• 한국정밀공학회지
• /
• 제15권9호
• /
• pp.15-24
• /
• 1998

In this research. we have proposed a new technique to determine .the combination of design parameters for the process design of a hot forged product using artificial neural network(ANN) and statistical design of experiments(DOE). The investigated problem involves the adequate selection of the aspect ratio of billet, the ram velocity and the friction factor as design parameters. An optimal billet satisfying the forming limitation, die filling, load and energy as well as more uniform distribution of effective strain, is determined by applying the ability of artificial neural network and considering the analysis of mean and variation on the functional requirement. This methodology will be helpful in designing and controlling parameters on the shop floor which would yield the best design solution.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권4호
• /
• pp.171-177
• /
• 2019

This study aims to investigate the effect of eating-out types on the acceptance intention of artificial seasoning when consumers eat out at restaurants. Eating-out types considered to be typical when customers visit restaurants, such as the food-exploratory type, health-oriented type, and convenience-seeking type, were studied. Based on the research of previous studies, three eating-out types were selected for the study, which were "food-exploratory", "convenience-seeking", "health-oriented". This study was conducted by AMOS 22.0 with 300 questionnaires, and the Structural Equation Model (SEM) was used for examining the hypotheses as statistical method in this study. As a result, eating-out types such as "food-exploratory" and "convenience-seeking" were found to significantly affect the acceptance intention of artificial seasoning. However, consumers' acceptance intention of artificial seasoning differed depending on their consumption value. The path coefficients from food-exploratory type and health-oriented type to acceptance intention were more significant in the hedonic-oriented group than the utilitarian-oriented group. The results of this study suggest eating-out types relate to acceptance intention of artificial seasoning and provide meaningful implications for consumers' psychological consumption value when they consider artificial seasoning.

• Journal of Ecology and Environment
• /
• 제38권3호
• /
• pp.343-352
• /
• 2015

The landscape setting of a habitat strongly influences the distribution, abundance, and species composition of waterfowl. Thus, habitat assessment is very important to understand the habitat characteristics that sustain waterfowl assemblages. In this study, we hypothesized that the excessive use of artificial materials when new wetlands are constructed negatively influences wintering waterfowl. To test this hypothesis, we measured environmental factors, assessed habitat, and investigated waterfowl at 13 artificial wetlands in the Nakdong River Basin. There were greater numbers of waterfowl species and individuals in artificial wetlands with high habitat assessment scores. In contrast, environmental factors did not affect waterfowl distribution. In particular, features of natural habitats, such as macrophytes and sandbars, and the surrounding land-use patterns were important factors for sustaining waterfowl assemblages in each created wetland. Our results show that promoting naturalness in wetlands and surrounding areas would increase the species diversity and abundance of waterfowl. Further, complex habitats, such as wetlands and some terrestrial habitats, support both aquatic and terrestrial species because mixed habitats feature a larger array of food sources than more limited habitats do.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.252-259
• /
• 2022

Artificial intelligence is used in fusion with image processing techniques using cameras. Image processing technology is a technology that processes objects in an image received from a camera in real time, and is used in various fields such as security monitoring and medical image analysis. If such image processing reduces the accuracy of recognition, providing incorrect information to medical image analysis, security monitoring, etc. may cause serious problems. Therefore, this paper uses a mixture of YOLOv4-tiny model and image processing algorithm and uses the COCO dataset for learning. The image processing algorithm performs five image processing methods such as normalization, Gaussian distribution, Otsu algorithm, equalization, and gradient operation. For RGB images, three image processing methods are performed: equalization, Gaussian blur, and gamma correction proceed. Among the nine algorithms applied in this paper, the Equalization and Gaussian Blur model showed the highest object detection accuracy of 96%, and the gamma correction (RGB environment) model showed the highest object detection rate of 89% outdoors (daytime). The image binarization model showed the highest object detection rate at 89% outdoors (night).

• Structural Engineering and Mechanics
• /
• 제87권6호
• /
• pp.517-527
• /
• 2023

The severe deterioration of structures has led to extensive research on the development of structural repair techniques using composite materials. Consequently, previous researchers have devised various analytical methods to predict the interface performance of bonded repairs. However, these analytical solutions are highly complex mathematically and necessitate numerous calculations with a large number of iterations to obtain the output parameters. In this paper, an artificial neural network prediction models is used to calculate the interfacial stress distribution in RC beams strengthened with FRP sheet. The R2value for the training data is evaluated as 0.99, and for the testing data, it is 0.92. Closed-form solutions are derived for RC beams strengthened with composite sheets simply supported at both ends and verified through direct comparisons with existing results. A comparative study of peak interfacial shear and normal stresses with the literature gives the usefulness and effectiveness of ANN proposed. A parametrical study is carried out to show the effects of some design variables, e.g., thickness of adhesive layer and FRP sheet.

