• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.93-101
• /
• 2023

In this paper, we propose a method of creating a 3D bounding box for an object using a vanishing point to increase the accuracy of object recognition in an image when recognizing an traffic object using a video camera. Recently, when vehicles captured by a traffic video camera is to be detected using artificial intelligence, this 3D bounding box generation algorithm is applied. The vertical vanishing point (VP1) and horizontal vanishing point (VP2) are derived by analyzing the camera installation angle and the direction of the image captured by the camera, and based on this, the moving object in the video subject to analysis is specified. If this algorithm is applied, it is easy to detect object information such as the location, type, and size of the detected object, and when applied to a moving type such as a car, it is tracked to determine the location, coordinates, movement speed, and direction of each object by tracking it. Able to know. As a result of application to actual roads, tracking improved by 10%, in particular, the recognition rate and tracking of shaded areas (extremely small vehicle parts hidden by large cars) improved by 100%, and traffic data analysis accuracy was improved.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.535-545
• /
• 2022

Improving the stability of the ground in seismic design requires an understanding of the dynamic behavior of the ground under seismic loads. The shaking table test is an important methodology to provide this understanding. This study aimed to assess the influence on boundary conditions, as they are among the most important factors affecting the test. This was achieved by testing the influence of boundary conditions on the seismic responses of model slopes at different locations in the testing apparatus. A model slope was fabricated at different locations in a laminar shear box, and the influence of the boundary conditions was then measured. Each model slope was created at 100, 50, and 25 cm from the soil wall, and sine wave seismic loads of the same size were inputted. The results confirmed that the acceleration was amplified by the influence of the boundary in the case of the slope being located 25 cm from the boundary, whereas the influence of the boundary conditions decreased when the slope was located at 50~100 cm.

• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.229-237
• /
• 2024

The logistics industry is converging with digital technology and growing into various logistics automation systems. However, inspection and loading/unloading, which are mainly performed in logistics work, depend on human resources, and the workforce is shrinking due to the decline in the productive population due to the low birth rate and aging. Although much research is being conducted on the development of automated logistics systems to solve these problems, there is a lack of research and development on load stacking stability, which has the potential to cause significant accidents. In this study, loading boxes with various sizes and positions of the center of gravity were set up, and a method for stacking that with high stability is presented. The size of the loading box is measured using a depth camera. The loading box's weight and center of gravity are measured and estimated by a developed device with four loadcells. The measurement error is measured through various repeated experiments and is corrected using the least squares method. The robot arm performs load stacking by determining the target position so that the centers of gravity of the loading boxes with unbalanced masses with a random sequence are transported in alignment. All processes were automated, and the results were verified by experimentally confirming load stacking stability.

• Journal of Sericultural and Entomological Science
• /
• v.53 no.2
• /
• pp.82-86
• /
• 2015

This study was carried out to develop the silkworm rearing technique in unused mulberry leaves after harvesting mulberry fruit. The growth of Gwasang No. 2 and Suhyang was very good compared to control cultivar Chungil in leaves size and new branch growth, but new branch and leaves of Daeshim was similar or small to control cultivar Chungil. The number of leaves of Gwasang No. 2 and Suhyang was lower than Chungil, but weight of leaves per tree was heavyer than Chungil. Mulberry leaf yield was Gwasang No. 2 521 kg/10a, Suhyang 189 kg/10a, Daeshim 73 kg/10a, Chungil 1,095 kg/10a. Content of mineral element of all three mulberry cultivars leaf for mulberry fruit production was higher than Chungil in N, P, K, Ca etc. Feeding quantity of silkworm of Gwasang No. 2 and Suhyang was much more than Chungil. Feeding quantity was highest at Suhyang in 96 kg/box. Growth duration of silkworm larvae was not different in all four mulberry culivars but weight of silkworms (5th instar 3rd day) was heavy at Gwasang No. 2 (2.07 g/head) and Suhyang (2.11 g/head) compared to control cultivar Chungil (1.92 g/head). Mortality of silkworms was 14.6% (Gwasang No. 2), 13.3% (Suhyang), 13.9% (Daesim), 12.6% (Chungil) and than higher at elder instar stage. The production amount of silkworm (5th instar 3rd day) was 35.4 kg/box (Gwasang No. 2), 36.6 kg/box (Suhyang), 35.0 kg/box (Daeshim), 33.6 kg/ box (Chungil). Amount of possible rearing silkworms was estimated 3.4box/10 a (Gwasang No. 2), 1.3box/10a (Suhyang), 0.5box/10a (Daeshim), 8.7box/10a (Chungil).

