• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.105-116
• /
• 2023

The fatality rate of secondary accidents is seven times that of general traffic accidents. If limited to highways, one in four deaths are said to occur from secondary accidents. Unexpected situations which do not give drivers time to prepare are the cause of secondary accidents. This risk results in more fatalities on highways with high driving speeds. Existing studies have conducted research on traffic accidents and on secondary traffic accidents that occur after a primary traffic accident, without considering unexpected situations that may occur on the road. Therefore, to reduce damage and casualties caused by secondary accidents, there is a need to create a safe road environment by removing the possibility of causing accidents. This study analyzes whether the day of occurrence, time of occurrence, and radius of the curve of an unexpected situation are related to the occurrence of an unexpected situation. This study was based on data of accidents that occurred in 2022 on the Cheonan-Nonsan Expressway and the Seoul-Yangyang Expressway. The radius of the curve was calculated by dividing the section of the highway into straight, clothoid, and curved sections through cluster analysis. Results of the analysis indicate that the day and time of occurrence and the curve radius are associated with unexpected situations.

• Journal of Aerospace System Engineering
• /
• v.17 no.4
• /
• pp.67-74
• /
• 2023

Recently, Urban Aircraft Mobility (UAM) has been attracting attention as a transportation system of the future, and small drones also play a role in various industries. The failure of various types of aviation systems can lead to crashes, which can result in significant property damage or loss of life. In the defense industry, where aviation systems are widely used, the failure of aviation systems can lead to mission failure. Therefore, this study proposes an anomaly detection model using deep learning technology to detect anomalies in aviation systems to improve the reliability of development and production, and prevent accidents during operation. As training and evaluating data sets, current data from aviation systems in an extremely low-temperature environment was utilized, and a deep learning network was implemented using the convolutional neural network, which is a deep learning technique that is commonly used for image recognition. In an extremely low-temperature environment, various types of failure occurred in the system's internal sensors and components, and singular points in current data were observed. As a result of training and evaluating the model using current data in the case of system failure and normal, it was confirmed that the abnormality was detected with a recall of 98 % or more.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.15 no.1
• /
• pp.63-73
• /
• 2013

The research was conducted to determine a seed germination and seedling establishment of rice plant under seed coating materials such as iron, silicate, and phyllite and under covered with silicate and iron coated & silicate covered in the puddled wet hill seeding and wet line seeding methods. The seedling establishment was high in silicate and untreated control of 100%>phyllite coating of 91.5%>silicate coating of 88%>iron coating and silicate covered of 86%>silicate covered of 75.5% in the puddled wet hill seeding method, respectively. At 35days after treatment there was high in seedling height at silicate covered of 23.8cm>control of 23.6cm>silicate coating of 21.4cm>phyllite coating of 20.2cm>iron coating and silicate covered of 16.8cm>iron coating of 15.4cm. In puddle wet line seeding method rice seedling establishment was high at control and silicate covered of 100%>iron coating and silicate covered by 97.5%>phyllite coating by 94.8%>iron coating by 86%. Seedling height was high in silicate covered of 22.1cm>control of 21.2cm>silicate coating of 20.0cm>phyllite coating of 19.0cm>iron coating of 17.7cm>iron coating and silicate covered of 17.0cm, respectively.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.30 no.3
• /
• pp.277-286
• /
• 1985

