소련군 헬리콥터와 운용

남충희,Nam, Chung-Hui 한국방위산업진흥회 1984 國防과 技術 Vol.- No.12

Pulmonary Sequestration [2례 보고]

남충희 대한흉부심장혈관외과학회 1981 Journal of Chest Surgery (J Chest Surg) Vol.14 No.4

The pulmonary sequestration is an uncommon congenital anomaly characterized by the presence of a part of lung tissue which is supplied by an aberrant artery from the aorta or its branch and usually has no communication with the normal bronchial tree. It was first presented by Hubber in 1777 and presented in details by Pryce in 1946. We present a case of extralobar pulmonary sequestration experienced recently with a case of intralobar type experienced in 1962. The patient was 11 year old male with the complaint of chronic productive cough. Serial chest films showed a large cyst with or without the air-fluid level on the posterobasal segment area of the left lower lobe. Bronchography showed no definite communication between the cyst and bronchial tree. On operation, the cystic lesion was supplied by an aberrant artery from the descending thoracic aorta 5 cm above the aortic hiatus and was sited at the posterobasal segment area of the left lower lobe. We performed the sequestrectomy and the sequestration was surrounded by its own pleura, 6.8x3.9x3.2 cm in size, contained the pale brown mucoid secretion in a large cyst and showed the primitive alveolar structure of the wall. The aberrant artery was 1 -5 cm long, 0.3 mm in internal diameter and arterio-sclerotic. We also compared 6 cases of collection, 5 intralobar and 1 extralobar type, presented in Korea.

머신러닝을 이용한 화합물 조성기반 초경질 소재 특성 예측

남충희 대한금속·재료학회 2022 대한금속·재료학회지 Vol.60 No.8

In this study, the mechanical properties of materials were predicted using machine learning to search for superhard materials. Based on an AFOW database consisting of DFT quantum calculation values, the mechanical properties of materials were predicted using various machine learning models. For supervised learning, the entire data was divided into training data and test data at a ratio of 8:2. Since the discovery of superhard materials can be predicted based on the bulk modulus and shear modulus, the bulk modulus was primarily predicted using only the chemical compositional ratio (chemical formula), and then the shear modulus was obtained using the predicted bulk moduli. To obtain good prediction performance, crossvalidation and hyper-parameter tuning were carried out. Each characteristic was predicted using XGBoost, one of the ensemble algorithms, and its performance was compared to the tree-based machine learning of RandomForest and Support Vector Machine regression using the coefficient of determination (R2) and rootmean- square-error (RMSE) as metrics. For the recently introduced four superhard materials (Mo0.9W1.1BC, ReWC0.8, MoWC2, and ReWB), the results of this study were similar to those of previous studies including the experimental values o r the DFT quantum calculations. The shear modulus was underpredicted, which can be understood since structural properties were not considering as a feature in our machine learning models.

머신러닝을 이용한 자성 소재의 포화 자화값 예측

남충희 한국자기학회 2022 韓國磁氣學會誌 Vol.32 No.6

Material design using machine learning is being used in various fields. In this study, along with the material properties calculated through the density functional theory (DFT), material’s features were obtained using only the chemical composition ratio using the python module of ‘Matminer’ and applied to machine learning. Based on the data of 164 magnetic materials from the Citrine database, the saturation magnetization value was predicted through three regression models of support-vector-machine, RandomForest, and XGBoost. Model optimization was performed through cross-validation and hyper-parameter tuning, and among the three models, XGBoost showed the best prediction performance. As for performance indicators, the R2 score and root-mean-square-error, which are mainly used in regression analysis, were used to compare and analyze the performance of the model. Finally, predictions were made for Fe (iron) that was not in the database, and it was confirmed that the more characteristic factors in machine learning, the better the performance.

