Hardware Module Design and Software Implementation of Multisensor Fire Detection and Notification System Using Fuzzy Logic and Convolutional Neural Networks (CNNs)

Table 5

Field test results.

Test	Expected result	Remarks
Power on fire detection unit	The fire detection unit boots automatically sets its date and time, tells the web service that it is online, and starts running the fuzzy logic detection algorithm	It was successful most of the time; Occasionally it failed to automatically update the date and time; a fix for that is soon to be tested
Leave the fire detection unit running under normal environmental conditions for three days	The fire detection unit keeps running the main detection program and keeps logs of readings from sensors	The system kept running; one of the units, however, overheated; this was attributed to the lack of a proper cooling system on the microprocessor board
Expose the fire detection unit to fire	The readings from the various sensors vary with the intensity of the flames, temperature, and smoke; the fuzzy logic algorithm classifies the inputs as a definite fire and sends an alert	For all the tests conducted, the system was able to detect the fire; beyond a 1-meter radius; however, the detected fire level had to be significant before the system could detect it
Expose the fire detection unit to very high levels of only one or two fire signatures	The fuzzy logic algorithm classifies the input as a potential fire	Successful
Send alert to web service on the detection of fire	The fire detection unit makes a request to the web service to alert all concerned users and the fire service about the detected fire	Successful
Send alert via SMS on detection of fire and absence of Internet connection	The fire detection unit sends the fire detection alert via SMS to all the concerned users and the fire service	Successful

Video output for classification tasks.