Fig. 23
From: The design of an indirect method for the human presence monitoring in the intelligent building
The reference [measured course of CO2 concentration (from February 1 to February 28, 2015)] and predicted filtered course of CO2 concentration using the LMS algorithm [the ANN with the BRM learned on the data (from June 1 to June 28, 2015)] and predicted within the cross-validation with the data from February 1 to February 28, 2015, using the ANN with the BRM (the number of neurons—400) (Table 3). 1.Arrival (5.2.2015 12:50:00), 2.departure (5.2.2015 14:40:00), TPP Δt1 = 1:50:00; 3.arrival (11.2.2015 8:20:00), 4.departure (11.2.2015 10:10:00), TPP Δt2 = 1:50:00; 5.arrival (17.2.2015 6:40:00), 6.departure (17.2.2015 10:50:00), TPP Δt3= 4:10:00; 7.arrival (19.2.2015 8:50:00), 8.departure (19.2.2015 9:20:00), TPP Δt4 = 0:30:00; 9.arrival (20.2.2015 8:00:00), 10.departure (20.2.2015 9:10:00), TPP Δt5 = 1:10:00; 11.arrival (24.2.2015 12:40:00), 12.departure (24.2.2015 15:00:00), TPP Δt6 = 2:20:00.