• 인터넷정보학회논문지
• /
• 제25권4호
• /
• pp.121-130
• /
• 2024

정보 통신 기술의 기하급수적인 발전에 따라 확보 가능한 데이터의 종류와 크기가 증가하고 있다. 이러한 대량의 데이터를 활용하기 위해, 통계 등 확보한 데이터를 분석하는 것이 중요하지만 다양화되고 복잡도가 증가한 데이터를 일반적인 방법으로 처리하는 것에는 명확한 한계가 있다. 한편, 연산 처리 능력 고도화 및 자동화 시스템에 대한 수요 증가에 따라 다양한 분야에 기계 학습을 적용하여 그동안 해결하지 못하였던 문제들을 풀고자 하는 시도가 증가하고 있다. 기계 학습 모델의 성능을 확보하기 위해서 모델의 입력에 사용되는 데이터를 가공하는 것과 해결하고자 하는 목적 함수에 따라 모델을 설계하는 것이 중요하다. 많은 연구를 통해 데이터의 종류 및 특성에 따라 데이터를 처리하는 방법이 제시되었으며, 그 방법에 따라 기계 학습의 성능에는 큰 차이가 나타난다. 그럼에도 불구하고, 데이터의 종류와 특성이 다양해짐에 따라 데이터 분석을 위하여 어떠한 데이터 처리 방법을 적용해야 하는지에 대한 어려움이 존재한다. 특히, 기계 학습을 이용하여 비선형적 문제를 해결하기 위해서는 다변량 데이터를 처리하는 것이 필수적이다. 본 논문에서는 다양한 형태의 변수를 포함하는 Kaggle의 Titanic 데이터셋을 이용하여 기계 학습 기반으로 데이터 분석을 수행하기 위한 다변량 정형 (tabular) 데이터 처리 방법에 대해 제시한다. 데이터 특성에 따른 통계 분석을 적용한 입력 변수 필터링, 데이터 정규화 등의 처리 방법을 제안하고, 데이터 시각화를 통해 데이터 구조를 분석한다. 마지막으로, 기계 학습 모델을 설계하고, 제안하는 다변량 데이터 처리를 적용하여 모델을 훈련시킨다. 그 이후, 훈련된 모델을 사용하여 탑승객의 생존 여부 예측 성능을 분석한다. 본 논문에서 제시하는 다변량 데이터 처리와 시각화를 적용하여 다양한 환경에서 기계 학습 기반 분석에 확장할 수 있을 것으로 기대한다.

• 산업공학
• /
• 제24권2호
• /
• pp.97-104
• /
• 2011

Research for multi-variate classification has been studied through two kinds of procedures which are feature selection and classification. Feature Selection techniques have been applied to select important features and the other one has improved classification performances through classifier applications. In general, each technique has been independently studied, however consideration of the interaction between both procedures has not been widely explored which leads to a degraded performance. In this paper, through integrating these two procedures, classification performance can be improved. The proposed model takes advantage of KBANN (Knowledge-Based Artificial Neural Network) which uses prior knowledge to learn NN (Neural Network) as training information. Each NN learns characteristics of the Feature Selection and Classification techniques as training sets. The integrated NN can be learned again to modify features appropriately and enhance classification performance. This innovative technique is called ALBNN (Algorithm Learning-Based Neural Network). The experiments' results show improved performance in various classification problems.

• 품질경영학회지
• /
• 제35권4호
• /
• pp.67-77
• /
• 2007

We tried new interpreting about the work of art in this paper. The work of art respects the intention of the artist to make it and interprets intention until now. After critics distinguish by a period, an area that they set to philosophical thought which is the time and interpreted. We set to each one subjectivity and interpreted between artist to make the work of art and appreciator. But in this paper, we tied various criteria which appreciates the work of art. We tried so that we presented the intimacy each other newly. Otherwise we tied with the subjectivity of the individual and are the try to be an objectification low through statistical technique. We looked into the culture and art in the introduction and explain the discussion about the work of art interpreting which the main subject. We set the category 6 area, and explain an each criteria explanation and assessment method. We tried to propose new interpreting as the intimacy to be multi-variate data analysis result of the assessment analysis.

• 아동학회지
• /
• 제28권5호
• /
• pp.253-267
• /
• 2007

This study examined the relationships between multiple intelligences as cognitive factors and affective factors of learning motivation and academic self-concept. The data were collected from 276 4th grade elementary school students and analyzed by correlation, multi-variate analysis, and step-wise multiple regression. Results were that (1) multiple intelligences, learning motivation, and academic self-concept had statistically significant correlations among themselves. Multi-variate analysis showed that intra-personal intelligence explained 58.6% of the linear combination of learning motivation and academic self-concept. (2) Intra-personal intelligence explained 29% to 58% of learning motivation and its sub-factors of achievement motivation, internal locus of control, self-efficacy, and self-regulation. (3) Intra-personal intelligence, logical-mathematical intelligence, musical intelligence, and inter-personal intelligence were explanatory variables for academic self-concept and its sub-factors.

