# Two-Stream Convolutional Neural Networks for Breathing Pattern Classification: Real-Time Monitoring of Respiratory Disease Patients

## TL;DR

A new two-stream neural network improves real-time breathing pattern classification for monitoring respiratory disease patients using wearable sensors.

## Contribution

A two-stream CNN with an autoencoder and classifier achieves higher accuracy and efficiency in breathing pattern classification.

## Key findings

- The TCNN achieved 94.63% classification accuracy, outperforming random forest and single-stream CNN models.
- The TCNN required fewer parameters and computations while maintaining robust performance compared to state-of-the-art models.
- The model mitigates performance decline with increasing network depth, a common issue in single-stream CNNs.

## Abstract

A two-stream convolutional neural network (TCNN) for breathing pattern classification has been devised for the continuous monitoring of patients with infectious respiratory diseases. The TCNN consists of a convolutional neural network (CNN)-based autoencoder and classifier. The encoder of the autoencoder generates deep compressed feature maps, which contain the most important information constituting data. These maps are concatenated with feature maps generated by the classifier to classify breathing patterns. The TCNN, single-stream CNN (SCNN), and state-of-the-art classification models were applied to classify four breathing patterns: normal, slow, rapid, and breath holding. The input data consisted of chest tissue hemodynamic responses measured using a wearable near-infrared spectroscopy device on 14 healthy adult participants. Among the classification models evaluated, random forest had the lowest classification accuracy at 88.49%, while the TCNN achieved the highest classification accuracy at 94.63%. In addition, the proposed TCNN performed 2.6% better in terms of classification accuracy than an SCNN (without an autoencoder). Moreover, the TCNN mitigates the issue of declining learning performance with increasing network depth, as observed in the SCNN model. These results prove the robustness of the TCNN in classifying breathing patterns despite using a significantly smaller number of parameters and computations compared to state-of-the-art classification models.