• 한국인공지능학회지
• /
• 제4권1호
• /
• pp.11-13
• /
• 2016

These days, medical technology has been developed rapidly to meet desire of living healthy life. Average lifespan was extended to let people see a doctor because of many reasons. This study has shown rate of leaving of hospitals to investigate the rate of not only department of surgery but also department of internal medicine. Linear model, tree, classification rule, association and algorithm of data mining were used. This study investigated by using J48 and AD tree of decision-making tree In this study, J48 and AD tree of decision-making tree of data mining were used to investigate based on result of both data. Both algorithms were found to have similar performance. Both algorithms were not equivalent to require detailed experiment. Collect more experimental data in the future to apply from various points of view. Development of medical technology gives dream, hope and pleasure. The ones who suffer from incurable diseases need developed medical technology. Environment being similar to the reality shall be made to experiment exactly to investigate data carefully and to let the ones of various ages visit hospital and to increase survival rate.

• Architectural research
• /
• 제8권1호
• /
• pp.77-84
• /
• 2006

In spite of enormous increase in data generation, its practical usage in the construction sector has not been prevalent enough compared to those of other industries. The author would explore the obstacles against efficient data application in the arena of expenditure forecasting, and suggest a forecasting method by applying Case-based Reasoning (CBR). The newly suggested method in the research, enables project managers to forecast monthly expenditures with less time and effort by retrieving and referring only projects of a similar nature, while filtering out irrelevant cases included in database. Among 99 projects collected, the cost data from 88 projects were processed to establish a new forecasting model. The remaining 10 projects were utilized for the validation of the model. From the comprehensive study, the choice of the numbers of referring projects was investigated in detail. It is concluded that selecting similar projects at 12~19 % out of the whole database will produce a more precise forecasting. The new forecasting model, which suggests the predicted values based on previous projects, is more than just a forecasting methodology; it provides a bridge that enables current data collection techniques to be used within the context of the accumulated information. This will eventually help all the participants in the construction industry to build up the knowledge derived from invaluable experience.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.1063-1066
• /
• 2005

다양한 학습 자료를 저장해두고 검색하는 시스템들은 주로 키워드 검색을 지원하고 있다. 여기서, 키워드 매칭 방식은 같은 분야의 자료라 하더라도 사용자가 입력한 키워드와 정확한 매칭이 되지 않을 경우 검색되지 못하는 문제점을 안고 있다. 또한 학습 테스트를 위한 학습 문제 자료는 키워드로 검색하기에는 포함한 정보의 양이 너무 적어 적용되기 어렵다. 본 논문에서는 이러한 문제점을 해결하기 위하여 학습문서를 입력할 때 문서에 포함되어 있는 각 단어들을 형태소 분석에 의하여 중요 명사들을 추출하고 데이터베이스화하는 기법을 도입하고 미리 마련한 유사한 용어 지식 데이터베이스를 활용하여 지능적이고 효율적인 학습자료 검색 기법을 제안한다.

• 한국의류학회지
• /
• 제29권11호
• /
• pp.1389-1398
• /
• 2005

The purposes of this study are to verify the sales promotion effect of bargain sale of department store, and to investigate the relationship between the effect of bargain sale and the consumer attitude toward economics. For those purposes, secondary data was collected. The data was composed of monthly sales data of women's casual wear, men's suit, inner wear, infant's wear, and golf wear in a department store from 1996 to 2003. The data on consumer attitude toward economics was collected from 'Consumer Attitude Index' issued by SERI. The results are as follows. First, there were differences in the sales promotion effects of bargain sale by merchandise class and by year. Men's suit was the class that the effect was highest, and inner wear was the class the effect was lowest. In addition, the effects were simultaneously lowered by year. Second, sales promotion effect of bargain sale had relationship with consumer attitude index. The yearly transitions of the two data were almost similar. This means that as the consumer attitude becomes pessimistic, the motivation to consume also becomes lower, so that sales promotion effect of bargain sale also decreases. In addition, women's wear and men's suit showed the most similar transition patterns with the consumer attitude index.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3221-3242
• /
• 2021

The purpose of the study is to examine the current study trend of 'QR code' and suggest a direction for the future study of big data analysis: (1) Background: study trend of 'QR code' and analysis of the text by subject field and year; (2) Methodology: data scraping and collection, EXCEL summary, and preprocess and big data analysis by R x 64 4.0.2 program package; (3) the findings: first, the trend showed a continuous increase in 'QR code' studies in general and the findings were applied in various fields. Second, the analysis of frequent keywords showed somewhat different results by subject field and year, but the overall results were similar. Third, the visualization of the frequent keywords also showed similar results as that of frequent keyword analysis; and (4) the conclusions: in general, 'QR code' studies are used in various fields, and the trend is likely to increase in the future as well. And the findings of this study are a reflection that 'QR code' is an aspect of our social and cultural phenomena, so that it is necessary to think that 'QR code' is a tool and an application of information. An expansion of the scope of the analysis is expected to show us more meaningful indications on 'QR code' study trends and development potential.

