http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 박태희(Park Tae Hui) (검색결과 6 건)
- 무료
- 기관 내 무료
- 유료
-
-
-
영흥 풍력발전단지의 풍력발전량 예측을 위한 입력변수 선정 및 인공신경망과 1차원 합성곱 신경망 비교
박태희(Tae-Hui Park),장다슬(Da-Seul Jang),배경민(Gyeong-Min Bae),김경민(Kyung-Min Kim),안종화(Johng-Hwa Ahn) 대한환경공학회 2021 대한환경공학회지 Vol.43 No.4
목적 : 본 연구에선 비선형적 풍력발전량 예측 모델 개발을 목적으로 총 설치 용량 46 MW의 풍력발전단지가 설치된 영흥 풍력발전 단지의 자료를 이용하여 인공신경망(artificial neural network, ANN)과 1차원 합성곱신경망(1-dimension convolutional neural network, 1D-CNN)의 성능을 비교하고자 하였다. 방법 : 자료는 46 MW 발전능력을 가진 영흥 풍력발전단지의 2018년 1월부터 12월의 1시간 단위 풍력발전량 자료와 기상청에서 얻은 기상자료를 이용하였다. 최적 입력변수를 선정을 위하여 문헌연구를 바탕으로 시행착오를 거쳐 인자를 선정하였다. 전처리 과정을 거친 17,306개의 자료의 80%를 학습(training), 20%를 테스트(test)으로 사용하였으며, 학습 자료의 20%를 검증(validation)자료로 구성하였다. 모델 내 활성화 함수로는 rectified linear unit를 사용하였으며, 시행착오법을 통해 하이퍼파라미터(hyperparameter)의 최적값을 도출하였다. 모든 모델은 Python의 Keras 라이브러리를 이용하여 설계하였으며, 성능지표인 결정계수(coefficient of determination, R²), 평균제곱근오차(root mean square error, RMSE), 평균절대오차(mean absolute error, MAE) 등은 Scikit-learn 라이브러리에서 이용하였다. 결과 및 토의 : 최적 입력변수는 풍속, 풍향, 온도, 습도 등이었다. ANN의 최적점으로는 은닉층 8층, 은닉층별 노드수는 모두 100으로 나왔다. 최적 ANN 모델에서 성능지표는 R²=0.848, MAE=1.054, RMSE=1.616이었다. 1D-CNN 의 최적점으로는 합성곱층 4층, 층별 필터 수는 1층부터 64, 128, 64, 32개, 전결합층 1층에 노드 100개이다. 최적 1D-CNN 모델의 성능지표는 R²=0.875, MAE=0.982, RMSE=1.583였다. 1D-CNN이 ANN보다 R²는 높고, MAE와 RMSE는 낮았다. ANN, 1D-CNN의 결정계수가 모두 0.8 이상으로 예측 성능이 우수하나, 1D-CNN이 ANN보다 모든 성능지표에서 높았다. 결론 : 최적화된 모델의 성능지표 비교 결과 1D-CNN이 ANN보다 높은 성능을 보여 영흥 풍력 발전소 발전량 예측에 적합할 것으로 보인다. 최적 입력변수는 풍속, 풍향, 온도, 습도였다. Objectives : In this study, deep learning models of artificial neural network (ANN) and one-dimension convolutional neural networks (1D-CNN) were compared to predict nonlinear wind power generation at Yeongheung wind power plant. Methods : The study site was Yeongheung-do, which has a 46 MW wind power plant. Hourly wind power and meteorological data from January to December 2018 were collected. After pre-processing with standardscaler, the training data were 64%, the validation data were 16%, and the test data were 20%. The optimum input variables of the model were selected using literature, and trial and error method. Rectified linear unit was used as the activation function. Hyperparameters were adjusted by trial and error method to optimized models. To compare the optimized models, the coefficient of determination (R²), mean absolute error (MAE), and root mean square error (RMSE) were used as the performance efficiency. Both ANN, and 1D-CNN were imported from the Keras library, and all of the performance efficiency was imported from the Scikit-learn library. Results and Discussion : The optimized input variables in this study were wind speed, wind direction, temperature, and humidity. The optimized ANN performance was R²=0.848, MAE=1.054, and RMSE=1.616, and the hyperparameters were 8 hidden layers with 100 nodes in each layer. The optimized 1D-CNN (R²=0.875, MAE=0.982, and RMSE=1.583) had 4 convolutional layers and the number of filters were 64, 128, 64, and 32 in order from the first layer, and one hidden fully connected layer had 100 nodes. The 1D-CNN had higher R², and lower MAE and RMSE than the ANN. Therefore, the 1D-CNN was selected as the optimized model to predict wind generation of the Yeongheung wind power plant. Conclusions : The optimized 1D-CNN model in this study was more effective in predicting the Yeongheung wind power plant than the ANN. The optimal input variables were wind speed, wind direction, temperature, and humidity.
-
백화점과 시장 구매자의 의복 소비가치와 소비자 만족에 관한 연구
박태희(Park Tae Hui),이명희(Lee Myeong Hui) 한국복식학회 2003 服飾 Vol.53 No.7
The purpose of this study was to investigate the relationship between the clothing consumption value and consumer satisfaction which were based on the purchase places such as department store and market, and to examine the influence of the clothing consumption value and demographic variables on the consumer satisfaction. The subjects were 364 females ranging in ages from twenties to fifties who dwelt in Seoul and in the suburbs of Seoul. Four factors of clothing consumption value derived by factor analysis : `functional value`, `emotional value`, `epistemic value`, and `conditional value`. The clothing consumption value and satisfaction of shopping system, purchase system, and consumption system of buyers at department store showed higher than that of buyers at market. Emotional value was most important in predicting the consumer satisfaction of buyers at department store, followed by epistemic value( -) and conditional value. Conditional value was most important in predicting the satisfaction of buyers at market, followed by emotional value and the academic background of buyers. Generally the higher the emotional and conditional value, the higher the consumer satisfaction, and the consumer satisfaction was influenced by epistemic value negatively.
-
-
국군간호사관학교 생도의 개인보호구에 대한 지식, 인식 및 태도
이유란 ( Lee Yu-ran ),김혜수 ( Kim Hye-su ),박태희 ( Park Tae-hui ),이지영 ( Lee Ji-young ),정다인 ( Jeong Da-in ),권은지 ( Kwon Eunji ) 국군간호사관학교 군건강정책연구소 2021 군진간호연구 Vol.39 No.2
Purpose: The purpose of this study was to investigate the knowledge, perception, and attitude on personal protective equipment (PPE) among Korea Armed Forces Nursing Academy (KAFNA) cadets. Methods: This cross-sectional descriptive study included 291 cadets attending at KAFNA. Data were collected by structured questionnaires and were analyzed through descriptive statistics, independent t-test, one-way ANOVA, and Pearson's correlation coefficient. Results: The score of knowledge on PPE was 14.49±1.83 points out of 20 points. Perception on PPE was 3.55±0.45 points, and attitude on PPE was 3.39±0.59 points out of 5 points, respectively. There was no correlation between knowledge and perception, despite a strong positive correlation among knowledge, perception, and attitude. Upper-grade cadets and cadets who have experience in PPE training showed higher knowledge and attitude on PPE. Conclusion: Results of this study provided as basic data for the education related to the use of PPE for KAFNA cadets. It will also be necessary to provide the repetitive education and practice for the curriculum to master PPE.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