• 대한영상의학회지
• /
• 제85권5호
• /
• pp.834-847
• /
• 2024

인공지능(artificial intelligence; 이하 AI)은 진단 정확도와 효율성을 높여 영상의학 분야에 변화를 가져오고 있지만, 예측 불확실성은 여전히 중요한 과제로 남아 있다. 본 리뷰에서는 주요 불확실성의 원인인 분포 외(out-of-distribution) 불확실성, 데이터 내재적 불확실성(aleatoric uncertainty), 모델 불확실성을 다루며, 안전한 AI 통합을 위해 독립적인 신뢰성 지표와 설명 가능한 AI의 중요성을 강조한다. 독립적인 신뢰성 지표는 AI 예측의 신뢰성을 평가하는 데 기여하며, 설명 가능한 AI는 투명성을 제공하여 AI와 영상의학 전문의 간의 협업을 강화한다. 오류 무관용(zero error tolerance) 모델의 개발은 오류를 최소화하도록 설계되어, 안전성의 새로운 기준을 제시하였다. 이러한 문제를 해결함으로써 AI는 영상의학에서 신뢰할 수 있는 동반자로 자리 잡아, 환자 진료 수준과 결과를 개선하는 데 기여할 것이다.

• Journal of Biosystems Engineering
• /
• 제25권3호
• /
• pp.213-220
• /
• 2000

Grafting of fruit-bearing vegetables has been widely used to increase the resistance to soil-borne diseases, to increase the tolerance to low temperature or to soil salinity, to increase the plant vigor, and to extend the duration of economic harvest time. After grafting, it is important to control the environment around grafted seedlings for the robust joining of a scion and rootstock. Usually the shading materials and plastic films are used to keep the high relative humidity and low light intensity in greenhouse or tunnel. It is quite difficult to optimally control the environment for healing and acclimation of grafted seedlings under natural light. So the farmers or growers rely on their experience for the production of grafted seedling with high quality. If artificial light is used as a lighting source for graft-taking of grafted seedlings, the light intensity and photoperiod can be easily controlled. The purpose of this study was to develop a prototype system for the graft-taking enhancement of grafted seedlings using artificial lighting and to investigate the effect of air current speed on the distribution of air temperature and relative humidity in a graft-taking enhancement system. A prototype graft-taking system was consisted by polyurethane panels, air-conditioning unit, system controller and lighting unit. Three band fluorescent lamps (FL20SEX-D/18, Kumho Electric, Inc.) were used as a lighting source. Anemometer (Climomaster 6521, KANOMAX), T-type thermocouples and humidity sensors (CHS-UPS, TDK) were used to measure the air current speed, air temperature and relative humidity in a graft-taking system. In this system, air flow acted as a driving force for the diffusion of heat and water vapor. Air current speed, air temperature and relative humidity controlled by a programmable logic controller (UP750, Yokogawa Electric Co) and an inverter (MOSCON-G3, SAMSUNG) had an even distribution. Distribution of air temperature and relative humidity in a graft-taking enhancement system was fairly affected by air current speed. Air current speed higher than 0.1m/s was required to obtain the even distribution of environmental factors in this system. At low air current speed of 0.1m/s, the evapotranspiration rate of grafted seedlings would be suppressed and thus graft-taking would be enhanced. This system could be used to investigate the effects of air temperature, relative humidity, air current speed and light intensity on the evaportranspiration rate of grafted seedlings.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2009년도 춘계학술대회 미래 IT융합기술 및 전략
• /
• pp.107-113
• /
• 2009

This paper deals with noninformative priors for such as Jeffres' prior, reference prior and probability matching prior for scale parameter of exponential distribution when the data are collected in multiple step stress accelerated life tests. We find the noninformative priors for this model and show that the reference prior satisfies first order matching criterion. Using artificial data, we perform Bayesian analysis for proposed priors.

• 한국지하수토양환경학회지:지하수토양환경
• /
• 제16권6호
• /
• pp.66-78
• /
• 2011

It is getting difficult to manage water resources in South Korea because more than half of annual precipitation is concentrated in the summer season and its intensity is increasing due to global warming and climate change. Artificial recharge schemes such as well recharge of surface water and roof-top rainwater harvesting can be a useful method to manage water resources in Korea. In this study, potential artificial recharge site is evaluated using geographic information system with hydrogeological and social factors. The hydrogeological factors include annual precipitation, geological classification based on geological map, specific capacity and depth to water level of national groundwater monitoring wells. These factors were selected to evaluate potential artificial recharge site because annual precipitation is closely related to source water availability for artificial recharge, geological features and specific capacity are related to injection capacity and depth to water is related to storage capacity of the subsurface medium. In addition to those hydrogeological factors, social aspect was taken into consideration by selecting the areas that is not serviced by national water works and have been suffered from drought. These factors are graded into five rates and integrated together in the GIS system resulting in spatial distribution of artificial recharge potential. Cheongsong, Yeongdeok in Gyeongsangbuk-do and Hadong in Gyeongsangnam-do, and Suncheon in Jeollanam-do were proven as favorable areas for applying artificial recharge schemes. Although the potential map for artificial recharge in South Korea developed in this study need to be improved by using other scientific factors such as evaporation and topographical features, and other social factors such as water-curtain cultivation area, hot spring resorts and industrial area where groundwater level is severely lowered, it can be used in a rough site-selection, preliminary and/or feasibility study for artificial recharge.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 C
• /
• pp.1126-1129
• /
• 1999

In this paper theoretical review for the design and the algorithm of Artificial Fault Generator, on the power distribution center is which able to purposely generate and get rid of fault with the view of testing distribution systems including switchgears, was made. For the following paper verification with EMTP will be performed in order to review the function and the algorithm so that the optimized design can be established.