• Journal of the Society of Disaster Information
• /
• v.19 no.1
• /
• pp.173-183
• /
• 2023

Purpose: In order to reduce industrial accidents caused by forklift trucks, it is actually necessary to analyze the causes of accidents. This study aims to present disaster prevention measures by analyzing accident cases by forklift accident type. Method: For the analysis of industrial accidents, including serious industrial accidents caused by forklifts from 2021 to 2022, accident statistics from the Korea Occupational Safety and Health Agency were used to analyze accidents in four types. Result: In the last two years, the total number of victims, including deaths and other serious injuries, was 2,559, which was 1,396 in 2021 and 1,163 in 2022. Disaster prevention measures were presented for industrial accidents by size and occurrence type of equipment that cause serious industrial accidents in which more than 1,000 people are injured annually. Conclusion: It is necessary to expand the number of workers subject to the forklift financial support project to less than 100. It is necessary to amend the proviso on boarding restrictions in Article 86, Paragraph 7 of the ｢Regulations on Industrial Safety and Health Standards｣. It is mandatory to install front and rear cameras. It is necessary to install driving-linked safety belts. It is necessary to install line beams obligatory. It is necessary to expand the subject of forklift special safety and health education to workplaces that have more than one forklift truck, and it is necessary to redesignate the training hours to 16 hours every year.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Journal of Animal Science and Technology
• /
• v.64 no.3
• /
• pp.574-587
• /
• 2022

This study was performed to development the alternative farrowing pen (AFP) and to investigate performance and behavior of lactating sows and their litter. A total of 64 multiparous sows were randomly divided into two groups and were allocated to farrowing crates (FCs) and AFPs. The AFPs contained a crate and support bars that could be folded to provide the sows with extra space on day 5 postpartum. Behavior was recorded by charge-coupled device cameras and digital video recorders, and the data were scanned every 2 min to obtain an instantaneous behavioral sample. Farrowing systems did not affect feed intake, back-fat thickness, litter size and piglet weight at birth and weaning (p > 0.05). In addition, there were no differences in the number of crushed piglets between the two farrowing systems (p > 0.05). However, the weaning-to-estrus interval was shorter in the sows of the AFPs than in thous of the FCs (p < 0.05). The sows spent most of their time lying down during the lactating period, at about 80% lateral recumbency and 10%-15% ventral recumbency. The only significant differences were in the feeding and drinking behavior between sows in the two farrowing systems (p < 0.05). The FC sows displayed more feeding and drinking behavior than the AFP sows, especially in the late lactating period (p < 0.05). Piglets in the FCs tended to spend more time walking than piglets in the AFPs (p < 0.05), whereas there were no differences in suckling and lying behavior between piglets in the two farrowing systems (p > 0.05). It is concluded that the AFPs with temporary crating until day 4 postpartum did not negatively affect performance and crushed piglet compared with the FCs. It also may improve animal welfare by allowing sows to move and turn around during the lactating period. Further research is needed to find suitable housing designs to enhance productivity and animal welfare.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.spc
• /
• pp.11-17
• /
• 2022

In this study, we address the development of a floating platform system based on a unmanned surface vessel for wide-area sensing and monitoring of hazardous and noxious substances (HNSs). For long endurance, a movable floating platform with no mooring lines was used and modified for HNS sensing and monitoring. The floating platform was equipped with various sensors such as optical and thermal imaging cameras, marine radar, and sensors for detecting HNSs in water and air. Additionally, for experiment validation in real outdoor environments, a portable gas-exposure system (PGS) was built and installed on the monitoring system. The software for carrying out the mission was integrated with the Robot Operating System (ROS) framework. The practical feasibility of the developed system was verified through experimental tests conducted in inland water and real-sea environments.

• Journal of the Korean Society of Radiology
• /
• v.17 no.2
• /
• pp.201-206
• /
• 2023

In order to improve the spatial resolution of the gamma camera, the size of the hole in the collimator must be reduced, so the sensitivity is reduced. In order to improve the sensitivity, the size of the hole must be increased, and thus the spatial resolution is reduced. In other words, spatial resolution and sensitivity show opposite characteristics. In this study, a gamma camera was designed to improve both spatial resolution and sensitivity. In order to obtain higher sensitivity in gamma cameras with the same spatial resolution, the structure of the scintillator was designed differently from the existing system. A scintillation pixel was used, and a partition wall was placed between the scintillation pixels to prevent incident gamma rays from being transmitted to other scintillation pixels to interact. Geant4 Application for Tomographic Emission (GATE) simulation was performed to evaluate the performance of the designed gamma camera. When the same sensitivity as the block-type scintillator was obtained, the spatial resolution increased by 16.5%, and when the same spatial resolution was obtained, the sensitivity increased by 61.5%. It is considered that the use of the gamma camera designed in this study can improve the sensitivity compared to the existing system while securing excellent spatial resolution.

