• Title/Summary/Keyword: 대체 모델

Search Result 1,179, Processing Time 0.032 seconds

CycleGAN Based Translation Method between Asphalt and Concrete Crack Images for Data Augmentation (데이터 증강을 위한 순환 생성적 적대 신경망 기반의 아스팔트와 콘크리트 균열 영상 간의 변환 기법)

  • Shim, Seungbo
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.21 no.5
    • /
    • pp.171-182
    • /
    • 2022
  • The safe use of a structure requires it to be maintained in an undamaged state. Thus, a typical factor that determines the safety of a structure is a crack in it. In addition, cracks are caused by various reasons, damage the structure in various ways, and exist in different shapes. Making matters worse, if these cracks are unattended, the risk of structural failure increases and proceeds to a catastrophe. Hence, recently, methods of checking structural damage using deep learning and computer vision technology have been introduced. These methods usually have the premise that there should be a large amount of training image data. However, the amount of training image data is always insufficient. Particularly, this insufficiency negatively affects the performance of deep learning crack detection algorithms. Hence, in this study, a method of augmenting crack image data based on the image translation technique was developed. In particular, this method obtained the crack image data for training a deep learning neural network model by transforming a specific case of a asphalt crack image into a concrete crack image or vice versa . Eventually, this method expected that a robust crack detection algorithm could be developed by increasing the diversity of its training data.

Development of Verification Method for ADCP (ADCP 유량 측정기기의 검정 방안 개발)

  • Noel Kang;Chi Young Kim;Kyung Min Kang;Yo Han Cho;Chang-Hwan Kim
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2023.05a
    • /
    • pp.305-305
    • /
    • 2023
  • 수문조사기기 검정은 강수량, 수위, 유량 등과 같은 수문자료를 관측하는 수문조사기기가 대상지역의 수문상황을 정확하게 관측하는지를 검사하는 일련의 과정으로 「수자원의 조사 계획 및 관리에 관한 법률」 제12조에 법적 기반을 두고 있다. 검정 대상은 강수량, 수위, 유속, 유사량, 토양수분량, 증발산량, 증발량 측정기기 총 7종이며, 환경부장관으로부터 한강홍수통제소가 검정업무를 위임받고, 한국건설기술연구원과 한국수자원조사기술원이 위탁받아 운영중에 있다. 최근에는 증발산량, 토양수분량 및 유량 측정기기기 등이 첨단화되어 기존 검정 방식에 대한보완 및 신설에 대한 요구가 증가하고 있다. 특히, 유량 측정시 기존에 사용하였던 회전식 유속계는 ADCP(Acoustic Doppler Current Profiler) 유량측정기기로 대체되어 활용률이 2013년 24%에서2021년 67%로 약 2.8배 급격히 증가하였다. 하지만 수문조사기기 검정 관련 고시 내 ADCP에 대한검사방법 및 허용오차 등의 규정이 부재하여 수문조사기기의 검정 공백이 발생하는 등의 문제가 존재하고 있다. 이에 본 연구에서는 ADCP 운영 및 기술 현황, 현행 법령, 국외 사례 등을 검토하여 ADCP 유량측정기기의 검사방법 및 허용오차에 대한 방안을 제시하고자 한다. ADCP 검사방법은 총 5단계로 외관검사, 자가진단 검사, 온도센서 검사, 수심측정 검사, 유량비교측정 검사에 따라 검정을 실시한다. 첫 번째 외관검사시에는 기기 외관과 센서 등 물리적 손상을 점검하고, 두 번째 자가진단 검사에서는 센서 변환 매트릭스 값, 수신부 센서 테스트, RAM/ROM 테스트, 통신 테스트 등에 관한 정상값 산출 여부를 확인한다. 세 번째 온도센서 검사에서는 검증용 온도센서를 이용한 값과 ADCP에 부착된 온도센서 값과 차이를 확인하고 ±2℃초과시 재검사 또는 적절한 조치를 취한 후 다음 단계의 검사를 진행한다. 네 번째 수심측정 검사에서는 수조 내 수심 측정을 확인하여 실제 수심과의 오차를 확인하고 ±1% 초과시 재검사 또는 적절한 조치 후 다음 검사를 실시한다. 유량비교 측정검사에서는 각 기기 간의 평균유량의 상대오차를 평가하는 것으로 ±5%미만에는 합격, ±5이상 ±10%미만에서는 재검사, ±10%이상에서는 공장수리를 권고하도록 하고, 1~5 단계의 검사를 통과한 기기를 대상으로 인증서를 발급하도록 한다. 유량비교 측정검사시에는 매년 ADCP를 사용하는 일반기업 및 공공기관 등이 모여 ADCP의 성능을 상호간 비교하는 'ADCP 기술협력 워크숍'을 확장하여 실시할 수 있다. 각 검사 단계의 허용오차는 USGS 또는 제조사 기준과 2022년 ADCP 기술협력 워크숍 성능검사 분석 결과를 토대로 하였다. 본 ADCP 검정 방안은 향후 ADCP 모델별로 단계별 시범 검토를 통해 세부사항에 대한 제시가 필요하며, 온도센서 검사, 수심측정 검사, 유량 비교측정검사에 대한 허용오차에 대한 타당성에대한 검증 및 검토가 이루어져야 할 것으로 사료된다.

