최근 소프트웨어 유통망(ESD)를 통해 유통되는 게임이 늘어남에 따라 사용자들이 원하는 게임을 찾는데 어려움을 겪고 있다. 이에 따라 사용자들이 원하는 게임을 찾기 쉽게 태그를 생성하는 모델의 필요성이 대두 되고 있다. 본 논문에서는 태그를 생성하는 모델을 BERT를 통해 설계하였다. 태그 100개 중 가장 적합한 태그를 4개 추출하기 위해 입력된 문장에 대해 각 태그별로 이진분류를 수행하고 이진분류 당시의 Softmax 값이 가장 컸던 태그 4개를 선택했다. 또한, 모델의 정확도를 위해서 약 33억 개의 다국어 단어로 학습한 pre-trained Multilingual BERT 모델과 약 5천만 개의 한국어 단어로 학습한 KoBERT 모델을 가져와 한국어 데이터로 학습(finetuning) 시켜 사용하였다. 실험에서 BERT 모델은 KoBERT 모델보다 F- 점수에서 9.19 % 더 나은 성능을 보입니다. 이는 언어 학습 데이터 세트의 크기가 특정 언어인 한국어 특성보다 더 중요하다는 것을 나타낸다.

This study studied a system that can redesign the production site layout and respond with dynamic simulation through fabric production process innovation for smart factory promotion and digital-oriented decision making of the production process. We propose to reflect the required throughput and throughput per unit facility of fabric production process as probability distribution, and to construct data-driven metabolism such as data collection, data conversion processing, data rake generation, production site monitoring and simulation utilization. In this study, we demonstrate digital-centric field decision smartization through architectural design for the smartization of fabric production plants and dynamic simulations that reflect it.

The Ozone Dynamics Investigation Nano-Satellite (ODIN) is a CubeSat design proposed by Chungnam National University as contribution to the CubeSat Competition 2019 sponsored by the Korean Aerospace Research Institute (KARI). The main objectives of ODIN are (1) to observe the polar ozone column density (latitude range of 60 to 80 in both hemispheres) and (2) to investigate the chemical dynamics between stratospheric ozone and ozone depleting substances (ODSs) through spectroscopy of the terrestrial atmosphere. For the operation of ODIN, a highly ecient power system designed for the specic orbit is required. We present the conceptual structural design of ODIN and an analysis of power generation in a sun synchronous orbit (SSO) using two dierent congurations of 3U solar panels (a deployed model and a non-deployed model). The deployed solar panel model generates 189.7 W through one day which consists of 14 orbit cycles, while the non-deployed solar panel model generates 152.6 W. Both models generate enough power for ODIN and the calculation suggests that the deployed solar panel model can generate slightly more power than the non-deployed solar panel model in a single orbit cycle. We eventually selected the non-deployed solar panel model for our design because of its robustness against vibration during the launch sequence and the capability of stable power generation through a whole day cycle.