http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
샴 네트워크 기반의 적은 데이터셋을 이용한 유사한 형태의 특정 객체 인식 연구
곽정훈,양견모,이종일,김민규,서갑호 제어·로봇·시스템학회 2022 제어·로봇·시스템학회 논문지 Vol.28 No.9
Target object recognition by a mobile robot is based on deep learning. To train a deep learning model to differentiate between target and non-target objects, a sufficiently large dataset that can extract features for classifying objects is required. In a general working environment, securing a sufficiently large dataset is difficult because the number of people designated as workers is constantly changing. Classifying the shapes of objects that are similar requires larger datasets than classifying the shapes of objects that are not similar. Therefore, a method for recognizing target objects with similar shapes using a small dataset is required. This paper proposes a Siamese-network–based target object recognition method for recognizing objects with similar shapes based on a small dataset. A trained Siamese network is used to recognize whether the input object is the target object based on its similarity to the target object. The results of target object recognition using the proposed method were experimentally analyzed. Further, ResNet-50 was used to evaluate the performance of the proposed method. Our findings show that the proposed method recognized objects with a difference of approximately 6% using a small dataset, indicating its higher efficiency than the classification-based object recognition method. .
곽정훈,최희철,최동윤,강희설,박치호,한정대,전병수,김형호,Kwag, J.H.,Choi, H.C.,Choi, D.Y.,Kang, H.S.,Park, C.H.,Han, J.D.,Jeon, B.S.,Kim, H.H. 한국축산환경학회 2002 축산시설환경학회지 Vol.8 No.2
This study was conducted to determine the volume of pig slurry productinn and the characteristics from 4 swine farms. For the composition of pig slurry produced, contents of N, $P_2O_5$ and $K_2O$, were 0.13, 0.25 and 0.13% in slurry, respectively. Water pollutant concentration in slurry of swine farms, $BOD_5$, $COD_MN$, SS, T-N and T-P, was $24,047mg/{\ell}$, $30,232mg/{\ell}$, $36,833mg/{\ell}$, $2,805mg/{\ell}$, $465mg/{\ell}$, respectively. The average volume of pig slurry was 6.30 ${\ell}/head/day$ and 6.32 ${\ell}$ in spring, 6.69 ${\ell}$ in summer, 6.09 ${\ell}$ in autumn, and 6.12 ${\ell}$ in winter. The average moisture content of slurry was 95.8%. The composition of slurry produced by pig farms.
기계교반 퇴비화시설에서의 구간별 발효온도에 따른 수분 증발량 및 특성 변화 연구
곽정훈,최동윤,박치호,정광화,김재환,강희설,양창범,라창식,Kwag J. H.,Choi D. Y.,Park C. H.,Jeong K. H.,Kim J. H.,Kang H. S.,Yang C. B.,La C. S. 한국축산환경학회 2004 축산시설환경학회지 Vol.10 No.3
에스커레이터식 기계교반 퇴비화시설의 적정관리를 위해 돈분 및 톱밥에 함유되어 있는 수분 투입량에 따른 발효온도 및 수분 함량변화를 조사하여 적정 관리방안을 제시하고자 본 시험을 실시하였으며 그 결과는 다음과 같다. 1. 발효조 내 온도는 발효조 내 혼합물 투입 후 4일 이상 경과해야 발효온도가 $70^{\circ}C$이상 유지되었으며, 발효조 내 투입되는 혼합물(돈분+톱밥)의 수분 함량은 평균 $72.9\%$로 추천치 보다 높게 조사되었으나, 적정수분 함량 조정은 발효조 27m 지점 즉, 투입후 5$\~$6일 후에나 적정수분 함량이 되었다. 2. 발효조 내 평균 수분 감소량은 $12.5\%$였고, 유기물량은 건물기준으로 $93.9\%$에서 $92.5\%$로 거의 감소가 없는 것으로 조사되었으며 아는 후반기에도 비슷한 경향을 보였다 3. 투입되는 열량가는 현물상태에서 평균 1,127.3kcal/kg이고 질소, 인산 가리성분은 각각 $1.0\%$, 1.1, 및 $0.38\%$로 조사되었으며 OM/N은 26.3로 조사되었으며 완제품의 수분 함량은 평균 $65.3\%$였으며 열량가 및 질소, 인산, 카리 등 비료성분은 각각 1,348.8Kcal/kg, $0.58\%$, $1.47\%$, $0.49\%$로 조사되었다. 4. 퇴비화 과정 중 중금속 함량은 Cu 58.9ppm, Cr 1.55 ppm, Pb 2.16 ppm, Cd 0.07 ppm, As 0.3 및 Hg 0,003ppm으로 조사되었으며 6 성분의 중금속은 비료관리법 기준치 이하로 조사되었다. This research was carried out to investigate the moisture evaporation and property change depenging on the composting temperature for the escalator reversing composting system. The system was supported by the Y livestock cooperative composting factory. According to the test, the composting remperature eas varied in the range of $65\~80^{\circ}C$. The water content was de-creased to $75\%$ and became about $60\%$ at the end of the phase. Total nitrogen became $0.58\%$, total phosphoric acid $1.47\%$ and potashium $0.49\%$ at the end of the phase.