Learning Predictive Models for Underground Coal Mine Environment Using Sensor Data

Reported casualties of mine workers is a routine affair, where a huge number of mine workers expire from mining incidents each year in underground coal mines due to harmful gases and suffocation. In this paper, a machine learning-based prediction system is designed to predict the possible hazed behaviour of the sensors to possibly prevent mine explosion or any other accident. An Arduino-based solution is placed in the mines where different sensors are mounted that can perceive the environmental factors, such as temperature and concentration, of different harmful gases. The data acquired from the sensor node is transmitted to the SD card module. The Alarm initiates a caution after sensing gas pressure above the critical state to save mine workers from any hazard. The sensor historical data is reorganized in a sliding window, and machine learning models are used to predict the next readings of each sensor.