Cigarette Smoke Detection System for Non-Smoking Areas Based on IoT and Face Recognition

Abstract

Indonesia is one of country with the highest number of smokers in Association of Southeast Asian Nations (ASEAN), 65.19 million people. This figure is equivalent to 34 % of the total population of Indonesia in 2016. There is a campaign to stop smoking in public places or Non-Smoking Areas because smoke can harm people. But some people violate and still smoke in Nonsmoking areas such as in Campus, School, or hospital. The Indonesian government has arranged forbidden places to smoke according to the Law of the Republic of Indonesia No.36 of 2009. Therefore a monitoring system is needed to detect offenders who smoke in no-smoking areas. Cigarette smoke detection system has made based on internet of face recognition and artificial intelligence technologies. This smoke detection system has designed using a raspberry pi B+, a gas sensor (MQ-2), GPS and camera, and data communication. We need an internet connection via WiFi or Ethernet to transfer data to the database server. When the Sensor releases the cigarette immediately, the system will send a notification to the administrator. The system also sends location and photos of smokers. The system will process and identify the smoker's identity. This system is expected to be implemented to support the smart city or smart campus.