardous zone is set to an output variable and 12 variables affecting an output are set as input variables. Multiple linear regression, principal component regression, and artificial neural network are employed to train predictive models. Mean absolute percentage errors of multiple linear regression, principal component regression, and artificial neural network are 44.2%, 49.3%, and 5.7% and root mean square errors are 1.389m, 1.602m, and 0.203 m respectively. Therefore, it can be concluded that the artificial neural network shows the best performance. This model can be easily used to evaluate the extent of hazardous zone for explosive gases.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.62-73
• /
• 2022

Researches on the prediction of domestic apartment sales price have been continuously conducted, but it is not easy to accurately predict apartment prices because various characteristics are compounded. Prior to predicting apartment sales price, the analysis of major factors, influencing on sale prices, is of paramount importance to improve the accuracy of sales price. Therefore, this study aims to analyze what are the factors that affect the apartment sales price in Gwangju, which is currently showing a steady increase rate. With 6 years of Gwangju apartment transaction price and various social factor data, several maching learning techniques such as multiple regression analysis, random forest, and deep artificial neural network algorithms are applied to identify major factors in each model. The performances of each model are compared with RMSE (Root Mean Squared Error), MAE (Mean Absolute Error) and R² (coefficient of determination). The experiment shows that several factors such as 'contract year', 'applicable area', 'certificate of deposit', 'mortgage rate', 'leading index', 'producer price index', 'coincident composite index' are analyzed as main factors, affecting the sales price.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.415-421
• /
• 2023

In this study, the piezoresistive properties of cementitious composites enhanced with carbon nanotubes for improved electrical conductivity were analyzed using a deep learning-based transformer algorithm. Experimental execution was performed in parallel for acquisition of training data. Previous studies on mixture design, specimen fabrication, chemical composition analysis, and piezoresistive performance testing are also reviewed in this paper. Notably, specimens in which fly ash substituted 50% of the binder material were fabricated and evaluated in this study, in addition to carbon nanotube-infused specimens, thereby exploring the potential enhancement of piezoresistive characteristics in conductive cementitious materials. The experimental results showed more stable piezoresistive responses in specimens with fly-ash substituted binder. The transformer model was trained using 80% of the gathered data, with the remaining 20% employed for validation. The analytical outcomes were generally consistent with empirical measurements, yielding an average absolute error and root mean square error between 0.069 to 0.074 and 0.124 to 0.132, respectively.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.221-228
• /
• 2024

Predicting insurance claims is a key task for insurance companies to manage risks and maintain financial stability. Accurate insurance claim predictions enable insurers to set appropriate premiums, reduce unexpected losses, and improve the quality of customer service. This study aims to enhance the performance of insurance claim prediction models by applying ensemble learning techniques. The predictive performance of models such as Random Forest, Gradient Boosting Machine (GBM), XGBoost, Stacking, and the proposed Dynamic Weighted Ensemble (DWE) model were compared and analyzed. Model performance was evaluated using Mean Absolute Error (MAE), Mean Squared Error (MSE), and the Coefficient of Determination (R²). Experimental results showed that the DWE model outperformed others in terms of evaluation metrics, achieving optimal predictive performance by combining the prediction results of Random Forest, XGBoost, LR, and LightGBM. This study demonstrates that ensemble learning techniques are effective in improving the accuracy of insurance claim predictions and suggests the potential utilization of AI-based predictive models in the insurance industry.