| dc.description.abstract | For many years, smoke detectors have been used as the most crucial _re detection sensors.Although smoke detectors do their job very well, they are not perfect and may causefalse or late alarms. This is because they only rely on one of the _re signs which is smoke.Fire has many other signs as well such as heat and light. It also a_ects its environmentalparameters such as temperature and humidity. But typically, buildings are not equippedwith sensors capable of sensing these changes. Recently, a few smartphone manufacturershave added temperature, humidity, and barometer sensors to their products which can beused for more reliable _re detection. In this thesis, a framework composed of one or moresmartphones and a back-end server is proposed which can detect and visualize indoor_re. For this purpose, the smartphones continuously collect, preprocess, and analyzedata from their sensors to detect if _re exists in their surroundings. The back-endserver facilitates the analysis processes in smartphones and provides crisis managementinstitutions such as police, _re department, and ambulance with real-time monitoringuser interface so that they can easily grasp useful information about the _re's locationand scale. The proposed _re detection framework is a learning system which needs tobe trained by real data. Therefore, a wide range of experiments is precisely designedand performed to make sure that the system can immediately and accurately detect _rein diverse environmental conditions.Keywords: Naive Bayes Classi_er, Smartphone, Sensor, Fire Detection. | nb_NO |
