IOT Based – Smart Helmet for Air Quality and Hazardous Event Detection for the Mining Industry

IOT Based - Smart Helmet for Air Quality and Hazardous Event Detection for the Mining Industry

C Prema, Assistant Professor,

Department of Electronics and Communication Engineering,

Sri Shakthi Institute of Engineering and Technology, L&T Bypass, Coimbatore, premacece@siet.ac.in

Paveen Karthik S, Raja Pandi R, Rajnitheesh A P, Yokesh S M Department of Electronics and Communication Engineering,

Sri Shakthi Institute of Engineering and Technology, L&T Bypass, Coimbatore

-

Abstract - The security of the underground mines must be increase because disasters in underground mines are very serious issues now days. The difficulties faced by miners working underground are gas explosion, temperature, etc. If any disaster occurs in mine and if miner gets injured, all the blame directly goes on supervisor. So there must be communication between miners, supervisor and control station. Therefore the purpose of the proposed system is to modify an existing mining safety. Helmet is one of the safety accessories miner should wear while mining. The aim is to make the helmet even safer by adding network. This added network is used to sense the environmental conditions around the miner working underground and all the real time values are wirelessly updated on the internet by using IoT so the control station get to know about the environmental conditions in which miner working and if any abnormal condition occur they are able to provide the rescue as early as possible. The system also includes the LCD and buzzer to let co-workers know if any unwanted event occurs with miner. The proposed system uses different sensors like Gas Sensor, dht11 Sensor, accelerometer, vibration and IR Sensor. Here the IR sensor is used as helmet removing sensor. And also in this system we use machine learning to analysis the employee health, Heart Disease is one among the major diseases affecting the individual around the world. There are several risk factors which leads to heart disease. The combination of logistic regression analysis and neural network provides a novel approach in predicting the heart disease. Initially logistic regression is applied to select the major risk factors for predicting the disease. It produces the significant risk factors that are useful in predicting the heart disease based on statistical p-value. The risk factors which are not having the significant impact are identified and removed. The resultant significant factors are provided as input to the neural network.

Keywords: Underground Mines, Mining Safety, IoT (Internet of Things), Helmet Safety, Gas Explosion, Environmental Monitoring, Real-time Monitoring, Communication System, Machine Learning, Logistic Regression, Neural Network, Heart Disease Prediction, Risk Factor Analysis, Gas Sensor, DHT11 Sensor,

Accelerometer, Vibration Sensor, IR Sensor, Helmet Removal Detection, Rescue Operation, Control Station, Buzzer Alert, LCD Display, Safety Equipment.