OCCUPANCY ESTIMATION METHOD BASED ON CARBON DIOXIDE CONCENTRATION USING DYNAMIC NEURAL NETWORK

摘要

The present invention relates to a method for estimating the number of persons in a room based on carbon dioxide concentration using a dynamic neural network. The method comprises: a measurement step for measuring the concentration of carbon dioxide contained in the indoor air; a storage step for storing the concentration of carbon dioxide measured in the measurement step in real time; a neural network configuration step for configuring at least one dynamic neural network part in order to estimate the number of residual persons positioned in a room using the concentration of carbon dioxide stored in the storage step; a neural network learning step for comparing the number of residual persons estimated from the dynamic neural network part configured in the neural network configuration step with a reference value previously input for the number of residual persons, comparing an error between the number of residual persons and the reference value with a predetermined threshold, and adjusting a weighted value and a deflection value of a transfer function which configures the dynamic neural network part in a direction along which the error of the reference value decreases; and an estimation step for estimating the number of residual persons through the dynamic neural network part adjusted in the neural network learning step, and proposes a technique of efficiently grasping persons in a room of a building. Thus, installation and maintenance costs can be cheaper than those of a conventional method for checking the number of persons in a room using video cameras or motion recognition sensors, and reliability can be improved by removing a dead zone. [Reference numerals] (100) Sensor part; (200) Storage part; (300) Dynamic neural network part; (400) Neural network learning part