9. Conclusions
Based on the study, it is establish that the feed-forward back-propagation neural network approach seems to be the better option for close and appropriate prediction of PPV to protect surrounding environment and structure. The use of any predictor without validation may invite further complication for smooth conduct of mining operations. This study indicates that all predictors used in the paper are either over estimating or under estimating the safe explosive charge to keep the PPV under the safe limit. Both the predictions are not appropriate for the site where populations are residing very near to mine. If more number of data sets are used in ANN, the prediction will be more accurate, because it does not follow the over fitting and under fitting law of curves as in the case of vibration predictors.