China
Africa
Explore chapters and articles related to this topic
Data Modeling for Systems Integration
Published in Adedeji B. Badiru, Systems Engineering Using the DEJI Systems Model®, 2023
The MAPE is based on the assumption that the severity of error is linearly related to its size. The MAPE is the sum of the absolute values of the errors divided by the corresponding observed values divided by the number of forecasts. The MAPE is often expressed as a percentage. This is to provide meaningful interpretation about each data point. The MAPE is defined as: MAPE=∑et/Xtn×100
Comparative Forecasts of Confirmed COVID-19 Cases in Botswana Using Box-Jenkin's ARIMA and Exponential Smoothing State-Space Models
Published in Amit Kumar Tyagi, Ajith Abraham, Recurrent Neural Networks, 2023
Ofaletse Mphale, V. Lakshmi Narasimhan
In another study (Atchadé, 2021), a comparison of different COVID-19 forecast models was conducted using the cross-validation technique. In this study MAPE was used to compute forecast accuracy for each model. The findings showed that an ETS model with additive error-trend and no season was the best-fit model. Furthermore, it was determined that to obtain MAPE threshold of 5 percent, the study required at least 100 days of forecasts. A simple time series model was proposed and used to forecast short-time behavior of COVID-19 cases using the global confirmed cases and deaths [34]. The findings indicated that the proposed model produced competitive forecasts and relevant estimates of uncertainties over a 10-day period for 4 months.
Short-term wind speed forecasting of downburst based on improved VARX model
Published in Hiroshi Yokota, Dan M. Frangopol, Bridge Maintenance, Safety, Management, Life-Cycle Sustainability and Innovations, 2021
Two error indexes are used to measure the accuracy of all the adopted decomposition methods, including the Mean Absolute Error (MAE) and the Mean Absolute Percentage Error (MAPE). The index of MAE are utilized to quantify the accuracy of forecasting, and the smaller they are, the better the prediction is. The MAPE is an important index to measure the error of the forecasting and it reflects the relationship between the error and the actual value In this study, The lower the percentage is, the better the performance is. The equations of the four indexes are given as: MAE=1N∑i=1NYi−YˆiMAPE=1N∑t=1NYˆi−YiYˆi×100%
A comparison between ARIMA, LSTM, ARIMA-LSTM and SSA for cross-border rail freight traffic forecasting: the case of Alpine-Western Balkan Rail Freight Corridor
Published in Transportation Planning and Technology, 2023
Miloš Milenković, Miloš Gligorić, Nebojša Bojović, Zoran Gligorić
To test the forecasting performance, we applied the mean absolute error (MAE), the mean average percent error (MAPE), and the root mean squared error (RMSE) defined as follows: where and represent the actual and predicted values of the time series in period , respectively. MAE represents the mean of absolute errors. MAPE is one of the most commonly used criteria to measure forecast accuracy. It represents the sum of the individual absolute errors divided by the actual observation. RMSE represents a square root of the average squared error.
Optimization design in perforated AL-CFRP hybrid tubes under axial quasi-static loading
Published in International Journal of Crashworthiness, 2022
Qi-hua Ma, Kai Wang, Xue-hui Gan, Yong-xiang Tian
The coefficient of determination (R2) [23] and mean absolute percentage error (MAPE) [24] are statistical parameters commonly used to verify fitting surfaces. They are defined by Equation (4) and Equation (7), respectively. And the sum of squares for error (SSE) and the sum of squares for total (SST) are defined by Equations (6) and (7), respectively. The value of R2 is between 0 and 1. The higher the value is, the higher the consistency between the fitting function and the research problem is. Besides, MAPE is used to measure the relative errors between the average test value and the real value on the test set, the smaller the value of MAPE is, the better the prediction model is. where s represent the number of sample points.
Identifying the precursors of vulnerability in agricultural value chains: A system dynamics approach
Published in International Journal of Production Research, 2021
Joshua Aboah, Mark M.J. Wilson, Kathryn Bicknell, Karl M. Rich
The model behaviour was statistically validated using the Mean Absolute Percentage Error (MAPE) and Theil U (Sterman et al. 2013), transient measures and comparative statistics (Sücüllü and Yücel 2014). The statistical measures were analysed in R studio®. MAPE and Theil U are estimated as Equations 7 and 8 respectively. Where At and Ft represent the actual cocoa production figures and model estimation respectively. MAPE indicates the percentage error in the model prediction. The Theil U statistic has a lower bound of 0, which corresponds to a perfect forecast. A value of 1, by contrast, is consistent with a naïve (no change) extrapolation (Bliemel 1973). Model validation results indicate a reliable percentage of the baseline model’s prediction accuracy as indicated by the MAPE, Theil U and level of error between the transient measures. The model validation results indicate that the model has a 17% error in its prediction accuracy and a Theil U of less than 0.3, which is a considerable improvement over a naïve no change forecast (Table 3).