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.11a
• /
• pp.225-228
• /
• 2008

In case of nonlinear analysis for reinforced concrete structure, the characteristics of the failure, which are depend on loading conditions, such as tension splitting, compression crushing and shear distortion should be considered. On the analytical evaluation for the failure behavior of these, the finite element techniques is the most widely used. After the maximum load, however, an analytical results by finite element technique are depending on the size of the element. In this study, integral nonlocal model which is one of those study for overcoming the element sensitivity and dependancy, used for the failure analysis of box culvert specimen. Comparing on the experimental and analytical results, validity and reliability of integral nonlocal model are investigate.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.7
• /
• pp.680-688
• /
• 2001

In this paper, we propose a reliable method for searching the optimally performing generalized brain-state-in-a-box (GBSB) neural associative memory using an evolution program (EP) given a set of prototype patterns to be stored as stable equilibrium points. First, we exploit some qualitative guidelines necessary to synthesize the GBSB model. Next, we parameterize the solution space utilizing the limited number of parameters to represent the solution space. Then, we recast the synthesis of GBSB neural associative memories as two constrained optimization problems, which are equivalent to finding a solution to the original synthesis problem. Finally, we employ an evolution program (EP), which enables us to find an optimal set of parameters related to the size of domains of attraction (DOA) for prototype patterns. The validity of this approach is illustrated by a design example and computer simulations.

• BMB Reports
• /
• v.29 no.1
• /
• pp.52-57
• /
• 1996

A specific DNA fragment from Korean radish (Raphanus sativus L.) was amplified by performing PCR with oligonucleotide primers which correspond to the highly conserved regions of plant peroxidases. The size of the PCR product was ca. 400 bp, as expected from the known plant peroxidase genes. Comparison of the nucleotide and deduced amino acid sequences of the PCR product to those of other plant peroxidase-encoding genes revealed that the amplified fragment corresponded to the highly conserved region I and III of plant peroxidases. By screening a genomic library of Korean radish using the amplified fragment as a probe, two positive clones, named prxK1 and prxK2, were isolated. Restriction mapping studies indicated that the 5.2 kb Sail fragment of the prxK1 clone and the 4.0 kb EcoRI fragment of the prxK2 clone encode separate isoperoxidase genes. Analyses of the promoter region of the prxK1 clone shows that putative CAAT box, CMT box, and TGA1b binding sequence (5' TGACGT) are present 718 bp upstream from the start codon.

• Journal of Advanced Marine Engineering and Technology
• /
• v.31 no.1
• /
• pp.51-57
• /
• 2007

In process of reinforced concrete (RC) box structure. the heat of hydration may cause serious thermal cracking. In order to eliminate hydration heat of mass concrete. this paper reports results of hydration heat control in mass concrete structure using the pulsating heat pipe. There were three RC box molds($1.2{\times}l.8{\times}2.4m^3$) which shows a difference as compared with each other. One was not equipped with pulsating heat pipe. The others were equipped with pulsating heat pipe. All of them were cooled with natural air convection. The pulsating heat pipe was composed of serpentine type copper pipe with 10 turns (outer diameter: 4mm. inner diameter: 2.8mm). The working fluid was R-22 and its charging ratio was 40% by volume. The conditions such as the number of turns. the length and the pitch of the pulsating heat pipe and the size of concrete structure were changed. Based on these experiments, it was confirmed that this construction method using pulsating heat pipe was effective to remove hydration heat of mass concrete structure and thus it was possible to prevent harmful thermal crack and construction Period and costs of concrete structure would be cut down.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.12
• /
• pp.1674-1680
• /
• 2002

An experimental study was made of a large-scale vortical structure over a backward-facing step. The Reynolds number based on the step height was R $e_{H}$ =33,000. To recognize the large-scale vortex, three components of velocity were measured. The measurements were performed in the recirculation zone (x/H=4.0) and the reattachment zone(x/H=7.5). To measure the wall pressure fluctuations in a turbulent flow over a backward-facing step, a 32-channel microphone array was installed beneath the wall in the streamwise and spanwise directions. From the measured pressure field, the size of large-scale vortex was obtained. As a detailed study, a conditionally-averaging technique was employed to characterize the coherent structure of the large-scale vortex. To see the relationship between the flow field and the relevant spatial mode of the pressure field, the spatial box filtering (SBF) was examined. A cross-correlation between velocity and pressure fluctuations was performed to identify the structure and the length scale of the large-scale vortex.x.