From a series of studies conducted on the local maize lines at the Agr. College of the Chungnam National Univ., a few maize lines with many tillers and ears per plant were identified and tentatively named as MET. The purpose of the study was to evaluate the MET lines, which were selfed for five generations, for silage purpose under the different plant densities. A hybrid, Suwon #19 and a synthetic variety, Puyo #3${\times}$#2, were included for comparison. Plant height at harvesting times showed no significant varietal differences. However, the MET lines were very slow in early plant growth compared to the hybrid or synthetic variety, probably due to inbreeding depression of the MET lines. Total fresh weight at the harvesting times was highest in the MET 1 line. The MET 1 line was about 2,000 kgr. per 10a. higher than the hybrid at the harvesting time. The highest fresh weight was obtained when grown under the plant density of 60 ${\times}$ 20cm. Total dry weight per unit area showed the same tendency as the fresh weight. Total dry weight of MET 1 line was about 2.4 tons per 10a., which was about 10% higher than the hybrid, Suwon #19. As the fresh weight, the total dry weight was also highest in the plant density of 60 ${\times}$ 20cm. The grain yield per 10 are of MET 1 was comparable to the grain yield of the hybrid, especially in the low plant density, 60 ${\times}$ 40cm. The average number of effective tillers of MET lines were 4.5, while the mean tiller number of the hybrid or synthetic variety were none. However, the lodging was one of the problem for growing MET lines. The 100 kernel weight of MET lines was about 9 gr., while the 100 kernel weight of the hybrid or synthetic variety was about 30 grm.

• Journal of Korean Society of Forest Science
• /
• v.112 no.1
• /
• pp.117-125
• /
• 2023

Outbreaks of Ramulus mikado (Insecta: Phasmatodea: Phasmatidae) in the hilly areas of Mt. Bongsan, Mt. Cheonggye, and elsewhere in Seoul and Gyeonggi occurred from 2020 to 2021, causing serious defoliation. We evaluated the insecticidal effects of six eco-friendly organic materials and the insect-pathogenic fungus Metarhizium anisopliae against R. mikado. The fungus was isolated from naturally dead bodies of R. mikado in forest ecosystems. The results revealed that three eco-friendly organic materials containing azadirachtin or geraniol as active ingredients showed high mortality in the range of 85.2%-100%, which were rates similar to that of the chemical insecticide fenitrothion emulsifiable concentrate. All R. mikado adults that were sprayed with a conidial suspension of M. anisopliae at different concentrations were killed within a few days. In conclusion, three eco-friendly organic materials and M. anisopliae could be good alternatives to chemical insecticides.

• Korean Journal of Environmental Biology
• /
• v.39 no.4
• /
• pp.486-494
• /
• 2021

Watermelon (Citrullus lanatus (Thunb.) Matsum. & Nakai) is sensitive to low temperature and shows retarded growth under 10℃. Although early transplanting guarantees higher returns, it requires cost and labor to maintain the appropriate temperature for plant growth. Therefore, cultivars tolerant to chilling stress is necessary to reduce the cost and labor requirements. The purpose of this study is to analyze data on plant growth and fruit enlargement under continuous chilling night temperature to develop new cultivars tolerant to chilling temperature. Two cultivars expected to have chilling tolerance and another cultivar sensitive to chilling temperature were grown in greenhouses with chilling and optimal night temperature conditions. In the early growth stage after transplanting, the cultivars expected to have chilling tolerance showed better vine length, fresh weight and dry weight. However, one of the tolerant cultivars showed significantly lower vine length, leaf length and width, and petiole length than the sensitive cultivar during pollination period and later growth stage, showing genotype specific responses. The fruit length, width, and weight were also significantly lower in the tolerant cultivar. The fruit set ratio was significantly higher in the chilling sensitive cultivar than the two tolerant cultivars. These results suggest that the present chilling tolerant cultivars in watermelon were selected based on their performance in the early growth stage, and further studies on chilling tolerance in different growth and development stages are required to develop cultivars adapted to various forcing cultivation systems.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.189-200
• /
• 2022

Ground subsidence on urban roads is a social issue that can lead to human and property damages. Therefore, it is crucial to detect underground cavities in advance and repair them. Underground cavity detection is mainly performed using ground penetrating radar (GPR) surveys. This process is time-consuming, as a massive amount of GPR data needs to be interpreted, and the results vary depending on the skills and subjectivity of experts. To address these problems, researchers have studied automation and quantification techniques for GPR data interpretation, and recent studies have focused on deep learning-based interpretation techniques. In this study, we described a hyperbolic event detection process based on deep learning for GPR data interpretation. To demonstrate this process, we implemented a series of algorithms introduced in the preexisting research step by step. First, a deep learning-based YOLOv3 object detection model was applied to automatically detect hyperbolic signals. Subsequently, only hyperbolic signals were extracted using the column-connection clustering (C3) algorithm. Finally, the horizontal locations of the underground cavities were determined using regression analysis. The hyperbolic event detection using the YOLOv3 object detection technique achieved 84% precision and a recall score of 92% based on AP50. The predicted horizontal locations of the four underground cavities were approximately 0.12 ~ 0.36 m away from their actual locations. Thus, we confirmed that the existing deep learning-based interpretation technique is reliable with regard to detecting the hyperbolic patterns indicating underground cavities.

