• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.513-524
• /
• 2022

Recently, detecting damages of civil infrastructures from digital images using deep learning technology became a very popular research topic. In order to adapt those methodologies to the field, it is essential to explain robustness of deep learning models. Our research points out that the existing pixel-based deep learning model evaluation metrics are not sufficient for detecting cracks since cracks have linear appearance, and proposes a new evaluation methodology to explain crack segmentation deep learning model more rationally. Specifically, we design, implement and validate a methodology to generate tolerance buffer alongside skeletonized ground truth data and prediction results to consider overall similarity of topology of the ground truth and the prediction rather than pixel-wise accuracy. We could overcome over-estimation or under-estimation problem of crack segmentation model evaluation through using our methodology, and we expect that our methodology can explain crack segmentation deep learning models better.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1573-1587
• /
• 2021

A Drone image is an ultra-high-resolution image that is several or tens of times higher in spatial resolution than a satellite or aerial image. Therefore, drone image-based remote sensing is different from traditional remote sensing in terms of the level of object to be extracted from the image and the amount of data to be processed. In addition, the optimal scale and size of data used for model training is different depending on the characteristics of the applied deep learning model. However, moststudies do not consider the size of the object to be found in the image, the spatial resolution of the image that reflects the scale, and in many cases, the data specification used in the model is applied as it is before. In this study, the effect ofspatial resolution and image size of drone image on the accuracy and training time of the semantic segmentation deep learning model of six wintering vegetables was quantitatively analyzed through experiments. As a result of the experiment, it was found that the average accuracy of dividing six wintering vegetablesincreases asthe spatial resolution increases, but the increase rate and convergence section are different for each crop, and there is a big difference in accuracy and time depending on the size of the image at the same resolution. In particular, it wasfound that the optimal resolution and image size were different from each crop. The research results can be utilized as data for getting the efficiency of drone images acquisition and production of training data when developing a winter vegetable segmentation model using drone images.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.221-227
• /
• 2021

In this paper, we conducted word-to-word similarity analysis of standardized datasets collected through web crawling for 10,000 Vertical Noise Mouses using Word2Vec, and made 92 students of computer engineering use the products presented for 5 days, and conducted self-report questionnaire analysis. The questionnaire analysis was conducted by collecting the words in the form of a narrative form and presenting and selecting the top 50 words extracted from the word frequency analysis and the word similarity analysis. As a result of analyzing the similarity of e-commerce user's product review, pain (.985) and design (.963) were analyzed as the advantages of click keywords, and the disadvantages were vertical (.985) and adaptation (.948). In the descriptive frequency analysis, the most frequently selected items were Vertical (123) and Pain (118). Vertical (83) and Pain (75) were selected for the advantages of selecting the long/demerit similar words, and adaptation (89) and buttons (72) were selected for the disadvantages. Therefore, it is expected that decision makers and product planners of medium and small enterprises can be used as important data for decision making when the method applied in this study is reflected as a new product development process and a review strategy of existing products.

• Journal of Aerospace System Engineering
• /
• v.15 no.5
• /
• pp.24-32
• /
• 2021

Personal Air Vehicle (PAV), Cargo UAS (Cargo UAS), and existing manned and unmanned aircraft are key vehicles for urban air mobility (UAM), and should demonstrate compatibility for the design of aircraft systems. The safety assessment required by for certification to ensure safety and reliability should be systematically performed throughout the entire cycle from the beginning of the aircraft development process. However, with the increasing complexity of safety critical aviation systems and the application of state-of-the-art systems, conventional experience-based and procedural-based safety evaluation methods make ir difficult to objectively assess safety requirements and system safety. Therefore, Model-Based Safety Assessment (MBSA) using modeling and simulation techniques is actively being studied at domestic and foreign countries to address these problems. In this paper, we propose a Model-Based Safety Evaluation framework utilizing modeling and simulation-based integrated flight simulators. Our case studies on the Traffic Collision Availability System (TCAS) and Wheel Brake System (WBS) confirmed that they are practical for future safety assessments.

• Journal of Korean Society of Forest Science
• /
• v.110 no.3
• /
• pp.440-452
• /
• 2021

This study identified and evaluated conditions for continued participation of private forest owners in forest carbon offset programs. The probability of continuing forest carbon offset projects, which delays greenhouse gas emissions by extending harvesting periods, increases with increasing price of carbon offset credits, public recognition of forest value, and education level. Willingness to Accept (WTA) was estimated using a Multiple Bounded Dichotomous Choice Question, which was 17,039 KRW/tCO₂ for extending age to 60 years, and 23,070 KRW/tCO₂ for 100 years. The following findings aim to promote participation and supply of carbon offset programs in private forests according to the study outcomes. First, introducing policies supporting private forest owners bearing opportunity costs for avoiding greenhouse gas emissions by postponing timber harvest is needed. Second, educational programs for private forest owners whose awareness of and interests in the public value of forest is necessary. Third, although having participated from the beginning of the offset program, finding ways to lead continuous participation of forest owners who are less likely to accept WTA is also necessary.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1199-1206
• /
• 2021

Accordingly, attention is also being paid to the agricultural use of remote sensing technique that non-destructively and continuously detects the growth and physiological status of crops. However, when remote sensing techniques are used for crop monitoring, it is possible to continuously monitor the abnormality of crops in real time. For this, standard growth information of crops is required and relative growth considering the cultivation environment must be identified. With the relationship between GDD (Growing Degree Days), which is the cumulative temperature related to crop growth obtained from ideal cultivation management, and the vegetation index as standard growth information, compared with the vegetation index observed with the spectralreflectance sensor(SRS_NDVI & SRS_PRI) in each rice paddy treated with standard cultivation management and non-fertilized, it was quantitatively identified as a time series. In the future, it is necessary to accumulate a database targeting various climatic conditions and varieties in the standard cultivation management area to establish a more reliable standard growth information.