• 한국터널지하공간학회 논문집
• /
• 제13권6호
• /
• pp.531-555
• /
• 2011

본 연구에서는 암반대응형 TBM의 소요 사양 산출과 커터헤드 설계를 위한 통계모델을 도출하고자 하였다. 이를 위하여 다양한 암반 조건에서 수집된 871개의 TBM 굴진자료와 51개의 암석 선형절삭시험 결과에 대해 다변량 회귀분석을 실시하여, 다양한 암석 특성과 절삭 조건을 고려한 최적 모델을 도출하였다. 회귀분석을 통해 도출된 설계모델들을 2개의 쉴드터널 현장에 적용한 결과, 커터 관입깊이, 커터 작용력 및 커터 간격과 같은 TBM 핵심 설계항목의 예측결과들이 실제 현장의 굴진결과와 잘 부합되는 것으로 나타났다.

• Journal of the Korean Data and Information Science Society
• /
• 제16권4호
• /
• pp.899-911
• /
• 2005

This paper conducts an explanatory analysis of the web sphere produced by National Assemblymen in South Korea, using some statistical methods. First, some descriptive metrics were employed. Next, the traditional methods of multi-variate analyses, multidimensional scaling and corresponding analysis, were applied to the data. Finally, cross-sectional data were compared to examine a change over time.

• 한국대기환경학회지
• /
• 제8권4호
• /
• pp.213-220
• /
• 1992

Simple correlation analysis, factor analysis, and multi-variate analysis have been performed to analyze the relationship between air pollution and meteorological factors for air pollution and meteorological data measured at Kwanghwamun in Seoul during the period of one year(January 1990 $\sim$ December 1990). As a result of simple correlation and factor analysis, $SO_2$, TSP and CO concentrations have shown high negative correlation with temperature and among these indicating that these are related with pollutant emission trend based upon heating fuel usage. Ozone has a good corrleation with solar radiation and relative humidity to have a closed relation with $O_3$ generation reaction mechanism. The result of multi-variate correlation analysis shows that the concentration of $SO_2$ and CO are adequate for correlation model with ambient temperature and wind speed and $O_3$ concentrations are adequate for that with solar radiation and wind speed. $SO_2$ and CO levels are considered to be affected first of all by heating fuel usage as a emssion source and wind speed as a dispersion effect. The $SO_2$ concentration in the condition that the temperature fall below zero is explained by multilicative model with wind speed, only one variable.

• Structural Monitoring and Maintenance
• /
• 제7권4호
• /
• pp.283-294
• /
• 2020

In this paper, an adaptive MEMD based modal identification technique for linear time-invariant systems is proposed employing multiple vibration measurements. Traditional empirical mode decomposition (EMD) suffers from mode-mixing during sifting operations to identify intrinsic mode functions (IMF). MEMD performs better in this context as it considers multi-channel data and projects them into a n-dimensional hypercube to evaluate the IMFs. Using this technique, modal parameters of the structural system are identified. It is observed that MEMD has superior performance compared to its traditional counterpart. However, it still suffers from mild mode-mixing in higher modes where the energy contents are low. To avoid this problem, an adaptive filtering scheme is proposed to decompose the interfering modes. The Proposed modified scheme is then applied to vibrations of a reinforced concrete road bridge. Results presented in this study show that the proposed MEMD based approach coupled with the filtering technique can effectively identify the parameters of the dominant modes present in the structural response with a significant level of accuracy.

• 산업경영시스템학회지
• /
• 제22권52호
• /
• pp.241-246
• /
• 1999

In this study, to specify an evaluation of human sensibility, the types of color, intensity of illuminations and lights consisting work environmental condition are decided, and image data from examining the change of human sensibility followed by changes of the above three conditions are obtained. Using the factor analysis and quantification theory in multi-variate analysis type of Sensibility Ergonomics, determinating the structure of factors, specifying the relations of environmental conditions and factors can be done so that the structure of image on human sensibility space with the change of environmental conditions is analyzed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.342-345
• /
• 2005

This paper describes dynamics analysis of a small training boat and a new type of ship's autopilot not only to keep her course but also to reduce her roll motion. Firstly, statistical analysis through multi-variate auto regressive model is carried out using the real data collected from the sea trial on an actual small training boat Sazanami after the navigational system of the boat was upgraded. It is shown that the roll motion is strongly influenced by the rudder motion and it is suggested that there is a possibility of reducing the roll motion by controlling the rudder order properly. Based on this observation, a new type of ship's autopilot that takes the roll motion into account is designed using the muti-variate modern control theory. Lastly, digital simulations by white noise are carried out in order to evaluate the proposed system and a typical result is demonstrated. As results of simulations, the proposed autopilot had good performance compared with the original data.