Odor identification method based on bionic globe circumference loop, computer device and computer readable storage medium

Abstract

The invention provides a odor recognition method based on a bionic spherical loop, a computer device and a computer readable storage medium, and the method comprises the steps: obtaining a signal outputted by a gas sensor array, and forming a sample data set; inputting data of the sample data set into the bionic spherical loop model for calculating a pulse time sequence; and inputting the pulse time sequence into a pulse neural network, carrying out feature learning and classification on the pulse time sequence by the pulse neural network, and outputting the identification accuracy of multipletypes of gases. The invention further provides a computer device and a computer readable storage medium for implementing the method. According to the invention, the algorithm processing flow of the electronic nose can be simplified, and the wide applicability of the electronic nose can be improved.

Description

technical field [0001] The invention relates to the technical field of intelligent odor identification, in particular, a method for identifying odors based on a bionic spherical circuit, a computer device and a computer-readable storage medium for realizing the method. Background technique [0002] The electronic nose is a detection instrument that simulates the biological sense of smell, and is usually used to detect the type of gas. A sensor array is arranged in the electronic nose, and the sensor array includes a plurality of gas sensors. These gas sensors are electrochemical sensors with partial selectivity. The sensor array detects and identifies gases, and can identify simple and complex odors. At present, the electronic nose provides the physical carrier of the bionic sense of smell, but it is far from the biological system in terms of information processing, and there is also a significant gap in recognition performance. [0003] The odor recognition method used by ...

AI Technical Summary

Problems solved by technology

This method needs to try a combination of various methods to optimize the data analysis method for specific applications when designing an electronic nose, in order to achieve good results, which hinders the popularization and application of electronic nose technology

In addition, each link of this method needs to be manually selected according to the signal characteristics, it is difficult to realize automatic data analysis, and it lacks wide applicability

Images