• Journal of Conservation Science
• /
• v.37 no.5
• /
• pp.505-515
• /
• 2021

In this study, we evaluated the slope stability of the Pohang Daljeon-ri columnar joint (Natural Monuments # 415) and calculated the maximum energy, jumping height and moving distance of rockfalls using a simulation. Based on the results, we established the range of rockfall risk. The slopes of the Pohang Daljeon-ri columnar joint have dip directions of 93.79°, 131.99°, 165.54° and 259.84° from left (SW) to right (NE). Furthermore, they have a fan-like shape. The Pohang Daljeon-ri columnar joints are divided into four sections depending on the dip direction. The measurement results of the discontinuous face show that zone 1 is 125, zone 2 is 261, zone 3 is 262, zone 4 is 43. The results of slope stability analyses for each section using a stereographic projection method correspond to the range of planar and toppling failure. Although it is difficult to diagnose the type of failure, risk evaluation of currently falling rocks requires further focus. The maximum movement distance of a rockfall in the simulation was approximately 66 m and the rockfall risk range was the entire area under slope. In addition, it is difficult to forecast where a rock will fall as it rolls in various directions due to topographic factors. Thus, the installation of measures to prevent falling is suggested to secure the stability based on the results of the rockfall simulations and its probabilistic analysis.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.5
• /
• pp.102-113
• /
• 2021

The deterioration environments caused by de-icing salt and airborne chlorides in the seashore, evaluated in the "Detailed guideline for safety and management practice of facilities (performance evaluation)", were reviewed in terms of penetrated chlorides into concrete on various road facilities. Target concrete structures, in this study, were 4 concrete barriers in Gangwon area, 3 concrete barriers and 1 retaining wall in Busan area, and 4 bridges in Gangwon-do, Seoul, Gyeonggi-do, and Busan. The deterioration environments were classified into three categories: direct and indirect de-icing salt attack, and airborne salt attack depending on the distance to seashore and the height of pier, and the penetrated chlorides in to concrete were analyzed. The results showed that (1) the regional deterioration environments were clearly classified by de-icing salt sprayed days (snowfall days), (2) the penetrated chlorides increased significantly when leakage occurred through slabs or expansion joints, and (3) the airborne chlorides affected to a height of 20 m concrete in the seashore, Busan. From these, it could be confirmed that the chloride ion penetration properties depend on the exposed aging environment, member location and height, and deterioration status, even on the same structure, so the selection of target members and location is very important in the inspection and maintenance. If the database of penetrated chlorides properties in various deterioration environments is constructed, it is expected that the proactive durability management on concrete structures will be possible in the field.

• Journal of Navigation and Port Research
• /
• v.45 no.6
• /
• pp.346-351
• /
• 2021

With the goal of eradicating overwork, overload, and speeding of general freight cars(cargo) by the Ministry of Land, Infrastructure and Transport, Infrastructure and Transport, the "The Fare of safe transportation for freight cars System" has been enforced since 2020. 'The Fare of safe transportation for freight cars' rate for each item is being applied and supplemented, but the 'The Cost of safe transportation for freight cars' of general freight cars (cargo) and steel items is under discussion. The purpose of this study was to estimate the willingness to pay( WTP) for cargo. A survey was conducted on shippers, transportation companies (arrangers, carriers), and cargo drivers (using direct questioning among contingent valuation method (CVM) and the Tobit Regression analysis was conducted, and the average and median values of freight rates were derived using the estimated results, and the willingness to pay by tonnage of freight cars was confirmed. It is expected that the results of this study can be used as a reference to the "The Fare of safe transportation for freight cars Committee" an organization for deliberation and resolution of the 'The Cost of safe transportation for freight cars'.

• Korean Journal of Breeding Science
• /
• v.43 no.5
• /
• pp.457-463
• /
• 2011

Plant specific gene family, NAC (NAM, ATAF, and CUC) transcription factors have been characterized for their roles in plant growth, development, and stress tolerance. In this study, we isolated OsNAC69 gene and analyzed expression level by inoculation of bacterial leaf blight pathogen, Xanthomonas oryzae pv. oryzae (Xoo). NAC transcription factor family can be divided into five groups (I-V). On the basis of phylogenetic analysis, OsNAC69 was fall into group II. OsNAC69 was strongly induced 1 hr after infected with Xoo. To investigate its biological function in the rice, we constructed vector for overexpression in rice, and then generated transgenic rice lines. Gene expression of OsNAC69-overexpressed transgenic rice lines were analyzed by northern blot. Analysis of disease resistance to pathogen Xoo, nine OsNAC69-overexpressed transgenic rice lines showing high expression level of OsNAC69 were shown more resistant than wild type. These results suggest that OsNAC69 gene may play regulatory role during pathogen infection.