• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.541-546
• /
• 2021

최근 전 세계적으로 인공지능과 머신러닝을 기반으로 임상정보를 활용한 다양한 고혈압 식별 및 예측 모델이 개발되고 있다. 그러나 고혈압 관련 모델에 대한 대부분의 선행연구는 침습적 및 고가의 분석비용을 통한 변수들이 대부분 사용되었고, 인종과 국가의 특징에 대한 고려가 충분히 제시되지 않았다. 따라서 이 연구의 목적은 일반적인 사회인구 통계학적 변수만을 사용하여 쉽게 이해할 수 있는 한국인 성인 고혈압 예측 모델을 제시하는 것이다. 이 연구에서 사용된 데이터는 질병관리청 국민건강영양조사 (2018년)를 이용하였다. 남성에서, wrapper-based feature subset selection 메소드와 naive Bayes를 이용한 모델이 가장 높은 예측 성능 (ROC = 0.790, kappa = 0.396)을 보였다. 여성의 경우, correlation-based feature subset selection 메소드와 naive Bayes를 사용한 모델이 가장 높은 예측 성능(ROC = 0.850, kappa = 0.495)을 나타내었다. 또한 모든 모델들에서 사회인구 통계학적 변수들만을 이용한 고혈압의 예측 성능이 남성보다 여성에게서 더 높게 나타나는 것을 발견하였다. 본 연구의 결과인 machine learning 기반 고혈압 예측 모델은 한국인에 대한 단순한 사회인구학적 특성만을 사용하였기 때문에 향후 공중 보건 및 역학 분야에서 쉽게 사용될 수 있을 것으로 예상된다.

• 사상체질의학회지
• /
• 제29권1호
• /
• pp.29-39
• /
• 2017

Objectives Facial features can be utilized as an indicator of Korean medical diagnosis. They are often measured by using the diagnostic device for an objective diagnosis. Accordingly, it is necessary to verify the reliability of the features which are obtained from the device for the accurate diagnosis. In this study, we attempt to evaluate the repeatability of facial feature variables using the Sasang Constitutional Analysis Tool(SCAT) for the Sasang Constitutional face diagnosis. Methods Facial pictures of two subjects were taken 24 times respectively for two days according to a standard guideline. In order to evaluate the repeatability, the coefficient of variation was calculated for the facial features extracted from frontal and profile images. Results The coefficient of variation was less than 10% in most of the facial features except the upper lip, trichion, and chins related features. Conclusions It was confirmed that the coefficient of variation was small in most of the features which enables the objective and reliable analysis of face. However, some features showed the low reliability because the location of facial landmarks related to them is ambiguous. In order to solve the problem, a clear basis for the location discussion is required.

• 한국콘텐츠학회논문지
• /
• 제20권12호
• /
• pp.49-57
• /
• 2020

본 연구는 우리나라 수출 분야 산업의 경쟁력을 나타내는 부가가치율을 다양한 머신러닝 기법을 활용하여 예측하였다. 아울러, 예측의 정확성 및 안정성을 높이기 위하여 머신러닝 기법 예측값들에 예측조합 기법을 적용하였다. 특히, 본 연구는 산업별 부가가치율에 영향을 주는 다양한 변수를 고려하기 위하여 재귀적특성제거 방법을 사용하여 주요 변수를 선별한 후 머신러닝 기법에 적용함으로써 예측과정의 효율성을 높였다. 분석결과, 예측조합 방법에 따른 예측값은 머신러닝 기법 예측값들보다 실제의 산업 부가가치율에 근접한 것으로 나타났다. 또한, 머신러닝 기법의 예측값들이 큰 변동성을 보이는 것과 달리 예측조합 기법은 안정적인 예측값을 나타내었다.

• 한국건설관리학회논문집
• /
• 제24권6호
• /
• pp.81-90
• /
• 2023

Climate change has resulted in increased frequency and intensity of heat waves, which poses a significant threat to the health and safety of construction workers, particularly those engaged in labor-intensive and heat-stress vulnerable working environments. To address this challenge, this study aimed to propose an interpretable machine learning approach for forecasting personal heat strain by considering the cumulative effect of heat exposure as a situational variable, which has not been taken into account in the existing approach. As a result, the proposed model, which incorporated the cumulative working time along with environmental and personal variables, was found to have superior forecast performance and explanatory power. Specifically, the proposed Multi-Layer Perceptron (MLP) model achieved a Mean Absolute Error (MAE) of 0.034 (℃) and an R-squared of 99.3% (0.933). Feature importance analysis revealed that the cumulative working time, as a situational variable, had the most significant impact on personal heat strain. These findings highlight the importance of systematic management of personal heat strain at construction sites by comprehensively considering the cumulative working time as a situational variable as well as environmental and personal variables. This study provided a valuable contribution to the construction industry by offering a reliable and accurate heat strain forecasting model, enhancing the health and safety of construction workers.

