• Korean Journal of Materials Research
• /
• v.33 no.4
• /
• pp.164-174
• /
• 2023

The bandgap characteristics of semiconductor materials are an important factor when utilizing semiconductor materials for various applications. In this study, based on data provided by AFLOW (Automatic-FLOW for Materials Discovery), the bandgap of a semiconductor material was predicted using only the material's compositional features. The compositional features were generated using the python module of 'Pymatgen' and 'Matminer'. Pearson's correlation coefficients (PCC) between the compositional features were calculated and those with a correlation coefficient value larger than 0.95 were removed in order to avoid overfitting. The bandgap prediction performance was compared using the metrics of R² score and root-mean-squared error. By predicting the bandgap with randomforest and xgboost as representatives of the ensemble algorithm, it was found that xgboost gave better results after cross-validation and hyper-parameter tuning. To investigate the effect of compositional feature selection on the bandgap prediction of the machine learning model, the prediction performance was studied according to the number of features based on feature importance methods. It was found that there were no significant changes in prediction performance beyond the appropriate feature. Furthermore, artificial neural networks were employed to compare the prediction performance by adjusting the number of features guided by the PCC values, resulting in the best R² score of 0.811. By comparing and analyzing the bandgap distribution and prediction performance according to the material group containing specific elements (F, N, Yb, Eu, Zn, B, Si, Ge, Fe Al), various information for material design was obtained.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Climate Change Research
• /
• v.7 no.3
• /
• pp.325-334
• /
• 2016

We projected the distribution of Hedera rhombea, an evergreen broad-leaved climbing plant, under current climate conditions and predicted its future distributions under global warming. Inaddition, weexplained model uncertainty by employing 9 single Species Distribution model (SDM)s to model the distribution of Hedera rhombea. 9 single SDMs were constructed with 736 presence/absence data and 3 temperature and 3 precipitation data. Uncertainty of each SDM was assessed with TSS (Ture Skill Statistics) and AUC (the Area under the curve) value of ROC (receiver operating characteristic) analyses. To reduce model uncertainty, we combined 9 single SDMs weighted by TSS and resulted in an ensemble forecast, a TSS weighted ensemble. We predicted future distributions of Hedera rhombea under future climate conditions for the period of 2050 (2040~2060), which were estimated with HadGEM2-AO. RF (Random Forest), GBM (Generalized Boosted Model) and TSS weighted ensemble model showed higher prediction accuracies (AUC > 0.95, TSS > 0.80) than other SDMs. Based on the projections of TSS weighted ensemble, potential habitats under current climate conditions showed a discrepancy with actual habitats, especially in the northern distribution limit. The observed northern boundary of Hedera rhombea is Ulsan in the eastern Korean Peninsula, but the projected limit was eastern coast of Gangwon province. Geomorphological conditions and the dispersal limitations mediated by birds, the lack of bird habitats at eastern coast of Gangwon Province, account for such discrepancy. In general, potential habitats of Hedera rhombea expanded under future climate conditions, but the extent of expansions depend on RCP scenarios. Potential Habitat of Hedera rhombea expanded into Jeolla-inland area under RCP 4.5, and into Chungnam and Wonsan under RCP 8.5. Our results would be fundamental information for understanding the potential effects of climate change on the distribution of Hedera rhombea.

• The Korean Journal of Applied Statistics
• /
• v.32 no.5
• /
• pp.671-681
• /
• 2019

Studies on predicting arrhythmia using machine learning have been actively conducted with increasing number of arrhythmia patients. Existing studies have predicted arrhythmia based on multivariate data of feature variables extracted from RR interval data at a specific time point. In this study, we consider that the pattern of the heart state changes with time can be important information for the arrhythmia prediction. Therefore, we investigate the usefulness of predicting the arrhythmia with multivariate time series data obtained by extracting and accumulating the multivariate vectors of the feature variables at various time points. When considering 1-nearest neighbor classification method and its ensemble for comparison, it is confirmed that the multivariate time series data based method can have better classification performance than the multivariate data based method if we select an appropriate time series distance function.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.3
• /
• pp.795-804
• /
• 2014

In this study, Andong Reservoir monthly and ten days inflows from July 2011 to September 2011 are predicted using SWAT model and ensemble technique. The weight method using monthly and ten days rainfall forecasts from Korea Meteorological Administration is applied for accurate analysis. If the rainfall prediction announced by Korea Meteorological Administration is close to the actual rainfall, the PDF-Ratio Method shows the best result. If the past high rainfall occurrence is close to the actual rainfall, the modified PDF-Ratio method shows the best result. This method can improve the prediction accuracy even though the Korea Meteorological Administration forecast is not accurate. On the contrary, if Korea Meteorological Administration forecast is different from the actual rainfall and the past rainfall occurrence statistics of lower section, the uniform method shows the best result.

