Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.

This paper proposed data driven techniques to forecast the time point of water management of the water reservoir without measuring manganese concentration with the empirical data as Juam Dam of years of 2015 and 2016. When the manganese concentration near the surface of water goes over the criteria of 0.3mg/l, the water management should be taken. But, it is economically inefficient to measure manganese concentration frequently and regularly. The water turnover by the difference of water temperature make manganese on the floor of water reservoir rise up to surface and increase the manganese concentration near the surface. Manganese concentration and water temperature from the surface to depth of 20m by 5m have been time plotted and exploratory analyzed to show that the water turnover could be used instead of measuring manganese concentration to know the time point of water management. Two models for forecasting the time point of water turnover were proposed and compared as follow: The regression model of CR20, the consistency ratio of water temperature, between the surface and the depth of 20m on the lagged variables of CR20 and the first lag variable of max temperature. And, the Box-Jenkins model of CR20 as ARIMA (2, 1, 2).

It is critical to forecast the maximum daily and monthly demand for power with as little error as possible for our industry and national economy. In general, long-term forecasting of power demand has been studied from both the consumer’s perspective and an econometrics model in the form of a generalized linear model with predictors. Time series techniques are used for short-term forecasting with no predictors as predictors must be predicted prior to forecasting response variables and containing estimation errors during this process is inevitable. In previous researches, seasonal exponential smoothing method, SARMA (Seasonal Auto Regressive Moving Average) with consideration to weekly pattern Neuron-Fuzzy model, SVR (Support Vector Regression) model with predictors explored through machine learning, and K-means clustering technique in the various approaches have been applied to short-term power supply forecasting. In this paper, SARMA and intervention model are fitted to forecast the maximum power load daily, weekly, and monthly by using the empirical data from 2011 through 2013. ARMA(2,1,2)(1,1,1)7 and ARMA (0,1,1)(1,1,0)12 are fitted respectively to the daily and monthly power demand, but the weekly power demand is not fitted by AREA because of unit root series. In our fitted intervention model, the factors of long holidays, summer and winter are significant in the form of indicator function. The SARMA with MAPE (Mean Absolute Percentage Error) of 2.45% and intervention model with MAPE of 2.44% are more efficient than the present seasonal exponential smoothing with MAPE of about 4%. Although the dynamic repression model with the predictors of humidity, temperature, and seasonal dummies was applied to foretaste the daily power demand, it lead to a high MAPE of 3.5% even though it has estimation error of predictors.

There have been various studies on measurements of flood risk and forecasting models. For river and dam region, PDF and FVI has been proposed for measurement of flood risk and regression models have been applied for forecasting model. For Bo region unlikely river or dam region, flood risk would unexpectedly increase due to outgoing water to keep water amount under the designated risk level even the drain system could hardly manage the water amount. GFI and general linear model was proposed for flood risk measurement and forecasting model. In this paper, FVI with the consideration of duration on GFI was proposed for flood risk measurement at Bo region. General linear model was applied to the empirical data from Bo region of Nadong river to derive the forecasting model of FVI at three different values of Base High Level, 2m, 2.5m and 3m. The significant predictor variables on the target variable, FVI were as follows: ground water level based on sea level with negative effect, difference between ground altitude of ground water and river level with negative effect, and difference between ground water level and river level after Bo water being filled with positive sign for quantitative variables. And for qualitative variable, effective soil depth and ground soil type were significant for FVI.

When the number of items of same type of industrial property is quite large, calculating depreciation for a group of such item may be more efficient than depreciating each item separately. Also, predicting the service life of a specific individual unit is very difficult to do with any degree of accuracy. Estimating the probable average service life (PASL) of many units (or dollars) is not an easy task; however, an average life of many units can probably be predicted with a much higher degree of accuracy than the life of some particular unit. Using the average of many units allows for some units having relatively short lives and some units having relatively long lives without specifying whether a particular unit will have a short or a long life. If the life of each vintage in an account are not estimated, then the broad group procedure can be used. The broad group procedure depreciates the several vintage in an account as a single group. The PASL for this procedure is the estimate of the average of lives of the individual dollars in the group. If the estimated PASL’s of the vintages are not the same, then a weighted average PASL would have to be calculated for each calendar year. In this paper, we illustrate the calculations of accrual rates and the annual depreciation charge for each of the calendar years by the broad group depreciation procedure.

