• Journal of the Korean Geotechnical Society
• /
• v.39 no.7
• /
• pp.31-37
• /
• 2023

Since tunnels are built underground, it is impossible to check visually the location and degree of deterioration of steel ribs. Therefore, in tunnel maintenance, GPR images are generally used to detect steel ribs. While research on GPR image analysis employing artificial neural networks has primarily focused on detecting underground pipes and road damage, there have been limited applications for analyzing tunnel GPR data, specifically for steel rib detection, both internationally and domestically. In this study, a one-step object detection algorithm called YOLO, based on a convolutional neural network, was utilized to automate the localization of steel ribs using GPR data. The performance of the algorithm is then analyzed. Two datasets were employed for the analysis. A dataset comprising 512 original images and another dataset consisting of 2,048 augmented images. The omission rate, which represents the ratio of undetected steel ribs to the total number of steel ribs, was 0.38% for the model using the augmented data, whereas the omission rate for the model using only the original data was 7.18%. Thus, from an automation standpoint, it is more practical to employ an augmented dataset.

• 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.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5D
• /
• pp.821-829
• /
• 2006

Traffic load comprise primary input to pavement design causing pavement damage. therefore it should be proceeded suitable traffic load distribution modeling for pavement design and analysis. Traffic load have been represented by equivalent single axle loads (ESALs) which convert mixed traffic stream into one value for design purposes. But there are some limit to apply ESALs to other roads because it is empirical value developed as part of the original AASHO(American Association of State Highway Officials) road test. There have been many efforts to solve these problems. Several leading country have implemented M-E(Mechanistic-Empirical) design procedures based on mechanical concept. As a result, they established traffic load quantification method using load distribution model known as Axle Load Spectra. This paper details Axle Load Spectra and presents axle load distribution model based on normal mixture distribution function using truck load data collected by WIM system installed in national highway. Axle load spectra and axle load distribution model presented in this paper could be useful for basic data when making traffic load quantification plan for pavement design, overweight vehicle permit plan and pavement maintenance cost plan.

• Information Systems Review
• /
• v.25 no.4
• /
• pp.113-130
• /
• 2023

Due to economic development and increasing gross national income, the number of automobiles continues to rise, leading to a serious issue of illegal parking due to limited road conditions and insufficient parking facilities. Illegal parking causes significant inconvenience and displeasure to people and can even result in accidents and loss of lives. The severity of accidents and their consequences, related to the growing number of vehicles and illegal parking, is escalating, particularly in the metropolitan areas. Consequently, efforts are being made to address this problem as a cause of social issues and come up with measures to reduce illegal parking. In particular, half of the public complaints in the metropolitan area are related to illegal parking, and the highest physical and human damage occurs in Gyeonggi. Thus, this study aims to use machine learning techniques based on data related to illegal parking in Suwon city, Gyeonggi, to categorize regional characteristics and propose effective measures to crack down on illegal parking. Additionally, practical, social, policy, and legal measures to decrease illegal parking in the metropolitan area are suggested. This study has academic significance in that it solved the problem of illegal parking, which is mentioned as one of the social problems that cause traffic congestion, by classifying regional characteristics using K-prototype, a machine learning algorithm. Furthermore, the results of this study contribute to practical and social aspects by providing measures to decrease illegal parking in the metropolitan area.

• Journal of Cadastre & Land InformatiX
• /
• v.53 no.2
• /
• pp.67-77
• /
• 2023

As cities become overcrowded and concentrated, the demand for public services continues to increase due to the improvement of the living standards of urban residents. Among them, fire service can be seen as one of the important public services by reducing damage caused by accidents in emergency situations and affecting the improvement of access to medical services for urban residents. Rapid movement of patients and medical institutions within golden time and proper first aid are essential elements in emergency situations, and Seoul is a super-large city with a large population of about 10 million people and has a large number of emergency medical patients. Therefore, this study used spatial regression analysis to examine the factors affecting the delay factors of emergency dispatch in Seoul to secure golden time, and derived management priorities, and suggested implications for the management of emergency vehicle dispatch delay factors. As a result of the main analysis, land-use characteristics were the most influential factor in emergency vehicle dispatch time, and land-use mixing, commercial area density, average patient age, and average road length were found to affect emergency vehicle dispatch time in order. This study can be used as important basic data for an accurate understanding of the delay factors for emergency dispatch and preparing countermeasures according to priorities.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.1
• /
• pp.39-45
• /
• 2024

