Application of Data Mining based on Classifier in Class Label Prediction of Coal Mining Data

For issue that coal mining data tends to be incomplete, noisy and inconsistent, some popular classifiers are applied to predict class label of coal mining dataset. Noise and bad points are rejected from coal mining data which will be exchanged to input format suitable for mining. Then different classifiers are used to classify class label after extracting features. In the end, classification results are analyzed and knowledge assimilation is done. Experiment results show that decision tree model gives 88% of accuracy to correctly predict class label whereas neural network model predicts 85% correct class label. This research provides a powerful class label prediction tool as well as increasing knowledge of data classification models.