• 대한원격탐사학회지
• /
• 제22권5호
• /
• pp.457-462
• /
• 2006

Sequential Pattern Mining is the mining approach which addresses the problem of discovering the existent maximal frequent sequences in a given databases. In the daily and scientific life, sequential data are available and used everywhere based on their representative forms as text, weather data, satellite data streams, business transactions, telecommunications records, experimental runs, DNA sequences, histories of medical records, etc. Discovering sequential patterns can assist user or scientist on predicting coming activities, interpreting recurring phenomena or extracting similarities. For the sake of that purpose, the core of sequential pattern mining is finding the frequent sequence which is contained frequently in all data sequences. Beside the discovery of frequent itemsets, sequential pattern mining requires the arrangement of those itemsets in sequences and the discovery of which of those are frequent. So before mining sequences, the main task is checking if one sequence is a subsequence of another sequence in the database. In this paper, we implement the subsequence matching method as the preprocessing step for sequential pattern mining. Matched sequences in our implementation are the normalized sequences as the form of number chain. The result which is given by this method is the review of matching information between input mapped sequences.

• 인터넷정보학회논문지
• /
• 제16권6호
• /
• pp.23-30
• /
• 2015

빅 데이터가 이슈화됨에 따라 데이터 분석의 결과를 기반으로 동작하는 많은 응용들이연구되고 왔고, 대표적인 응용들은 전자상거래 시스템의 상품 추천 서비스, 검색 엔진에서의 검색 서비스, 소셜 네트워크 서비스에서의 친구 추천 서비스 등이 있다. 본 논문은 기존의 데이터 마이닝 기법 중 데이터 집합에서 나타나는 유사한 패턴들을 마이닝하는 빈발 패턴 트리와 컴퓨터 과학의 이론에 기초한 결정트리를 결합하여 결정 빈발 트리 알고리즘을 제안한다. 이는 기존의 빈발 패턴 트리 알고리즘은 패튼 트리에서 패턴 생성에 대한 정확성은 보장되나 소셜 데이터처럼 다양한 패턴이 나타는 데이터에 대해서는 많은 수의 패턴들을 생성시켜 분석에 대한 어려움이 있어, 서브트리들과의 수렴 여부를 판단하는 모델로 변형시켜 문제를 개선한다. 또한 맵리듀스로 모델링하여 분산처리를 통한 고속 처리 알고리즘을 제시한다.

• 정보처리학회논문지D
• /
• 제14D권1호
• /
• pp.9-20
• /
• 2007

유전자들의 그룹은 복잡한 상호작용들을 통해 세포의 기능이 조절되며 이러한 상호작용을 하는 유전자 그룹들을 유전자 조절 네트워크 (GRNs: Gene Regulatory Networks)라고 한다. 이전의 유전자 발현 분석 기법인 군집화와 분류는 단지 상동성에 의한 유전자들 사이의 소속을 결정하는 데에는 유용하나 분자 활동에서의 같은 클래스에서 발견되어지는 유전자들 사이의 조절 관계를 식별할 수 없다. 더욱이 유전자들이 어떻게 연관되는 지와 유전자들이 서로 어떻게 조절하는지에 대한 매커니즘의 이해가 필요하다. 따라서 이 논문에서는 시계열 마이크로어레이 데이터로부터의 유전자들의 조절 관계를 발견하기 위해서 빈발 패턴 마이닝과 연쇄 규칙을 이용한 새로운 접근법을 제안하였다. 이 기법에서는 먼저, 빈발 패턴 마이닝 적용을 위한 적절한 데이터 변환 방법을 제안하였고 FP-growth을 이용하여 유전자 발현 패턴들을 발견한다. 그런 다음, 연쇄 규칙을 이용하여 빈발한 유전자 패턴들로부터 유전자 조절 네트워크를 구축하였다. 마지막으로 제안된 기법의 검증은 공개된 유전자들의 조절 관계와 실험 결과의 일치함을 보임으로써 평가하였다.

