Smart Home System Using Multisensor Based Fire Detection

Abstract

Currently, the smart home system is used to control a device remotely, this tool is useful as a security tool as well as a management tool for energy sources and the use of electricity. A current smart home system must have several criteria of use, namely that it is easy to use and can run on any platform, this combination is sometimes not provided by the iot device maker so there are only control features without any additional security features, therefore this research will be made. an IoT device that is integrated with a sensor security sensor where the sensor can be a motion sensor, a smoke sensor, and a fire sensor, why is this tool important considering the number of fires is a common problem in households or offices so a quick response is needed so that the fire does not it happens again. Fire is a problem that can occur anywhere, be it in office buildings, housing estates or in public facilities. Delay in handling results in losses, it can be mental or material losses. The occupants of the building must get information or early warning when a fire occurs in order to evacuate immediately. The fire alarm system that is commonly used is a conventional fire system, but due to several causes and certain factors, often the fire alarm does not work properly and instead sends a false alarm. In this study, there are 3 sensors, namely the MQ-2 sensor, the TMP102 sensor, and the flame sensor which are connected to the Arduino Uno microcontroller. The Arduino Uno microcontroller is implanted with the decision tree method as the output decision maker. There are 3 processes, namely the process of determining the dataset, forming a decision tree and forming rules. This system has 3 attributes that are used to detect the state of the condition, namely temperature, light intensity and smoke content.