앙상블 기계학습 모델을 이용한 비정질 소재의 효과 및 전이온도 예측

남충희 한국재료학회 2024 한국재료학회지 Vol.34 No.7

In this study, the magnetocaloric effect and transition temperature of bulk metallic glass, an amorphous material, were predicted through machine learning based on the composition features. From the Python module ‘Matminer’, 174 compositional features were obtained, and prediction performance was compared while reducing the composition features to prevent overfitting. After optimization using RandomForest, an ensemble model, changes in prediction performance were analyzed according to the number of compositional features. The R2 score was used as a performance metric in the regression prediction, and the best prediction performance was found using only 90 features predicting transition temperature, and 20 features predicting magnetocaloric effects. The most important feature when predicting magnetocaloric effects was the ‘Fe’ compositional ratio. The feature importance method provided by ‘scikit-learn’ was applied to sort compositional features. The feature importance method was found to be appropriate by comparing the prediction performance of the Fe-contained dataset with the full dataset.

시장개방을 맞은 건설업계의 대응방안

남충희 대한기계설비건설협회 1994 기계설비 Vol.44 No.-

딥러닝을 이용한 나노소재 투과전자 현미경의 초해상 이미지 획득

남충희 한국재료학회 2022 한국재료학회지 Vol.32 No.8

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256  256 pixels (high resolution: HR) from TEM measurements and 32  32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO4 nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.

인공신경망을 이용한 벌크 비정질 합금 소재의 포화자속밀도 예측 성능평가

남충희 한국재료학회 2023 한국재료학회지 Vol.33 No.7

In this study, based on the saturation magnetic flux density experimental values (Bs) of 622 Fe-based bulk metallic glasses (BMGs), regression models were applied to predict Bs using artificial neural networks (ANN), and prediction performance was evaluated. Model performance evaluation was investigated by using the F1 score together with the coefficient of determination (R2 score), which is mainly used in regression models. The coefficient of determination can be used as a performance indicator, since it shows the predicted results of the saturation magnetic flux density of full material datasets in a balanced way. However, the BMG alloy contains iron and requires a high saturation magnetic flux density to have excellent applicability as a soft magnetic material, and in this study F1 score was used as a performance indicator to better predict Bs above the threshold value of Bs (1.4 T). After obtaining two ANN models optimized for the R2 and F1 score conditions, respectively, their prediction performance was compared for the test data. As a case study to evaluate the prediction performance, new Fe-based BMG datasets that were not included in the training and test datasets were predicted using the two ANN models. The results showed that the model with an excellent F1 score achieved a more accurate prediction for a material with a high saturation magnetic flux density.

기계학습을 이용한 밴드갭 예측과 소재의 조성기반 특성인자의 효과

남충희 한국재료학회 2023 한국재료학회지 Vol.33 No.4

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.

벌크금속유리 합금의 자기냉각효과 예측을 위한 유전 알고리즘 기반 기계학습 모델 최적화

남충희 한국자기학회 2024 한국자기학회지 Vol.34 No.5

본 연구에서는 벌크금속유리 소재의 자기냉각 효과값을 예측하기 위해서 XGB 모델을 이용하였다. 파이썬 모듈인 ‘Pymatgen’과 ‘ M atminer’를 통해서 조성기반 특성인자 174개를 얻었으며 과대적합을 줄이기 위해서 적절한 특성인자를 탐색하는 방법을 적용하였다. 첫번째 Pearson correlation coefficient를 확인하여 상관 관계가 높은 특성인자를 줄여 104개의 특성인자를 얻었다. 두번째 XGB 모델에서 제공하는 특성인자 중요도 방법을 통해서 회귀성능 결과를 바탕으로 40개의 주요 특성인자를 찾았다. 마지막으로 2단계 유전알고리즘을 통해서 최종 12개의 최적화된 특성인자를 찾았으며 이를 통해서 과대적합을 방지하고 향상된 자기냉각효과 예측성능을 확인할 수 있었다. This study used an XGB model to predict the magnetocaloric effect values of bulk metallic glass materials. A total of 174 composition-based features were obtained using the Python modules ‘Pymatgen’ and ‘Matminer’, and a feature selection method was applied to reduce overfitting. First, by examining the Pearson correlation coefficient, we reduced the number of features with high correlations, resulting in 104 features. Second, using the feature importance method provided by the XGB model, 40 key features were identified based on the regression performance results. Finally, through a two-stage genetic algorithm, 12 optimized features were selected, which helped prevent overfitting and improve the prediction performance of the magnetocaloric effect.