  • PDF

The Characteristics of Zhu Xi's Theory of I-Qing in Yi Xue Qi Meng(易學啓蒙) (『역학계몽』에 나타난 주자역학의 특징 - 소강절 역학의 수용과 변용을 중심으로 -)

  • Yi, Suhn Gyohng
    • The Journal of Korean Philosophical History
    • /
    • no.28
    • /
    • pp.387-415
    • /
    • 2010
  • This article examines Zhu Xi(朱熹)'s theory of I-Qing(易經) present in Yi Xue Qi Meng. Zhu Xi aims to establish a novel Confucian theory of I-Qing, examining the study of I-Qing in Han Dynasity and the Taoist theory of I-Qing. To this end, he embraces Shao Yong(邵雍)'s theory of Xian Tian. Adapting the notion of Xian Tian(先天) as developed by Shao, he completes the Image-Number(象數) Theory of Hetu-Luoshu(河圖洛書). While discussing Hetu Luoshu, Zhu Xi argues that the Image and Number are not merely a form of prognostication, but a medium that reveals the principles of the nature and the sagely ways of mind. In addition, by studing I-Zhuan(易傳) in authoring Yi Xue Qi Meng, Zhu Xi maintains that the notions of Image and Number as he understands were to be approved by Confucius. This leads to the unification of Sho Yong's Tai-Ji(太極), Zou Dun Yi(周 敦頤)'s Tai-Ji, and Tai-Ji in Hetu. Through this work, Zhu Xi attempts to construct a systematic philosophy that straddles ontology and value theory, while identifying Li (理) with Xiang (象) and Shu (數). The Image-Number Theory of Hetu-Luoshu has replaced numerous theories of Image and Number at the time of Zhu Xi. Based on this theory, he restores the method of divination as presented in Xi CI Zhuan(繫辭傳). By successfully applying his theory of Image and Number to interpreting a number of recorded examples of divination during the Spring and Autumn period and the Warring States period, Zhu Xi demonstrates that his theory is not only an abstract metaphysical theory, but also can function as an adaptable method of divination.

Successful Positioning Strategy of KIA K5 - by understanding market needs - (기아자동차 K5의 포지셔닝 성공사례 - 변화하는 시장을 이해하고 주도하다 -)

