• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.1
• /
• pp.280-294
• /
• 2023

Unmanned aerial vehicles (UAVs) and millimeter-wave frequencies play key roles in supporting 5G wireless communication systems. They expand the field of wireless communication by increasing the data capacities of communication systems and supporting high data rates. However, short wavelengths, owing to the high millimeter-wave frequencies can cause problems, such as signal attenuation and path loss. To address these limitations, research on high directional beamforming technologies continue to garner interest. Furthermore, owing to the mobility of the UAVs, it is essential to track the beam angle accurately to obtain full beamforming gain. This study presents a beam tracking method based on the unscented Kalman filter using hybrid beamforming. The simulation results reveal that the proposed beam tracking scheme improves the overall performance in terms of the mean-squared error and spectral efficiency. In addition, by expanding analog beamforming to hybrid beamforming, the proposed algorithm can be used even in multi-user and multi-stream environments to increase data capacity, thereby increasing utilization in new-radio multiple-input multiple-output orthogonal frequency-division multiplexing systems.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.135-135
• /
• 2020

우리나라의 기후 자료는 일반적으로 기상청에서 발표하는 종관기상관측(ASOS)과 방재기상관측(AWS), 그리고 북한이 세계기상기구(WMO, World Meteorogical Organization)의 기상통신망(GTS)을 통해 보낸 북한기상관측(NKO)을 사용 할 수 있다. 그러나 이 중 40년 이상의 완전한 관측 자료를 얻을 수 있는 건 ASOS가 유일하지만 공간적인 표현에 한계를 갖고 있다. AWS는 관측소가 많다는 장점이 있지만 관측 기간이 길지 않고 이용 가능한 기간에도 관측이 연속적이지 못한 경우가 많다. NKO는 비록 27개의 관측소가 있지만 많은 데이터가 누락되어 일별 기후자료의 사용에 한계를 갖고 있다. 이러한 미관측 기간이나 관측 자료의 누락은 연속적인 시계열 자료분석을 기반으로 하는 수자원 모델링에 있어서 문제를 야기한다. 본 연구는 1973년부터 2019년까지 47년의 신뢰도 높은 한반도 일일 기후 자료를 구축하기 위해 다양한 방법론을 비교하였다. 추정에 사용한 방법은 총 7개로 EM algorithm for probabilistic principal components (PPCA-EM), Inverse distance weight method (IDWM), Nearest neighbor method (NNM), Multivariate normal copulas (Copula), Elastic net model (Elastic), Ordinary kriging (OK), Regularized principal components with EM algorithm (RPCA-EM)를 살펴보았다. 다양한 형태의 결측치를 가정하여 그 결과값을 비교하였고 이는 Root mean squared error(RMSE), Kling-Gupta efficiency(KGE), Nash-Sutcliffe efficiency(NSE)를 통해 평가하였다. 최종 선택된 방법론을 통하여 한반도 전역을 그리드 기반의 강수 및 최저온도/최고온도의 일별자료로 생성하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.105-105
• /
• 2021

본 연구에서는 2차원 비선형 천수모형과 수심평균된 스칼라 이송모형을 해석하는 수치모형에 대해 기술하였다. 수치모형의 정확성을 보장함과 동시에 안정성을 높이기 위해 유한체적법, 플럭스 재구성 및 minmod 제한자를 사용하였다. 비선형 천수방정식의 이송항과 바닥 경사항은 계산된 수심의 양수 보존과 흐름의 정상 상태를 보장하기 위한 second order well-balanced positivity preserving central-upwind method를 이용하여 수치적으로 이산화되었다. 마찬가지로, 이송-확산 방정식 내 이송항은 동일한 2차 풍상차분법을 통해 수치적으로 풀이하였다. 격자점 경계면에서의 불연속으로 인한 수치진동을 방지하기 위해 이송항의 계산에 포함된 보존항의 차이로 인해 발생하는 스칼라의 수치확산을 최소화하기 위해 무차원의 비소산함수를 도입하였다. 또한, 확산항은 유한차분법을 이용하여 이산화하였다. 제안된 수치모형은 시간미분항의 계산을 위해 오일러 기법을 적용하여 계산된 수심 및 스칼라의 양수 보존여부와 함께 정지된 흐름의 정상 상태의 보존여부를 확인하였다. 제안된 수치모형의 해석 정확성을 평가하기 위해 1, 2차원 공간 내 다양한 흐름 조건에서의 해석해를 이용한 3개의 벤치마크 테스트를 수행하였다. 평균 제곱근 오차(Root Mean Squared Error, RMSE)를 산정하여 수치모형의 성능을 정량적으로 평가하였으며, 비소산함수를 적용함에 따라 스칼라의 수치확산이 감소하게 되었음을 확인하였다. 또한, 세 차례의 벤치마크 테스트 결과는 공통적으로 수치모형에 의해 계산된 결과값이 비소산함수를 고려함에 따라 해석해와 잘 일치함을 확인하였다.