• 한국식생활문화학회지
• /
• 제28권3호
• /
• pp.272-281
• /
• 2013

To study the importance of family meals in adolescents, 251 middle school students were surveyed through a questionnaire on their family meal patterns, dietary behaviors, food intake, and life satisfaction. The family meals were defined as "meals with all family members living together" by 62.2% of the students. For the frequency of family meals, 42.2% of the students replied having family meals "More than once a day". A common reason for the difficulty in having a family meal was a "lack of time" (73.3% of the students). Students tended to respond that they would be most fond in having meals with entire family members with traditional Korean food. Having more frequent family meals was found to benefit both individual and familial dietary behavior. In terms of food intake according to the frequency of family meals, the group having frequent family meals consumed significantly more rice, tofu, legumes, meats, fishes, eggs, green vegetables, seaweeds, fruits, milk, and milk products. This indicates that students can achieve a balanced diet through family meals. In terms of emotional status, the group having more frequent family meals showed a higher satisfaction with their daily life, health, nutritional status, and care from their relatives. In terms of personal mental status, the group having more frequent family meals was also found to be more effective at controlling undesirable emotions such as loneliness, indignation, and lethargy. As a result of this study, students in the group having more frequent family meals were found to have a positive dietary behavior, a balanced nutrition, a higher life satisfaction, and a more stable mental status. This result is useful as nutritional and educational information in schools to impress upon the public the importance of family meals for adolescents.

• Current Research on Agriculture and Life Sciences
• /
• 제15권
• /
• pp.53-67
• /
• 1997

The objective of this study is to provide with the hydro-meteological and probabilistic characteristics of the storms of typhoons that have been passed through the Korean peninsula during the last twenty-three years since 1961. The paths and intensities of the typhoons were analyzed. Fifty weather stations were selected and the rainfall data during typhoon periods were collected. Rainfall data were analyzed for the patterns and probabilistic distributions. The results were presented to describe the areal distributions of probabilistic characteristics. The results obtained from this study can be summarized as follows: 1. The most frequent typhoon path that has passed through the Korean peninsula was type E, followed by types CWE, W, WE, and S. The most frequent typhoon intensity was type B, followed by A, super A, and e types, respectively. 2. The third quartile typhoon rainfall patterns appear most frequently followed by the second, first, and last quartiles, respectively, in Seoul, Pusan, Taegu, Kwangju and Taejon. The single typhoon rainfalls with long rainfall durations tended to show delayed type rainfall patterns predominantly compared to the single rainfalls with short rainfall durations. 3. The most frequent probabilistic distribution of typhoon rainfall event is Pearson type-III, followed by Two-parameter lognormal distribution, and Type-I extremal distribution. 4. The most frequent probability distribution model of seashore location was Pearson type-III distribution. The most frequent probability distribution model of inland location was two parameter lognormal distribution.

• 한국콘텐츠학회논문지
• /
• 제11권1호
• /
• pp.56-64
• /
• 2011

스트림데이터는 무한하고 연속적인 특성을 지니고 있기 때문에 전체 데이터를 기반으로 빈발 항목 집합을 탐사하는 것은 어렵다. 이 때문에 데이터의 특성과 사용자의 특성을 반영한 특수한 데이터마이닝 방법이 필요하다. 이 논문에서는 사용자가 최근에 발생한 데이터에 더 많은 관심이 있다는 특성을 반영하여 빈발 항목을 탐사하는 FIMWB 방법을 제안한다. FIMWB는 과거 데이터의 발생 시점과 현재 시점과의 시간 간격에 따라 가변적인 가중치를 배치에 부여하여 최신 데이터에 더 많은 관심과 중요성을 반영한다. FP-Digraph는 FIMWB를 통해 탐사된 빈발 항목으로 그래프를 구성하여 빈발 항목 집합을 탐사한다. 실험 결과로 FIMWB 방법이 불필요한 항목의 생성을 감소시키고 트리기반(FP-Tree)의 빈발 항목 집합 탐사에 비해 제안하는 FP-Digraph 방법이 스트림 데이터 환경에 더 적합함을 알 수 있다.

• 한국정보통신학회논문지
• /
• 제15권1호
• /
• pp.147-156
• /
• 2011

최근 정보시스템의 활용도가 높아짐에 따라, 많은 데이터를 이용하여 필요한 상품을 빠르게 추출하는 방법들에 대한 연구가 활발히 이루어지고 있다. 숨겨진 패턴을 탐색하는 연관 규칙 탐색 기법들이 많은 관심을 받고 있으며, Apriroi 알고리즘은 대표적인 기법이다. 그러나 Apriori 알고리즘은 반복적인 스캔으로 인한 탐색시간 증가 문제를 가지고 있다. 본 논문에서는 빈발항목의 탐색시간을 단축하기 위한 알고리즘을 제안한다. 제안한 알고리즘은 트랜잭션 데이터베이스를 이용하여 매트릭스를 생성하고 매트릭스에서 트랜잭션들의 평균 항목 개수와 정의한 최소 지지도를 사용하여 빈발 항목을 탐색한다. 트랜잭션의 평균 항목 개수는 트랜잭션의 수를 줄이는데 사용되고 최소 지지도는 항목을 줄이는데 사용된다. 제안한 알고리즘의 성능 평가는 기존 알고리즘과의 탐색시간 비교와 정확도 비교로 이루어진다. 실험 결과는 제안한 알고리즘이 기존의 Apriori와 매트릭스 알고리즘보다 최종 빈발 항목의 추출에서 빠르고 효율적으로 탐색이 이루어지는 것을 확인하였다.

