• Nuclear Engineering and Technology
• /
• 제54권5호
• /
• pp.1825-1834
• /
• 2022

Performing high-fidelity computational fluid dynamics (HF-CFD) to predict the flow and heat transfer state of the coolant in the reactor core is expensive, especially in scenarios that require extensive parameter search, such as uncertainty analysis and design optimization. This work investigated the performance of utilizing a multi-fidelity reduced-order model (MF-ROM) in PWR rod bundles simulation. Firstly, basis vectors and basis vector coefficients of high-fidelity and low-fidelity CFD results are extracted separately by the proper orthogonal decomposition (POD) approach. Secondly, a surrogate model is trained to map the relationship between the extracted coefficients from different fidelity results. In the prediction stage, the coefficients of the low-fidelity data under the new operating conditions are extracted by using the obtained POD basis vectors. Then, the trained surrogate model uses the low-fidelity coefficients to regress the high-fidelity coefficients. The predicted high-fidelity data is reconstructed from the product of extracted basis vectors and the regression coefficients. The effectiveness of the MF-ROM is evaluated on a flow and heat transfer problem in PWR fuel rod bundles. Two data-driven algorithms, the Kriging and artificial neural network (ANN), are trained as surrogate models for the MF-ROM to reconstruct the complex flow and heat transfer field downstream of the mixing vanes. The results show good agreements between the data reconstructed with the trained MF-ROM and the high-fidelity CFD simulation result, while the former only requires to taken the computational burden of low-fidelity simulation. The results also show that the performance of the ANN model is slightly better than the Kriging model when using a high number of POD basis vectors for regression. Moreover, the result presented in this paper demonstrates the suitability of the proposed MF-ROM for high-fidelity fixed value initialization to accelerate complex simulation.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.208-216
• /
• 2023

The purpose of our study is to design datasets for Artificial Intelligence learning for cold sea fish farming. Salmon is considered one of the most popular fish species among men and women of all ages, but most supplies depend on imports. Recently, salmon farming, which is rapidly emerging as a specialized industry in Gangwon-do, has attracted attention. Therefore, in order to successfully develop salmon farming, the need to systematically build data related to salmon and salmon farming and use it to develop aquaculture techniques is raised. Meanwhile, the catch of pollack continues to decrease. Efforts should be made to improve the major factors affecting pollack survival based on data, as well as increasing the discharge volume for resource recovery. To this end, it is necessary to systematically collect and analyze data related to pollack catch and ecology to prepare a sustainable resource management strategy. Image data was obtained using CCTV and underwater cameras to establish an intelligent aquaculture strategy for salmon and pollock, which are considered representative fish species in Gangwon-do. Using these data, we built learning data suitable for AI analysis and prediction. Such data construction can be used to develop models for predicting the growth of salmon and pollack, and to develop algorithms for AI services that can predict water temperature, one of the key variables that determine the survival rate of pollack. This in turn will enable intelligent aquaculture and resource management taking into account the ecological characteristics of fish species. These studies look forward to achievements on an important level for sustainable fisheries and fisheries resource management.

• Structural Engineering and Mechanics
• /
• 제73권3호
• /
• pp.271-286
• /
• 2020

Passive control technologies are commonly used in several areas to suppress structural vibrations by the addition of supplementary damping, and some modal damping may be heavy beyond critical damping even for regular structures with energy dissipation devices. The design of passive control structures is typically based on (complex) mode superposition approaches. However, the conventional mode superposition approach is predominantly applied to cases of under-critical damping. Moreover, when any modal damping ratio is equal or close to 1.0, the system becomes defective, i.e., a complete set of eigenvectors cannot be obtained such that some well-known algorithms for the quadratic eigenvalue problem are invalid. In this paper, a generalized complex mode superposition method that is suitable for under-critical, critical and over-critical damping is proposed and expressed in a unified form for structural displacement, velocity and acceleration responses. In the new method, the conventional algorithm for the eigenvalue problem is still valid, even though the system becomes defective due to critical modal damping. Based on the modal truncation error analysis, modal corrected methods for displacement and acceleration responses are developed to approximately consider the contribution of the truncated higher modes. Finally, the implementation of the proposed methods is presented through two numerical examples, and the effectiveness is investigated. The results also show that over-critically damped modes have a significant impact on structural responses. This study is a development of the original complex mode superposition method and can be applied well to dynamic analyses of non-classically damped systems.

