1 January 2012 in Psychiatry Investigation
Lee JS, et al. Psychiatry Investig. 2012 Jun;9(2):187-190. http://dx.doi.org/10.4306/pi.2012.9.2.187
31 January 2024 in The Journal of Korean Institute of Information Technology
머신러닝에 중요한 데이터 셋의 구성과 품질을 올리는 기술인 데이터 증강은 적은 양의 데이터를 바탕으로 다양한 알고리즘을 통해 데이터의 양을 늘리는 기술이다. 본 연구에서는 대규모 언어 모델인 GPT(Generative Pre-trained Transformer)를 활용한 데이터 증강으로 감정 분석 모델의 성능을 향상시키는 방법을 제안하고 평가한다. 데이터 셋의 클래스 불균형 문제를 해결하기 위해 가중치를 적용한 로직을 사용하였고, 생성된 데이터의 품질 및 다양성에 대한 한계를 극복하기 위해 프롬프트 엔지니어링을 적용했다. 실험결과, 제안한 방법은 데이터의 품질을 유지하면서 다양성을 높이고, 클래스 불균형 문제를 효과적으로 해결할 수 있어 KoBERT 모델을 이용해 GPT를 활용한 데이터 증강이 모델의 성능을 향상시킬 수 있음을 보였다.
30 August 2019 in Korean Journal of Food Preservation
The aim of this study was to develop a loess-coated ripening system for Gouda cheese. The quality characteristics of the coated Gouda cheese one and two months after the ripening were compared. The moisture content of loess was the lowest in white clay (WL). The antifungal effect of WL was slightly higher than that of the other samples. It was confirmed that the heavy metal content in the loess was within the soil pollution concern standard and countermeasure standard. The content of NH3-N was the lowest at 143.51 mg% in WL followed by 204.88 mg% in red loess (RL). Gouda cheese is a hard cheese. In the present study, the moisture content after 60 days of ripening was within the range for WG (WL-coated Gouda cheese after ripening) only. During ripening, the pH and titratable acidity of the cheese increased in all samples. The mineral contents of the cheese increased in the order of Na, Ca, Mg, and K. The NH3-N content of the LG (laterite-coated Gouda cheese after ripening) was lowest after 60 days of ripening. The WG showed the greatest reduction in NH3-N content from 30 to 60 days of ripening. The heavy metal content in the Gouda cheeses coated with loess and ripening was within the food standard range.
30 November 2021 in Journal of Tourism and Leisure Research
Data analysis has recently become a big trend in modern society, which naturally gave rise to the term of data science. In particular, in the era of big data, the importance of scientific decision-making and policy implementation, to make decisions and strategies using data, will continue to increase in the field of tourism. In this situation, interest in R as an alternative to SPSS is increasing significantly. As a free open source program, R is excellent in package extensibility, the introduction of the latest techniques, data visualization, and reproducible research, so it can be usefully employed in data analysis in tourism. In tourism field, R is expected to be actively used while sufficiently replacing SPSS. R would be one of the good choices to deal with statistics more broadly and to bring scalability in many academic fields, including tourism.