• 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.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 춘계학술발표대회
• /
• pp.31-33
• /
• 2007

Devising an efficient one-pass frequent pattern mining algorithm has been an issue in data mining research in recent past. Pattern growth algorithms like FP-Growth which are found more efficient than candidate generation and test algorithms still require two database scans. Moreover, FP-growth approach requires rebuilding the base-tree while mining with different support counts. In this paper we propose an item-based tree, called I-Tree that not only efficiently mines frequent patterns with single database scan but also provides multiple mining scopes with multiple support thresholds. The 'build-once-mine-many' property of I-Tree allows it to construct the tree only once and perform mining operation several times with the variation of support count values.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5287-5303
• /
• 2018

Handling vast amount of data found in large transactional datasets is an obvious challenge for the conventional data mining algorithms. Addressing this challenge, our paper proposes a parallel approach for proper decomposition of mining problem into sub-problems in order to find frequent patterns from these datasets. The proposed, Pattern Mining for Large Distributed Dataset (PMLDD) approach, ensures minimum dependencies as well as minimum communications among sub-problems. It establishes a linear aggregation of the intermediate results so that it can be adapted to large-scale programming models like MapReduce. In this context, an algorithmic structure for MapReduce programming model is presented. PMLDD guarantees an efficient load balancing among the sub-problems by a specific selection criterion. Further, it optimizes the number of required iterations over the dataset for mining frequent patterns as compared to the existing approaches. Finally, we believe that our approach is scalable enough to handle larger datasets in terms of performance evaluation, and the result analysis justifies all these mentioned concerns.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.771-773
• /
• 2005

웹 환경에서 사용자들의 정보검색 패턴을 얻어내기 위해 흔히 로그 파일의 정보검색 패턴을 분석하는 기존 연구들이 있어 왔다. 이들에서 흔히 사용하는 방법은 경로 순회 패턴(path traversal patterns)에서 효율적으로 빈번 패턴(frequent patterns)을 찾아내는 알고리즘을 제안하는 것이다. 하지만 이들의 기존 연구의 가장 일반적인 문제점들 중의 하나는 일반적인 패턴 즉, 복잡한 형태 패턴(topological patterns)에 대한 적절한 해답을 찾아주지는 못한다는 것이다. 따라서 본 논문에서는 일반적인 패턴 유형을 정의하고 이들로부터 정보검색 패턴을 알아내는 효율적인 알고리즘을 제안하고자 한다.

• 한국의류학회지
• /
• 제35권3호
• /
• pp.359-370
• /
• 2011

This study analyzes the textiles design of natural indigo dyed products in Korea and Japan. In this study, a total of 556 Korean natural indigo dyed products, and 2,730 Japanese natural indigo dyed products were used for analysis. The subjects of this study were 556 natural indigo dyed products and 2,730 Japanese natural indigo dyed products selling natural indigo dyed products which were found using search engine keywords of natural indigo dyeing and natural dyeing. Research and analysis was treated regarding the products, items, patterns, and the representation techniques of the patterns. The results of this study are as follows. In the pattern used for natural indigo dyed products, 71.4% of Korean products have no pattern, but 77.1% of Japanese products have patterns. On the representation techniques of the patterns, Korean products used tie-dyeing and a dip patterned fabric. While in the Japanese products, the most frequent patterning techniques were paraffin dye, followed by tie-dyeing, yarn-dyed and weaving, screen printing, and yarn-dyed and knitting. Regarding the kinds of patterns for natural indigo dyed products, only 8 kinds of patterns were used in Korean products; however, over 50 kinds of various patterns were used in Japanese products. Most patterns in the Korean products were ion patterns made by tie-dyeing. While in the Japanese products, the most frequent patterns were stripe patterns, followed by flower, dot, and ion patterns. Based on these research results, the problems of the textile design of Korean natural indigo dyed products were that most of the products have no pattern, and even though there were patterns, they lacked variations between the products. While in the case of Japan, they used the traditional and modem patterns of various textile representation techniques.

• 대한산업공학회지
• /
• 제32권3호
• /
• pp.242-252
• /
• 2006

Data mining is the exploration and analysis of huge amounts of data to discover meaningful patterns. One of the most important data mining problems is association rule mining. Recent studies of mining association rules have proposed a closure mechanism. It is no longer necessary to mine the set of all of the frequent itemsets and their association rules. Rather, it is sufficient to mine the frequent closed itemsets and their corresponding rules. In the past, a number of algorithms for mining frequent closed itemsets have been based on items. In this paper, we use the transaction itself for mining frequent closed itemsets. An efficient algorithm is proposed that is based on a link structure between transactions. Our experimental results show that our algorithm is faster than previously proposed methods. Furthermore, our approach is significantly more efficient for dense databases.