During a flood season, Bo region could be easily exposed to flood due to increase of ground water level and the water drain difficulty even the water amount of Bo can be managed. GFI for the flood risk is measured by mean depth to water during a dry season and minimum depth to water and tangent degree during a flood season. In this paper, a forecasting model of the target variable, GFI and predictors as differences of height between ground water and Bo water, distances from water resource, and soil characteristics are obtained for the dry season of 2012 and the flood season of 2012 with empirical data of Gangjungbo and Hamanbo. Obtained forecasting model would be used for keep the value of GFI below the maximum allowance for no flooding during flooding seasons with controlling the values of significant predictors.

Several different depreciation systems may be used for group depreciation. The vintage group procedure treats the same type of property placed in service during the same year as a distinct group for depreciation purposes; therefore an estimate of the probable average service life and net salvage ratio(s) of each individual vintage is necessary. The vintage group procedure calculates an accrual rate for each vintage and the accrual rate for an account for specific calendar year is the weighted average vintage accrual rate for that calendar year. A further refinement would be to divide each vintage into groups such that all of the dollars in a group have the same estimated life-an equal life group (ELG). Then each ELG is depreciated over its estimated life. The effect is to recover each dollar over the estimated number of years it is in service. Each vintage is divided into several equal life groups (ELGs) such that all the property in a specific ELG has the same estimated life. The accrual rate for each ELG is based on the estimated life of that ELG. The vintage accrual rate for a specific year is the weighted average ELG accrual rate for that calendar year. In this paper, we illustrate the calculations of vintage accrual rates for each of the calendar years by the ELG depreciation systems.

The methods for constructing network of observational locations for measuring water quality in water reservoirs have been widely proposed, but they had some limitations to be applied to river areas, which lie in awkward clustering and finding representati

When the number of items of same type of industrial property is quite large, calculating depreciation for a group of such items may be more efficient than depreciating each item separately. Several different depreciation systems may be used for group depr

Ship handling simulator is a virtual ship navigating system with three dimensional screen system and simulation programs. FTS simulation can produce theoretically infinite experiment tests without time constraint, but which results in collecting determins

효과적인 수질관리를 위해서는 수질정보의 기대수준에 맞는 신뢰성 있는 수질자료가 확보되어야 한다. 이런 점에서 볼 때 수질모니터링은 조사지점, 수질항목, 측정주기 등이 성패의 중요한 요인이 되며, 이중에서 특히 조사지점은 가장 중요한 사항으로 판단된다. 그러나 지금까지 수질조사를 위한 관측지점은 대부분 정성적 판단에 따라 정해지고 있었기 때문에 수질 대표성이 문제가 되기도 하였다. 본 논문에서는 이와같은 수질측정망 구축 시 문제점을 과학적인 통계기법을 적

항만이나 항로에서의 심층적인 선박운항 안전성 평가를 위한 목적으로 주로 선박운항 시뮬레이션 시스템이 사용되고 있다. 하지만, 실제 해상에서 선박이 조우할 수 있는 환경 조건은 매우 다양한 반면, 비용이나 시간적인 제약으로 인하여 실시간 선박운항 시뮬레이션은 극히 한정된 경우에 대해서만 수행되는 것이 일반적이다. 본 논문에서는, 이러한 실시간 시뮬레이션 실험 조건을 효과적이고 체계적으로 도출하기 위한 통계적 기법에 대하여 제안하고, 이 기법을 실제 선박 운항 안전성 평가를 위한 시뮬레이션 연구에 적용한 실증 분석 결과를 사례 연구로 기술하였다. 실증 분석에는 주성분을 이용한 종합 운항 난이도 산정 방법과 누적 확률분포 개념을 이용하여 선박 운항 난이도가 높은 실험 조건을 실시간 시뮬레이션 실험 조건으로 선택하는 기법을 제시하였다.