• Journal of the Korea Society of Computer and Information
• /
• v.29 no.10
• /
• pp.69-75
• /
• 2024

Noise caused by adverse weather conditions in data collected during autonomous driving can lead to object recognition errors, potentially resulting in critical accidents. While this risk is widely acknowledged, there is a lack of research that quantitatively and systematically analyzes it. Therefore, this study aims to examine and quantify the extent to which noise affects object detection in autonomous driving environments. To this end, we utilized the YOLO v5 model trained on unprocessed datasets. The test data were divided into noise ratios of 0% (Original), 20%, 40%, 60%, and 80%, and the detection results were evaluated by constructing a Confusion Matrix. Experimental results show that as the noise ratio increases, the True Positive (TP) rate decreases, and the F1-score also significantly drops across all noise levels, specifically from 0.69 to 0.47, 0.29, 0.18, and 0.14. These findings are expected to contribute to enhancing the stability of autonomous driving technology. Future research will focus on collecting real datasets that include naturally occurring noise and developing more effective noise removal techniques.

• ETRI Journal
• /
• v.38 no.4
• /
• pp.787-797
• /
• 2016

Mining, construction, and other special vehicles for heavy use are designed to work under high-performance and off-road working conditions. The driving and executive mechanisms of the support structures and superstructures of these vehicles frequently operate under high loads. Such high loads place the equipment under constant risk of an accident and can jeopardize the dynamic stability of the machinery. An experimental investigation was conducted on a refuse collection vehicle. The aim of this research was to determine the working conditions of a real vehicle: the kinematics of the waste container, that is, a hydraulic rotate drum for waste collection; the dynamics of the load manipulator (superstructure); the vibrations of the vehicle mass; and the strain (stress) of the elements responsible for the supporting structure. For an examination of the force (weight) on the rear axle of a heavy vehicle, caused by its own weight and additional load, a universal measurement system is proposed. As a result of this investigation, we propose an alternative system for continuous vehicle weighing during waste collection while in motion, that is, an on-board weighing system, and provide suggestions for measuring equipment designs.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.275-282
• /
• 2015

Recently, Vecna BEAR type robot to save injured individuals from inaccessible areas has been developed to minimize the loss of life. Because this robot is driven on rough terrain, there is a risk of rollover and vibration, which could impact the injured. In order to guarantee its stability, an algorithm is required that can estimate the speed limits for various environments in real time. Therefore, a dynamic model for real-time analysis is needed for this algorithm. Because the tracks used as the driving component of Vecna BEAR type robot consist of many parts, it is impossible to analyze the multibody tracks in real time. Thus, a lumped track model that satisfies the requirements of a short computation time and adequate accuracy is required. This study performed lumped track modeling, and the traction force was verified using RecurDyn, which is a dynamic commercial program.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.5
• /
• pp.48-56
• /
• 2009

Regulation of Visible Light Transmission Percentage (VLT%) has been argued because it was known that the degree of darkness of tinted vehicle can affect to driving maneuver. Previously, it was proven that low level of VLT affects capacity reduction. But, due to lack of field data they could not analyze the effect of Car-Following model parameters. This study focuses on the effect of a tinted vehicle on following traffic flow. RTK GPS receiving data through field experiment analyzed based on headway distance, acceleration noise, sensitivity, and reaction time. As a result of analysis through GM 1st Model and 3rd Model, influence of following vehicle vary inversely with VLT and risk according as tinting of lead vehicle is third vehicle bigger than second vehicle. Also the results patterns of GM 3rd model include distance-headway are same with GM 1st Model. In the further need to research for influence analysis of traffic flow stability by the level of VLT.

• Journal of Digital Convergence
• /
• v.19 no.12
• /
• pp.457-462
• /
• 2021

As South Korea is a mountainous topography, installation of tunnel is essential for construction of expressway in straight lines. According to "2019 Road Bridge and Tunnel Status Report", there are 2,682 tunnels in Korea with total length of 2,077km. Tunnels take up 1.9% of total road length and the number of tunnel increased by 94% with 1,300 newly constructed tunnels over the 10 years. According to domestic and foreign researches, a long tunnel over 1km in expressway has dark lightings and monotonous wall design which decrease driver's concentration and make the driver feel bored. This leads to feeling fatigue and drowsiness more easily. In response, Korea Expressway Corporation installed design lighting that increases attentiveness on 10 tunnels with total length over 3km by 2020. To reduce the risks of accident that may happen inside the tunnel, this study conducted a comparative analysis on characteristics of each type of LED landscape lighting installed inside the expressway tunnel. The study aimed on providing the basic material for effective installation of LED landscape lighting for securing driving stability, reducing fatigue, and lowering the risk of drowsiness.