• Journal of Korean Society on Water Environment
• /
• v.39 no.1
• /
• pp.1-8
• /
• 2023

Monitoring and prediction of water quality are essential for effective river pollution prevention and water quality management. In this study, a multi-classification model was developed to predict chlorophyll-a (Chl-a) level in rivers. A model was developed using CatBoost, a novel ensemble machine learning algorithm. The model was developed using hourly field monitoring data collected from January 1 to December 31, 2015. For model development, chl-a was classified into class 1 (Chl-a≤10 ㎍/L), class 2 (10<Chl-a≤50 ㎍/L), and class 3 (Chl-a>50 ㎍/L), where the number of data used for the model training were 27,192, 11,031, and 511, respectively. The macro averages of precision, recall, and F1-score for the three classes were 0.58, 0.58, and 0.58, respectively, while the weighted averages were 0.89, 0.90, and 0.89, for precision, recall, and F1-score, respectively. The model showed relatively poor performance for class 3 where the number of observations was much smaller compared to the other two classes. The imbalance of data distribution among the three classes was resolved by using the synthetic minority over-sampling technique (SMOTE) algorithm, where the number of data used for model training was evenly distributed as 26,868 for each class. The model performance was improved with the macro averages of precision, rcall, and F1-score of the three classes as 0.58, 0.70, and 0.59, respectively, while the weighted averages were 0.88, 0.84, and 0.86 after SMOTE application.

• Atmosphere
• /
• v.28 no.3
• /
• pp.263-272
• /
• 2018

The high-resolution ocean surface wind vector produced by scatterometer was assimilated within the Local Ensemble Transform Kalman Filter (LETKF) in Korea Institute of Atmospheric Prediction Systems (KIAPS). The Advanced Scatterometer (ASCAT) on Metop-A/B wind data was processed in the KIAPS Package for Observation Processing (KPOP), and a module capable of processing surface wind observation was implemented in the LETKF system. The LETKF data assimilation cycle for evaluating the performance improvement due to ASCAT observation was carried out for approximately 20 days from June through July 2017 when Typhoon Nepartak was present. As a result, we have found that the performance of ASCAT wind vector has a clear and beneficial effect on the data assimilation cycle. It has reduced analysis errors of wind, temperature, and humidity, as well as analysis errors of lower troposphere wind. Furthermore, by the assimilation of the ASCAT wind observation, the initial condition of the model described the typhoon structure more accurately and improved the typhoon track prediction skill. Therefore, we can expect the analysis field of LETKF will be improved if the Scatterometer wind observation is added.

• Atmosphere
• /
• v.33 no.4
• /
• pp.355-365
• /
• 2023

To proactively manage climate risk, near-term climate predictions on annual to decadal time scales are of great interest to various communities. This study evaluates the near-term climate prediction skills in East Asia with DePreSys4 retrospective decadal predictions. The model is initialized every November from 1960 to 2020, consisting of 61 initializations with ten ensemble members. The prediction skill is quantitatively evaluated using the deterministic and probabilistic metrics, particularly for annual mean near-surface temperature, land precipitation, and sea level pressure. The near-term climate predictions for May~September and November~March averages over the five years are also assessed. DePreSys4 successfully predicts the annual mean and the five-year mean near-surface temperatures in East Asia, as the long-term trend sourced from external radiative forcing is well reproduced. However, land precipitation predictions are statistically significant only in very limited sporadic regions. The sea level pressure predictions also show statistically significant skills only over the ocean due to the failure of predicting a long-term trend over the land.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• International Journal of Internet, Broadcasting and Communication
• /
• v.15 no.3
• /
• pp.58-65
• /
• 2023

Bankruptcy is a significant risk for start-up companies, but with the help of cutting-edge artificial intelligence technology, we can now predict bankruptcy with detailed explanations. In this paper, we implemented the Category Boosting algorithm following data cleaning and editing using OpenRefine. We further explained our model using the Shapash library, incorporating domain knowledge. By leveraging the 5C's credit domain knowledge, financial analysts in banks or investors can utilize the detailed results provided by our model to enhance their decision-making processes, even without extensive knowledge about AI. This empowers investors to identify potential bankruptcy risks in their business models, enabling them to make necessary improvements or reconsider their ventures before proceeding. As a result, our model serves as a "glass-box" model, allowing end-users to understand which specific financial indicators contribute to the prediction of bankruptcy. This transparency enhances trust and provides valuable insights for decision-makers in mitigating bankruptcy risks.