http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
건설공사 공종별 사고유형 및 사고객체 교차분석을 통한 중점안전관리항목 도출
유나영 ( Yoo Nayeong ),김하림 ( Kim Harim ),이찬우 ( Lee Chanwoo ),조훈희 ( Cho Hunhee ) 한국건축시공학회 2022 한국건축시공학회 학술발표대회 논문집 Vol.22 No.1
The construction industry has a higher disaster rate than other industries, so safety education and management are highly important. In order to reduce the construction accident rate, it is necessary to study the key safety management factors reflecting the characteristics of the construction industry, where there are differences in processes and manpower input for each process, and a small number of managers. Therefore, in this study, key safety management factors for each Process of construction were derived through cross-analysis between safety accident types and accident occurrence objects through disaster case data. The extracted key safety management factors are expected to provide useful information for safety education and supervision of construction sites.
서유민(Youmin Seo),안차민(Chamin Ahn),유나영(Nayeong Yoo),이선혜(Seonhye Lee),홍현석(Hyeonseok Hong),김현(Hyun Kim) 대한전자공학회 2023 대한전자공학회 학술대회 Vol.2023 No.11
In recent years, large-scale events and festivals face the potential for critical incidents. To prevent these incidents, CNN-based crowd-counting systems with high accuracy, such as CSRNet, are proposed. However, their extensive parameter size limits its application on mobile and edge devices. To solve this problem, RTL-based AI accelerators, which design processing engines optimized for AI models, are attracting a attention as an alternative platform to GPU due to their advantages of low power and lost cost. This paper proposes a CNN-based crowd counting system by designing CSRNet on the FPGA platform. In terms of algorithm optimization, we applied pruning and quantization to CSRNet to reduce the parameter size, and in terms of hardware design, we applied loop unrolling and dataflow optimization to parallelize operations and conducted a design based on data reuse patterns. As a result of Xilinx Ultrascale+ MPSoC ZCU102 implementation, the proposed IP uses only 24.92% of LUTs, 2.88% of FFs, and 3.17% of DSPs while offering advantages in terms of low power consumption and cost-effectiveness compared to GPUs.