• 한국멀티미디어학회논문지
• /
• 제23권2호
• /
• pp.301-316
• /
• 2020

Algorithm journalism refers to the practices of automated news generation using algorithms that generate human sounding narratives. Algorithm journalism is known to have strengths in automating repetitive tasks through rapid and accurate analysis of data, and has been actively used in news domains such as sports and finance. In this paper, we propose an interactive card news system that generates personalized local election articles in 2018. The system consists of modules that collects and analyzes election data, generates texts and images, and allows users to specify their interests in the local elections. When a user selects interested regions, election types, candidate names, and political parties, the system generates card news according to their interest. In the study, we examined how personalized card news are evaluated in comparison with text and card news articles by human journalists, and derived implications on the potential use of algorithm in reporting political events.

• 여성건강간호학회지
• /
• 제29권3호
• /
• pp.219-228
• /
• 2023

Purpose: Preterm birth is increasing, and obstetric nurses should have the competency to provide timely care. Therefore, training is necessary in the maternal nursing practicum. This study aimed to investigate the effects of practice education using a preterm-labor assessment algorithm on preterm labor-related knowledge and clinical practice confidence in senior nursing students. Methods: A pre-post quasi-experimental design with three groups was used for 61 students. The preterm-labor assessment algorithm was modified into three modules from the preterm-labor assessment algorithm by March of Dimes. We evaluated preterm labor-related knowledge, clinical practice confidence, and educational satisfaction. Data were analyzed with the paired t-test and repeated-measures analysis of variance. Results: The practice education using a preterm-labor assessment algorithm significantly improved both preterm labor-related knowledge and clinical practice confidence (paired t=-7.17, p<.001; paired t=-5.51, p<.001, respectively). The effects of the practice education using a preterm-labor assessment algorithm on knowledge lasted until 8 weeks but decreased significantly at 11 and 13 weeks after the program, while the clinical practice confidence significantly decreased at 8 weeks post-program. Conclusion: The practice education using a preterm-labor assessment algorithm was effective in improving preterm labor-related knowledge and clinical practice confidence. The findings suggest that follow-up education should be conducted at 8 weeks, or as soon as possible thereafter, to maintain knowledge and clinical confidence, and the effects should be evaluated.

• 컴퓨터교육학회논문지
• /
• 제11권4호
• /
• pp.1-12
• /
• 2008

본 논문은 초등정보교육과정의 "문제해결방법과 절차" 영역에 필요한 알고리즘적 사고 문제 모델로서 추가적인 학습 없이 바로 적용 가능하도록 알고리즘적 사고 기초 문제 모델을 제안하고, 초등수학내용요소를 이용한 기초 문제들과 평가 방법을 제안하였다. 이를 위해 5단계 난이도를 갖는 순서도 설계 방법에 기초하여, 알고리즘적 사고 문제 모델과 기초 문제 모델을 제안하고, 제안된 기초 모델에 초등 수학내용요소를 적용하여 초등 알고리즘적 사고 기초 문제를 도출한다. 그리고 개발된 알고리즘적 사고 문제들에 대해 실험 수업을 실시하여 알고리즘적 사고에 따른 답안들의 다양성과 효율성 평가 방법, 5단계 난이도 단계에 따라 개발된 문제들의 난이도 적절성에 대한 분석을 통해 본 논문에서 제안된 문제들의 알고리즘적 사고 문제로서의 적합성을 검증하였다.

• 전기학회논문지
• /
• 제65권10호
• /
• pp.1755-1760
• /
• 2016

Automation of greenhouses has proved to be extremely helpful in maximizing crop yields and minimizing labor costs. The optimum conditions for cultivating plants are regularly maintained by the use of programmed sensors and actuators with constant monitoring of the system. In this paper, we have designed a prototype of a smart greenhouse using Arduino microcontroller, simple yet improved in feedbacks and algorithms. Only three important microclimatic parameters namely moisture level, temperature and light are taken into consideration for the design of the system. Signals acquired from the sensors are first isolated and filtered to reduce noise before it is processed by Arduino. With the help of LabVIEW program, Time domain analysis and Fast Fourier Transform (FFT) of the acquired signals are done to analyze the waveform. Especially, for smoothing the outlying data digitally, Moving average algorithm is designed. With the implement of this algorithm, variations in the sensed data which could occur from rapidly changing environment or imprecise sensors, could be largely smoothed and stable output could be created. Also, actuators are controlled with constant feedbacks to ensure desired conditions are always met. Lastly, data is constantly acquired by the use of Data Acquisition Hardware and can be viewed through PC or Smart devices for monitoring purposes.

