• Journal of Construction Engineering and Project Management
• /
• v.4 no.4
• /
• pp.9-16
• /
• 2014

The purpose of this paper is to develop a model for forecasting early design construction cost of building projects using Artificial Neural Network (ANN). Eighty questionnaires distributed among construction organizations were utilized to identify significant parameters for the building project costs. 169 case studies of building projects were collected from the construction industry in Gaza Strip. The case studies were used to develop ANN model. Eleven significant parameters were considered as independent input variables affected on "project cost". The neural network model reasonably succeeded in estimating building projects cost without the need for more detailed drawings. The average percentage error of tested dataset for the adapted model was largely acceptable (less than 6%). Sensitivity analysis showed that the area of typical floor and number of floors are the most influential parameters in building cost.

• Journal of Information Technology Applications and Management
• /
• v.13 no.4
• /
• pp.57-70
• /
• 2006

Location Based Service (LBS) provides high-value added service to users and various works about IBS have been actively performed. The core technology or LBS is positioning of the users. In the field of positioning, outdoor positioning and indoor positioning are developed separately. We are proposing a design of an outdoor-indoor positioning system, implementing a prototype of the system, and verifying the usefulness of the system through experiments. Our experimental results shows that the average error of our system is 4.8 m in the case of out-door positioning and it is 3.3 m in the case of in-door positioning.

• Journal of Wetlands Research
• /
• v.25 no.2
• /
• pp.75-82
• /
• 2023

Data for measuring the flow rate of streams are used as important basic data for the development and maintenance of water resources, and many experts are conducting research to make more accurate measurements. Especially, in Korea, monsoon rains and heavy rains are concentrated in summer due to the nature of the climate, so floods occur frequently. Therefore, it is necessary to measure the flow rate most accurately during a flood to predict and prevent flooding. Thus, the U.S. Geological Survey (USGS) introduces 1, 2, 3 point method using a flow meter as one way to measure the average flow rate. However, it is difficult to calculate the average flow rate with the existing 1, 2, 3 point method alone.This paper proposes a new 1, 2, 3 point method formula, which is more accurate, utilizing one probabilistic entropy concept. This is considered to be a highly empirical study that can supplement the limitations of existing measurement methods. Data and Flume data were used in the number of holesman to demonstrate the utility of the proposed formula. As a result of the analysis, in the case of Flume Data, the existing USGS 1 point method compared to the measured value was 7.6% on average, 8.6% on the 2 point method, and 8.1% on the 3 point method. In the case of Coleman Data, the 1 point method showed an average error rate of 5%, the 2 point method 5.6% and the 3 point method 5.3%. On the other hand, the proposed formula using the concept of entropy reduced the error rate by about 60% compared to the existing method, with the Flume Data averaging 4.7% for the 1 point method, 5.7% for the 2 point method, and 5.2% for the 3 point method. In addition, Coleman Data showed an average error of 2.5% in the 1 point method, 3.1% in the 2 point method, and 2.8% in the 3 point method, reducing the error rate by about 50% compared to the existing method.This study can calculate the average flow rate more accurately than the existing 1, 2, 3 point method, which can be useful in many ways, including future river disaster management, design and administration.

• Nuclear Engineering and Technology
• /
• v.25 no.2
• /
• pp.222-232
• /
• 1993

In this paper, we present two sets of fuzzy algorithms for the steam generator level control ; one for the high power operations where the flow error is available and the other for the low power operations where the flow error is not available. These are converted to a PID type controller for the high power case and to a quadratic function form of a controller for the low power case. These controllers are implemented on the Compact Nuclear Simulator at Korea Atomic Energy Research Institute and tested by a set of four simulation experiments for each. For both cases, the results show that the total variation of the level error and of the flow error are about 50% of those by the PI controllers with about one half of the control action. For the high power case, this is mainly due to the fact that a combination of two PD type controllers in the velocity algorithm form rather than a combination of two PI type controllers in the position algorithm form is used. For the low power case, the controller is essentially a PID type with a very small integral component where the average values for the derivative component input and for the controller output are used.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.61-71
• /
• 2003

