http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
( Haein Keum ),( Guyoung Kang ) 한국응용생명화학회(구 한국농화학회) 2018 Journal of Applied Biological Chemistry (J. Appl. Vol.61 No.4
Hemoglobin (Hb) is a member of heme-protein that can perform catalytic non-specific chain reaction in the presence of hydrogen peroxide (H<sub>2</sub>O<sub>2</sub>). Catalytic ability of Hb to degrade pyrene was demonstrated using soil contaminated with 14C pyrene and 10 mg pyrene /kg soil. The composition of soil was similar to previously used soil except that it had lower organic carbon content. Bench scale laboratory tests were conducted in the presence of buffer only, H<sub>2</sub>O<sub>2</sub> only, or Hb with H<sub>2</sub>O<sub>2</sub> for 24 h. After 24 h reaction, 0.1 and 1.3% of <sup>14</sup>C pyrene in contaminated soil were mineralized with H<sub>2</sub>O<sub>2</sub> only or Hb plus H<sub>2</sub>O<sub>2</sub>. No mineralization to <sup>14</sup>CO<sub>2</sub> was detected with buffer only. Approximately 12.2% of pyrene was degraded in the presence of H<sub>2</sub>O<sub>2</sub> only while 44.0% of pyrene was degraded in the presence of Hb plus H<sub>2</sub>O<sub>2</sub> during 24 h of catalytic reaction. When degradation intermediate products were examined, two chemicals were observed in the presence of H<sub>2</sub>O<sub>2</sub> only while 25 chemicals were found in the presence of Hb plus H<sub>2</sub>O<sub>2</sub>. While most degradation products were simple hydrocarbons, four of the 27 chemicals had aromatic rings. However, none of these four chemicals was structurally related to pyrene. These results suggest that Hb catalytic system could be used to treat pyrene-contaminated soil as an efficient and speedy remediation technology. In addition, intermediate products generated by this system are not greatly affected by composition change in soil organic matter content.
Prediction of Corporate Bankruptcy with Machine Learning
Haein Lee,Byunghoon Yu,Jang Hyun Kim,Heungju Park 한국재무학회 2022 한국재무학회 학술대회 Vol.2022 No.11
This study examines the predictability of various machine learning and deep learning models in corporate default forecasts. Using a sample of U.S. corporate defaults over the period of 1963-2020, we find Ensemble classifier and Bi-LSTM classifier forecast the corporate bankruptcy better than other models and the predictability of the Ensemble classifier is more stable in year-to-year variability. Further, machine learning models outperform deep learning models in high yield grade samples, while deep learning models performs better than machine learning models in investment grade samples.
Haein Lee,Hae Sun Jung,Seon Hong Lee,Jang Hyun Kim 한국인터넷정보학회 2023 KSII Transactions on Internet and Information Syst Vol.17 No.9
Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as “Metaverse” keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.