• 전기학회논문지
• /
• 제57권4호
• /
• pp.715-717
• /
• 2008

The connectivity weighted Hough transform is a useful method for detecting well-connected short lines without generating false lines yet requires extensive computation. This letter describes a method that reduces the computation of the connectivity weighted Hough transform by removing unnecessary weight calculations using the gradient angles of feature points. In simulations with synthetic images and experiments with liquid crystal display panel images, the proposed method showed significantly improved speed without compromising detectability.

• International Journal of Industrial Entomology and Biomaterials
• /
• 제3권2호
• /
• pp.135-139
• /
• 2001

Experiments were held in Egypt to test a new Package of practices for commercial cocoon production, including adding secondary macro and micronutrients to the mulberry garden, disease free rearing regime, low temperature rearing in young instars and natural mounting fur silkworms. This package for seed silkworm rearing lead to increase in fecundity by 67-121eggs (15.12-26.22%) and yield of standard boxes per 1 parent egg boxes by 57-58 egg boxes(48.33-51.66%) respectively in comparison th the traditional cocoon production technology.

• 산업경영시스템학회지
• /
• 제23권60호
• /
• pp.67-72
• /
• 2000

In this paper we consider to parallel machines scheduling problems for minimizing mean tardiness that is known NP-complete. This problems is classified into two cases, one of which is the case which processing time are identical and the other, nonidentical. A Tabu Search method is applied to the problems considered in this paper to get an improved solution. To this end, we design move attribute, Tabu attribute and Tabu tenure, and thereafter perform the experiments to the problems.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.225-226
• /
• 2022

In order to secure the practicality of services using drones, improve on-site operability, and improve the convenience of aircraft maintenance, it is necessary to develop a drone station that can be safely stored while ensuring charging performance. Therefore, a total seven points of improvement were derived through laboratory experiments after the development of the first prototype, and an improved second prototype will be developed in the future based on the preceding processes.

• Asian-Australasian Journal of Animal Sciences
• /
• 제13권8호
• /
• pp.1154-1161
• /
• 2000

Two experiments were conducted to evaluate the efficacy of cupric citrate (Cu-citrate) relative to cupric sulfate $(CuSO_4)$ as a Cu source for weanling and grow-finish pigs. In addition, the use of liver and bile Cu concentrations as indices of the bioavailability of Cu sources was investigated. Experiment one consisted of a nursery phase (35 d; initial BW=6.4 kg, final BW=21.4 kg) followed by a grow-finish phase (103 d; initial BW=21.5 kg, final BW=111.7 kg). Experiment two only consisted of a nursery phase (35 d; initial BW=6.3 kg, final BW=18.6 kg). Dietary treatments were identical for both experiments and consisted of: control (10 ppm $CuSO_4$); control+66 or 225 ppm $CuSO_4$; control+33, 66, or 100 ppm Cu-citrate. An antibiotic was included in diets for Exp. 1 but not Exp. 2. In both experiments, growth performance variables were similar for pigs receiving Cu-citrate and $CuSO_4$; however, growth performance was not improved by high concentrations of $CuSO_4$. Liver and bile Cu were increased (p<0.05) by 225 ppm $CuSO_4$; however, lower dietary concentrations of Cu from either $CuSO_4$ or Cu-citrate did not affect the Cu concentration of liver or bile relative to that observed in the control pigs. Irrespective of Cu source, there was no linear (p>0.10) increase in plasma Cu with increasing Cu concentrations in the diet for both experiments. However, the plasma Cu concentrations were highest (p<0.10) in pigs receiving diets supplemented with 225 ppm $CuSO_4$. Sixteen randomly chosen pigs per treatment in Exp. 1 were continued through the grow-finish phase. Body weight gain and feed intake were improved (p<0.10) by 66 ppm $CuSO_4$, but other dietary Cu treatments did not alter pig performance compared to the control diet. Plasma Cu concentrations were increased (p<0.10) by 225 ppm $CuSO_4$ in the growing phase and by 225 ppm $CuSO_4$ and 100 ppm Cu-citrate in the finishing phase. These data reveal no consistent effect of $CuSO_4$ on performance; therefore, it is difficult to assess the efficacy of these two Cu sources. In addition, these studies demonstrate that liver and bile Cu are not good indicators of Cu bioavailability in pigs fed adequate to pharmacological concentrations of Cu.

