A hybrid NRS- CART algorithm and its application on coal mine floor water-inrush prediction

Abstract

With the increase of water-inrush accidents from coal mine, water-inrush prediction has become a significant aim for coal mine safety experts. As an intelligent classifying algorithm, the Classification and Regression Tree (CART) is a potential method for predicting the possibility of water inrush from coal seam floor. One of its main advantages is that the Decision Rules (DRs) can be extracted from its structure.Another is that these DRs can be used to analysis safety problems.However, the time of establishing the decision tree is too long because of the existence of the redundant information. This paper presents an effective method named NRS-CART, which is a hybrid method by combining neighborhood rough set (NRS) and classification and regression tree (CART). Moreover, the novel approach was used to detect and classify water-inrush possibilities. The experimental results showed that it only took 0.3455 seconds to predict the water-inrush possibility using the proposed method, whereas the CART spent 1.0411 seconds to predict for the same dataset, and at the same time the prediction accuracy was also improved from 88.78% to 93.90%.

Embedded Data Imputation for Environmental Intelligent Sensing: A Case Study

“…For instance, in [ 17 ], the authors exploit artificial neural network models to impute data (in particular, anomalies) through time series data. Decision trees (DT) and CART algorithms are applied in [ 18 , 19 ], respectively, to solve the missing data issues. Other examples include support vector machines (SVM) and self organizing maps (SOM), which are exploited in [ 20 , 21 ], respectively.…”