Existent DDHV draws and is calculating K coefficient. D coefficient from sum of traffic volume two-directions time. There is difference of design order and actuality order, error of DDHV estimation value, problem of irregular change etc. of DDHV thereby. In this study, among traffic volume of each other independent two direction(going up, going down), decide design target order in the directional traffic volume, presented way(way) applying without separating K coefficient and D coefficient at the same time. The result were analysis about national highway permanent count point 360 points 30 orders by existing DDHV estimation value method(separation plan) analysis wave and following variation appear. - design order and actuality order are collision at 357 agencies(99.2%) - actuality order special quality : Measuring efficiency of average 80 orders, maximum 1,027 order, minimum 2 orders - error distribution of design order and actuality order : inside 10 hours is(30$\pm$10hour) 106 points(29.4%), 254 points(70.6%) more than 30 orders and $\pm$10 orders error occurrence be - DDHV estimation value : Average 8.4%, maximum 46.7% The other side, average 50 orders. error improvement effect of DDHV 8.4% was analysed that is at design hourly volume computation by inseparability method in case of AADT premises correct thing because inseparability plan agrees actuality order at whole agency with design order and measuring efficiency of DDHV estimation value is "0".t;0".uot;.

• Tribology and Lubricants
• /
• v.38 no.4
• /
• pp.152-161
• /
• 2022

Chemical mechanical planarization (CMP) is a technology that planarizes the surfaces of semiconductor devices using chemical reaction and mechanical material removal, and it is an essential process in manufacturing highly integrated semiconductors. In the CMP process, a conditioning process using a diamond conditioner is applied to remove by-products generated during processing and ensure the surface roughness of the CMP pad. In previous studies, prediction of pad wear by CMP conditioning has depended on numerical analysis studies based on mathematical simulation. In this study, using an artificial neural network, the ratio of conditioner coverage to the distance between centers in the conditioning system is input, and the average conditioning density, standard deviation, nonuniformity (NU), and conditioning density distribution are trained as targets. The result of training seems to predict the target data well, although the average conditioning density, standard deviation, and NU in the contact area of wafer and pad and all areas of the pad have some errors. In addition, in the case of NU, the prediction calculated from the training results of the average conditioning density and standard deviation can reduce the error of training compared with the results predicted through training. The results of training on the conditioning density profile generally follow the target data well, confirming that the shape of the conditioning density profile can be predicted.

• KDI Journal of Economic Policy
• /
• v.14 no.1
• /
• pp.121-145
• /
• 1992

This paper examines characteristics of time series data related to the construction investment(stationarity and time series components such as secular trend, cyclical fluctuation, seasonal variation, and random change) and surveys predictibility, fitness, and explicability of independent variables of various models to build a short-term construction investment forecasting model suitable for current economic circumstances. Unit root test, autocorrelation coefficient and spectral density function analysis show that related time series data do not have unit roots, fluctuate cyclically, and are largely explicated by lagged variables. Moreover it is very important for the short-term construction investment forecasting to grasp time lag relation between construction investment series and leading indicators such as building construction permits and value of construction orders received. In chapter 3, we explicate 7 forecasting models; Univariate time series model (ARIMA and multiplicative linear trend model), multivariate time series model using leading indicators (1st order autoregressive model, vector autoregressive model and error correction model) and multivariate time series model using National Accounts data (simple reduced form model disconnected from simultaneous macroeconomic model and VAR model). These models are examined by 4 statistical tools that are average absolute error, root mean square error, adjusted coefficient of determination, and Durbin-Watson statistic. This analysis proves two facts. First, multivariate models are more suitable than univariate models in the point that forecasting error of multivariate models tend to decrease in contrast to the case of latter. Second, VAR model is superior than any other multivariate models; average absolute prediction error and root mean square error of VAR model are quitely low and adjusted coefficient of determination is higher. This conclusion is reasonable when we consider current construction investment has sustained overheating growth more than secular trend.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.537-550
• /
• 2000

