A Novel Algorithm for Outlier Detection in High Dimension and its Application in Mine Disaster Forewarning

The aim of outlier detection was to find out abnormal data patterns concealed in abundant data sets which were sparse and isolate. Mine disaster occurred much more frequently in our country, so it was urgent to take out an effective method to prevent mine disaster and guarantee miner´s life and property of the company. In this paper, we presented a new method-AHHDOD, it could not only find out the abnormal data patterns, but also can give the attribution of them. At the end, this method was put into use in the mine disaster forewarning system. The results proved that this method was credible and acceptable.