• 한국산업융합학회 논문집
• /
• 제26권1호
• /
• pp.35-46
• /
• 2023

A model test is performed to measure the sloshing impact pressure in the liquid tank. A preprocessing is performed to learn the model test results applied with various environmental conditions. In this study, we propose a method for generating data similar to the total pressure data using Generative Adversarial Networks. In addition, after approximating the generated result to the three parameter Weibull distribution, the difference of the three parameters was compared through the RMSE and SMAPE calculation results. As a result, the distribution of the generated data showed similar results to the total pressure data distribution.

• 대한토목학회논문집
• /
• 제26권4B호
• /
• pp.329-334
• /
• 2006

Southern Great Plain 1999 실험을 통하여 획득된 L-band와 C-band 토양수분 측정치의 공간 변화 양상을 분석하였다. L-band 토양수분 측정치의 스펙트럼은 관측 스케일의 변화와 함께 토양수분의 공간 변화 양상이 변화됨을 보여주었고, 이러한 변화 양상은 모래함유비와 같은 토양 특성의 공간 변화 양상과 일치함을 보여주었다. 그리고 C-band 토양수분 측정치의 공간 변화 양상은 관측 스케일의 변화와 상관없이 일정한 변화도를 가지는 것으로 나타났다. 이는 식생피복의 공간 변화 양상과 동일함을 보여주는 것이다. 이러한 결과는 AMSR기기를 이용하여 현재 진행되고 있는 토양수분의 전 지구 관측치의 downscaling시 고려되어야 할 것이다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2008년도 추계학술발표대회
• /
• pp.413-416
• /
• 2008

In the presence of multiple continuous queries, multi-query optimizing is a new challenge to process multiple stream data in real-time. So, in this paper, we proposed an approach to optimize multi-query of sliding window on network traffic data streams and do some comparisons to traditional queries without optimizing. We also detail some method of scheduling on different data streams, while different scheduling made different results. We test the results on variety of multi-query processing schedule, and proofed the proposed method is effectively optimized the data stream similar multi-queries.

• 한국진공학회지
• /
• 제5권2호
• /
• pp.99-106
• /
• 1996

Two types of regularization method (singular system and HMP approaches) for generating depth-concentration profiles from angle-resolved XPS data were evaluated. Both approaches showed qualitatively similar results although they employed different numerical algorithms. The application of the regularization method to simulated data demonhstrates its excellent utility for the complex depth profile system . It includes the stable restoration of depth-concentration profiles from the data with considerable random error and the self choice of smoothing parameter that is imperative for the successful application of the regularization method. The self choice of smoothing parameter is based on generalized cross-validation method which lets the data themselves choose the optimal value of the parameter.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제18권1호
• /
• pp.20-32
• /
• 2018

Purpose: The purpose of this study is to set up an anomaly detection criteria for sensor data coming from a motorcycle. Methods: Five sensor values for accelerator pedal, engine rpm, transmission rpm, gear and speed are obtained every 0.02 second from a motorcycle. Exploratory data analysis is used to find any pattern in the data. Traditional process control methods such as X control chart and time series models are fitted to find any anomaly behavior in the data. Finally unsupervised learning algorithm such as k-means clustering is used to find any anomaly spot in the sensor data. Results: According to exploratory data analysis, the distribution of accelerator pedal sensor values is very much skewed to the left. The motorcycle seemed to have been driven in a city at speed less than 45 kilometers per hour. Traditional process control charts such as X control chart fail due to severe autocorrelation in each sensor data. However, ARIMA model found three abnormal points where they are beyond 2 sigma limits in the control chart. We applied a copula based Markov chain to perform statistical process control for correlated observations. Copula based Markov model found anomaly behavior in the similar places as ARIMA model. In an unsupervised learning algorithm, large sensor values get subdivided into two, three, and four disjoint regions. So extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior in the sensor values. Conclusion: Exploratory data analysis is useful to find any pattern in the sensor data. Process control chart using ARIMA and Joe's copula based Markov model also give warnings near similar places in the data. Unsupervised learning algorithm shows us that the extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior.