• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.2
• /
• pp.21-25
• /
• 2023

The purpose of this study was to compare the performance using multiple regression models to predict the energy consumption of steel industry. Specific independent variables were selected in consideration of correlation among various attributes such as CO2 concentration, NSM, Week Status, Day of week, and Load Type, and preprocessing was performed to solve the multicollinearity problem. In data preprocessing, we evaluated linear and nonlinear relationships between each attribute through correlation analysis. In particular, we decided to select variables with high correlation and include appropriate variables in the final model to prevent multicollinearity problems. Among the many regression models learned, Boosted Decision Tree Regression showed the best predictive performance. Ensemble learning in this model was able to effectively learn complex patterns while preventing overfitting by combining multiple decision trees. Consequently, these predictive models are expected to provide important information for improving energy efficiency and management decision-making at steel industry. In the future, we plan to improve the performance of the model by collecting more data and extending variables, and the application of the model considering interactions with external factors will also be considered.

• Korean Journal of Clinical Laboratory Science
• /
• v.39 no.3
• /
• pp.271-276
• /
• 2007

Helicobacter pylori (H. pylori) infection is common in korea and high incidence at gastric ulcer and duodenal ulcer. $^{14}C-urea$ breath test ($^{14}C-UBT$) is regarded as a highly reliable and non-invasive method for the diagnosis of H. pylori infection. The purpose of this study was to evaluate the diagnositc performance of a new and rapid $^{14}C-UBT$, which was equipped with Geiger-Muller counter and compared the results with those obtained by gastroduodenoscopic biopsies (GBx). One hundred sixty-eight patients (M : F = 118 : 50) underwent $^{14}C-UBT$, rapid urease test (CLO test), and GBx. The results of $^{14}C-UBT$ were classified as positive (>50 cpm), borderline (25$^{14}C-UBT$ or CLO test results with GBx as a glod standard. In the assessment of the presence of H. pylori infection, the $^{14}C-UBT$ global performance yielded positive predictive value, negative predictive value and accuracy of 93.3% and 83.3%, respectively. However, the CLO test had performance yielded positive predictive value, negative predictive value and accuracy of 76.9%, 50.0%, respectively. In this study $^{14}C-UBT$ is a highly accurate, simple and non-invasive method or the diagnosis of follow up H. pylori infection.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.35 no.4
• /
• pp.213-220
• /
• 2009

Purpose: The present study was aimed to examine the usefulness of 18F-FDG PET/CT in the evaluation of cervical lymph node metastasis in patients with oral cancer. Materials and methods: Twenty-two patients who underwent neck dissection to treat oral cancer were subjected for examination. The cervical node metastasis was evaluated by means of clinical examination, CT scan, PET, and histologic examination. By comparing the results of each examination modality with those of histologic examination, it's sensitivity, specificity, positive predictive value, and negative predictive value were determined. Results: The oral cancer was more frequent in males with a ratio of 2.14:1. The sixth decade showed the highest incidence in age distribution with mean of $56{\pm}16$. Histologic findings showed that squamous cell carcinoma was the most common (15 patients), and mucoepidermoid carcinoma (3), malignant melanoma (2), and adenoid cystic carcinoma and ghost cell odontogenic carcinoma (1 each), in order. In most cases, wide surgical excision of the primary cancer and neck dissection was performed, followed by reconstruction with free flaps when necessary. When comparing the results of each examination modality with those of the histologic examination, clinical examination showed sensitivity, specificity, positive predictive value, and negative predictive value at 11%, 85%, 33%, and 58%, respectively. CT scans showed at 67%, 77%, 67%, and 77%, while $^{18}F$-FDG PET/CT at 78%, 77%, 70%, and 83%, respectively. Conclusions: These results suggest that PET is more useful, compared with clinical examination and CT scans, in the evaluation of cervical lymph node metastasis in patients with oral cancer.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.4
• /
• pp.21-29
• /
• 2017

Previous visual analytics researches has focused on reducing the uncertainty of predicted results using a variety of interactive visual data exploration techniques. The main purpose of the interactive search technique is to reduce the quality difference of the predicted results according to the level of the decision maker by understanding the relationship between the variables and choosing the appropriate model to predict the unknown variables. However, it is difficult to create a predictive model which forecast time series data whose overall trends is unknown such as youth physical growth data. In this paper, we pro pose a novel predictive analysis technique to forecast the physical growth value in small pieces of time series data with un certain trends. This model estimates the distribution of data at a particular point in time. We also propose a visual analytics system that minimizes the possible uncertainties in predictive modeling process.

• Journal of The Geomorphological Association of Korea
• /
• v.24 no.3
• /
• pp.105-118
• /
• 2017

The debris slope landforms which are existent in Korean mountains is generally on the steep slopes and mostly covered by vegetation, it is difficult to investigate the landform. Therefore a scientific method is required to come up with an effective field investigation plan. For this purpose, the use of Remote Sensing and GIS technologies for a spatial analysis is essential. This study has extracted the potential area of debrisslope landform formation using Fuzzy set and Bayesian Predictive Discriminate Model as mathematical data integration methods. The first step was to obtain information about debris locations and their related factors. This information was verified through field investigation and then used to build a database. In the second step, the map that zoning the study area based on the degree of debris formation possibility was generated using two modeling methods, and then cross validation technique was applied. In order to quantitatively analyze the accuracy of two modeling methods, the calculated potential rate of debrisformation within the study area was evaluated by plotting SRC(Success Rate Curve) and calculating AUC(Area Under the Curve). As a result, the prediction accuracy of Fuzzy set model wes 83.1% and Bayesian Predictive Discriminate Model wes 84.9%. It showed that two models are accurate and reliable and can contribute to efficient field investigation and debris landform management.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.171-177
• /
• 2021

