http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Hakkyung Lee (검색결과 5 건)
- 무료
- 기관 내 무료
- 유료
-
무선센서 네트워크를 이용한 지하광산 내 환경 모니터링과 통신 시스템의 연구 동향 분석 및 고찰
이승준(Seungjun Lee),박요한(Yohan Park),이학경(Hakkyung Lee),김진(Jin Kim) 한국암반공학회 2018 터널과지하공간 Vol.28 No.3
지하광산 내 심각한 사고가 전 세계적으로 끊임없이 발생하고 있다. 작업자의 생명과 건강을 확보하고 생산성을 향상시키기 위해서 최근 갱내 무선센서 네트워크 기반 환경 모니터링 및 통신 시스템의 구축을 위한 수많은 연구가 진행되고 있다. 국내에서도 최근 정보통신기술의 도입으로 이러한 시스템의 개발 및 구축 사례가 증가하기 시작했지만 갱내통기를 고려한 환경 모니터링에 대한 국내연구는 미비하다. 본 연구에서는 갱내 무선센서 네트워크의 구축 및 환경 모니터링에 관련한 해외의 다양한 연구 동향을 분석하였고, 특히 환경 모니터링 시스템의 갱내통기와 관련한 7가지 세부 주제에 대하여 고찰하였다. 또한 실시간 모니터링을 수행한 연구의 동향을 통기 네트워크 해석에 활용되는 상용 소프트웨어 별로 정리하여 고찰하였다. 본 연구를 통해 국내광산에 적용하기 위해 추후 연구가 필요한 주제와 국내에 적용 중인 갱내환경 기준에 대해 논의하였다. 본 논문은 국내 지하광산 내 무선센서 네트워크 기반의 환경모니터링과 통신 시스템의 구축과 관련한 향후 연구에 도움이 될 것으로 기대된다. Severe mine disasters have continued to occur around the world. To ensure worker’s health and safety and enhance the productivity, a number of studies have been conducted for the development of wireless sensor network (WSN), environmental monitoring, and communication system in underground mines. An increase in development and application of these systems has just begun with the introduction of information and communication technology into the mining industry in Korea, and yet there have been only a few studies that considered the underground mine ventilation system. This study presented the literature review on the development of WSN and environmental monitoring in underground mines, and especially, on 7 subjects in terms of underground mine ventilation. Moreover, studies that especially conducted real-time environmental monitoring were reviewed and categorized by each commercial software commonly utilized for the ventilation network analysis. For the application in domestic underground mines, further issues were discussed regarding research subjects that may be needed in the future and domestic environmental standards that has been used in the underground mine operation. This paper is expected to be useful for the development of WSN-based environmental monitoring and communication system, as well as for related studies in the future.
-
-
앙상블 기법을 활용한 대형복합건축물의 화재 피난가능시간 예측에 관한 해석적 연구
이두희(DooHee Lee),김학경(HakKyung Kim),김전수(Jeon Soo Kim),황현수(Hyun Soo Hwang),최두찬(DooChan Choi) 한국방재학회 2022 한국방재학회논문집 Vol.22 No.5
최근 건축물의 화재위험도가 높아짐에 따라 화재발생 시 많은 인명피해가 발생하고 있으며, 성능위주설계의 중요성이 강조되고있나. 그러나 성능위주 소방설계를 위한 시뮬레이션의 경우, 많은 인력 및 시간이 소요되며 경미한 변경에도 다시 수행해야하는 어려움이 있다. 따라서 본 연구에서는 앙상블기법을 적용하여 화재거리 별 허용피난시간을 화재인자 및 공간인자로쉽게 예측할 수 있는 예측모델을 개발하고자 하였다. FDS 데이터에 기반하여 기계학습을 통해 개발한 예측모델은 결정계수가0.91에 달하는 높은 예측률을 보였으며, 이러한 예측모델을 적용하여 실시간으로 거리별 ASET을 도출할 수 있을 것으로판단된다. With the recent increase in the risk of fire in buildings, the number of casualties that occur in the event of a fire have increased. This emphasizes the importance of performance-based design. However, simulating a performance-based design requires a lot of manpower and time, and re-simulation with minor changes is a difficult task. Therefore, in this study, we attempt to develop a prediction model that can easily predict the ASET for each fire distance as a fire factor and spatial factor by applying ensemble learning. The prediction model developed using machine learning based on FDS data showed a high coefficient of determination of 0.91, and we believe that ASET for each distance can be derived in real time by applying this prediction model.
-
Hanwool Park,Yechan Yoo,Yoonjin Park,Changdae Lee,Hakkyung Lee,Injung Kim,Kang Yi 한국정보과학회 2018 Journal of Computing Science and Engineering Vol.12 No.1
Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.
-
Park, Hanwool,Yoo, Yechan,Park, Yoonjin,Lee, Changdae,Lee, Hakkyung,Kim, Injung,Yi, Kang Korean Institute of Information Scientists and Eng 2018 Journal of Computing Science and Engineering Vol.12 No.1
Deep convolutional neural network (DCNN) is an advanced technology in image recognition. Because of extreme computing resource requirements, DCNN implementation with software alone cannot achieve real-time requirement. Therefore, the need to implement DCNN accelerator hardware is increasing. In this paper, we present a field programmable gate array (FPGA)-based hardware accelerator design of DCNN targeting handwritten Hangul character recognition application. Also, we present design optimization techniques in SDAccel environments for searching the optimal FPGA design space. The techniques we used include memory access optimization and computing unit parallelism, and data conversion. We achieved about 11.19 ms recognition time per character with Xilinx FPGA accelerator. Our design optimization was performed with Xilinx HLS and SDAccel environment targeting Kintex XCKU115 FPGA from Xilinx. Our design outperforms CPU in terms of energy efficiency (the number of samples per unit energy) by 5.88 times, and GPGPU in terms of energy efficiency by 5 times. We expect the research results will be an alternative to GPGPU solution for real-time applications, especially in data centers or server farms where energy consumption is a critical problem.
ScienceON
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
