Linear classification algorithm, medium and device for true and false cough sounds in patients with cervical spinal cord injury

Abstract

The invention provides a linear classification algorithm for true and false cough sounds of patients with cervical spinal cord injury, which is characterized in that: a number of unvoiced and voiced samples are obtained, and the initial sequence of the unvoiced and voiced samples is intercepted and processed by filtering; the obtained sequence is calculated Zero-crossing rate and maximum autocorrelation coefficient; establish a linear classifier based on the zero-crossing rate and maximum autocorrelation coefficient, and use unvoiced and voiced samples as sample sets to train the linear classifier; use the trained linear classifier to identify True cough and shout-type pseudocough in patients with cervical spinal cord injury. The algorithm of the present invention overcomes the difficulty of training the recognition model due to insufficient cough sound training samples of patients with cervical spinal cord injury, and can identify true and false coughs only by using unvoiced and voiced sound signals, avoiding the impact of false coughs of shouting types on the analysis of cough intensity At the same time, the model of this method is simple and the calculation amount is small, which is convenient for implementation in wearable devices.

Description

technical field [0001] The invention relates to the fields of medical equipment and medical signal processing, and more particularly, to a linear classification algorithm, medium and equipment for true and false cough sounds of patients with cervical spinal cord injury. Background technique [0002] Cervical spinal cord injury has a very high mortality and disability rate, and there are many complications. Studies have shown that the quality of respiratory function often determines the recovery and survival rate of patients, and also determines whether it is necessary to provide patients with assisted breathing devices. Cough is the original protective reflex of human beings. It is a perfect product of the coordination of respiratory muscles and nervous system. It is also a concentrated expression of lung reserve function. The strength of cough sounds can reflect the quality of respiratory function to a certain extent. [0003] However, some patients with cervical spinal co...

AI Technical Summary

Problems solved by technology

[0004] The current common cough recognition algorithm does not consider the difference between the above two sounds, and cannot be directly applied to the respiratory function evaluation of patients with cervical spinal cord injury

In addition, there is currently no publicly available cough sound sample data set for patients with cervical spinal cord injury, and the number of cough sound samples collected by each hospital is also limited

The lack of training samples has caused great difficulties in establishing a true and false cough recognition model through machine learning methods

[0005] Under the condition of insufficient training samples, how to establish a recognition algorithm for the real cough and the pseudo-cough of the shouting type in patients with cervical spinal cord injury has not yet been solved

Images