http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
유사 주기적 구매 패턴 분석을 통한 구매 시점 예측 및 마케팅 활용
김재완(Jae-Wan Kim),이원석(Won-Suk-Lee) 한국정보기술학회 2017 Proceedings of KIIT Conference Vol.2017 No.6
기계적으로 생성된 패턴과는 달리 인간이나 자연에서 발생시키는 데이터의 주기적인 패턴은 정확한 시간간격으로 형성되지 않는다. 큰 규모의 데이터에서 모든 현상에 대해 이러한 패턴을 분석하고 다음 행동을 예측하는 것은 쉽지 않은 과제다. 이러한 패턴을 유사주기 패턴이라 한다. 유사주기 패턴은 그 특징에 따라 시간유사주기 패턴, 미발생 유사주기 패턴, 복합 유사주기 패턴으로 분류된다. 본 연구에서는 각 유형별 주기 패턴 표현형을 정의하고, 이를 이용해 실제 제품 구매 데이터에서 유사주기 패턴을 찾는다. 또한 이 패턴을 이용해 구매 시점 예측 및 주기성 상실 분석, 고객 충성도 향상 등을 위한 마케팅 등에 활용하는 방안을 제시하고자 한다. Unlike mechanically generated patterns, periodical behaviors made by humans or nature are not formed at precise time intervals. It is hard to analyze those patterns and predict the time of next action in large scale data. We call these patterns as pseudo periodic patterns. A pseudo periodic patterns can be classified into three. these are timing pseudo periodic pattern, non-occurrence pseudo periodic pattern, complex pseudo periodic pattern according to its characteristics. In this paper, we define periodic pattern representation form and use it to find pseudo periodic pattern of data from actual purchase data. In addition, we will utilize these patterns to present a method predicting future purchasing time, periodicity loss and customer loyalty marketing.
광섬유를 통한 광 주파수 전송에서 광 위상 잡음의 능동 제거
이원규,김재완,유한영,김억봉,Lee, Won-Kyu,Kim, Jae-Wan,Ryu, Han-Young,Kim, Eok-Bong 한국광학회 2007 한국광학회지 Vol.18 No.1
광섬유 망을 통해 수 kHz의 좁은 선폭을 가지는 $1.5{\mu}m$ 레이저광원을 높은 전송 안정도로 전송하였다. 525 m 길이의 단일모드 광섬유를 통과하면서 발생하는 광 위상 잡음을 능동적으로 제거하는 실험 장치를 구성하였고, 이렇게 하여 전송된 광 주파수의 전송 안정도는 1 초의 평균시간에서 $2{\times}10^{-17}$로 측정되었다. 전송된 광 주파수의 품질을 주파수 영역과 시간 영역에서 정량적으로 분석하였다. We have transferred a narrow-linewidth $1.5{\mu}m$ laser beam through a 525 m fiber network with excellent transfer stability. The fiber-induced optical phase noise during the fiber transmission is cancelled by configuring a noise-canceling servo. The transfer instability was $2{\times}10^{-17}$ at 1 s of averaging time. We quantitatively analyzed the transferred optical frequency in the frequency domain and in the time domain.
양원경(Won Kyung Yang),정춘식(Chun Sik Jung),정기화(Ki Wha Jung),김재완(Jae Wan Kim),이은방(Eun Bang Lee) 대한약학회 1992 약학회지 Vol.36 No.2
The rhizoma of Zingiber officinalehas been used as antiemetic, expectorants, stomachache relieving drugs and digestive accelerators. From the observation of antigastritic action of the methanol extract of the rhizoma, it was fractionated with hexane, chloroform, ethyl acetate and butanol, followed by bioassay on antigastritic and antiulcerative activity. The hexane and the chloroform fraction reduced significantly HCl.ethanol induced gastric lesion at the dose of 370 and 210mg/kg, p.o., respectively. On the gastric ulceration and gastric secretion in pylorus-ligated rats, the hexane fraction decreased the volume of gastric secretion and acid output, and also increased pH at the dose of 370mg/kg, i.d.. It showed considerable curative ratio of acetic acid induced ulcer without inhibition of indomethacin induced gastric lesion. The methanol extract showed low acute toxicity with minimum lethal dose of more than 3000mg/kg, p.o. in mice. In conclusion, Zingiberis rhizoma exhibited antigastric and antiulcerative activity which might be attributable to inhibition of gastric secretion. It is revealed that the active component may be present in the hexane fraction.
다중 해시함수 기반 데이터 스트림에서의 아이템 의사 주기 탐사 기법
이학주(Hak Joo Lee),김재완(Jae Wan Kim),이원석(Won Suk Lee) 한국IT서비스학회 2017 한국IT서비스학회지 Vol.16 No.1
Recently in-memory data stream processing has been actively applied to various subjects such as query processing, OLAP, data mining, i.e., frequent item sets, association rules, clustering. However, finding regular periodic patterns of events in an infinite data stream gets less attention. Most researches about finding periods use autocorrelation functions to find certain changes in periodic patterns, not period itself. And they usually find periodic patterns in time-series databases, not in data streams. Literally a period means the length or era of time that some phenomenon recur in a certain time interval. However in real applications a data set indeed evolves with tiny differences as time elapses. This kind of a period is called as a pseudo-period. This paper proposes a new scheme called FPMH (Finding Periods using Multiple Hash functions) algorithm to find such a set of pseudo-periods over a data stream based on multiple hash functions. According to the type of pseudo period, this paper categorizes FPMH into three, FPMH-E, FPMH-PC, FPMH-PP. To maximize the performance of the algorithm in the data stream environment and to keep most recent periodic patterns in memory, we applied decay mechanism to FPMH algorithms. FPMH algorithm minimizes the usage of memory as well as processing time with acceptable accuracy.