IoT-Based Harmful Toxic Gases Monitoring and Fault Detection on the Sensor Dataset Using Deep Learning Techniques

One of the main reasons for accidents among workers is harmful gas leakage. Many people die in chemical industries and their surrounding areas. The present invention responsible monitoring controlling hazardous toxic gases like nitrogen dioxide (NO2), carbon monoxide, ozone (O3), sulfur (SO2), LPG, hydrocarbon gases, silicones, hydrocarbons, alcohol, CH4, hexane, benzine, as well environmental conditions, such temperature relative humidity to prevent industrial accidents. Arduino UNO R3 board used central microcontroller. It connected Cloud via AQ3 sensor, Minipid 2 HS PID IR5500 open path infrared detector, DHT11 Temperature Humidity Sensor, MQ3 ESP8266 WIFI Module, which can store real-time sensor data send alert messages industry’s safety control board. Machine learning artificial intelligence will be make an intelligent prediction (AI). information gathered examined real-time. provided through accessed worldwide. Sensor quality critical Internet Things (IoT) applications because poor renders them useless. Error detection improves IoT-based monitoring, controlling, system. Live from sensors or datasets should analyzed properly using appropriate techniques. Hence, hybrid hidden Markov models are applied error technique dataset. This outperformed dataset array under dynamic mixtures lived data. Our method compared other existing technologies. HMM ANN fault methods performed on produced 0.01% false positive rate.