In terms of distribution planning, accurate electric load prediction is one of the most important factors. The future load prediction has manually been performed by calculating the maximum electric load considering loads transfer/switching and multiplying it with the load increase rate. In here, the risk of human error is inherent and thus an automated maximum electric load forecasting system is required. Although there are many existing methods and techniques to predict future electric loads, such as regression analysis, many of them have limitations in reflecting the nonlinear characteristics of the electric load and the complexity due to Photovoltaics (PVs), Electric Vehicles (EVs), and etc. This study, therefore, proposes a method of predicting future electric loads on distribution lines by using Machine Learning (ML) method that can reflect the characteristics of these nonlinearities. In addition, predictive models were developed based on actual data collected at KEPCO's existing distribution lines and the adequacy of developed models was verified as well. Also, as the distribution planning has a direct bearing on the investment, and amount of investment has a direct bearing on the maximum electric load, various baseline such as maximum, lowest, median value that can assesses the adequacy and accuracy of proposed ML based electric load prediction methods were suggested.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.4 no.2
• /
• pp.79-85
• /
• 2023

The Tibetan Plateau is home to the only alpine crane species, the black-necked crane (Grus nigricollis). Conservation efforts are severely hampered by a lack of knowledge on the spatial distribution and breeding habitats of this species. The ecological niche modeling framework used to predict the spatial distribution of this species, based on the maximum entropy and occurrence record data, allowed us to generate a species-specific spatial distribution map in Ladakh, Trans-Himalaya, India. The model was created by assimilating species occurrence data from 486 geographical sites with 24 topographic and bioclimatic variables. Fourteen variables helped forecast the distribution of black-necked cranes by 96.2%. The area under the curve score for the model training data was high (0.98), indicating the accuracy and predictive performance of the model. Of the total study area, the areas with high and moderate habitat suitability for black-necked cranes were anticipated to be 8,156 km² and 6,759 km², respectively. The area with high habitat suitability within the protected areas was 5,335 km². The spatial distribution predicted using our model showed that the majority of speculated conservation areas bordered the existing protected areas of the Changthang Wildlife Sanctuary. Hence, we believe, that by increasing the current study area, we can account for these gaps in conservation areas, more effectively.

• Journal of Forest and Environmental Science
• /
• v.32 no.1
• /
• pp.94-98
• /
• 2016

Calamus andamanicus Kurz is one of the commercially important solitary rattans endemic to Andaman and Nicobar islands. The habitat suitability modeling program, MaxEnt, was used to predict the potential ecological niches of this species, based on bioclimatic variables. The study revealed high potential distribution of C. andamanicus across both Andaman and Nicobar islands. Of the 33 spatially unique points, 21 points were recorded from South and North Andamans and 12 from Great Nicobar Islands. The islands like Little Andaman, North Sentinel, Little Nicobar, Tllangchong, Teressa were also predicted positive even though this rattan is not recorded from these islands. Mean diurnal range, higher precipitation in the wettest month of the year, annual precipitation and precipitation in the driest month are the main predictors of this species distribution.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.245-249
• /
• 1997

A feasibility study on the characterization of incipient insulator failure for distribution fault prediction is presented. In this study, real distribution data was collected and analyzed to isolate incipient failure signatures or parameters which were expected to show distinct behaviors before and after failure incident. Several signal analysis methods were applied to isolate the parameters and a new strategy of analysis, the event-date concept, was also applied to find a relationship between non-harmonic and high frequency signal activities and imminent insulator failures.

• Journal of Korean Society on Water Environment
• /
• v.26 no.3
• /
• pp.460-467
• /
• 2010

For D-WTP's sedimentation basin and distribution reservoir, and water tap the predictive models proposed tentatively herein included the models for estimating TTHM concentration in precipitated water, for treated water and for tap water, and the estimated correlation formula between treated water's TTHM concentration and tap water. As for TTHM-concentration predictive model in sedimentation water, the coefficient of determination is 0.866 for best-fitted short-term $DOC{\times}UV_{254}$ based Model (TTHM). As for $HAA_5$-concentration predictive model in sedimentation water, the coefficient of determination is 0.947 for the suitable $UV_{254}$-based model ($HAA_5$). In case of the predictive model in treated water, the coefficient of determination is 0.980 for best-fitted $DOC{\times}UV_{254}$ based model (TTHM) using coagulated waters, while the coefficient of determination is 0.983 for best-fitted $DOC{\times}UV_{254}$ based model ($HAA_5$) using coagulated waters, which described the $HAA_5$ concentration well. However, the predictive model for tap water could not be compatible with the one for treated water, only except for possibility inducing correlation formula for prediction, [i.e., the correlation formula between TTHM concentration and tap water was verified as TTHM (tap water) = $1.162{\times}TTHM$ (treated water), while $HAA_5$ (tap water) = $0.965{\times}HAA_5$ (treated water).] The correlation analysis between DOC and $KMnO_4$ consumption by process resulted in higher relationship with filtrated water, showing that its regression is $DOC=0.669{\times}KMnO_4$ consumption - 0.166 with 0.689 of determination coefficient. By substituting it to the existing DOC-based model ($HAA_5$) for treated water, the consequential model formula was made as follows; $HAA_5=8.35(KMnO_4\;consumption{\times}0.669-0.166)^{0.701}(Cl_2)^{0.577}t^{0.150}0.9216^{(pH-7.5)}1.022^{(Temp-20^{\circ}C)}$