Basing on the studies above, the EMR forecasting criteria for rockburst danger degree was profoundly researched (Dou et al. 2002, 2004; Chen et al. 2008).
Secondly, the method chose some sample objects and adopted the decision tree algorithm C5.0 to mine the landslide forecast criteria according to the factor values of each sample object.
Out-of-sample forecast criteria select EGARCH innovations for sessions 1 and 2, while simpler models with no EGARCH innovations and no jump distinction are preferred for sessions 5 and 6.
Forecast acceptability criterion.
70% confidence interval is taken and statistical results of forecasting error criteria are shown in Table 3.
Table 3 Forecasting error criteria statistics of different SSCBs SSCBs Ramp start time Ramp duration Ramp end time Ramp swing Ramp rate NMAE RMSE (min) NMAE RMSE (min) NMAE RMSE (min) MAE RMSE (p.u).
An alternative near-optimum linear detection criterion forecasts the minimization of the conditional probability of error [14, 15].
Open image in new window Fig. 6 Modelling and forecasting results using clustering criterion 2. We can see that after relaxing the clustering criterion, the number of the subsequences has further reduced to 21 (M = 21), and each of them is smoother.
In the qualitative phase of the model identification, EDFM identifies the variables relevant to the process; i.e. the subset of variables, within a given window width, that provides the best forecasting, following the parsimony criterion.
In order to evaluate the robustness of the statistical scenarios forecasting model, two evaluation criteria are defined to characterize the error relationship between forecasted and actual values of ramp event characteristics.
