Classification of Respiratory States Using Spectrogram with Convolutional Neural Network

Abstract

This paper proposes an approach to the classification of respiration states based on a neural network model by visualizing respiratory signals using a spectrogram. The analysis and processing of human biosignals are still considered some of the most crucial and fundamental research areas in both signal processing and medical applications. Recently, learning-based algorithms in signal and image processing for medical applications have shown significant improvement from both quantitative and qualitative perspectives. Human respiration is still considered an important factor for diagnosis, and it plays a key role in preventing fatal diseases in practice. This paper chiefly deals with a contactless-based approach for the acquisition of respiration data using an ultra-wideband (UWB) radar sensor because it is simple and easy for use in an experimental setup and shows high accuracy in distance estimation. This paper proposes the classification of respiratory states by using a feature visualization scheme, a spectrogram, and a neural network model. The proposed method shows competitive and promising results in the classification of respiratory states. The experimental results also show that the method provides better accuracy (precision: 0.86 and specificity: 0.90) than conventional methods that use expensive equipment for respiration measurement.

Recent advances in acoustic technology for aquaculture: A review

“…Sound is the fluctuating phenomena of sound waves created by an object's vibration that passes through a medium (gas, solid or liquid) and are audible to both human and animal hearing organs 104 . Time domain features, frequency domain features and spectrogram features are all visualized in sound 105,106 …”

“…104 Time domain features, frequency domain features and spectrogram features are all visualized in sound. 105,106 The word hydrophone is composed of the word 'hydro', meaning water and 'phone', meaning sound. Simply put, hydrophone is a device for measuring sound in water.…”

A low-complexity sleep apnea detection method using millimeter-wave radar

“…According to the latest criteria in the American Academy of Sleep Medicine (AASM) manual, sleep apnea is defined as a decrease in the amplitude of the respiratory signal of more than 90% from the pre-event baseline value with a duration of more than 10 seconds. The existing sleep apnea detection methods generally include polysomnography based, electrocardiography based, 1 oxygen saturation based, 2 audio based, 3 visual based 4 and radar based [5][6][7][8][9][10][11][12][13][14] methods. Among them, the radar sensor has the advantages of completely non-contact, continuously stable performance, privacy protection, and not being affected by the covering of clothes and quilts.…”

“…Radar-based sleep apnea detection methods are mainly divided into three categories: traditional detection method (TDM), [5][6][7] machine learning method (MLM), [8][9][10][11][12] and deep learning method (DLM). 13,14 Fugui Qi, et. al 5 calculated the wavelet information entropy spectrum and judged apnea based on reference threshold.…”

“…Further, Cheolhyeong Park, et. al 14 classified various respiratory patterns by applying the CNN network. Normally, DLM requires large-scale labeled data to prevent overfitting and obtain good generalization ability.…”