  • Seo, Jiyoung;Lee, Doo-Hee;Lee, Jong-Ho;Jeon, Ki Heung
    • Asia Marketing Journal
    • /
    • v.13 no.3
    • /
    • pp.265-274
    • /
    • 2011
  • The objective of this case study is to analyze how effectively KIA K5, which is a leading mid-size car brand, has positioned itself into the mid-size car market. Before KIA launched the K5, Sonata and SM5 were the leading brands in the mid-size car market. They had loyal customers who like their similar images. As many competitors keep launching new brands or new designs into the car industry, Sonata and SM5 were pressured to introduce new versions. But, the YF Sonata and the New SM5 failed to catch up with the new trends in the market. Whilst YF Sonata was perceived as too innovative, the New SM5 was treated as an old car by the target customers of the mid-size car. While the two leading brands struggled to attract customers, KIA K5 found a new market space by identifying and focusing on the lucrative replace and up-grade demand segment and filling the gap between the current product category values and the emerging mid-size car category values. The K5 found the right values that customers need and successfully articulated the values to the customers. This case study illustrates that a successful positioning strategy can be effectively employed to attract customers in the saturated car manufacturing industry. This case can be summarized as the successful positioning strategy of KIA K5 is comprised of four primary pillars: design innovation, market analysis, STP (segmentation, targeting, and positioning), and launch strategy. The KIA K5 case study provides valuable insights and implications for many other companies that are planning to find a proper positioning strategy for their own business.

  • PDF

Influence of Digital Experience Factors on Purchase - Focusing on Moderating Effects of Digital Experience Frequency - (디지털 경험 요소가 구매에 미치는 영향 -경험빈도의 조절효과를 중심으로-)

  • Jung, Sang Hee;Chung, Byoung Gyu
    • Journal of Venture Innovation
    • /
    • v.3 no.2
    • /
    • pp.23-39
    • /
    • 2020
  • The 4th Industrial Revolution and Covid 19 are moving the fashion industry from offline to online. Fashion shows that took place offline are being replaced by online. Online is greatly increasing consumers' digital customer experience based on digital technologies. In this study, we studied the effect of digital experience factors on digital customer satisfaction based on the Schmitt(1999)'s experience marketing. The effect of digital customer satisfaction on purchase, continuous use intention, and recommendation intention were also studied. In addition, the moderating effect of experience frequency was studied. We randomly sampled 180 individuals among fashion mall users.. SPSS 24, AMOS 23 and Process Macro 3.5 were used for statistical analysis. In the study in which digital experience factors influence digital customer satisfaction, all except the digital act showed positive influence. The impact of influence was digital sense (β = .366) > digital think (β = .225)> digital feel (β = .191) > digital relate(β = .163). Digital customer satisfaction have been positive impact on purchasing, continuance use and recommendation intention. In the moderating effect of digital experience frequency, between digital feel, digital act and digital customer experience showed a statistically effective relationship. Based on the this study, We suggested theoretical and practical implications.

Study on Predicting the Designation of Administrative Issue in the KOSDAQ Market Based on Machine Learning Based on Financial Data (머신러닝 기반 KOSDAQ 시장의 관리종목 지정 예측 연구: 재무적 데이터를 중심으로)

  • Yoon, Yanghyun;Kim, Taekyung;Kim, Suyeong
    • Asia-Pacific Journal of Business Venturing and Entrepreneurship
    • /
    • v.17 no.1
    • /
    • pp.229-249
    • /
    • 2022
  • This paper investigates machine learning models for predicting the designation of administrative issues in the KOSDAQ market through various techniques. When a company in the Korean stock market is designated as administrative issue, the market recognizes the event itself as negative information, causing losses to the company and investors. The purpose of this study is to evaluate alternative methods for developing a artificial intelligence service to examine a possibility to the designation of administrative issues early through the financial ratio of companies and to help investors manage portfolio risks. In this study, the independent variables used 21 financial ratios representing profitability, stability, activity, and growth. From 2011 to 2020, when K-IFRS was applied, financial data of companies in administrative issues and non-administrative issues stocks are sampled. Logistic regression analysis, decision tree, support vector machine, random forest, and LightGBM are used to predict the designation of administrative issues. According to the results of analysis, LightGBM with 82.73% classification accuracy is the best prediction model, and the prediction model with the lowest classification accuracy is a decision tree with 71.94% accuracy. As a result of checking the top three variables of the importance of variables in the decision tree-based learning model, the financial variables common in each model are ROE(Net profit) and Capital stock turnover ratio, which are relatively important variables in designating administrative issues. In general, it is confirmed that the learning model using the ensemble had higher predictive performance than the single learning model.

