LAUSR

Fire was discovered by humankind many years ago. Until today, it is still important to human in their daily livings. Fire is useful when it is under control. However, it may lead to destruction if it is uncontrolled. Fires can be classified into two groups – flaming fire and smoldering fire. Flaming fire produces a large volume of flames but smaller volume of smoke. Usually, flaming fire is due to the ignition of materials such as flammable materials or liquids. A smoldering fire is a type of fire that is slow in spreading, low in temperature, and flameless. It is a condition in which the material is being burned slowly with smoke but without flame. The smoke produced by such fire may contain toxic chemicals such as cyanide and carbon monoxide. Fig. 1 shows the total number of building fires from 2012-2016 in Malaysia [1]. It can be observed that the number of reported fire cases over the five years remains high at the average of five thousand cases. The types of buildings can be further broken down into a few categories, such as residential, retail, factory, institution, office, public place, and others. Among these categories, residential premises contributed to the highest building fire incident each year. Referring to the National Fire Protection Association (NFPA) [2], most fire casualties are due to the inhalation of smoke rather than burns. Even before the victims can reach the exit of the building, they were already intoxicated by the smoke itself. One of the reasons is that most of the oxygen was consumed by the fire itself during burning, which Abstract: Fire can be made useful for various purposes. However, uncontrollable fire may result in property damage and human death. The major factor of fire deaths is due to excessive smoke inhalation. Therefore, early detection of fire is crucial in fire detection systems. The conventional fire detection system does not come with a false alarm prevention system. Besides, the system is unable to tell the exact location of the fire. In this project, an Internet of Things (IoT) based fire safety system is developed to overcome these problems. The proposed system consists of three major parts which are the detector, processing unit and surveillance. The detector unit is an integration of ESP32, carbon monoxide sensor, ionization smoke detector, buzzer, temperature and humidity sensor. As the processing unit, Raspberry Pi is used to run the Node-RED application, which processes the data and performs monitoring. The communication between the detector and processing unit is based on the Message Queuing Telemetry Transport (MQTT) protocol. A surveillance unit is where a camera is installed to monitor the condition of the surrounding. The response of the system is based upon the sensor’s values or the user’s response. Once the fire breakout is confirmed, the system will immediately sound the alarm, and Global Positioning System (GPS) coordinates and floor plan of the accommodation will send to the nearby fire station. The floor plan is developed to track the exact location of the fire. Experiments are carried out on the proposed fire safety system, and encouraging results are produced.