Early Warning System for Seismic Events in Coal Mines Using Machine Learning
arXiv:1609.06957v1
Originality Synthesis-oriented
AI Analysis
This addresses safety risks for coal mine workers, but it is incremental as it uses ensembles of existing models on a specific dataset.
The paper tackled predicting dangerous seismic events in coal mines up to 8 hours in advance, achieving a winning score of 0.939 AUC in a data mining challenge.
This document describes an approach to the problem of predicting dangerous seismic events in active coal mines up to 8 hours in advance. It was developed as a part of the AAIA'16 Data Mining Challenge: Predicting Dangerous Seismic Events in Active Coal Mines. The solutions presented consist of ensembles of various predictive models trained on different sets of features. The best one achieved a winning score of 0.939 AUC.