• 문화기술의 융합
• /
• 제8권4호
• /
• pp.339-345
• /
• 2022

심혈관 질환은 전 세계적으로 주요 사망원인들 중 하나이다. 본 연구는 보다 우수한 심혈관질환 판별 모델을 생성하기 위한 방법에 대한 연구로써, 3가지 변수 선택법과 7가지 머신러닝 알고리즘을 바탕으로 사회인구학적 변수들을 이용하여 고혈압과 이상지질혈증 판별모델들을 생성하고, 생성된 모델들의 성능을 비교 평가한다. 본 연구의 결과에서는 두 가지 질병 모두에서, 전체변수 및 correlation-based feature subset selection 메소드 기반 모델들에서는 naive Bayes 모델이 다른 머신러닝을 이용한 모델들보다 다소 우수한 판별 성능이 있는 것으로 나타났고, wrapper 메소드 기반 변수 선택법에서는 logistic regression 모델이 다른 모든 모델보다 성능이 다소 우수한 것으로 나타났다. 본 연구의 결과는 원격의료 및 대중보건 분야에서 향후 한국인의 심혈관질환 판별 및 예측 모델 생성을 위한 참고자료로 활용될 수 있을 것으로 기대된다.

• 한국산업융합학회 논문집
• /
• 제5권1호
• /
• pp.33-38
• /
• 2002

This paper proposes an efficient method for improving the performance of polynomial adaline using the dimension reduction of independent variables. The adaptive principal component analysis is applied for reducing the dimension by extracting efficiently the features of the given independent variables. It can be solved the problems due to high dimensional input data in the polynomial adaline that the principal component analysis converts input data into set of statistically independent features. The proposed polynomial adaline has been applied to classify the patterns. The simulation results shows that the proposed polynomial adaline has better performances of the classification for test patterns, in comparison with those using the conventional polynomial adaline. Also, it is affected less by the scope of the smoothing factor.

• Kyungpook Mathematical Journal
• /
• 제18권2호
• /
• pp.211-215
• /
• 1978

In the present paper, we obtain two new and interesting finite summation formulae for the H-function of two variables in a very neat and elegant form. The novel feature of the paper is that the method used here in deriving these formulae is simple and direct and does not impose heavy restrictions on the parameters involved. On account of the most general nature of the H-function of two variables, a number of related finite summation formulae for a number of other useful functions can also be obtained as special cases of our results. As an illustration, we have obtained here from our main results, the corresponding finite summation formulae for $Kamp{\acute{e}}$ de $F{\acute{e}}riet$ function. Appell's function and Gauss' hypergeometric function which are also believed to be new.

• 한국항공운항학회지
• /
• 제20권1호
• /
• pp.19-25
• /
• 2012

The air traffic situation variables were emphasized in this research to review the awareness level of job performance of military air traffic controllers in application of air traffic situation variables such as detection of aircraft identification, type of aircraft, position ,speed, altitude, determination of separation between departing and arriving in-trail aircraft, physical airport conditions, adverse weather conditions, NAVAID outage and ATC facilities' operational status. In this respect, This study was conducted under the auspice of ATC facility operating agencies and devoting air force air traffic controller's participation by answering the questionnaires from nine radar approach control facilities and other air traffic control towers.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2005년도 춘계학술대회 논문집
• /
• pp.266-269
• /
• 2005

The effect of exit temperature on the thickness of recrystallization layer during Al extrusion process was investigated. The recrystallization layer of an extruded Al alloy is an important feature of the product in a wide range of applications, particularly those within the automotive industry. The thicker recrystallized layer in the Al alloys can give rise to a number of problems including reduced fatigue resistance and orange peel during cold forming. But the interaction of extrusion process variables with the thickness of recrystallization layer is poorly understood, and there is limited information available regarding the role of the main hot extrusion variables. Using the 3650 US ton extrusion press, this paper describes the effect of the main process variables such as billet temperature, ram speed, and exit temperature on the thickness of recrystallization layer for the A6XXX Al alloy.

• 산업공학
• /
• 제12권4호
• /
• pp.551-556
• /
• 1999

In this paper, we compare the performance of three data mining classification algorithms(neural network, decision tree, logistic regression) in consideration of various characteristics of categorical input and output data. $2^{4-1}$. 3 fractional factorial design is used to simulate the comparison situation where factors used are (1) the categorical ratio of input variables, (2) the complexity of functional relationship between the output and input variables, (3) the size of randomness in the relationship, (4) the categorical ratio of an output variable, and (5) the classification algorithm. Experimental study results indicate the following: decision tree performs better than the others when the relationship between output and input variables is simple while logistic regression is better when the other way is around; and neural network appears a better choice than the others when the randomness in the relationship is relatively large. We also use Taguchi design to improve the practicality of our study results by letting the relationship between the output and input variables as a noise factor. As a result, the classification accuracy of neural network and decision tree turns out to be higher than that of logistic regression, when the categorical proportion of the output variable is even.