• Title/Summary/Keyword: 시게열

Search Result 5, Processing Time 0.019 seconds

The Present and Future of Research Industry in Korea (우리나라 조사산업의 현황과 전망)

  • Park, Moo-Ik
    • Survey Research
    • /
    • v.1 no.2
    • /
    • pp.161-177
    • /
    • 2000
  • Research industry in Korea has shown remarkable development in the past decade, mainly owing to the fact that the confidence level on the research itself has been largely improved as the major predictions based on poll result hit the mark in the past presidential elections, and also the change of management style in Korean business based on the rational decision making process. In this article, I will analyze the change of Koreans behavior toward public opinion research in diachronic manner and show the number and activities of Research Organizations in order to look into the present condition of research industry and then think about the future and the desirable direction of Korean research industry.

  • PDF

Mathematical Modelling of Love and its Nonlinear Analysis (사랑의 수학적 모델링과 거동 해석)

  • Kim, Soon-Whan;Shon, Young-Woo;Bae, Young-Chul
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.9 no.11
    • /
    • pp.1297-1304
    • /
    • 2014
  • Love which is one of the emotional of mankind, has been studied in sociology and psychology as a matter of grate concern. In this paper We represent romantic behaviors in the love equation of Romeo and Juliet as time series and phase portraits. Also we analyze the behavior's relation by using time series and phase portraits when external force applied as the third person between Romeo and Juliet.

Clustering Performance Analysis for Time Series Data: Wavelet vs. Autoencoder (시계열 데이터에 대한 클러스터링 성능 분석: Wavelet과 Autoencoder 비교)

  • Hwang, Woosung;Lim, Hyo-Sang
    • Annual Conference of KIPS
    • /
    • 2018.10a
    • /
    • pp.585-588
    • /
    • 2018
  • 시계열 데이터의 특징을 추출하여 분석하는 과정에서 시게열 데이터가 가지는 고차원성은 차원의 저주(Course of Dimensionality)로 인해 데이터내의 유효한 정보를 찾는데 어려움을 만든다. 이러한 문제를 해결하기 위해 차원 축소 기법(dimensionality reduction)이 널리 사용되고 있지만, 축소 과정에서 발생하는 정보의 희석으로 인하여 시계열 데이터에 대한 군집화(clustering)등을 수행하는데 있어서 성능의 변화를 가져온다. 본 논문은 이러한 현상을 관찰하기 위해 이산 웨이블릿 변환(Discrete Wavelet Transform:DWT)과 오토 인코더(AutoEncoder)를 차원 축소 기법으로 활용하여 시계열 데이터의 차원을 압축 한 뒤, 압축된 데이터를 K-평균(K-means) 알고리즘에 적용하여 군집화의 효율성을 비교하였다. 성능 비교 결과, DWT는 압축된 차원수 그리고 오토인코더는 시계열 데이터에 대한 충분한 학습이 각각 보장된다면 좋은 군집화 성능을 보이는 것을 확인하였다.

In Situ Measurement of Breaking Wave Pressures (碎波壓의 實海域 측정)

  • 심재설;전인식
    • Journal of Korean Society of Coastal and Ocean Engineers
    • /
    • v.11 no.3
    • /
    • pp.141-148
    • /
    • 1999
  • The magnitude of breaking wave forces given by plunging breakers incident on a pile structure is much greater than the forces calculated by Morison's formula, but those forces may act on pile for very short duration in the range of a few multiples of 0.01 second. Hence, a dynamic analysis for the impact forces of breaking waves may be necessary for the accurate determination of pile displacements in the first stage of design. The time series of the impact force along the pile length is thus required, which may be estimated from the pressure distribution. In the present study, breaking wave pressures are measured for a vertical pile at real field which is easily subjected to plunging breakers in stormy weather conditions. The measured data are analyzed and compared with other results to quantify the characteristics of breaking wave pressures in real fields.

  • PDF

Mathematical Modelling of Happiness and its Nonlinear Analysis (행복의 수학적 모델링과 비선형 해석)

  • Kim, Soon-Whan;Choi, Sun-Koung;Bae, Young-Chul;Park, Young-Ho
    • The Journal of the Korea institute of electronic communication sciences
    • /
    • v.9 no.6
    • /
    • pp.711-717
    • /
    • 2014
  • Happiness has been studied in sociology and psychology as a matter of grave concern. In this paper the happiness model that a new second -order systems can be organized equivalently with a Spring-Damper-Mass are proposed. This model is organized a 2-dimensional model of identically type with Duffing equation. We added a nonlinear term to Duffing equation and also applied Gaussian white noise and period sine wave as external stimulus that is able to cause of happiness. Then we confirm that there are random motion, periodic motion and chaotic motion according to parameter variation in the new happiness model.