Occupancy Detection Through Light, Temperature, Humidity and Co2 Sensors U sing Ann
Previous studies showed that knowing occupancy certainly can save energy in the control system of building. In
this regard, occupancy detection has a significant role in many smart building applications such as heating, cooling,
ventilation (HVAC) and lighting system. In this paper, various Artificial Neural Network algorithms were applied to the
dataset composed by samples obtained from light, temperature, humidity and CO2 sensors. When the results were compared,
it was seen that Limited Memory Quasi-Newton algorithm has the highest accuracy rate with 99.061%. The lowest accuracy
rate was obtained from Batch Back algorithm with 80.324%.
Keywords- Occupancy Detection, Classification, Artificial Neural Network