Proximal Policy Optimization Reinforcement Learning based Optimal Path Planning Study of Surion Agent against Enemy Air Defense Threats (근접 정책 최적화 기반의 적 대공 방어 위협하 수리온 에이전트의 최적 기동경로 도출 연구)

  • Jae-Hwan Kim;Jong-Hwan Kim
    • Journal of the Korea Society for Simulation
    • /
    • v.33 no.2
    • /
    • pp.37-44
    • /
    • 2024
  • The Korean Helicopter Development Program has successfully introduced the Surion helicopter, a versatile multi-domain operational aircraft that replaces the aging UH-1 and 500MD helicopters. Specifically designed for maneuverability, the Surion plays a crucial role in low-altitude tactical maneuvers for personnel transportation and specific missions, emphasizing the helicopter's survivability. Despite the significance of its low-altitude tactical maneuver capability, there is a notable gap in research focusing on multi-mission tactical maneuvers that consider the risk factors associated with deploying the Surion in the presence of enemy air defenses. This study addresses this gap by exploring a method to enhance the Surion's low-altitude maneuvering paths, incorporating information about enemy air defenses. Leveraging the Proximal Policy Optimization (PPO) algorithm, a reinforcement learning-based approach, the research aims to optimize the helicopter's path planning. Visualized experiments were conducted using a Surion model implemented in the Unity environment and ML-Agents library. The proposed method resulted in a rapid and stable policy convergence for generating optimal maneuvering paths for the Surion. The experiments, based on two key criteria, "operation time" and "minimum damage," revealed distinct optimal paths. This divergence suggests the potential for effective tactical maneuvers in low-altitude situations, considering the risk factors associated with enemy air defenses. Importantly, the Surion's capability for remote control in all directions enhances its adaptability in complex operational environments.

Lateral Resistance Behavior Analysis of Drilled Shafts in Multi-layered Soil (다층지반에 근입된 현장타설말뚝의 수평 지지거동분석)

  • Jang, Seo-Yong;Jeong, Jae-Hoon;Kim, Jong-Ryeol
    • Journal of the Korea institute for structural maintenance and inspection
    • /
    • v.12 no.4
    • /
    • pp.61-70
    • /
    • 2008
  • In this research, load-transfer-function method was selected, because that is widely used in geotechnical engineering among the analysis methods to verify the behavior of load-lateral displacement. Lateral loading test of field scale was conducted, this measured data was analyzed. From the analysis, the model of load-lateral displacement was suggested. The test results were studied and compared to the commercial programs, 'LPILE', which contain the load transfer functions proposed before. By analysis of measure data of load-lateral displacement that expressed to several functions, $y=ae^{bx}$ model was the simplest and applicable to the field. In that case a value converged about 1.3, b value had a tendency to converge about 0.02. From the comparison analysis between measured data and load transfer function by 'LPILE', it is examined that if the lateral load is small, calculated displacements of them show a similar value compared to measured values. Furthermore, the bigger lateral loads, the bigger calculated values compared to the measured data. If the results are compared by Matlock-Reese method and Matlock-API method, Matlock-Reese method shows result of safe side because lateral displacement is calculated greatly relatively.