Seismic safety of expansion joints for piping systems has been underscored by water pipe ruptures and leaks resulting from the Gyeongju and Pohang earthquakes. Metal bellows in piping systems are applied to prevent damage from earthquakes and road subsidence in soft ground. Designed with a series of corrugated segments called convolutions, metal bellows exhibit flexibility to accommodate displacements. Several studies have examined variations in convolution shapes and layers based on the intended performance to be evaluated. Nonetheless, the research on the seismic performance of complex bellows having multiple corrugation heights is limited. In this study, monotonic loading tests, cyclic loading tests, and fatigue tests were conducted to evaluate the shear performance in seismic conditions, of metal bellows with variable convolution heights. Single- and triple-layer bellows were considered for the experimentation. The results reveal that triple-layer bellows exhibit larger maximum deformation and fatigue life than single-layer bellows. However, the high stiffness of triple-layer bellows in resisting internal pressure poses certain disadvantages. The convolutions are less flexible at lower displacements and experience leakage at a rate related to the variable height of the convolutions in certain conditions. At lower deformation rates, the fatigue life is rated higher as the number of layers increase. It converges to a similar fatigue life at higher deformation rates.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.33 no.4
• /
• pp.99-111
• /
• 2015

The objectives of this study were to investigate the location, shape, environment, and vegetation of the Village Forest in Gyeonggi-do and to evaluate the ecological integration and changes of the Village Forests to figure out the measures for conservation and management. There were 23 Village Forests remain in Gyeonggi-do. Ten Village Forests were established based on Feng-shui background. Many of them were found in Yongin area and southeast of Icheon. The Village Forests were owned by local community at 9 village and privately owned at 8 villages. Most Village Forests were managed by local communities except for the two managed by private person. Fifty-two percent of the Village Forests were in strip shape, and most of them were established by Feng-shui background or for the prevention of disasters. The average size of the Village Forests was relatively small at 3,046m2. The most frequent tree species found at the Village Forest were Zelkova serrata and Pinus densiflora. Over half of the number of Village Forests showed vertical structure of overstory trees only or overstory-sub overstory combination, which seemed to be resulted from the loss of understory plants by the activities of local residents. The Village Forests that had over 30% of damaged trees were found at 7 villages. The damages were caused by the road construction close to the groves, soil compaction, and tree death by covering lower stem with soil. The vitality of the damaged trees seemed to be significantly low compared to that of the undamaged. There were factors that determined the changes in the Village Forests: community ritual, institutional protection, designation as a water resource protection district, road construction, land use change, windstorm hazards, and development of forest areas. In order to conserve and manage the Village Forests appropriately, it is necessary to limit excessive use of the grove areas and maintain proper tree growing conditions by improving the soil environment. The development of neighborhood areas need to be controlled and community activities should be encouraged to maintain or restore the original landscape of the groves. Protection measures and supporting policies need to be enforced to keep the Village Forests from disappearing in near future.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.8 no.5
• /
• pp.137-145
• /
• 2008

In this study, to reduce the flood damage caused by flood discharge exceeding project flood, the primary technology was applied to determining the optimal location and size for underground sluiceway. The Jungrang Stream was selected for this study because the stream was overflowed and the embankment section of the stream was destroyed owing to localized torrential rainfall in 1998 and 2001. Considering 200-year frequency storm, the inlets of the underground discharge channel were located at Seoul City limits, the confluence of Danghyun Stream, Wolgye 1-gyo, and the confluence of Mukdong Stream. The outlets were located at the estuary of Jungrang Stream and rightbank of Banpo Bridge in Han River. The transverse discharge according to the variation of overflow depth at the inlet of underground discharge channel was estimated and the effect of inundation reduction was analyzed. To examine the appropriate scale of the underground discharge channel, the 8 operation methods for the management of outlet discharge were compared considering four rules (only storage, the constant discharge rate, the constant discharge volume, and the mixture of the constant discharge rate and discharge volume). As a result, the effect of inundation reduction was most significantly improved when the inlet was located at the confluence of Danghyun Stream. The appropriate size of underground sluiceway for 200-year frequency storm was studied, and as a result, the appropriate diameters of the underground discharge channel were 12 m in case of only storage(Rule D), 9m in 50% of discharge(Rule E), 8 m in constant discharge volume(Rule F), and 7 m in mixture method(Rule G). This investigation process can be applied to design the underground discharge channel when the inundation damage is significant in coastal area due to embankment overflow. The underground discharge channel in Jungrang Stream can also be used as an underground road to link Seoul City to Uijeongbu City during dry season.