• 한국정보통신학회논문지
• /
• 제26권8호
• /
• pp.1248-1254
• /
• 2022

스쿨존에서 교통사고를 사전에 예방하려고 노력하고 있다. 하지만, 스쿨존 내 교통사고는 계속 발생하고 있다. 운전자가 어린이보호구역 내 상황 정보를 미리 알 수 있으면, 사고를 줄일 수 있다. 본 논문에서는 스쿨존 내 사각지대를 없애는 카메라, 사전 교통정보를 수집할 수 있는 번호인식 카메라 시스템을 설계한다. 차량속도 및 보행자를 인식하는 LIDAR 시스템을 개선하여 설계한다. 카메라 및 LIDAR에서 인식된 보행자 및 차량 영상 정보를 수집하고 가공하여, 인공지능 시계열 분석 및 인공지능 알고리즘을 적용한다. 본 논문에서 제안한 딥러닝으로 학습된 인공지능 교통사고 예방 시스템은, 스쿨존 진입 전 차량 내 모바일 장치에 스쿨존의 정보를 운전자에게 전달하는 강제 푸시서비스를 한다. 그리고 LED 안내판에 스쿨존 교통정보를 알람으로 제공한다.

• 한국지능시스템학회논문지
• /
• 제15권2호
• /
• pp.236-244
• /
• 2005

본 연구에서는 퍼지관계 및 진화론적 최적 다층 퍼셉트론에 기초한 퍼지다항식 뉴럴네트워크(FPNN)의 새로운 구조를 소개하고, 포괄적인 설계방법론을 토의하며, 그리고 일련의 수치적인 실험이 수행된다. 진화론적 최적 FPNN(EFPNN)의 구축을 위해 컴퓨터지능(CI)의 기반 기술을 이용한다. EFPNN의 구조는 규칙베이스 퍼지뉴럴네트워크와 다항식 뉴럴네트워크의 결합에 의한 유전자 최적 구동 하이브리드 시스템의 시너지 이용으로 얻어진다. 퍼지뉴럴네트워크는 EFPNN의 전체규칙 구조의 전반부에 기여하고, EFPNN의 후반부는 다항식 뉴럴네트워크를 사용하여 설계된다. EFPNN의 후반부를 위한 유전론적 최적 다항식 뉴럴네트워크의 개발은 두 최적화 기법에 의해 수행된다. 즉 구조적 최적화는 유전자알고리즘에 의해 수행되고, 파라미터 최적화는 최소자승법 기반의 학습을 통해 행하여진다. EFPNN의 성능 평가를 위해, 모델은 몇 가지 수치 예제를 이용한다. 비교에 의한 해석은 제안된 EFPNN이 이전에 제시된 다른 지능형 모델보다 높은 정확도 뿐만 아니라 좀 더 우수한 예측능력을 가지는 모델임을 보여준다.

• 창의정보문화연구
• /
• 제5권3호
• /
• pp.237-243
• /
• 2019

컴퓨팅 기술을 활용하여 문제를 해결하는 능력, 의사소통하는 능력, 협업하는 능력 등이 미래사회에 필요한 핵심역량으로 자리잡고 있다. 이러한 역량을 향상시키기 위해 우리나라 정보 교과에서는 알고리즘과 프로그래밍 능력을 중요한 목표로 설정하고 있다. 알고리즘적 사고는 컴퓨팅 사고력의 핵심적인 요소로 알고리즘을 설계하거나 프로그래밍 하는데 매우 중요한 역할을 하는 것으로 알려져 있고, 정보 교과의 목표를 설정하거나 학생의 성취를 측정할 때 활용되고 있다. 따라서 본 연구에서는 초,중,고등학생의 알고리즘적 사고를 측정하는 문항을 개발하고 수준을 측정하였다. 측정 결과, 학교급이 높아질 수록 알고리즘적 사고를 향상되는 것으로 분석되었고, 성별간 차이는 없는 것으로 분석되었다. 본 연구를 통해 알고리즘적 사고의 수준을 위한 문항을 구성하거나 난이도를 설정하는데 가이드를 제공할 수 있을 것으로 사료된다.