In this study, Neural Networks models were used to forecast daily streamflow at Jindong station of the Nakdong River basin. Neural Networks models consist of CASE 1(5-5-1) and CASE 2(5-5-5-1). The criteria which separates two models is the number of hidden layers. Each model has Fletcher-Reeves Conjugate Gradient BackPropagation(FR-CGBP) and Scaled Conjugate Gradient BackPropagation(SCGBP) algorithms, which are better than original BackPropagation(BP) in convergence of global error and training tolerance. The data which are available for model training and validation were composed of wet, average, dry, wet+average, wet+dry, average+dry and wet+average+dry year respectively. During model training, the optimal connection weights and biases were determined using each data set and the daily streamflow was calculated at the same time. Except for wet+dry year, the results of training were good conditions by statistical analysis of forecast errors. And, model validation was carried out using the connection weights and biases which were calculated from model training. The results of validation were satisfactory like those of training. Daily streamflow forecasting using Neural Networks models were compared with those forecasted by Multiple Regression Analysis Mode(MRAM). Neural Networks models were displayed slightly better results than MRAM in this study. Thus, Neural Networks models have much advantage to provide a more sysmatic approach, reduce model parameters, and shorten the time spent in the model development.

• The Journal of Korean Society for Radiation Therapy
• /
• v.15 no.1
• /
• pp.35-40
• /
• 2003

I. Purpose Confirming an error to be able to break out in a method to move couch manually while operator sees the skin marks on patient in case of curing head who got 2 targets adjoined, so we analyze coordinates price of couch, evaluate reproducibility and precision of change movements between targets. II. Materials and Methods In radiotherapy, for confirming errors in manual movements by operators by exchanging between two targets to treat patient head, we read coordinates price(vertical, longitudinal, lateral three directions of couch) shown on a monitor of LINAC( CL 2100, Varian, USA) in order to evaluate accuracy about the length that moved in time for moving couch manually. After reading movement length of coordinates recorded in three directions of all treatment, we compared distance between targets recorded in RTP(Pinnacle, ADAC, USA) with reading coordinates price of couch, setting actually done the same patient for ten times, coordinates were recorded, treated for evaluating averages and degrees of errors and standard deviations. III. Results In method to confirm skin marks of patient by operators' view and to move couch manually, average standard deviations of movements between two targets are vertical 1.4mm, longitudinal 0.9mm, lateral 2.2mm in each direction. As for the error in straight dimension, it is about 3.6mm averages and 5.1mm maximum. The average of errors in each directions was vertical 1mm, longitudinal 0.7mm, lateral 2.7mm. The greatest error broke out in lateral direction with $25\%$ of all cases ; to exceed an error average. IV. Conclusions If operators moved manually couch for changing target points, errors about 3.6mm average degrees occur. It is important that operators confirm the errors prices of actual couch coordinates for asking a correct movement between the targets adjoined each other ; in case of treatment demanding high precision like 3D conformal therapy or IMRT. Therefore, if we apply couch coordinates confirmation to reproducibility and to precision evaluation of treatment, it's expected that we can execute high-quality radiotherapy.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.2
• /
• pp.191-198
• /
• 2015

In this study, the flow characteristics at the ventilation holes was analyzed by using numerical method when carbon composite brake disk was rotated at a constant speed. In order to ensure the validity of the analysis results, grid dependency test was performed by considering the accuracy and appropriateness, and 4mm mesh size was selected for decrease of the maximum error rate 63.6%. As a result, the outside air flows in the clearance between the disk and shaft in case of B model. whereas, the outside air flows in the clearance or the outlet of the ventilation holes in case of A and C models. And also average static pressure at the outlet was changed depending on shape of the ventilation holes and rotational speed of the disk in case of A and C models. Besides, in the B model, intake air according to the clearance goes with side surface of ventilation hole, and so increased by mean velocity of 4.64m/s and mean pressure of 0.58pa in the ventilation hole outlet, in case of disk rotational speed of 146.21rad/s.