• BMB Reports
• /
• v.57 no.8
• /
• pp.375-380
• /
• 2024

Early proatherogenic inflammation constitutes a significant risk factor for atherogenesis development. Despite this, the precise molecular mechanisms driving this pathological progression largely remain elusive. Our study unveils a pivotal role for the microRNA miR-328-5p in dampening endothelial inflammation by modulating the stability of JUNB (JunB proto-oncogene). Perturbation of miR-328-5p levels results in heightened monocyte adhesion to endothelial cells and enhanced transendothelial migration, while its overexpression mitigates these inflammatory processes. Furthermore, miR-328-5p hinders macrophage polarization toward the pro-inflammatory M1 phenotype, and exerts a negative influence on atherosclerotic plaque formation in vivo. By pinpointing JUNB as a direct miR-328-5p target, our research underscores the potential of miR-328-5p as a therapeutic target for inflammatory atherosclerosis. Reintroduction of JUNB effectively counteracts the anti-atherosclerotic effects of miR-328-5p, highlighting the promise of pharmacological miR-328-5p targeting in managing inflammatory atherosclerosis.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.240-257
• /
• 2022

Autonomous vehicles use various local sensors such as camera, radar, and lidar to perceive the surrounding environment. However, it is difficult to predict the movement of vulnerable road users using only local sensors that are subject to limits in cognitive range. This is true especially when these users are blocked from view by obstacles. Hence, this paper developed an algorithm for collision avoidance with VRU using V2X information. The main purpose of this collision avoidance system is to overcome the limitations of the local sensors. The algorithm first evaluates the risk of collision, based on the current driving condition and the V2X information of the VRU. Subsequently, the algorithm takes one of four evasive actions; steering, braking, steering after braking, and braking after steering. A simulation was performed under various conditions. The results of the simulation confirmed that the algorithm could significantly improve the performance of the collision avoidance system while securing vehicle stability during evasive maneuvers.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.27 no.4
• /
• pp.296-313
• /
• 1982

At a time when world population and food supply are in a delicate balance, it is essential that we look at factors to improve this balance. We can alter the environment to better fit the plant's needs, or we can alter the plant to better fit the environment. Improved technology has allowed us to increase the yield level. For moderately detrimental weather events technology has generally decreased the yield variation, yet for major weather disasters the variation has increased. We have raised the upper level, but zero is still the bottom level. As we concentrate the production of particular crops into limited areas where the environment is closest to optimum, we may be increasing the risk of a major weather related disaster. We need to evaluate the degree of variability of different crops, and how weather and technology can interact to affect it. The natural limits of crop production are imposed by important ecological factors. Production is a function of the climate, the soil, and the crop and all activities related to them. In looking at the environment of a crop we must recognize these are individuals, populations and ecosystems. Under intensive agriculture we try to limit the competition to one desired species. The environment is made up of a complex of factors; radiation, moisture, temperature and wind, among others. Plant response to the environment is due to the interaction of all of these factors, yet in attempting to understand them we often examine each factor individually. Variation in crop yields is primarily a function of limiting environmental parameters. Various weather parameters will be discussed, with emphasis placed on how they impact on crop production. Although solar radiation is a driving force in crop production, it often shows little relationship to yield variation. Water may enter into crop production as both a limiting and excessive factor. The effects of moisture deficiency have received much more attention than moisture excess. In many areas of the world, a very significant portion of yield variation is due to variation in the moisture factor. Temperature imposes limits on where crops can be grown, and the type of crop that can be grown in an area. High temperature effects are often combined with deficient moisture effects. Cool temperatures determine the limits in which crops can be grown. Growing degree units, or heat accumulations, have often been used as a means of explaining many temperature effects. Methods for explaining chilling effects are more limited.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.119-133
• /
• 2022

Due to the improvement of surveying, mapping and communication techniques, various apps for road direction guides and vehicle navigations have been developed. Although such a development has impacted on walking and driving, there is a limit to improving the daily convenience of the socially impaired people. This is mainly due to the fact that the software have been developed for normal pedestrians and drivers. Therefore, visually impaired people still have problems with the confusion of direction and/or non-provision of risk factors in walking. This study aimed to propose a scheme which constructs data for mobility-impaired or traffic-impaired people based on various geospatial information. The factors and components related to walking for the visually impaired are selected by geospatial data and a walking route guidance network that can be applied to a commercial software. As a result, it was confirmed that road direction guidance would be possible if additional contents, such as braille blocks (dotted/linear), sound signals, bus stops, and bollards are secured. In addition, an initial version of the application software was implemented based on the suggested data model and its usefulness was evaluated to a visually impaired person. To advance the stability of the service in walking for the visually impaired people, various geospatial data obtained by multiple institutes are necessary to be combined, and various sensors and voice technologies are required to be connected and utilized through ICT (Information and Communications Technologies) technology in near future.