• Transactions of Materials Processing
• /
• v.32 no.2
• /
• pp.74-80
• /
• 2023

A deformation behavior of commercially pure titanium (CP-Ti) is highly dependent on material and processing parameters, such as deformation temperature, deformation direction, and strain rate. This study aims to predict the multivariable and nonlinear tensile behavior of CP-Ti using machine learning based on three algorithms: artificial neural network (ANN), light gradient boosting machine (LGBM), and long short-term memory (LSTM). The predictivity for tensile behaviors at the cryogenic temperature was lower than those in the room temperature due to the larger data scattering in the train dataset used in the machine learning. Although LGBM showed the lowest value of root mean squared error, it was not the best strategy owing to the overfitting and step-function morphology different from the actual data. LSTM performed the best as it effectively learned the continuous characteristics of a flow curve as well as it spent the reduced time for machine learning, even without sufficient database and hyperparameter tuning.

• The Journal of shipping and logistics
• /
• v.35 no.1
• /
• pp.93-109
• /
• 2019

This study applied the statistically significant factors to the short-run model in the existing nonlinear long-run equilibrium relation analysis for the forecasting of maritime economy using the mixed cycle model. The most common univariate AR(1) model and out-of-sample forecasting are compared with the root mean squared forecasting error from the mixed-frequency model, and the prediction power of the mixed-frequency approach is confirmed to be better than the AR(1) model. The empirical results from the analysis suggest that the new approach of high-level mixed frequency model is a useful for forecasting marine industry. It is consistent that the inclusion of more information, such as higher frequency, in the analysis of long-run equilibrium framework is likely to improve the forecasting power of short-run models in multivariate time series analysis.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.321-322
• /
• 2023

본 논문에서는 Scikit-learn 패키지의 LinearRegression 모델과 Keras 딥러닝 모델을 활용하여 수도권 도시 환경 요인에 따른 범죄 발생 건수를 예측 모델을 제안한다. 연구 방법으로 범죄 발생과 유의미한 관계가 있다고 파악되는 수도권의 각 자치구 별 데이터셋을 분석하여, CCTV, 파출소, 가로등의 수가 범죄 발생에 유의미한 영향을 끼치는 것을 확인하였다. 독립 변수들 간에 Scale을 줄이고자 정규화를 진행했고, 종속변수의 정규성 확보를 위해 로그변환을 취했다. 손실 함수는 회귀문제에서 사용되는 'relu'함수를 사용했고 모델의 성능을 확인할 수 있는 지표로 MSE(Mean Squared Error)를 사용해 모델을 구성하였다. 본 논문에서 설계한 이 프로그램은 범죄 발생율이 높은 지역구에 경찰 인력의 추가적 배치, 안전 시설 확충 등 실무적 조치를 취함에 있어 근거를 제공할 수 있을 것으로 사료된다.

• Korean Journal of Construction Engineering and Management
• /
• v.24 no.6
• /
• pp.81-90
• /
• 2023

Climate change has resulted in increased frequency and intensity of heat waves, which poses a significant threat to the health and safety of construction workers, particularly those engaged in labor-intensive and heat-stress vulnerable working environments. To address this challenge, this study aimed to propose an interpretable machine learning approach for forecasting personal heat strain by considering the cumulative effect of heat exposure as a situational variable, which has not been taken into account in the existing approach. As a result, the proposed model, which incorporated the cumulative working time along with environmental and personal variables, was found to have superior forecast performance and explanatory power. Specifically, the proposed Multi-Layer Perceptron (MLP) model achieved a Mean Absolute Error (MAE) of 0.034 (℃) and an R-squared of 99.3% (0.933). Feature importance analysis revealed that the cumulative working time, as a situational variable, had the most significant impact on personal heat strain. These findings highlight the importance of systematic management of personal heat strain at construction sites by comprehensively considering the cumulative working time as a situational variable as well as environmental and personal variables. This study provided a valuable contribution to the construction industry by offering a reliable and accurate heat strain forecasting model, enhancing the health and safety of construction workers.

• Journal of Information Technology Applications and Management
• /
• v.30 no.6
• /
• pp.91-111
• /
• 2023

This study aims to identify the influencing factors of intention to use cloud services using the SEM-ANN two-step approach. In previous studies of SEM-ANN, SEM presented R² and ANN presented MSE(mean squared error), so analysis performance could not be compared. In this study, R² and MSE were calculated and presented by SEM and ANN, respectively. Then, analysis performance was compared and feature importances were compared by sensitivity analysis. As a result, the ANN default model improved R² by 2.87 compared to the PLS model, showing a small Cohen's effect size. The ANN optimization model improved R² by 7.86 compared to the PLS model, showing a medium Cohen effect size. In normalized feature importances, the order of importances was the same for PLS and ANN. The contribution of this study, which links structural equation modeling to artificial intelligence, is that it verified the effect of improving the explanatory power of the research model while maintaining the order of importance of independent variables.