Medical ventilator capable of early detecting and recognizing types of pneumonia, gas recognition chip, and method for recognizing gas thereof

摘要

A medical ventilator capable of early detecting and recognizing types of pneumonia, a gas recognition chip, and a method for recognizing gas thereof are disclosed. The gas recognition chip of the medical ventilator comprises a sensor array, a sensor interface circuit, a stochastic neural network chip, a memory and a microcontroller. The sensor array receives a plurality of multiple types of gases to produce odor signals corresponding to each type of gas. The sensor interface circuit analyzes the odor signals to produce gas pattern signals corresponding to each type of gas. The stochastic neural network chip amplifies the differences between the gas pattern signals and performs dimensional reduction on the gas pattern signals to aid the analysis. The memory stores training data. The microcontroller performs a mixed gas recognizing algorithm to early detect and recognize the type of the pneumonia according to the gas training data.

主权项

1. A gas recognition chip, comprising:
a sensor array, including a plurality of sensors and a plurality of sensing films applied on the sensors correspondingly, and each of the sensing films being provided with selectivity to adsorb plural types of gases, and each of the sensors being provided to produce an odor signal corresponding to each of the respective gases adsorbed by the sensing film; a sensor interface circuit, for reading and analyzing the odor signal of each of the gases to generate a gas pattern signal corresponding to each of the respective gases; a stochastic neural network chip, for amplifying the difference between the gas pattern signals and reducing the dimensions of each gas pattern signal to produce an analysis result; a memory, for storing gas training data; and a microcontroller, for receiving the analysis result, and executing a mixed gas recognizing algorithm according to the analysis result to recognize the type of the gas, and classify an unknown gas not existed in the gas training data, and producing a recognition result according to the gas training data, wherein the microcontroller transmits data of the unknown gas to the stochastic neural network chip and the memory when the microcontroller detects the unknown gas, so that the gas recognition chip has a self learning ability, wherein the mixed gas recognizing algorithm includes a K nearest neighbor (KNN) algorithm, a linear least squares regression algorithm and a median-threshold K nearest neighbor (MTKNN) classification algorithm, and the median-threshold K nearest neighbor classification algorithm is used to find a distance between every two data in the gas training data first, and then find a median of the distances to determine whether the gas is the unknown gas.