본문 바로가기 주메뉴 바로가기
22대 대한민국 국회 국회정보길라잡이 국회의원검색
회원가입 로그인
HOME

정보검색

소장정보 검색

국회도서관 홈으로 정보검색 소장정보 검색
결과 내 검색 동의어 포함
결과 내 검색 동의어 포함

-

초록보기

많은 연구자들이 다양한 모델을 이용하여 물의 수질을 평가하기 위해 노력하고 있다. 평가 모델에는 결측값이 없는 데이터셋이 필요하지만, 관측 데이터셋에는 결측값이 다수 포함되는 것이 현실이다. 단순히 결측값을 삭제하는 방법은 경우에 따라 기저 데이터의 분포를 왜곡시키고 모델의 예측성능에도 편의(bias)를 불러올 위험성이 있다. 본 연구에서는 수질 데이터의 결측값 처리에 적합한 기법을 탐색하기 위해, 기존의 KNN과 MICE Imputation, 그리고 생성형 신경망 모델인 Autoencoder와 Denoising Autoencoder를 기반으로 몇 가지 대치 기법을 실험하였다. 실험 결과, KNN과 MICE Imputation의 결과를 평균한 Combined Imputation이 실측치에 가장 가깝게 값을 추정하였으며, 이 기법을 적용하여 결측값을 처리한 관측 데이터셋을 support vector machine과 ensemble 기반의 분류 모델로 평가한 결과, 결측값을 삭제했을 때에 비해 Accuracy, F1 score, ROC-AUC score, 그리고 MCC(Mathews Correlation Coefficient) 지표가 향상되었다.

Many researchers make efforts to evaluate water quality using various models. Such models require a dataset without missing values, but in real world, most datasets include missing values for various reasons. Simple deletion of samples having missing value(s) could distort distribution of the underlying data and pose a significant risk of biasing the model’s inference when the missing mechanism is not MCAR. In this study, to explore the most appropriate technique for handing missing values in water quality data, several imputation techniques were experimented based on existing KNN and MICE imputation with/without the generative neural network model, Autoencoder(AE) and Denoising Autoencoder(DAE). The results shows that KNN and MICE combined imputation without generative networks provides the closest estimated values to the true values. When evaluating binary classification models based on support vector machine and ensemble algorithms after applying the combined imputation technique to the observed water quality dataset with missing values, it shows better performance in terms of Accuracy, F1 score, RoC-AuC score and MCC compared to those evaluated after deleting samples having missing values.

권호기사

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 목차
(A) combined greedy neighbor generation method of local search for the traveling salesman problem Yongho Kim, Junha Hwang p. 1-8

Context-based prompt selection methodology to enhance performance in prompt-based learning Lib Kim, Namgyu Kim p. 9-21

(A) design and implementation of the deep learning-based senior care service application using AI speaker Mun Seop Yun, Sang Hyuk Yoon, Ki Won Lee, Se Hoon Kim, Min Woo Lee, Ho-Young Kwak, Won Joo Lee p. 23-30

Generative AI parameter tuning for online self-directed learning Jin-Young Jun, Youn-A Min p. 31-38

Missing value imputation technique for water quality dataset Jin-Young Jun, Youn-A Min p. 39-46

Audio generative AI usage pattern analysis by the exploratory study on the participatory assessment process Hanjin Lee, Yeeun Lee p. 47-54

Implementation of a thin film hydroponic cultivation system using HMI Gyu-Seok Lee, Tae-Sung Kim, Myeong-Chul Park p. 55-62

Development of an immersive virtual reality-based bathroom self-remodeling system Mi-Young Song p. 63-72

(A) study on strategic development approaches for cyber seniors in the information security industry Seung Han Yoon, Ah Reum Kang p. 73-82

Propose a static web standard check model Hee-Yeon Won, Jae-Woong Kim, Young-Suk Chung p. 83-89

(A) study on the perception of sports psychological counseling Min-Woo Jeon, Seong-Hoon An p. 91-103

(The) effect of maladaptive perfectionism, self-leadership, and social support on nursing students’ clinical practice stress Mi-Sook Park, Mi-Jin You p. 105-114

Implementation of a vibration notification system to support driving for drivers with cognitive delay impairment Gyu-Seok Lee, Tae-Sung Kim, Myeong-Chul Park p. 115-123

(A) study on the impact of impoverished and disabled women's entry into the labor market : focusing on the level and type of social capital Gull Lim p. 125-134

(A) study on the impact of transactional leadership on job performance and job satisfaction : the mediating effect of job engagement Eun-Jin Choi, Sang-Chul Lee, Yang-Kyun Kim p. 135-143

(A) study on the development of training model by enforcement of the IP Code(SOLAS Chapter XV) MoonGyo Cho, JeongMin Kim p. 145-153

Empirical study for causal relationship between weather and e-commerce purchase behavior Hyun-Jin Yeo p. 155-160

Antecedents affecting the information privacy concerns in personalized recommendation service of OTT Yujin Kim, Hyung-Seok Lee p. 161-175

Sensibility by weather and e-commerce purchase behavior Hyun-Jin Yeo p. 177-182

Study on domestic trends of green fuel policy Sangseop Lim, Sang-Mi Im, Seok-Hun Kim p. 183-189

추천서가 (다양한 추천 자료를 만나보세요)

권호기사보기

권호기사 목록 테이블로 기사명, 저자명, 페이지, 원문, 기사목차 순으로 되어있습니다.
기사명 저자명 페이지 원문 기사목차