• 패션비즈니스
• /
• 제19권4호
• /
• pp.57-74
• /
• 2015

The history of foot-binding was once regarded as a unique practice accentuating the beauty of a woman and the culture of the costume, to be found nowhere except in China. This thesis makes it an aim to understand the culture of costume in China by analyzing the beauty of foot-binding, and its meanings associated with the historical background of the costume. The method of investigation was by both previous literature on the topic and case analysis. The shoes were analyzed by colors, patterns and decorations; selecting 70 pieces easily accessible in the Tianjin Huaxia Shoes Culture Museum. In terms of form, the general type was of the most frequent, followed by one with an elevated toe, mixed type, and one of the downward toe, sequentially. The color of foot-binding shoes were mostly vivid chromatic colors, while the achromatic ones like black and grey constituting significant portions. In view of the patterns, plants patterns were the most frequent, followed by the mixed patterns of mostly flowers with butterflies, bats, and birds desiring the prosperity of descendants. In view of the ornaments, embroidery was the most frequent, while the mixed shoes included tassels, sequins, applique, and shoes without ornaments were of distributions. The forms, colors, patterns and ornaments clearly associated with the wishes of artistic beauty, sexuality, and rise in women's social status may be in the hope of leading others to understand the costume culture embedded in the Chinese by providing important clues about them.

• 한국식생활문화학회지
• /
• 제9권3호
• /
• pp.241-250
• /
• 1994

In this study, we analyzed 2-day food records of the 1990 Korean National Nutrition Survey data for 2,000 households, and investigated most popular menu patterns by area, income, meal. The basic menu patterns of Korean, excluding side dishes, were Rice+Soup, Rice+Stew, Rice, Others, Rice+Soup+Stew in the order of proportion for all analyzed sectors. And the proportion of menus with the rice as a main dish was about 90% on the whole. The most popular menus of Korean were Rice+Soup+Kimchi(4.52%), Noodle+Kimchi(4.30%). When they ate rice as a main dish, they had soup, kimchi, and 1 or 2 other side dishes. At large cities, Noodle+Kimchi was the most frequent menu(5.20%). On the other hands, small cities and rural areas, Rice+Soup+Kimchi+Cooked vegetable was common. For the households which salaries less than 5 million won, Rice+Stew+Kimchi is the most prevalent, but households which salaries higher than 5 million won, Noodle+Kimchi was most frequent. At breakfast and dinner, the proportion of Rice+Stew+Kimchi+Cooked vegetable was 4.70%. But at lunch, Noodle+Kimchi was the most frequent and other menu combinations based on noodle were also common. Therefore most households showed conventional rice based menu patterns, but these patterns were decreasing for the large cities, and high income households. Especially at lunch, they used various menus which were not based on rice.

• 대한토목학회논문집
• /
• 제39권3호
• /
• pp.461-467
• /
• 2019

IoT (Internet of Things) 기술과 위치기반 기술의 발전은 대용량의 이동데이터를 급속하게 생성하고 있다. 대용량 이동 데이터의 분석은 도시 이동의 흐름 및 교통 계획 등에 활용되고 있다. 본 연구에서는 불규칙한 공간적 및 시간적 해상도의 택시 승차 정보로부터 빈번 승차 패턴을 분석하였다. 택시 승차 지점을 중심으로 군집 분석을 실시한 후 군집분석에 기반한 영역을 기준으로 순차패턴 분석을 적용하여 택시 승차 지점이 빈번하게 일어나는 패턴을 분석하였다. 실험용 데이터는 서울특별시 택시 운행 정보로부터 아침 출근 시간인 7시부터 9시 사이의 승차 정보를 분석하였다. 분석 결과는 아침 출근 시간대에 가장 빈도가 높게 발생하는 승차 순차 패턴은 강남 지역 안에서 많이 발생하였으며 지역과의 연계에 있어서는 강남으로부터 서울 시청 지역으로의 이동이 많이 발생하였다. 또한 본 연구는 순차 패턴 분석을 위한 기본 단위로 행정동 경계를 기준으로 분석하였다. 하지만 행정동 경계 기반의 분석은 지역간의 이동 패턴을 찾기가 어려웠다. 본 연구 결과는 향후 택시 공차율 감소와 도시 흐름관리를 위하여 활용할 수 있을 것으로 사료된다.

• 디지털융복합연구
• /
• 제15권6호
• /
• pp.229-236
• /
• 2017

효율적인 빈발 패턴 알고리즘은 연관 규칙 마이닝이나 융복합을 위한 마이닝 과정에서 필수적인 요소이며 많은 활용성을 가지고 있다. 패턴 마이닝을 위한 많은 모델들이 빈발 패턴에 관한 정보를 추출하여 FP-트리를 이용하여 저장하고 있다. 본 논문에서는 항목들의 무게중심을 이용한 새로운 빈발 패턴 알고리즘(CAWFP-Growth)을 제안하여 항목들이 가지는 가중치와 빈도수를 같이 고려하여 항목간의 중심을 계산하여 기존의 FP-Growth 알고리즘의 효율성을 향상시킨다. 제안한 방법은 하향 폐쇄의 성질을 유지하기 위한 기존의 전역적 최대치 가중치 지지도를 필요로 하지 않기 때문에 자연히 빈발 패턴의 탐색시간이 줄어들고 정보의 손실을 줄일 수 있다. 실험결과를 통하여 제안된 알고리즘이 기존의 동적가중치를 이용하는 다른 방법과 비교해볼 때, 항목들의 무게중심이 빈발패턴의 정확한 정보를 유지하고 FP-트리의 처리시간을 줄여주기 때문에 제안한 방법의 중요성을 보이고 있다 또한 가상 분산모드에서 맵리듀스 프레임을 기반으로 빅데이터를 모델링하고 향후 완전분산 모드에서 제안한 알고리즘의 모델링이 필요하다.