• Journal of the Korean Statistical Society
• /
• 제16권1호
• /
• pp.1-9
• /
• 1987

Recently a new form of the extended Yule-Walker equations for a mixed autoregressive moving-average process of orders p and q has been proposed. It can be used to obtain p+q+1 parameter values from the first p+q+1 autocovariance terms. The autoregressive part of the equations is linear and can be easily solved. In contrast the moving-average part is composed of nonlinear simultaneous equations. Thus some iterative algorithms are necessary to solve them. The iterative algorithm presented by Choi(1986) is very simple but its convergence has not been proved yet. In this paper a Newton-Raphson solution for the moving-average parameters is presented and its convergence is shown. Also numerical example illustrate the performance of the algorithm.

• 대기
• /
• 제24권2호
• /
• pp.197-206
• /
• 2014

The effects of different averaging operators and atmospheric stability on the turbulent fluxes are investigated using the vertical velocity, air temperature, carbon dioxide concentration, and absolute humidity data measured at 10 Hz by a 3-dimensional sonic anemometer and an open-path $CO_2/H_2O$ infrared gas analyzer installed at a height of 18.5 m on the rooftop of the Jungnang KT building located at a typical residential area in Seoul, Korea. For this purpose, 7 different averaging operators including block average, linear regression, and moving averages during 100 s, 300 s, 600 s, 900 s, and 1800 s are considered and the data quality control procedure such as physical limit check and spike removal is also applied. It is found that as the averaging interval becomes shorter, turbulent fluxes computed by the moving average become smaller and the ratios of turbulent fluxes computed by the 100 s moving average to the fluxes by the 1800 s moving average under unstable stability are smaller than those under neutral stability. The turbulent fluxes computed by the linear regression are 85~92% of those computed by the 1800 s moving average and nearly the same as those computed by 900 s moving average, implying that the adequate selection of an averaging operator and its interval will be very important to estimate more accurate turbulent fluxes at urban area.

• Journal of Sport and Applied Science
• /
• 제4권1호
• /
• pp.17-30
• /
• 2020

Moving sport tourism refers to travel that combines sport activity and tours to a particular destination. Although moving sport tourism is one of the fastest growing segments of the sport tourism industry, it is still lack of related-knowledge and academic studies. Hence, this study is conducted to explore the characteristics of moving sport tourism and to provide implications for sport tourism industry and future research. For this, ten participants who regularly participated in bicycle tours for the last 10 years were recruited for this study. The sample consisted of 9 males and 1 female. The average age of the participants was 44.6 years of which all but 2 had a full-time job. The average period of participating in bicycle tour was 7.9 years. For analysing data, content analysis approach was used. Interviews were tape recoded and data were multiple reviewed to identify the similar themes and to categorize them into conceptual constructs. Results suggest two requirements of moving sport tourism(moving and concurrent), three characteristics of moving sport tourism(self-directed, exploring, non-linear, purposive-riding, partial competitive, cultural touring) and two categories of moving sport tourism(full moving sport tourism and partial moving sport tourism). Implications for sport tourism industry and future studies were discussed.

• 한국융합학회논문지
• /
• 제6권4호
• /
• pp.161-167
• /
• 2015

시계열 데이터를 예측하는 것은 매우 어려운 작업이다. 비선형적인 특성을 갖는 신호에서 얻어지는 데이터들이 불확실성을 가지고 있기 때문이다. 본 논문은 특정 시계열 데이터의 정확한 예측을 위하여 시계열 자료가 어떤 패턴에 따라 변화한다는 전제하에서 과거 자료들을 평균하여 미분으로써, 시계열 변화 패턴의 찾았다. 또한 미분 데이터의 반영 비율에 따라 특이성을 갖는 시계열데이터를 일반화하기 위하여 확률변수를 적용하였다. 순환변동과 계절변동을 소거하고, 불규칙 변동만을 추출하여 경향의 추세를 더한 예측값을 계산하게 된다. 이렇게 예측된 값은 이동평균과 단순이동평균에 의하여 가장 좋은 결과값을 갖는 알고리즘과 비교를 통하여 제안 알고리즘의 우수성을 입증하였다.

• 한국인터넷방송통신학회논문지
• /
• 제14권5호
• /
• pp.35-43
• /
• 2014

데이터 할당 기술은 데이터 방송 시스템의 성능을 향상시키기 위해서 필수적이다. 본 논문은 다중 데이터 질의가 제기되는 환경에서 방송채널에 데이터를 할당하는 주제를 연구하여 DAMA(Data Allocation using Moving Average)로 명명된 새로운 데이터 할당 기법을 제안한다. 제안된 기법은 각 데이터의 방송빈도를 자신의 액세스 확률의 이동 평균에 의해 결정하는 전략을 채택한다. DAMA는 질의 크기에 따라 액세스 확률의 영향력을 적절하게 제어할 수 있기 때문에 질의 응답시간의 성능을 향상시킬 수 있다. 제안된 기법의 성능 평가를 위해 시뮬레이션이 수행되었다. 실험 결과에 따르면, 평균 응답시간의 성능에서 DAMA는 다른 기법보다 우수한 성능을 보인다.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1530-1537
• /
• 2016

Recently, solar power generation shows the significant growth in the renewable energy field. Using the short-term prediction, it is possible to control the electric power demand and the power generation plan of the auxiliary device. However, a short-term prediction can be used when you know the weather forecast. If it is not possible to use the weather forecast information because of disconnection of network at the island and the mountains or for security reasons, the accuracy of prediction is not good. Therefore, in this paper, we proposed a system capable of short-term prediction of solar power generation amount by using only the weather information that has been collected by oneself. We used temperature, humidity and insolation as weather information. We have applied a moving average to each information because they had a characteristic of time series. It was composed of min, max and average of each information, differences of mutual information and gradient of it. An artificial neural network, SVM and RBF Network model was used for the prediction algorithm and they were combined by Ensemble method. The results of this suggest that using a moving average during pre-processing and ensemble prediction models will maximize prediction accuracy.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.818-833
• /
• 2017

