http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
UnityPGTA : 강화학습을 이용한 유니티 플랫포머 게임의 테스팅 자동화 도구
박세찬,김덕엽,이우진 한국정보과학회 2024 정보과학회논문지 Vol.51 No.2
The cost of game testing in the video game industry is significant, accounting for nearly half of the expenses. Research efforts are underway to automate testing processes to reduce testing costs. However, existing research on test automation often involves manual tasks such as script writing, which is costly and labor-intensive. Additionally, implementations using virtual environments like VGDL and GVG-AI pose challenges when applied to real game testing. In this paper, we propose a tool for automating game testing with the aim of system fault detection, focusing on a Unity platformer game. The proposed tool is based on a commercial game engine, autonomously analyzing the game without human intervention to establish an automated game testing environment. We compare and analyze the error detection results of the proposed tool with a random baseline model using open-source games, demonstrating the tool's effectiveness in performing automated game analysis and testing environment setup, ultimately reducing testing costs and improving quality and stability.
수치해석을 활용한 지하역사 기류분포 및 PM10 농도분포 연구
박세찬,권순박,김민해,이용갑 한국냄새환경학회 2019 실내환경 및 냄새 학회지 Vol.18 No.1
To reduce subway passengers’ exposure to PM10 (particulate matter less than 10 micrometers), management ofPM10 concentration in underground stations is critical. In this study, we attempted to investigate the distributionof airflow PM10 concentration in an underground station. The numerical simulations were performed usingcomputational fluid dynamics. In order to apply to CFD, measurement of air volume (supplied and exhausted air)and PM10 concentration were conducted at the concourse and platform areas of the underground station. The resultsof the simulation agreed with the actual PM10 concentration, and we confirmed the distribution of PM10concentration depending on air volume conditions. This result will be helpful to reduce the PM10 in an undergroundstation when using ventilation system.
Passive Sampler를 이용한 석유화학단지 주변 지역 VOCs의 공간분포 특징 연구
박세찬,김정호,이가혜,노수진,채정석,김민영,전준민,이상신,김종범 한국대기환경학회 2022 한국대기환경학회지 Vol.38 No.5
The northern region of Chungcheongnam-do is located in several large-scale industrial facilities. The region of Daesan has a large-scale petrochemical complex, accounting for 7.3% of the nation’s total VOCs(volatile organic compounds, VOCs) emission. In this study, VOCs were measured at 31 locations in the Daesan area using a passive sampler; VOCs concentration distribution by area and the influence of the different seasons on the VOCs in the area were investigated. The result of seasonal measurement of VOCs, the highest concentration was measured in winter (18.6 ppb), summer (12.0 ppb), and spring and autumn (10.5 ppb). Benzene and toluene accounted for 69.1 to 72.7% of the VOCs concentration regardless of the season. The result of investigating the affected area based on the benzene measurement, high concentrations of VOCs were identified in a specific area. Although the distance from the pollutant source is important, it was confirmed that the diffusion depends on the wind direction, wind speed and topography. In order to improve the problems of highconcentration VOC areas, continuous monitoring and national policies will be required.
생분해성 섬유 방사 공정 데이터 특성을 고려한 물성 예측 모델 개발
박세찬 ( Sechan Park ),김덕엽 ( Deok Yeop Kim ),서강복 ( Kang Bok Seo ),이우진 ( Woo Jin Lee ) 한국정보처리학회 2022 한국정보처리학회 학술대회논문집 Vol.29 No.1
최근 노동 집약적인 성격의 섬유 산업에서는 AI를 통해 공정에 들어가는 시간과 비용을 줄이고 품질을 최적화 하려는 시도를 하고 있다. 그러나 섬유 방사 공정은 데이터 수집에 필요한 비용이 크고 체계적인 데이터 처리 시스템이 부족하여 축적된 데이터양이 적다. 또 방사 목적에 따라 특정 변수 위주의 조합에 대한 데이터만을 우선적으로 수집하여 데이터 불균형이 발생하며, 물성 측정환경차이로 인해 동일 방사조건에서 수집된 샘플 간에도 오차가 존재한다. 이러한 데이터 특성들을 고려하지 않고 AI 모델에 활용할 경우 과적합과 성능 저하 등의 문제가 발생할 수 있다. 따라서 본 논문에서는 물성 단위 및 허용오차를 고려한 이상치 처리 기법과 데이터 불균형 정도 및 물성과의 상관성을 고려한 오버샘플링 기법을 물성 예측 모델에 적용한다. 두 기법들을 모델에 적용한 결과 그렇지 않은 모델에 비해 물성 예측 오차와 방사 공정 데이터에 대한 모델의 적합도가 개선됨을 보인다.
데이터 불균형과 측정 오차를 고려한 생분해성 섬유 인장 강신도 예측 모델 개발
박세찬 ( Se-chan Park ),김덕엽 ( Deok-yeop Kim ),서강복 ( Kang-bok Seo ),이우진 ( Woo-jin Lee ) 한국정보처리학회 2022 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.11 No.12
Recently, the textile industry, which is labor-intensive, is attempting to reduce process costs and optimize quality through artificial intelligence. However, the fiber spinning process has a high cost for data collection and lacks a systematic data collection and processing system, so the amount of accumulated data is small. In addition, data imbalance occurs by preferentially collecting only data with changes in specific variables according to the purpose of fiber spinning, and there is an error even between samples collected under the same fiber spinning conditions due to difference in the measurement environment of physical properties. If these data characteristics are not taken into account and used for AI models, problems such as overfitting and performance degradation may occur. Therefore, in this paper, we propose an outlier handling technique and data augmentation technique considering the characteristics of the spinning process data. And, by comparing it with the existing outlier handling technique and data augmentation technique, it is shown that the proposed technique is more suitable for spinning process data. In addition, by comparing the original data and the data processed with the proposed method to various models, it is shown that the performance of the tensile tenacity and elongation prediction model is improved in the models using the proposed methods compared to the models not using the proposed methods.