High fructose and high fat diet increased bone volume of trabecular and cortical bone in growing female rats (고과당 및 고지방 식이의 섭취가 성장기 동물모델의 골성장과 골성숙에 미치는 영향)

  • Ahn, Hyejin;Yoo, SooYeon;Park, Yoo-Kyoung
    • Journal of Nutrition and Health
    • /
    • v.48 no.5
    • /
    • pp.381-389
    • /
    • 2015
  • Purpose: The objective of this study was to investigate the effects of a high fructose and fat diet on bone growth and maturation in growing female rats. Methods: Three-week-old female SD rats were randomly assigned to four experimental groups; the control group (CON: fed control diet based on AIN-93G, n = 8); the high-fructose diet group (HFrc: fed control diet with 30% fructose, n = 8); the high-fat diet group (Hfat: fed control diet with 45 kcal% fat, n = 8); and the high-fat diet plus high fructose group (HFrc + HFat: fed diets 45 kcal% fat with 30% fructose, n = 8). Each group was assigned their respective diets for the remaining eight weeks. Bone-related parameters (bone mineral density (BMD) and structural parameters, osteocalcin (OC), deoxypyridinoline (DPD)) and morphologic changes of kidney were analyzed at the end of the experiment. Results: Final body weights and weight gain were higher in the HFat and HFrc + HFat groups and showed higher tendency in the HFrc group compared with those of the CON group (p < 0.05); however, no significant difference in caloric intake was observed among the four experimental groups. The serum OC levels of the HFrc and HFrc + HFat groups were lower than those of the CON and HFat groups (p < 0.05). Urinary levels of DPD did not differ among the experimental groups. BV/TV and Tb.N of trabecular bone were higher in the HFrc + HFat group and showed a higher tendency in the HFrc group than those of the CON and HFat groups (p < 0.05). Tb.Pf of trabecular bone were lower in the HFrc + HFat group than those in the CON and HFat groups (p < 0.05). However, no difference in trabecular BMD was observed among the experimental groups. Cortical bone volume was higher in the HFat and HFrc + HFat groups than in the CON and HFrc groups (p < 0.05). No morphology change in kidney was observed among the experimental groups. Conclusion: Our study suggests that 8 weeks of high-fructose and high fat intake could improve the bone quality (Structural parameters) of trabecular and cortical bone of tibia in growing female rats.

Genetic Model of Mineral Exploration for the Korean Au-Ag Deposits; Mugeug Mineralized Area (한국 금-은 광상의 효율적 탐사를 위한 성인모델;무극 광화대를 중심으로)

  • 최선규;이동은;박상준;최상훈;강흥석
    • Economic and Environmental Geology
    • /
    • v.34 no.5
    • /
    • pp.423-435
    • /
    • 2001
  • The gold-silver vein deposits in the Mugeug mineralized area are emplaced in late Cretaceous biotite granite associated with the pull-apart type Cretaceous Eumseong basin. Mugeug mine in northern part is composed of multiple veins showing relatively high gold fineness and is characterized by sericitization, chloritization and epidotization. The ore-forming fluids were evolved by dilution and cooling mechanisms at relatively high temperature and salinity (=30$0^{\circ}C$,1~9 equiv. wt. % NaCl) and highly-evolved meteoric water ($\delta$$^{18}$ O;-1.2~3.7$\textperthousand$) and gold mineralization associated with sulfides tormed at temperatures between 260 and 22$0^{\circ}C$ and within sulfur fugacity range of 10$^{-11.5}$ ~ 10$^{-13.5}$ atm. In contrast, Geumwang, Geumbong and Taegueg mines show the low fineness values, in southern part are characterized by increasing tendency of simple and/or stockwork veins and by kaolinitization, silicificatitan, carbonatization and smectitization. These droposits formed at relatively low temperature and salinity (<23$0^{\circ}C$, <3 equiv. wt. % NaCl) from ore-forming fluids containing greater amounts of less-evolved meteoric waters ($\delta$$^{18}$ O;-5.5~4.0$\textperthousand$), and silver mineralization representing various gold-and/or silver-bearing minerals formed at temperatures between 200 and 15$0^{\circ}C$ and from sulfur fugacity range of 10$^{-15}$ ~10$^{-18}$ atm These results imply that mineralization in the Mugueg area formed at shallow-crustal level and categorize these deposits as low-sulfidation epithermal type. The genetic differences between the northern and southern parts reflect the evolution of the hydrothermal system due to a different physicochemical environment from heat source area (Mugeug mine) to marginal area (Taegeum mine) in a geothermal field.

  • PDF