This paper introduces a new algorithm that renders motion blur using triangular motion paths. A triangle occupies a set of pixels when moving from a position in the start of a frame to another position in the end of a frame. This is a motion path of a moving triangle. For a given pixel, we use a motion path of each moving triangle to find a range of time that this moving triangle is visible to the camera. Then, we sort visible time ranges in the depth-time dimensions and use bitwise operations to solve the occlusion problem. Thereafter, we compute an average color of each moving triangle based on its visible time range. Finally, we accumulate an average color of each moving triangle in the front-to-back order to produce the final pixel color. Thus, our algorithm performs shading after the visibility test and renders motion blur in real time.

• 한국정보과학회논문지:데이타베이스
• /
• 제33권1호
• /
• pp.42-55
• /
• 2006

본 논문에서는 단일 색인을 사용하는 임의 계수의 이동평균 변환 지원 서브시퀀스 매칭 방법을 제안한다. 단일 색인을 사용함으로써, 제안한 방법은 색인 저장 공간 및 색인 관리의 오버헤드를 크게 줄일 수 있다. 이동평균 변환은 시계열 데이타 내의 노이즈 영향을 감소시킴으로써, 시계열 데이타 전체의 경향을 파악하는데 매우 유용하다. 그런데, 기존 연구에서는 임의 계수를 지원하기 위해 여러 색인을 생성해야 하고, 이에 따라 색인 저장 공간의 오버헤드와 색인 관리의 오버헤드가 발생하는 문제점이 있다. 본 논문에서는 우선 이동평균 변환의 정의를 확장한 다계수 이동평균 변환(poly-order moving average transform) 개념을 제시한다. 다계수 이동평균 변환이란, 각 윈도우를 하나의 이동평균 계수에 대해서 이동평균 변환하는 것이 아니라, 여러 계수에 대해서 이동평균 변환하여 윈도우의 집합을 구성하는 변환으로서, 이동평균 변환의 정의를 여러 계수로 구성된 집합에 대해서 확장한 것이다. 다음으로, 이러한 다계수 이동평균 변환 개념을 사용한 서브시퀀스 매칭 방법의 이론적 근거인 정확성을 정리로서 제시하고 증명한다. 또한, 다계수 이동평균 변환을 기존 서브시퀀스 매칭 연구인 Faloutsos 둥의 방법 및 DualMatch에 각각 적용하여, 두 가지 이동평균 변환 지원 서브시퀀스 매칭 방법을 제시한다. 실험 결과, 제안한 두 가지 서브시퀀스 매칭 방법은 모든 경우에 있어서 순차 스캔보다 성능을 크게 향상시킨 것으로 나타났다. 실제 주식 데이타에 대한 실험 결과, 제안한 방법은 순차 스캔에 비해서 평균 22.4배${\~}$33.8배까지 성능을 향상시킨 것으로 나타났다. 또한, 각 계수에 대해 모두 색인을 생성하는 경우와 비교할 때, 성능 저하는 매우 적은 반면 필요한 색인 공간은 크게 줄인 것으로 나타났다(일곱 개의 계수를 사용한 경우, 성능 저하는 평균 $9\%{\~}42\%$에 불과한 반면 색인 공간은 약 1/7.0로 크게 줄인다). 이와 같이 성능 측면과 색인 공간 및 관리 측면에서의 우수성에 덧붙여, 제안한 방법은 이동평균 변환 이외의 다른 변환을 지원하는 서브시퀀스 매칭으로 일반화 될 수 있는 장점이 있다 따라서, 제안한 방법은 이동평균 변환을 포함하는 많은 다른 종류의 변환을 지원하는 서브시퀀스 매칭에 폭넓게 적용되는 우수한 연구결과라 사료된다.

• International Journal of Control, Automation, and Systems
• /
• 제5권6호
• /
• pp.701-706
• /
• 2007

The measurement accuracy for heart rate or $SpO_2$ using photoplethysmography (PPG) is influenced by how well the noise from motion artifacts and other sources can be removed. Eliminating the motion artifacts is particularly difficult since its frequency band overlaps that of the basic PPG signal. Therefore, we propose the Periodic Moving Average Filter (PMAF) to remove motion artifacts. The PMAF is based on the quasi-periodicity of the PPG signals. After segmenting the PPG signal on periodic boundaries, we average the $m^{th}$ samples of each period. As a result, we remove the motion artifacts well without the deterioration of the characteristic point.

• 한국환경과학회지
• /
• 제27권12호
• /
• pp.1227-1239
• /
• 2018

In this study, daily precipitation data and daily average temperature data of meteorological observatories in Daegu, Busan, Daejeon, Seoul, Mokpo, and Gwangju cities inland and offshore were analyzed by using moving average method. Were compared. Overall, summarizing changes in precipitation and temperature over the 24 seasons, precipitation and temperature in all six stations increased compared to the past 1960s. In the case of precipitation, precipitation increased at the end of July and early August, whereas precipitation in April, September and early October decreased. In the case of temperature, especially in February, the temperature increased, and in Mokpo, the temperature from August to December showed a general decline. Changes in precipitation and temperature due to seasons in the 24 seasons affect agriculture and our everyday life, and further research is needed to determine how these changes will affect agricultural water supply, crop growth and daily life. The results of this study can be useful.