• 스마트미디어저널
• /
• 제9권4호
• /
• pp.134-143
• /
• 2020

자동차 번호판 인식 기술은 도로의 교통상황 통제, 과속차량 단속, 도주 차량의 추적 등 현대 교통 시설 및 교통 안전망을 책임지고 있는 핵심 기술 중 하나이다. 이 기법은 과거에도 연구되었던 분야였으나 최근 딥러닝 기술의 발전으로 다양한 기법들을 적용하여 향상된 성능을 보이는 분야이며, 크게 자동차 번호판 검출과 번호판 인식으로 나뉜다. 본 연구에서는 다양한 객체 검출 모델과 WPOD-Net(Warped Planar Object Detection Network) 모델을 활용하여 자동차 번호판 검출 성능을 향상시키기 위한 실험을 진행하였으며, 객체 검출 모델을 활용하여 번호판을 검출하는 기존 방식들 대신 차량을 검출한 다음 번호판을 검출하는 방식을 택하여 정확도를 높였다. 특히 Super-Resolution 기법 중 하나인 Fast-SRGAN 모델을 활용하여 이미지 내에 존재하는 노이즈를 제거하는 처리를 통해 최종 성능을 향상시켰다. 결과적으로 92.38%에서 96.72%로 선행 연구 대비 평균 4.34% 향상된 성능이 실험을 통해 확인되었다.

• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.469-483
• /
• 2023

The dynamic characteristics of wind turbine blades are usually monitored by contact sensors with the disadvantages of high cost, difficult installation, easy damage to the structure, and difficult signal transmission. In view of the above problems, based on computer vision technology and the improved YOLOv5 (You Only Look Once v5) deep learning model, a non-contact dynamic characteristic monitoring method for wind turbine blade is proposed. First, the original YOLOv5l model of the CSP (Cross Stage Partial) structure is improved by introducing the CSP2_2 structure, which reduce the number of residual components to better the network training speed. On this basis, combined with the Deep sort algorithm, the accuracy of structural displacement monitoring is mended. Secondly, for the disadvantage that the deep learning sample dataset is difficult to collect, the blender software is used to model the wind turbine structure with conditions, illuminations and other practical engineering similar environments changed. In addition, incorporated with the image expansion technology, a modeling-based dataset augmentation method is proposed. Finally, the feasibility of the proposed algorithm is verified by experiments followed by the analytical procedure about the influence of YOLOv5 models, lighting conditions and angles on the recognition results. The results show that the improved YOLOv5 deep learning model not only perform well compared with many other YOLOv5 models, but also has high accuracy in vibration monitoring in different environments. The method can accurately identify the dynamic characteristics of wind turbine blades, and therefore can provide a reference for evaluating the condition of wind turbine blades.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1841-1857
• /
• 2023

CenterNet, a novel object detection algorithm without anchor based on key points, regards the object as a single center point for prediction and directly regresses the object's height and width. However, because the objects have different sizes, directly regressing their height and width will make the model difficult to converge and lose the intrinsic relationship between object's width and height, thereby reducing the stability of the model and the consistency of prediction accuracy. For this problem, we proposed an algorithm based on the regression of the diagonal half-length and the center angle, which significantly compresses the solution space of the regression components and enhances the intrinsic relationship between the decoded components. First, encode the object's width and height into the diagonal half-length and the center angle, where the center angle is the angle between the diagonal and the vertical centreline. Secondly, the predicted diagonal half-length and center angle are decoded into two length components. Finally, the position of the object bounding box can be accurately obtained by combining the corresponding center point coordinates. Experiments show that, when using CenterNet as the improved baseline and resnet50 as the Backbone, the improved model achieved 81.6% and 79.7% mAP on the VOC 2007 and 2012 test sets, respectively. When using Hourglass-104 as the Backbone, the improved model achieved 43.3% mAP on the COCO 2017 test sets. Compared with CenterNet, the improved model has a faster convergence rate and significantly improved the stability and prediction accuracy.

