Frequency-Modulated Continuous Wave Radar Respiratory Pattern Detection Technology Based on Multifeature

Abstract

Respiratory diseases including apnea are often accompanied by abnormal respiratory depth, frequency, and rhythm. If different abnormal respiratory patterns can be detected and recorded, with their depth, frequency, and rhythm analyzed, the detection and diagnosis of respiratory diseases can be achieved. High-frequency millimeter-wave radar (76–81 GHz) has low environmental impact, high accuracy, and small volume, which is more suitable for respiratory signal detection and recognition compared with other contact equipment. In this paper, the experimental platform of frequency-modulated continuous wave (FMCW) radar was built at first, realizing the noncontact measurement of vital signs. Secondly, the energy intensity and threshold of respiration signal during each period were calculated by using the rectangular window, and the accurate judgment of apnea was realized via numerical comparison. Thirdly, the features of respiratory and heart rate signals, the number of peaks and valleys, the difference between peaks and valleys, the average and the standard deviation of normalized short-term energy, and the average and the standard deviation and the minimum of instantaneous frequency, were extracted and analyzed. Finally, support vector machine (SVM) and K-nearest neighbor (KNN) were used to classify the extracted features, and the accuracy was 98.25% and 88.75%, respectively. The classification and recognition of respiratory patterns have been successfully realized.

Protein Phosphatase 2A Activation Promotes Heart Transplant Acceptance in Mice

“…CAV is characterized by the formation of an occlusive neointimal layer in the vessels, consisting primarily of vascular SMCs and an accumulation of extracellular matrix proteins, ultimately resulting in graft fibrosis and cardiac hypertrophy. 38 The pathogenesis of CAV is not fully understood despite considerable long-term survival of heart transplant patients 68 and the relatively high incidence of CAV among transplant recipients at 10-y posttransplantation. 69 One of many challenges in this area of research enquiry is that most experimental models of allograft HF result from acute rejection and occur in the short term; thus the process of chronic rejection is difficult to model and study in animal models.…”

Machine Learning in RADAR-based Physiological Signals Sensing: A Scoping Review of the Models, Datasets and Metrics

“…Some papers discuss breathing patterns with variations in amplitude, such as deep or heavy breathing and breath holding [115], [129], [133]. Sixteen of the twenty-two papers included evaluate their algorithm on simulated breathing patterns, asking subjects involved in the study to emulate the desired waveform [38], [115]- [117], [119], [122]- [124], [127]- [130], [133], [142], [143], [146]. In one case, model training is carried out on a simulated pattern, while testing on people with a real disorder [146].…”

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.…”

“…Therefore, it has been considered as an very important non-contact sleep apnea detection technique. 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.…”

“…6 And Qisong Wang, et. al 7 not only judged apnea based on the energy of the signal, but also extracted multiple features to classify various respiratory patterns by support vector machine (SVM) and K-nearest neighbor (KNN). Most of the apnea detection methods based on MLM were to extract features first and then classify by an appropriate classifier.…”