• Korean Journal of Applied Biomechanics
• /
• v.33 no.3
• /
• pp.110-117
• /
• 2023

Objective: The purpose of this study was to find out kinematic and kinetic differences the lower extremity joint according to the landing type during vertical jump movement after jump landing, and to present an efficient landing method to reduce the incidence of injury in youth players. Method: Total of 24 Youth players under Korean Sport and Olympic Committee, who used either heel contact landing (HCG) or toe contact landing (TCG) participated in this study (HCG (12): CG height: 168.7 ± 9.7 cm, weight: 60.9 ± 11.6 kg, age: 14.1 ± 0.9 yrs., career: 4.3 ± 2.9 yrs., TCG height: 174.8 ± 4.9 cm, weight: 66.9 ± 9.9 kg, age 13.9 ± 0.8 yrs., career: 4.7 ± 2.0 yrs.). Participants were asked to perform jump landing consecutively followed by vertical jump. A 3-dimensional motion analysis with 19 infrared cameras and 2 force plates was performed in this study. To find out the significance between two landing styles independent t-test was performed and significance level was set at .05. Results: HCG showed a significantly higher dorsi flexion, extension and flexion angle at ankle, knee and hip joints, respectively compared with those of TCG (p<.05). Also, HCG revealed reduced RoM at ankle joint while it showed increased RoM at knee joint compared to TCG (p<.05). In addition, HGC showed greater peak force, a loading rate, and impulse than those of TCG (p<.05). Finally, greater planta flexion moment was revealed in TCG compared to HCG at ankle joint. For the knee joint HCG showed extension and flexion moment in E1 and E2, respectively, while TCG showed opposite results. Conclusion: Compared to toe contact landing, the heel contact landing is not expected to have an advantage in terms of absorbing and dispersing the impact of contact with the ground to the joint. If these movements continuously used, performance may deteriorate, including injuries, so it is believed that education on safe landing methods is needed for young athletes whose musculoskeletal growth is not fully mature.

• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.23-31
• /
• 2010

Due to the fact that fisheye lens can provide super wide angles with the minimum number of cameras, field-of-view over 180 degrees, many vehicles are attempting to mount the camera system. Not only use the camera as a viewing system, but also as a camera sensor, camera calibration should be preceded, and geometrical correction on the radial distortion is needed to provide the images for the driver's assistance. In this thesis, we introduce a geometric correction technique to minimize the loss of the image data from a vehicle fish-eye lens having a field of view over $180^{\circ}$, and a asymmetric distortion. Geometric correction is a process in which a camera model with a distortion model is established, and then a corrected view is generated after camera parameters are calculated through a calibration process. First, the FOV model to imitate a asymmetric distortion configuration is used as the distortion model. Then, we need to unify the axis ratio because a horizontal view of the vehicle fish-eye lens is asymmetrically wide for the driver, and estimate the parameters by applying a non-linear optimization algorithm. Finally, we create a corrected view by a backward mapping, and provide a function to optimize the ratio for the horizontal and vertical axes. This minimizes image data loss and improves the visual perception when the input image is undistorted through a perspective projection.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.1
• /
• pp.1-8
• /
• 2009

The objective of this study is to design a system that automatically monitors the state of interior spaces like offices where lots of people are coming and going through image data and environment data, which includes temperature, humidity, and other conditions, and implement and test related application programs. In practice, there are lots of image data automatically obtained by unmanned equipments, such as certain types of CCTVs, for monitoring situation in usual interior spaces. This image data can be used as a more effective manner by establishing a system that recognizes situation in specific interior spaces based on the relationship between image and environment data. For instance, it is possible to perform unmanned on/off controls for various electronic equipments, such as air conditioners, lights, and other devices, through analyzing the data acquisited from environment sensors (temperature, humidity, and illumination) as dynamic states are not maintained for a specified period of time. For implementing these controls, this study analyzes environment data acquisited from temperature and humidity sensors and image data input from wireless cameras to recognize situation and that can be used to automatically control environment variables configured by users. Experiments were applied in a laboratory where unmanned controls were effectively performed as automatic on/off controls for the air conditioner and lights installed in the laboratory as certain motions were detected or undetected for a specified period of time.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.57-64
• /
• 2023

The ROK military faces a significant challenge in its vigilance mission due to demographic problems, particularly the current aging population and population cliff. This study demonstrates the crucial role of the 4th industrial revolution and its core artificial intelligence algorithm in maximizing work efficiency within the Command&Control room by mechanizing simple tasks. To achieve a fully developed military surveillance system, we have chosen multi-object tracking (MOT) technology as an essential artificial intelligence component, aligning with our goal of an intelligent and automated surveillance system. Additionally, we have prioritized data visualization and user interface to ensure system accessibility and efficiency. These complementary elements come together to form a cohesive software application. The CCTV video data for this study was collected from the CCTV cameras installed at the 1st and 2nd main gates of the 00 unit, with the cooperation by Command&Control room. Experimental results indicate that an intelligent and automated surveillance system enables the delivery of more information to the operators in the room. However, it is important to acknowledge the limitations of the developed software system in this study. By highlighting these limitations, we can present the future direction for the development of military surveillance systems.

• Land and Housing Review
• /
• v.14 no.3
• /
• pp.145-155
• /
• 2023

Recently, with the widespread adoption of Building Information Modeling (BIM) technology in the construction industry, various object detection algorithms have been used to verify errors between 3D models and actual construction elements. Since the characteristics of objects vary depending on the type of construction facility, such as buildings, bridges, and tunnels, appropriate methods for object detection technology need to be employed. Additionally, for object detection, initial object images are required, and to obtain these, various methods, such as drones and smartphones, can be used for image acquisition. The study uses a 360° camera optimized for internal tunnel imaging to capture initial images of the tunnel structures of railway and road facilities. Various object detection methodologies including the YOLO, SSD, and R-CNN algorithms are applied to detect actual objects from the captured images. And the Faster R-CNN algorithm had a higher recognition rate and mAP value than the SSD and YOLO v5 algorithms, and the difference between the minimum and maximum values of the recognition rates was small, showing equal detection ability. Considering the increasing adoption of BIM in current railway and road construction projects, this research highlights the potential utilization of 360° cameras and object detection methodologies for tunnel facility sections, aiming to expand their application in maintenance.