Absolute Percentage Error (absolute + percentage_error)

Distribution by Scientific Domains
Engineering80%

Kinds of Absolute Percentage Error

  • mean absolute percentage error
    		•

    Selected Abstracts

    From Model to Forecasting: A Multicenter Study in Emergency Departments

    ACADEMIC EMERGENCY MEDICINE, Issue 9 2010
    Mathias Wargon MD
    ACADEMIC EMERGENCY MEDICINE 2010; 17:970,978 © 2010 by the Society for Academic Emergency Medicine Abstract Objectives:, This study investigated whether mathematical models using calendar variables could identify the determinants of emergency department (ED) census over time in geographically close EDs and assessed the performance of long-term forecasts. Methods:, Daily visits in four EDs at academic hospitals in the Paris area were collected from 2004 to 2007. First, a general linear model (GLM) based on calendar variables was used to assess two consecutive periods of 2 years each to create and test the mathematical models. Second, 2007 ED attendance was forecasted, based on a training set of data from 2004 to 2006. These analyses were performed on data sets from each individual ED and in a virtual mega ED, grouping all of the visits. Models and forecast accuracy were evaluated by mean absolute percentage error (MAPE). Results:, The authors recorded 299,743 and 322,510 ED visits for the two periods, 2004,2005 and 2006,2007, respectively. The models accounted for up to 50% of the variations with a MAPE less than 10%. Visit patterns according to weekdays and holidays were different from one hospital to another, without seasonality. Influential factors changed over time within one ED, reducing the accuracy of forecasts. Forecasts led to a MAPE of 5.3% for the four EDs together and from 8.1% to 17.0% for each hospital. Conclusions:, Unexpectedly, in geographically close EDs over short periods of time, calendar determinants of attendance were different. In our setting, models and forecasts are more valuable to predict the combined ED attendance of several hospitals. In similar settings where resources are shared between facilities, these mathematical models could be a valuable tool to anticipate staff needs and site allocation. [source]

    Short-Term Traffic Volume Forecasting Using Kalman Filter with Discrete Wavelet Decomposition

    COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, Issue 5 2007
    Yuanchang Xie
    Short-term traffic volume data are often corrupted by local noises, which may significantly affect the prediction accuracy of short-term traffic volumes. Discrete wavelet decomposition analysis is used to divide the original data into several approximate and detailed data such that the Kalman filter model can then be applied to the denoised data and the prediction accuracy can be improved. Two types of wavelet Kalman filter models based on Daubechies 4 and Haar mother wavelets are investigated. Traffic volume data collected from four different locations are used for comparison in this study. The test results show that both proposed wavelet Kalman filter models outperform the direct Kalman filter model in terms of mean absolute percentage error and root mean square error. [source]

    A new recursive neural network algorithm to forecast electricity price for PJM day-ahead market

    INTERNATIONAL JOURNAL OF ENERGY RESEARCH, Issue 6 2010
    Paras Mandal
    Abstract This paper evaluates the usefulness of publicly available electricity market information in predicting the hourly prices in the PJM day-ahead electricity market using recursive neural network (RNN) technique, which is based on similar days (SD) approach. RNN is a multi-step approach based on one output node, which uses the previous prediction as input for the subsequent forecasts. Comparison of forecasting performance of the proposed RNN model is done with respect to SD method and other literatures. To evaluate the accuracy of the proposed RNN approach in forecasting short-term electricity prices, different criteria are used. Mean absolute percentage error, mean absolute error and forecast mean square error (FMSE) of reasonably small values were obtained for the PJM data, which has correlation coefficient of determination (R2) of 0.7758 between load and electricity price. Error variance, one of the important performance criteria, is also calculated in order to measure robustness of the proposed RNN model. The numerical results obtained through the simulation to forecast next 24 and 72,h electricity prices show that the forecasts generated by the proposed RNN model are significantly accurate and efficient, which confirm that the proposed algorithm performs well for short-term price forecasting. Copyright © 2009 John Wiley & Sons, Ltd. [source]

    Sensitivity analysis of neural network parameters to improve the performance of electricity price forecasting

    INTERNATIONAL JOURNAL OF ENERGY RESEARCH, Issue 1 2009
    Paras Mandal
    Abstract This paper presents a sensitivity analysis of neural network (NN) parameters to improve the performance of electricity price forecasting. The presented work is an extended version of previous works done by authors to integrate NN and similar days (SD) method for predicting electricity prices. Focus here is on sensitivity analysis of NN parameters while keeping the parameters same for SD to forecast day-ahead electricity prices in the PJM market. Sensitivity analysis of NN parameters include back-propagation learning set (BP-set), learning rate (,), momentum (,) and NN learning days (dNN). The SD parameters, i.e. time framework of SD (d=45 days) and number of selected similar price days (N=5) are kept constant for all the simulated cases. Forecasting performance is carried out by choosing two different days from each season of the year 2006 and for which, the NN parameters for the base case are considered as BP-set=500, ,=0.8, ,=0.1 and dNN=45 days. Sensitivity analysis has been carried out by changing the value of BP-set (500, 1000, 1500); , (0.6, 0.8, 1.0, 1.2), , (0.1, 0.2, 0.3) and dNN (15, 30, 45 and 60 days). The most favorable value of BP-set is first found out from the sensitivity analysis followed by that of , and ,, and based on which the best value of dNN is determined. Sensitivity analysis results demonstrate that the best value of mean absolute percentage error (MAPE) is obtained when BP-set=500, ,=0.8, ,=0.1 and dNN=60 days for winter season. For spring, summer and autumn, these values are 500, 0.6, 0.1 and 45 days, respectively. MAPE, forecast mean square error and mean absolute error of reasonably small value are obtained for the PJM data, which has correlation coefficient of determination (R2) of 0.7758 between load and electricity price. Numerical results show that forecasts generated by developed NN model based on the most favorable case are accurate and efficient. Copyright © 2008 John Wiley & Sons, Ltd. [source]

    NUTRIENT LOADING ASSESSMENT IN THE ILLINOIS RIVER USING A SYNTHETIC APPROACH,

    JOURNAL OF THE AMERICAN WATER RESOURCES ASSOCIATION, Issue 4 2003
    Baxter E. Vieux
    ABSTRACT: A synthetic relationship is developed between nutrient concentrations and discharge rates at two river gauging sites in the Illinois River Basin. Analysis is performed on data collected by the U.S. Geological Survey (USGS) on nutrients in 1990 through 1997 and 1999 and on discharge rates in 1988 through 1997 and 1999. The Illinois River Basin is in western Arkansas and northeastern Oklahoma and is designated as an Oklahoma Scenic River. Consistently high nutrient concentrations in the river and receiving water bodies conflict with recreational water use, leading to intense stakeholder debate on how best to manage water quality. Results show that the majority of annual phosphorus (P) loading is transported by direct runoff, with high concentrations transported by high discharge rates and low concentrations by low discharge rates. A synthetic relationship is derived and used to generate daily phosphorus concentrations, laying the foundation for analysis of annual loading and evaluation of alternative management practices. Total nitrogen (N) concentration does not have as clear a relationship with discharge. Using a simple regression relationship, annual P loadings are estimated as having a root mean squared error (RMSE) of 39.8 t/yr and 31.9 t/yr and mean absolute percentage errors of 19 percent and 28 percent at Watts and Tahlequah, respectively. P is the limiting nutrient over the full range of discharges. Given that the majority of P is derived from Arkansas, management practices that control P would have the most benefit if applied on the Arkansas side of the border. [source]