• Imaging Science in Dentistry
• /
• 제31권1호
• /
• pp.9-16
• /
• 2001

Purpose: To investigate bone and disc configuration on MR images in internal derangement related to age. Materials and methods: MR images of 150 TMJs in 107 patients were analyzed to determine the morphologic changes. Two groups were distinguished to be correlated with age. Group I consisted of TMJs that were diagnosed as having anterior disc displacement with reduction (ADDwR), and Group 2 consisted of TMJs that were diagnosed as having anterior disc displacement without reduction (ADDwoR). We assessed the configuration of the articular disc, degree of anterior disc displacement, and osseous changes of TMJs. Results: The third decade (83 of 150 joints) was most frequent in this study. In the ADDwR group biconcave discs was most frequent at all ages except fifth decade, but in the ADDwoR group deformed discs was most frequent at third and forth decades. In the ADDwR group slightly displaced discs was most frequent at all ages, but in the ADDwoR group severely displaced discs was most frequent at second decade, and the degree of disc displacement was increased with aging over 30 years of age. TM joints showed osseous changes in 17% of the ADDwR group, and in 30% of the ADDwoR group. MR findings of osseous changes of the TMJ were not found to be significantly correlated with age. Conclusion: The prevalence of deformation of disc, displacement of disc, and osseous changes of TMJ was higher in the ADDwoR group than in the ADDwR group. MR findings of disc configuration and degree of disc displacement were found to be correlated with age.

• 대한간호학회지
• /
• 제24권1호
• /
• pp.96-114
• /
• 1994

This study was carried out to describe and analyze experimental studies conducted in graduates nursing degree. Of 170 experimental studies conducted during the past three decades between 1962 and August 1991, 150 studies were available, including 124 master’s and 26 doctoral theses. This study examined their general characteristics and detailed research methods using percentiles. The results were as follows 1. Most of the studies adopted a quasi-experimental design. 2. The subjects of the studies were chosen by convenience sampling except for two studies whose subjects were drawn by randomization. Studies comparing experimental and control groups were in the highest proportion and the most frequent sample sizes of each group were 21 to 30 for both experimental and control groups. 3. As to measurement, physiological measures were most frequent followed by psychsociological measures and active report questionnaires. Each study, on average, adopted two kind of measurement tools. Studies in which the data collection period was of 1~2 months were in the highest pro-portion. 4. All doctoral theses and 67.0% of master’s theses examined specific research hypotheses. Of these studies, the results of 92.5% supported the hypotheses. 5. Parametric statistics were the major analytical methods. In particular, t-test was used most frequently followed by Chi square, F-test, and Pearson Correlation Coefficients. 6. Patients were the most frequent study subjects. Frequent nursing interventions were information and education followed by support, distraction, and nursing treatments. 7. With regards to the dependent variables, “feelings” such as anxiety, pain, and depression were most frequent. In addition “exchanging” such as restoring, metabolism, cardiopulmonary function, infection and vital signs were adopted as the dependent variables in 29.1％ of the studies examined, while 12.3% of the studies selected “choosing” such as stress, health behavior, or role performance.

• 문화기술의 융합
• /
• 제8권6호
• /
• pp.647-653
• /
• 2022

데이터 마이닝은 데이터를 탐색하고 분석하여 데이터 사이의 관계나 패턴 등의 지식을 탐사하는 기법이다. 실세계에서 발생하는 데이터는 시간 속성을 포함한다. 시간 속성을 포함하는 데이터에서 유용한 지식을 찾아내기 위한 시간 데이터마이닝 연구는 미래를 예측할 수 있는 예측 판단에 효율적으로 활용될 수 있다. 본 논문은 데이터베이스를 일정한 시간 간격 단위로 구분하고, 시간 단위에서 빈발한 패턴 아이템셋을 발견하기 위한 시간 단위 그룹핑을 이용하는 알고리즘을 제안한다. 제안하는 알고리즘은 시간 단위에 포함된 트랜잭션과 아이템 정보를 매트릭스로 구성하고, 그룹핑을 통한 시간 단위에서의 빈발한 아이템셋을 발견한다. 성능평가의 실험 결과에서 수행시간은 기존의 알고리즘보다 1.2배 소요되지만, 2배 이상의 빈발 아이템셋이 탐사되었다.