• Journal of Korean Society of Transportation
• /
• v.25 no.1 s.94
• /
• pp.121-132
• /
• 2007

Up to now Permanent traffic volumes have been counted by Automatic Vehicle Classification (AVC) on National Highways. When counted data have missing items or errors, the data must be revised to stay statistically reliable This study was carried out to estimate correct data based on outoregression and seasonal AutoRegressive Integrated Moving Average (ARIMA). As a result of verification through seasonal ARIMA, the longer the missed period is, the greater the error. Autoregression results in better verification results than seasonal ARIMA. Traffic data is affected by the present state mote than past patterns. However. autoregression can be applied only to the cases where data include similar neighborhood patterns and even in this case. the data cannot be corrected when data are missing due to low qualify or errors Therefore, these data shoo)d be corrected using past patterns and seasonal ARIMA when the missing data occurs in short periods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.775-779
• /
• 2006

강우자료의 구축은 수문해석에 있어 가장 기본적이며 중요한 단계라 할 수 있다. 하지만 수문 관측 자료의 경우 결측치가 존재하여 그에 대한 보정이 필요한 경우가 종종 발생하게 된다. 따라서 수문자료의 분석을 수행하기에 앞서 우선 자료에 대한 검정을 실시하고, 결측치가 존재할 경우는 이를 보정하여 분석을 수행하여야 한다. 본 연구에서는 다변량통계기법의 하나인 다중회귀분석을 이용하여 강우 결측치를 보정하였다. 본 연구에서는 다중공선성과 자기상관에 대하여 고려한 다중회귀모형을 구성하였다. 모형의 구성시 모든 결측지점에 적용이 가능하지 않아 일반성이 떨어짐을 확인 할 수 있었지만, 모형이 구성될 경우 통계적 적합도와 유의수준을 확인 할 수 있는 장점이 있었으며, 다중회귀모형이 구성되는 경우 좋은 보정 결과를 주는 것을 확인 할 수 있었다.

• 한국ITS학회:학술대회논문집
• /
• 2003.11a
• /
• pp.234-240
• /
• 2003

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.203-215
• /
• 2003

In order to provide the drivers with more reliable transportation information in NHTMS(National Highway Transportation Management System), it is important to estimate the expected passage time by using the traffic volume and speed. In this study, we analyze the characteristics of the traffic volume in the national highway and we investigate two real-time adjustment methods: the average adjustment method and the auto-regressive adjustment method. In addition, we compare them using the real data collected at the National Highway Route 3 in 2000.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.2
• /
• pp.1-13
• /
• 2015

Traffic volume data is basic information that is used in a wide variety of fields. Existing missing traffic volume data imputation method did not take the effect on the rainfall. This research analyzed considering of the rainfall effect in missing traffic volume data imputation method. In order to consider the effect of rainfall, established the following assumption. When missing of traffic volume data generated in rainy days it would be more accurate to use only the traffic volume data of the past rainy days. To confirm this assumption, compared for accuracy of imputed results at three kinds of imputation method(Unconditional Mean, Auto Regression, Expectation-Maximization Algorithm). The analysis results, the case on consideration of the rainfall effect was more low error occurred.

• 한국ITS학회:학술대회논문집
• /
• 2004.11a
• /
• pp.270-275
• /
• 2004

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.6 no.1
• /
• pp.35-39
• /
• 2001

Multibeam echosounder data, collected to investigate seabed features and topography, are usually subject to outliers resulting from the ship's irregular movements and insufficient correction for pressure calibration to the positions of beams. We introduce a statistical method which adjusts the outliers using the ARMA (Autoregressive Moving Average) technique. Our method was applied to a set of real data acquired in the East Sea. In our approach, autocorrelation of the data is modeled by an AR (1) model. If an observation is substantially different from that obtained from the estimated AR (1) model, it is declared as an outlier and adjusted using the estimated AR (1) model. This procedure is repeated until no outlier is found. The result of processing shows that outliers that are far greater than signals in amplitude were successfully removed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.2
• /
• pp.200-209
• /
• 2019

When forecasting future values, a model estimated after minimizing training errors can yield test errors higher than the training errors. This result is the over-fitting problem caused by an increase in model complexity when the model is focused only on a given dataset. Some regularization and resampling methods have been introduced to reduce test errors by alleviating this problem but have been designed for use with only a given dataset. In this paper, we propose a new optimization approach to reduce test errors by transforming a test error minimization problem into a training error minimization problem. To carry out this transformation, we needed additional data for the given dataset, termed pseudo data. To make proper use of pseudo data, we used three types of missing data imputation techniques. As an optimization tool, we chose the least squares method and combined it with an extra pseudo data instance. Furthermore, we present the numerical results supporting our proposed approach, which resulted in less test errors than the ordinary least squares method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.452-456
• /
• 2002

The sensor based control system has some sensor fault while operating in the field. In this paper, a sensor fault detection and reconstruction system for a sun tracking controller has been researched by using polynomial regression and principle component analysis approach. The developed sun tracking system controls tow actuators with sensor based mechanism as on-line control and sun orbit information as off-line control, alternatively. To show the validity of the developed system, several experiments were illustrated.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.1
• /
• pp.35-42
• /
• 2008

Instrumented sharp indentation test is a well-directed method to measure hardness and elastic modulus. The sharp indenter such as Berkovich and conical indenters have a geometrical self-similarity in theory, but the self-similarity ceases to work in practice due to inevitable indenter tip-blunting. In this study we analyzed the load-depth curves of conical indenter with finite tip-radius via finite element method. Using the numerical regression data obtained from Kick's law, we first confirmed that loading curvature is significantly affected by tip radius as well as material properties. We then established a new method to evaluate Young's modulus, which successfully provides the value of elastic modulus with an average error of less than 2%, regardless of tip-radius and material properties of both indenter and specimen.