• Animal Bioscience
• /
• 제36권12호
• /
• pp.1869-1879
• /
• 2023

Objective: This study was to evaluate the effects of individual or combinational use of phytase, protease, and xylanase on total tract digestibility of corn, soybean meal, and distillers dried grains with soluble (DDGS) fed to pigs. Methods: Each experiment had four 4×4 Latin squares using 16 barrows. Each period had 5-d adaptation and 3-d collection. All experiments had: CON (no enzyme); Phy (CON+phytase); Xyl (CON+xylanase); Pro (CON+protease); Phy+Xyl; Phy+Pro, Xyl+Pro, Phy+Xyl+Pro. Each Latin square had 'CON, Phy, Xyl, and Phy+Xyl'; 'CON, Phy, Pro, and Phy+Pro'; 'CON, Pro, Xyl, and Xyl+Pro'; and 'Phy+Xyl, Phy+Pro, Xyl+Pro, Phy+Xyl+Pro'. Results: The digestible energy (DE), metabolizable energy (ME), and nitrogen retention (NR) of corn were not affected by enzymes but the apparent total tract digestibility (ATTD) of phosphorus (P) was improved (p<0.01) by Phy. The DE and ATTD dry matter (DM) in soybean meal were increased (p<0.05) by Phy+Pro and the ATTD P was improved (p<0.01) by Phy, Phy+Pro, and Phy+Xyl. The DE, ME, and ATTD DM in DDGS were improved (p<0.05) by Phy+Xyl and the ATTD P was improved (p<0.01) by Phy, Phy+Pro, and Phy+Xyl. Conclusion: Phytase individually or in combination with xylanase and protease improved the Ca and P digestibility of corn, soybean meal, and DDGS, from the hydrolysis of phytic acid. The supplementation of protease was more effective when combined with phytase and xylanase in the soybean meal and DDGS possibly due to a higher protein content in these feedstuffs. Xylanase was more effective in DDGS diets due to the elevated levels of non-starch polysaccharides in these feedstuffs. However, when xylanase was combined with phytase, it demonstrated a higher efficacy improving the nutrient digestibility of pigs. Overall, combinational uses of feed enzymes can be more efficient for nutrient utilization in soybean meal and DDGS than single enzymes.

• 한국가금학회지
• /
• 제14권1호
• /
• pp.1-8
• /
• 1987

사료의 에너지와 단백질 수준이 산란계의 능력에 미치는 영향을 조사하기 위하여 3회의 시험을 실시하였다. 시험1에서는 352일령의 마니나 브라운종을, 시험 2에서는 280일령의 갈색 와렌종을, 시험 3에서는 317일령의 갈색 와렌종을 각각 이용하였다. 각 시험에서 공히 총 360수의 공시계를 18수씩 20개구로 나누어 4개처리에 5반복으로 배치하였다. 시험 설계는 2가지 수준의 에너지(2500과 2800 kcal ME/kg)와 2가지 수준의 단백질 (13% 및 16 %)을 조합한 2$\times$2 요인시험을 실시하였다. 모든 공시계는 산란계용 Cage에 cage 당 2수씩 수용하였으며 시험 1과 2에서는 4주간의 시험기간동안 시험사료와 물을 자유로이 급여하였고 시험3에서는 2주간의 시험기간동안 사료섭취량을 1일 수당 130g으로 제한하여 급여하였다. 시험 1과 2에서 고에너지 사료를 섭취한 닭이 산란율이 다소 높았으나 유의성은 없었다. 그러나 시험 1에서는 단백질 수준이 산란율에 영향을 미치지 못하였다. 사료를 제한 급여한 시험3에서는 고에너지 사료에서 산란율이 개선되었으며(P〈0.05) 단백질 수준도 산란율에 영향을 미쳤으나 유의성은 없었다. 시험 1과 2에서 란중은 에너지 수준이나 단백질 수준에 의하여 영향을 받지 않았으나 시험 3에서는 고에너지 수준에서 란중도 약간 개선되는 경향을 보였다. 3회의 시험 모두에서 사료의 단백질이나 에너지 수준이 증가할 때 egg mass가 증가하는 경향을 보였다. 사료의 에너지나 단백질 수준이 증가할 때 사료섭취량은 감소하고 사료효율이 개선되는 경향을 보였다. 또한 사료의 에너지 수준이 증가할 때 단백질 효율(egg mass/단백질섭취량)이 개선되었으며 사료의 단백질 수준이 증가할 때 에너지 효율(egg mass /ME 섭취량) 이 개선되었다.