• Journal of agriculture & life science
• /
• v.50 no.4
• /
• pp.59-71
• /
• 2016

The occurrence and growth of grass and sedge weed species were investigated in the transplanted rice fields that have different transplanting dates from Apr. 30 to Jun 19 with 10-day interval. The growth and yield of rice plant grown without weed control examined in each plot that has different transplanting dates. Both grass and sedge weeds showed greater plant numbers in the early transplanted plots(Apr. 30 and May 10) than late transplanted plots. Based on the occurring number and dry weight of weeds, the experimental plots were classified into two groups, early group and late group. Weed occurrence and growth were not dramatically different within a group even the occurrence was enhanced as delayed transplanting. Echinochloa spp. that was the most problematic weed showed higher dry weight in early-transplanted field until July, however, the greater dry weight was observed in the late-transplanted plots after August. Sedge weeds including Eleocharis kuroguwai and Scirpus juincoides showed persistently higher value of dry weight in early-transplanted plots than late plots over the experimental period. As the puddling was conducted earlier, emergences of grass and sedge weeds were occurred early and weed growth rate became greater. Therefore, growth and yield of rice that transplanted early decreased more strongly due to the strong suppression by grass and sedge weeds showing the enhanced weed growth rates in early-transplanted plots. Based on the weed growth rate, the adverse effects of grass weeds was maintained for longer period than sedge weeds that showed higher growth rates before heading date of rice plant.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.15-27
• /
• 2022

In the past five years, the fatality rate of single-vehicle accidents has been 4.7 times higher than that of all accidents, so it is necessary to establish a system that can detect and respond to single-vehicle accidents immediately. The IoT(Internet of Thing)-based real-time traffic accident recognition system proposed in this study is as following. By attaching an IoT sensor which detects the impact and vehicle ingress to the guardrail, when an impact occurs to the guardrail, the image of the accident site is analyzed through artificial intelligence technology and transmitted to a rescue organization to perform quick rescue operations to damage minimization. An IoT sensor module that recognizes vehicles entering the monitoring area and detects the impact of a guardrail and an AI-based object detection module based on vehicle image data learning were implemented. In addition, a monitoring and operation module that imanages sensor information and image data in integrate was also implemented. For the validation of the system, it was confirmed that the target values were all met by measuring the shock detection transmission speed, the object detection accuracy of vehicles and people, and the sensor failure detection accuracy. In the future, we plan to apply it to actual roads to verify the validity using real data and to commercialize it. This system will contribute to improving road safety.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.27-36
• /
• 2023

In recent years, ransomware attacks have become more organized and specialized, with the sophistication of attacks targeting specific individuals or organizations using tactics such as social engineering, spear phishing, and even machine learning, some operating as business models. In order to effectively respond to this, various researches and solutions are being developed and operated to detect and prevent attacks before they cause serious damage. In particular, honeypots can be used to minimize the risk of attack on IT systems and networks, as well as act as an early warning and advanced security monitoring tool, but in cases where ransomware does not have priority access to the decoy file, or bypasses it completely. has a disadvantage that effective ransomware response is limited. In this paper, this honeypot is optimized for the user environment to create a reliable real-time dynamic honeypot file, minimizing the possibility of an attacker bypassing the honeypot, and increasing the detection rate by preventing the attacker from recognizing that it is a honeypot file. To this end, four models, including a basic data collection model for dynamic honeypot generation, were designed (basic data collection model / user-defined model / sample statistical model / experience accumulation model), and their validity was verified.