http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
캐비닛 엑스선 검색장비 이미지품질평가 고도화 방안 연구
윤연아 ( Yeon Ah Yoon ),정진형 ( Jin Hyeong Jung ),김용수 ( Yong Soo Kim ) 한국품질경영학회 2021 품질경영학회지 Vol.49 No.1
Purpose: This study proposes methods and procedures for evaluating imaging security systems quality of cabinet x-ray screening system to enhance performance certification technology. Also, conducted a comparative analysis of the literature of test-kit for imaging security quality evaluation. Methods: Comparative analysis of the test-kits and related documents for image quality assessment of cabinet x-ray screening equipment. This allows assessment items were selected and the methods for each assessment item were proposed. In addition, the configuration method of the assessment team was established by applying the technology readiness assessment(TRA). Results: Four of the assessment items were selected when estimate image quality by a comparative analysis of literature. For each assessment item, the evaluation method and minimum level of availability were determined. Finally, this paper proposes an imaging quality assessment of cabinet X-ray imaging security systems. Conclusion: Development of imaging security systems evaluation procedures for cabinet X-ray screening systems can be help improve performance certification of aviation security equipment.
SHAP를 활용한 중요변수 파악 및 선택에 따른 잔여유효수명 예측 성능 변동에 대한 연구
윤연아(Yeon Ah Yoon),이승훈(Lee Seung Hoon),김용수(Yong Soo Kim) 한국산업경영시스템학회 2021 한국산업경영시스템학회지 Vol.44 No.4
Recently, the importance of preventive maintenance has been emerging since failures in a complex system are automatically detected due to the development of artificial intelligence techniques and sensor technology. Therefore, prognostic and health manage-ment (PHM) is being actively studied, and prediction of the remaining useful life (RUL) of the system is being one of the most important tasks. A lot of researches has been conducted to predict the RUL. Deep learning models have been developed to improve prediction performance, but studies on identifying the importance of features are not carried out. It is very meaningful to extract and interpret features that affect failures while improving the predictive accuracy of RUL is important. In this paper, a total of six popular deep learning models were employed to predict the RUL, and identified important variables for each model through SHAP (Shapley Additive explanations) that one of the explainable artificial intelligence (XAI). Moreover, the fluctuations and trends of prediction performance according to the number of variables were identified. This paper can suggest the possibility of explainability of various deep learning models, and the application of XAI can be demonstrated. Also, through this proposed method, it is expected that the possibility of utilizing SHAP as a feature selection method.
인공지능 기반 장비의 자동탐지 성능인증을 위한 시험법 설계
김기연(Ki-Yeon Kim),정진형(Jin Hyeong Jung),윤연아(Yeon Ah Yoon),김용수(Yong Soo Kim) 한국신뢰성학회 2020 신뢰성응용연구 Vol.20 No.1
Purpose: This paper examined the design of a standard test method for certifying the performance of automatic detection equipment using artificial intelligence (AI). Methods: First, indicators for measuring the detection performance were determined and the terms were redefined. Then, the number of iterations required to give a criterion value at a given confidence level for data following the binomial distribution was calculated. As a case study, an aviation security x-ray scanner was tested. Results: If failures occur before the number of allowable times during the trial, the minimum probability of occurrence of true positive (TP) can be demonstrated. This means that F2-Score is satisfied, and the performance can be certified. Conclusion: This method can be used in industries that operate automatic detectors based on AI technology. The method should contribute to the development of a national certification system and improve product quality control.
광업 데이터의 시계열 분석을 통해 실리카 농도를 예측하기 위한 머신러닝 모델
이승훈 ( Lee Seung Hoon ),윤연아 ( Yoon Yeon Ah ),정진형 ( Jung Jin Hyeong ),심현수 ( Sim Hyun Su ),장태우 ( Chang Tai-woo ),김용수 ( Kim Yong Soo ) 한국품질경영학회 2020 품질경영학회지 Vol.48 No.3
Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.
와이블분포 기반 관측중단데이터에서의 베이지안 기법 및 전통적 기법 간 신뢰도 추정 기법 성능 비교
조형준(Hyoung Jun Cho),윤연아(Yeon Ah Yoon),장태우(Tai-Woo Chang),김용수(Yong Soo Kim) 한국신뢰성학회 2020 신뢰성응용연구 Vol.20 No.3
Purpose: This paper reports on the corresponding guidelines to help users select a suitable estimation method. The guidelines were derived by evaluating the reliability estimation performance of different estimation methods. Methods: Weibull distribution parameters were calculated using the least squares and maximum likelihood estimators, aling with the Bayesian methods. The scale and shape parameters were estimated to calculate the life-time. Finally, the analysis of variance was performed to compare the accuracy of the various methods. Results: Bayesian methods, which employed prior information, exhibited a relatively high performance for all sample sizes. As the sample size increased, the performance was similar to that of the least squares and maximum likelihood estimators. The performance of the Bayesian methods fluctuated according to the prior information. Conclusion: The reliability of various methods to analyze Weibull-distribution-based censoring data was analyzed. The results can be used in reliability assessment, to achieve the target reliability in the product development phase.