• Korean Journal of Environment and Ecology
• /
• v.33 no.1
• /
• pp.9-15
• /
• 2019

Artiodactyla, which is an even-toed mammal, widely inhabits worldwide. In recent years, wild Artiodactyla species have attracted public attention due to the rapid increase of crop damage and road-kill caused by wild Artiodactyla such as water deer and wild boar and the decrease of some species such as long-tailed goral and musk deer. In spite of such public attention, however, there have been few studies on Artiodactyla in Korea, and no studies have focused on the trend analysis of Artiodactyla, making it difficult to understand actual problems. Many recent studies on trend used text-mining and co-occurrence analysis to increase objectivity in the classification of research subjects by extracting keywords appearing in literature and quantifying relevance between words. In this study, we analyzed texts from research articles of three countries (Korea, China, and Japan) through text-mining and co-occurrence analysis and compared the research subjects in each country. We extracted 199 words from 665 articles related to Artiodactyla of three countries through text-mining. Three word-clusters were formed as a result of co-occurrence analysis on extracted words. We determined that cluster1 was related to "habitat condition and ecology", cluster2 was related to "disease" and cluster3 was related to "conservation genetics and molecular ecology". The results of comparing the rates of occurrence of each word clusters in each country showed that they were relatively even in China and Japan whereas Korea had a prevailing rate (69%) of cluster2 related to "disease". In the regression analysis on the number of words per year in each cluster, the number of words in both China and Japan increased evenly by year in each cluster while the rate of increase of cluster2 was five times more than the other clusters in Korea. The results indicate that Korean researches on Artiodactyla tended to focus on diseases more than those in China and Japan, and few researchers considered other subjects including habitat characteristics, behavior and molecular ecology. In order to control the damage caused by Artiodactyla and to establish a reasonable policy for the protection of endangered species, it is necessary to accumulate basic ecological data by conducting researches on wild Artiodactyla more.

• Korean Journal of Environment and Ecology
• /
• v.28 no.5
• /
• pp.500-509
• /
• 2014

To prevent freezing of the road by fallen snow, Calcium chloride($CaCl_2$) as a deicer is used to very often and it can be harmful to roadside trees. This study was conducted to investigate the effects of Calcium chloride($CaCl_2$) as a deicer on growth and physiological traits of Acer triflorum according to different concentration of $CaCl_2$. We measured growth, chlorophyll contents, gas exchangement characteristics, chlorophyll fluorescence and mineral nutrition concentration in plant and soil. The experimental group was composed of four treatments including 0mM(control), 9mM(0.5 %), 18mM(1.0 %), 54mM(3.0 %). Before germinating new shoot, the dissolution of $CaCl_2$ was irrigated twice interval of a week. At 30 days after treatment, all treatments decreased total cholorophyll content, photosynthetic rate, transpiration rate, stomatal conductance and photochemical efficiency($F_v/F_m$) with increasing concentration of $CaCl_2$ and especially, they significantly reduced in 3.0 % treatment. In contrast, chlorophyll a/b ratio increased with an increase of $CaCl_2$ concentration and water use efficiency increased in 1.0 % and 3.0 % treatments. At 50 days after treatment, all treatments were decreased in chl a, chl b, total chlorophyll content, carotenoid content, photosynthetic capacity, photochemical efficiency($F_v/F_m$) and quantum yield of photosystem II(${\Phi}_{PSII}$) compared with control and 3.0 % treatments were withered. $Ca^{2+}$ and $Cl^-$ were accumulated in leaves and soil, which inhibited water absorption and electron transport and it caused the reduction of height growth rate more than 50 %. Although there was a little difference according to time and $CaCl_2$ concentration, all treatments decreased in growth rate and physiological activity slowed down. As time passed, these results got worse. Therefore we need to take a measure earlier in order to minimize damage of trees.